first commit

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/__init__.py

@@ -0,0 +1,53 @@
+"""
+The :mod:`sklearn.decomposition` module includes matrix decomposition
+algorithms, including among others PCA, NMF or ICA. Most of the algorithms of
+this module can be regarded as dimensionality reduction techniques.
+"""
+
+
+from ._nmf import (
+    NMF,
+    MiniBatchNMF,
+    non_negative_factorization,
+)
+from ._pca import PCA
+from ._incremental_pca import IncrementalPCA
+from ._kernel_pca import KernelPCA
+from ._sparse_pca import SparsePCA, MiniBatchSparsePCA
+from ._truncated_svd import TruncatedSVD
+from ._fastica import FastICA, fastica
+from ._dict_learning import (
+    dict_learning,
+    dict_learning_online,
+    sparse_encode,
+    DictionaryLearning,
+    MiniBatchDictionaryLearning,
+    SparseCoder,
+)
+from ._factor_analysis import FactorAnalysis
+from ..utils.extmath import randomized_svd
+from ._lda import LatentDirichletAllocation
+
+
+__all__ = [
+    "DictionaryLearning",
+    "FastICA",
+    "IncrementalPCA",
+    "KernelPCA",
+    "MiniBatchDictionaryLearning",
+    "MiniBatchNMF",
+    "MiniBatchSparsePCA",
+    "NMF",
+    "PCA",
+    "SparseCoder",
+    "SparsePCA",
+    "dict_learning",
+    "dict_learning_online",
+    "fastica",
+    "non_negative_factorization",
+    "randomized_svd",
+    "sparse_encode",
+    "FactorAnalysis",
+    "TruncatedSVD",
+    "LatentDirichletAllocation",
+]

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_base.py

@@ -0,0 +1,164 @@
+"""Principal Component Analysis Base Classes"""
+
+# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
+#         Olivier Grisel <olivier.grisel@ensta.org>
+#         Mathieu Blondel <mathieu@mblondel.org>
+#         Denis A. Engemann <denis-alexander.engemann@inria.fr>
+#         Kyle Kastner <kastnerkyle@gmail.com>
+#
+# License: BSD 3 clause
+
+import numpy as np
+from scipy import linalg
+
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..utils.validation import check_is_fitted
+from abc import ABCMeta, abstractmethod
+
+
+class _BasePCA(
+    _ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator, metaclass=ABCMeta
+):
+    """Base class for PCA methods.
+
+    Warning: This class should not be used directly.
+    Use derived classes instead.
+    """
+
+    def get_covariance(self):
+        """Compute data covariance with the generative model.
+
+        ``cov = components_.T * S**2 * components_ + sigma2 * eye(n_features)``
+        where S**2 contains the explained variances, and sigma2 contains the
+        noise variances.
+
+        Returns
+        -------
+        cov : array of shape=(n_features, n_features)
+            Estimated covariance of data.
+        """
+        components_ = self.components_
+        exp_var = self.explained_variance_
+        if self.whiten:
+            components_ = components_ * np.sqrt(exp_var[:, np.newaxis])
+        exp_var_diff = np.maximum(exp_var - self.noise_variance_, 0.0)
+        cov = np.dot(components_.T * exp_var_diff, components_)
+        cov.flat[:: len(cov) + 1] += self.noise_variance_  # modify diag inplace
+        return cov
+
+    def get_precision(self):
+        """Compute data precision matrix with the generative model.
+
+        Equals the inverse of the covariance but computed with
+        the matrix inversion lemma for efficiency.
+
+        Returns
+        -------
+        precision : array, shape=(n_features, n_features)
+            Estimated precision of data.
+        """
+        n_features = self.components_.shape[1]
+
+        # handle corner cases first
+        if self.n_components_ == 0:
+            return np.eye(n_features) / self.noise_variance_
+
+        if np.isclose(self.noise_variance_, 0.0, atol=0.0):
+            return linalg.inv(self.get_covariance())
+
+        # Get precision using matrix inversion lemma
+        components_ = self.components_
+        exp_var = self.explained_variance_
+        if self.whiten:
+            components_ = components_ * np.sqrt(exp_var[:, np.newaxis])
+        exp_var_diff = np.maximum(exp_var - self.noise_variance_, 0.0)
+        precision = np.dot(components_, components_.T) / self.noise_variance_
+        precision.flat[:: len(precision) + 1] += 1.0 / exp_var_diff
+        precision = np.dot(components_.T, np.dot(linalg.inv(precision), components_))
+        precision /= -(self.noise_variance_**2)
+        precision.flat[:: len(precision) + 1] += 1.0 / self.noise_variance_
+        return precision
+
+    @abstractmethod
+    def fit(self, X, y=None):
+        """Placeholder for fit. Subclasses should implement this method!
+
+        Fit the model with X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+
+    def transform(self, X):
+        """Apply dimensionality reduction to X.
+
+        X is projected on the first principal components previously extracted
+        from a training set.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            New data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Returns
+        -------
+        X_new : array-like of shape (n_samples, n_components)
+            Projection of X in the first principal components, where `n_samples`
+            is the number of samples and `n_components` is the number of the components.
+        """
+        check_is_fitted(self)
+
+        X = self._validate_data(X, dtype=[np.float64, np.float32], reset=False)
+        if self.mean_ is not None:
+            X = X - self.mean_
+        X_transformed = np.dot(X, self.components_.T)
+        if self.whiten:
+            X_transformed /= np.sqrt(self.explained_variance_)
+        return X_transformed
+
+    def inverse_transform(self, X):
+        """Transform data back to its original space.
+
+        In other words, return an input `X_original` whose transform would be X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_components)
+            New data, where `n_samples` is the number of samples
+            and `n_components` is the number of components.
+
+        Returns
+        -------
+        X_original array-like of shape (n_samples, n_features)
+            Original data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Notes
+        -----
+        If whitening is enabled, inverse_transform will compute the
+        exact inverse operation, which includes reversing whitening.
+        """
+        if self.whiten:
+            return (
+                np.dot(
+                    X,
+                    np.sqrt(self.explained_variance_[:, np.newaxis]) * self.components_,
+                )
+                + self.mean_
+            )
+        else:
+            return np.dot(X, self.components_) + self.mean_
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_factor_analysis.py

@@ -0,0 +1,456 @@
+"""Factor Analysis.
+
+A latent linear variable model.
+
+FactorAnalysis is similar to probabilistic PCA implemented by PCA.score
+While PCA assumes Gaussian noise with the same variance for each
+feature, the FactorAnalysis model assumes different variances for
+each of them.
+
+This implementation is based on David Barber's Book,
+Bayesian Reasoning and Machine Learning,
+http://www.cs.ucl.ac.uk/staff/d.barber/brml,
+Algorithm 21.1
+"""
+
+# Author: Christian Osendorfer <osendorf@gmail.com>
+#         Alexandre Gramfort <alexandre.gramfort@inria.fr>
+#         Denis A. Engemann <denis-alexander.engemann@inria.fr>
+
+# License: BSD3
+
+import warnings
+from math import sqrt, log
+import numpy as np
+from scipy import linalg
+
+
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..utils import check_random_state
+from ..utils.extmath import fast_logdet, randomized_svd, squared_norm
+from ..utils.validation import check_is_fitted
+from ..exceptions import ConvergenceWarning
+
+
+class FactorAnalysis(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
+    """Factor Analysis (FA).
+
+    A simple linear generative model with Gaussian latent variables.
+
+    The observations are assumed to be caused by a linear transformation of
+    lower dimensional latent factors and added Gaussian noise.
+    Without loss of generality the factors are distributed according to a
+    Gaussian with zero mean and unit covariance. The noise is also zero mean
+    and has an arbitrary diagonal covariance matrix.
+
+    If we would restrict the model further, by assuming that the Gaussian
+    noise is even isotropic (all diagonal entries are the same) we would obtain
+    :class:`PPCA`.
+
+    FactorAnalysis performs a maximum likelihood estimate of the so-called
+    `loading` matrix, the transformation of the latent variables to the
+    observed ones, using SVD based approach.
+
+    Read more in the :ref:`User Guide <FA>`.
+
+    .. versionadded:: 0.13
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Dimensionality of latent space, the number of components
+        of ``X`` that are obtained after ``transform``.
+        If None, n_components is set to the number of features.
+
+    tol : float, default=1e-2
+        Stopping tolerance for log-likelihood increase.
+
+    copy : bool, default=True
+        Whether to make a copy of X. If ``False``, the input X gets overwritten
+        during fitting.
+
+    max_iter : int, default=1000
+        Maximum number of iterations.
+
+    noise_variance_init : ndarray of shape (n_features,), default=None
+        The initial guess of the noise variance for each feature.
+        If None, it defaults to np.ones(n_features).
+
+    svd_method : {'lapack', 'randomized'}, default='randomized'
+        Which SVD method to use. If 'lapack' use standard SVD from
+        scipy.linalg, if 'randomized' use fast ``randomized_svd`` function.
+        Defaults to 'randomized'. For most applications 'randomized' will
+        be sufficiently precise while providing significant speed gains.
+        Accuracy can also be improved by setting higher values for
+        `iterated_power`. If this is not sufficient, for maximum precision
+        you should choose 'lapack'.
+
+    iterated_power : int, default=3
+        Number of iterations for the power method. 3 by default. Only used
+        if ``svd_method`` equals 'randomized'.
+
+    rotation : {'varimax', 'quartimax'}, default=None
+        If not None, apply the indicated rotation. Currently, varimax and
+        quartimax are implemented. See
+        `"The varimax criterion for analytic rotation in factor analysis"
+        <https://link.springer.com/article/10.1007%2FBF02289233>`_
+        H. F. Kaiser, 1958.
+
+        .. versionadded:: 0.24
+
+    random_state : int or RandomState instance, default=0
+        Only used when ``svd_method`` equals 'randomized'. Pass an int for
+        reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Components with maximum variance.
+
+    loglike_ : list of shape (n_iterations,)
+        The log likelihood at each iteration.
+
+    noise_variance_ : ndarray of shape (n_features,)
+        The estimated noise variance for each feature.
+
+    n_iter_ : int
+        Number of iterations run.
+
+    mean_ : ndarray of shape (n_features,)
+        Per-feature empirical mean, estimated from the training set.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    PCA: Principal component analysis is also a latent linear variable model
+        which however assumes equal noise variance for each feature.
+        This extra assumption makes probabilistic PCA faster as it can be
+        computed in closed form.
+    FastICA: Independent component analysis, a latent variable model with
+        non-Gaussian latent variables.
+
+    References
+    ----------
+    - David Barber, Bayesian Reasoning and Machine Learning,
+      Algorithm 21.1.
+
+    - Christopher M. Bishop: Pattern Recognition and Machine Learning,
+      Chapter 12.2.4.
+
+    Examples
+    --------
+    >>> from sklearn.datasets import load_digits
+    >>> from sklearn.decomposition import FactorAnalysis
+    >>> X, _ = load_digits(return_X_y=True)
+    >>> transformer = FactorAnalysis(n_components=7, random_state=0)
+    >>> X_transformed = transformer.fit_transform(X)
+    >>> X_transformed.shape
+    (1797, 7)
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        tol=1e-2,
+        copy=True,
+        max_iter=1000,
+        noise_variance_init=None,
+        svd_method="randomized",
+        iterated_power=3,
+        rotation=None,
+        random_state=0,
+    ):
+        self.n_components = n_components
+        self.copy = copy
+        self.tol = tol
+        self.max_iter = max_iter
+        self.svd_method = svd_method
+
+        self.noise_variance_init = noise_variance_init
+        self.iterated_power = iterated_power
+        self.random_state = random_state
+        self.rotation = rotation
+
+    def fit(self, X, y=None):
+        """Fit the FactorAnalysis model to X using SVD based approach.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+
+        y : Ignored
+            Ignored parameter.
+
+        Returns
+        -------
+        self : object
+            FactorAnalysis class instance.
+        """
+
+        if self.svd_method not in ["lapack", "randomized"]:
+            raise ValueError(
+                f"SVD method {self.svd_method!r} is not supported. Possible methods "
+                "are either 'lapack' or 'randomized'."
+            )
+
+        X = self._validate_data(X, copy=self.copy, dtype=np.float64)
+
+        n_samples, n_features = X.shape
+        n_components = self.n_components
+        if n_components is None:
+            n_components = n_features
+
+        self.mean_ = np.mean(X, axis=0)
+        X -= self.mean_
+
+        # some constant terms
+        nsqrt = sqrt(n_samples)
+        llconst = n_features * log(2.0 * np.pi) + n_components
+        var = np.var(X, axis=0)
+
+        if self.noise_variance_init is None:
+            psi = np.ones(n_features, dtype=X.dtype)
+        else:
+            if len(self.noise_variance_init) != n_features:
+                raise ValueError(
+                    "noise_variance_init dimension does not "
+                    "with number of features : %d != %d"
+                    % (len(self.noise_variance_init), n_features)
+                )
+            psi = np.array(self.noise_variance_init)
+
+        loglike = []
+        old_ll = -np.inf
+        SMALL = 1e-12
+
+        # we'll modify svd outputs to return unexplained variance
+        # to allow for unified computation of loglikelihood
+        if self.svd_method == "lapack":
+
+            def my_svd(X):
+                _, s, Vt = linalg.svd(X, full_matrices=False, check_finite=False)
+                return (
+                    s[:n_components],
+                    Vt[:n_components],
+                    squared_norm(s[n_components:]),
+                )
+
+        elif self.svd_method == "randomized":
+            random_state = check_random_state(self.random_state)
+
+            def my_svd(X):
+                _, s, Vt = randomized_svd(
+                    X,
+                    n_components,
+                    random_state=random_state,
+                    n_iter=self.iterated_power,
+                )
+                return s, Vt, squared_norm(X) - squared_norm(s)
+
+        else:
+            raise ValueError(
+                "SVD method %s is not supported. Please consider the documentation"
+                % self.svd_method
+            )
+
+        for i in range(self.max_iter):
+            # SMALL helps numerics
+            sqrt_psi = np.sqrt(psi) + SMALL
+            s, Vt, unexp_var = my_svd(X / (sqrt_psi * nsqrt))
+            s **= 2
+            # Use 'maximum' here to avoid sqrt problems.
+            W = np.sqrt(np.maximum(s - 1.0, 0.0))[:, np.newaxis] * Vt
+            del Vt
+            W *= sqrt_psi
+
+            # loglikelihood
+            ll = llconst + np.sum(np.log(s))
+            ll += unexp_var + np.sum(np.log(psi))
+            ll *= -n_samples / 2.0
+            loglike.append(ll)
+            if (ll - old_ll) < self.tol:
+                break
+            old_ll = ll
+
+            psi = np.maximum(var - np.sum(W**2, axis=0), SMALL)
+        else:
+            warnings.warn(
+                "FactorAnalysis did not converge."
+                + " You might want"
+                + " to increase the number of iterations.",
+                ConvergenceWarning,
+            )
+
+        self.components_ = W
+        if self.rotation is not None:
+            self.components_ = self._rotate(W)
+        self.noise_variance_ = psi
+        self.loglike_ = loglike
+        self.n_iter_ = i + 1
+        return self
+
+    def transform(self, X):
+        """Apply dimensionality reduction to X using the model.
+
+        Compute the expected mean of the latent variables.
+        See Barber, 21.2.33 (or Bishop, 12.66).
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            The latent variables of X.
+        """
+        check_is_fitted(self)
+
+        X = self._validate_data(X, reset=False)
+        Ih = np.eye(len(self.components_))
+
+        X_transformed = X - self.mean_
+
+        Wpsi = self.components_ / self.noise_variance_
+        cov_z = linalg.inv(Ih + np.dot(Wpsi, self.components_.T))
+        tmp = np.dot(X_transformed, Wpsi.T)
+        X_transformed = np.dot(tmp, cov_z)
+
+        return X_transformed
+
+    def get_covariance(self):
+        """Compute data covariance with the FactorAnalysis model.
+
+        ``cov = components_.T * components_ + diag(noise_variance)``
+
+        Returns
+        -------
+        cov : ndarray of shape (n_features, n_features)
+            Estimated covariance of data.
+        """
+        check_is_fitted(self)
+
+        cov = np.dot(self.components_.T, self.components_)
+        cov.flat[:: len(cov) + 1] += self.noise_variance_  # modify diag inplace
+        return cov
+
+    def get_precision(self):
+        """Compute data precision matrix with the FactorAnalysis model.
+
+        Returns
+        -------
+        precision : ndarray of shape (n_features, n_features)
+            Estimated precision of data.
+        """
+        check_is_fitted(self)
+
+        n_features = self.components_.shape[1]
+
+        # handle corner cases first
+        if self.n_components == 0:
+            return np.diag(1.0 / self.noise_variance_)
+        if self.n_components == n_features:
+            return linalg.inv(self.get_covariance())
+
+        # Get precision using matrix inversion lemma
+        components_ = self.components_
+        precision = np.dot(components_ / self.noise_variance_, components_.T)
+        precision.flat[:: len(precision) + 1] += 1.0
+        precision = np.dot(components_.T, np.dot(linalg.inv(precision), components_))
+        precision /= self.noise_variance_[:, np.newaxis]
+        precision /= -self.noise_variance_[np.newaxis, :]
+        precision.flat[:: len(precision) + 1] += 1.0 / self.noise_variance_
+        return precision
+
+    def score_samples(self, X):
+        """Compute the log-likelihood of each sample.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The data.
+
+        Returns
+        -------
+        ll : ndarray of shape (n_samples,)
+            Log-likelihood of each sample under the current model.
+        """
+        check_is_fitted(self)
+        X = self._validate_data(X, reset=False)
+        Xr = X - self.mean_
+        precision = self.get_precision()
+        n_features = X.shape[1]
+        log_like = -0.5 * (Xr * (np.dot(Xr, precision))).sum(axis=1)
+        log_like -= 0.5 * (n_features * log(2.0 * np.pi) - fast_logdet(precision))
+        return log_like
+
+    def score(self, X, y=None):
+        """Compute the average log-likelihood of the samples.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            The data.
+
+        y : Ignored
+            Ignored parameter.
+
+        Returns
+        -------
+        ll : float
+            Average log-likelihood of the samples under the current model.
+        """
+        return np.mean(self.score_samples(X))
+
+    def _rotate(self, components, n_components=None, tol=1e-6):
+        "Rotate the factor analysis solution."
+        # note that tol is not exposed
+        implemented = ("varimax", "quartimax")
+        method = self.rotation
+        if method in implemented:
+            return _ortho_rotation(components.T, method=method, tol=tol)[
+                : self.n_components
+            ]
+        else:
+            raise ValueError("'method' must be in %s, not %s" % (implemented, method))
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]
+
+
+def _ortho_rotation(components, method="varimax", tol=1e-6, max_iter=100):
+    """Return rotated components."""
+    nrow, ncol = components.shape
+    rotation_matrix = np.eye(ncol)
+    var = 0
+
+    for _ in range(max_iter):
+        comp_rot = np.dot(components, rotation_matrix)
+        if method == "varimax":
+            tmp = comp_rot * np.transpose((comp_rot**2).sum(axis=0) / nrow)
+        elif method == "quartimax":
+            tmp = 0
+        u, s, v = np.linalg.svd(np.dot(components.T, comp_rot**3 - tmp))
+        rotation_matrix = np.dot(u, v)
+        var_new = np.sum(s)
+        if var != 0 and var_new < var * (1 + tol):
+            break
+        var = var_new
+
+    return np.dot(components, rotation_matrix).T

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_fastica.py

@@ -0,0 +1,735 @@
+"""
+Python implementation of the fast ICA algorithms.
+
+Reference: Tables 8.3 and 8.4 page 196 in the book:
+Independent Component Analysis, by  Hyvarinen et al.
+"""
+
+# Authors: Pierre Lafaye de Micheaux, Stefan van der Walt, Gael Varoquaux,
+#          Bertrand Thirion, Alexandre Gramfort, Denis A. Engemann
+# License: BSD 3 clause
+
+import warnings
+
+import numpy as np
+from scipy import linalg
+
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..exceptions import ConvergenceWarning
+
+from ..utils import check_array, as_float_array, check_random_state
+from ..utils.validation import check_is_fitted
+
+__all__ = ["fastica", "FastICA"]
+
+
+def _gs_decorrelation(w, W, j):
+    """
+    Orthonormalize w wrt the first j rows of W.
+
+    Parameters
+    ----------
+    w : ndarray of shape (n,)
+        Array to be orthogonalized
+
+    W : ndarray of shape (p, n)
+        Null space definition
+
+    j : int < p
+        The no of (from the first) rows of Null space W wrt which w is
+        orthogonalized.
+
+    Notes
+    -----
+    Assumes that W is orthogonal
+    w changed in place
+    """
+    w -= np.linalg.multi_dot([w, W[:j].T, W[:j]])
+    return w
+
+
+def _sym_decorrelation(W):
+    """Symmetric decorrelation
+    i.e. W <- (W * W.T) ^{-1/2} * W
+    """
+    s, u = linalg.eigh(np.dot(W, W.T))
+    # Avoid sqrt of negative values because of rounding errors. Note that
+    # np.sqrt(tiny) is larger than tiny and therefore this clipping also
+    # prevents division by zero in the next step.
+    s = np.clip(s, a_min=np.finfo(W.dtype).tiny, a_max=None)
+
+    # u (resp. s) contains the eigenvectors (resp. square roots of
+    # the eigenvalues) of W * W.T
+    return np.linalg.multi_dot([u * (1.0 / np.sqrt(s)), u.T, W])
+
+
+def _ica_def(X, tol, g, fun_args, max_iter, w_init):
+    """Deflationary FastICA using fun approx to neg-entropy function
+
+    Used internally by FastICA.
+    """
+
+    n_components = w_init.shape[0]
+    W = np.zeros((n_components, n_components), dtype=X.dtype)
+    n_iter = []
+
+    # j is the index of the extracted component
+    for j in range(n_components):
+        w = w_init[j, :].copy()
+        w /= np.sqrt((w**2).sum())
+
+        for i in range(max_iter):
+            gwtx, g_wtx = g(np.dot(w.T, X), fun_args)
+
+            w1 = (X * gwtx).mean(axis=1) - g_wtx.mean() * w
+
+            _gs_decorrelation(w1, W, j)
+
+            w1 /= np.sqrt((w1**2).sum())
+
+            lim = np.abs(np.abs((w1 * w).sum()) - 1)
+            w = w1
+            if lim < tol:
+                break
+
+        n_iter.append(i + 1)
+        W[j, :] = w
+
+    return W, max(n_iter)
+
+
+def _ica_par(X, tol, g, fun_args, max_iter, w_init):
+    """Parallel FastICA.
+
+    Used internally by FastICA --main loop
+
+    """
+    W = _sym_decorrelation(w_init)
+    del w_init
+    p_ = float(X.shape[1])
+    for ii in range(max_iter):
+        gwtx, g_wtx = g(np.dot(W, X), fun_args)
+        W1 = _sym_decorrelation(np.dot(gwtx, X.T) / p_ - g_wtx[:, np.newaxis] * W)
+        del gwtx, g_wtx
+        # builtin max, abs are faster than numpy counter parts.
+        lim = max(abs(abs(np.diag(np.dot(W1, W.T))) - 1))
+        W = W1
+        if lim < tol:
+            break
+    else:
+        warnings.warn(
+            "FastICA did not converge. Consider increasing "
+            "tolerance or the maximum number of iterations.",
+            ConvergenceWarning,
+        )
+
+    return W, ii + 1
+
+
+# Some standard non-linear functions.
+# XXX: these should be optimized, as they can be a bottleneck.
+def _logcosh(x, fun_args=None):
+    alpha = fun_args.get("alpha", 1.0)  # comment it out?
+
+    x *= alpha
+    gx = np.tanh(x, x)  # apply the tanh inplace
+    g_x = np.empty(x.shape[0], dtype=x.dtype)
+    # XXX compute in chunks to avoid extra allocation
+    for i, gx_i in enumerate(gx):  # please don't vectorize.
+        g_x[i] = (alpha * (1 - gx_i**2)).mean()
+    return gx, g_x
+
+
+def _exp(x, fun_args):
+    exp = np.exp(-(x**2) / 2)
+    gx = x * exp
+    g_x = (1 - x**2) * exp
+    return gx, g_x.mean(axis=-1)
+
+
+def _cube(x, fun_args):
+    return x**3, (3 * x**2).mean(axis=-1)
+
+
+def fastica(
+    X,
+    n_components=None,
+    *,
+    algorithm="parallel",
+    whiten="warn",
+    fun="logcosh",
+    fun_args=None,
+    max_iter=200,
+    tol=1e-04,
+    w_init=None,
+    random_state=None,
+    return_X_mean=False,
+    compute_sources=True,
+    return_n_iter=False,
+):
+    """Perform Fast Independent Component Analysis.
+
+    The implementation is based on [1]_.
+
+    Read more in the :ref:`User Guide <ICA>`.
+
+    Parameters
+    ----------
+    X : array-like of shape (n_samples, n_features)
+        Training vector, where `n_samples` is the number of samples and
+        `n_features` is the number of features.
+
+    n_components : int, default=None
+        Number of components to extract. If None no dimension reduction
+        is performed.
+
+    algorithm : {'parallel', 'deflation'}, default='parallel'
+        Apply a parallel or deflational FASTICA algorithm.
+
+    whiten : str or bool, default="warn"
+        Specify the whitening strategy to use.
+        If 'arbitrary-variance'  (default), a whitening with variance arbitrary is used.
+        If 'unit-variance', the whitening matrix is rescaled to ensure that each
+        recovered source has unit variance.
+        If False, the data is already considered to be whitened, and no
+        whitening is performed.
+
+        .. deprecated:: 1.1
+            From version 1.3, `whiten='unit-variance'` will be used by default.
+            `whiten=True` is deprecated from 1.1 and will raise ValueError in 1.3.
+            Use `whiten=arbitrary-variance` instead.
+
+    fun : {'logcosh', 'exp', 'cube'} or callable, default='logcosh'
+        The functional form of the G function used in the
+        approximation to neg-entropy. Could be either 'logcosh', 'exp',
+        or 'cube'.
+        You can also provide your own function. It should return a tuple
+        containing the value of the function, and of its derivative, in the
+        point. The derivative should be averaged along its last dimension.
+        Example:
+
+        def my_g(x):
+            return x ** 3, np.mean(3 * x ** 2, axis=-1)
+
+    fun_args : dict, default=None
+        Arguments to send to the functional form.
+        If empty or None and if fun='logcosh', fun_args will take value
+        {'alpha' : 1.0}.
+
+    max_iter : int, default=200
+        Maximum number of iterations to perform.
+
+    tol : float, default=1e-04
+        A positive scalar giving the tolerance at which the
+        un-mixing matrix is considered to have converged.
+
+    w_init : ndarray of shape (n_components, n_components), default=None
+        Initial un-mixing array of dimension (n.comp,n.comp).
+        If None (default) then an array of normal r.v.'s is used.
+
+    random_state : int, RandomState instance or None, default=None
+        Used to initialize ``w_init`` when not specified, with a
+        normal distribution. Pass an int, for reproducible results
+        across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    return_X_mean : bool, default=False
+        If True, X_mean is returned too.
+
+    compute_sources : bool, default=True
+        If False, sources are not computed, but only the rotation matrix.
+        This can save memory when working with big data. Defaults to True.
+
+    return_n_iter : bool, default=False
+        Whether or not to return the number of iterations.
+
+    Returns
+    -------
+    K : ndarray of shape (n_components, n_features) or None
+        If whiten is 'True', K is the pre-whitening matrix that projects data
+        onto the first n_components principal components. If whiten is 'False',
+        K is 'None'.
+
+    W : ndarray of shape (n_components, n_components)
+        The square matrix that unmixes the data after whitening.
+        The mixing matrix is the pseudo-inverse of matrix ``W K``
+        if K is not None, else it is the inverse of W.
+
+    S : ndarray of shape (n_samples, n_components) or None
+        Estimated source matrix.
+
+    X_mean : ndarray of shape (n_features,)
+        The mean over features. Returned only if return_X_mean is True.
+
+    n_iter : int
+        If the algorithm is "deflation", n_iter is the
+        maximum number of iterations run across all components. Else
+        they are just the number of iterations taken to converge. This is
+        returned only when return_n_iter is set to `True`.
+
+    Notes
+    -----
+    The data matrix X is considered to be a linear combination of
+    non-Gaussian (independent) components i.e. X = AS where columns of S
+    contain the independent components and A is a linear mixing
+    matrix. In short ICA attempts to `un-mix' the data by estimating an
+    un-mixing matrix W where ``S = W K X.``
+    While FastICA was proposed to estimate as many sources
+    as features, it is possible to estimate less by setting
+    n_components < n_features. It this case K is not a square matrix
+    and the estimated A is the pseudo-inverse of ``W K``.
+
+    This implementation was originally made for data of shape
+    [n_features, n_samples]. Now the input is transposed
+    before the algorithm is applied. This makes it slightly
+    faster for Fortran-ordered input.
+
+    References
+    ----------
+    .. [1] A. Hyvarinen and E. Oja, "Fast Independent Component Analysis",
+           Algorithms and Applications, Neural Networks, 13(4-5), 2000,
+           pp. 411-430.
+    """
+    est = FastICA(
+        n_components=n_components,
+        algorithm=algorithm,
+        whiten=whiten,
+        fun=fun,
+        fun_args=fun_args,
+        max_iter=max_iter,
+        tol=tol,
+        w_init=w_init,
+        random_state=random_state,
+    )
+    S = est._fit(X, compute_sources=compute_sources)
+
+    if est._whiten in ["unit-variance", "arbitrary-variance"]:
+        K = est.whitening_
+        X_mean = est.mean_
+    else:
+        K = None
+        X_mean = None
+
+    returned_values = [K, est._unmixing, S]
+    if return_X_mean:
+        returned_values.append(X_mean)
+    if return_n_iter:
+        returned_values.append(est.n_iter_)
+
+    return returned_values
+
+
+class FastICA(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
+    """FastICA: a fast algorithm for Independent Component Analysis.
+
+    The implementation is based on [1]_.
+
+    Read more in the :ref:`User Guide <ICA>`.
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Number of components to use. If None is passed, all are used.
+
+    algorithm : {'parallel', 'deflation'}, default='parallel'
+        Apply parallel or deflational algorithm for FastICA.
+
+    whiten : str or bool, default="warn"
+        Specify the whitening strategy to use.
+        If 'arbitrary-variance' (default), a whitening with variance arbitrary is used.
+        If 'unit-variance', the whitening matrix is rescaled to ensure that each
+        recovered source has unit variance.
+        If False, the data is already considered to be whitened, and no
+        whitening is performed.
+
+        .. deprecated:: 1.1
+            From version 1.3 whiten='unit-variance' will be used by default.
+            `whiten=True` is deprecated from 1.1 and will raise ValueError in 1.3.
+            Use `whiten=arbitrary-variance` instead.
+
+    fun : {'logcosh', 'exp', 'cube'} or callable, default='logcosh'
+        The functional form of the G function used in the
+        approximation to neg-entropy. Could be either 'logcosh', 'exp',
+        or 'cube'.
+        You can also provide your own function. It should return a tuple
+        containing the value of the function, and of its derivative, in the
+        point. Example::
+
+            def my_g(x):
+                return x ** 3, (3 * x ** 2).mean(axis=-1)
+
+    fun_args : dict, default=None
+        Arguments to send to the functional form.
+        If empty and if fun='logcosh', fun_args will take value
+        {'alpha' : 1.0}.
+
+    max_iter : int, default=200
+        Maximum number of iterations during fit.
+
+    tol : float, default=1e-4
+        Tolerance on update at each iteration.
+
+    w_init : ndarray of shape (n_components, n_components), default=None
+        The mixing matrix to be used to initialize the algorithm.
+
+    random_state : int, RandomState instance or None, default=None
+        Used to initialize ``w_init`` when not specified, with a
+        normal distribution. Pass an int, for reproducible results
+        across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        The linear operator to apply to the data to get the independent
+        sources. This is equal to the unmixing matrix when ``whiten`` is
+        False, and equal to ``np.dot(unmixing_matrix, self.whitening_)`` when
+        ``whiten`` is True.
+
+    mixing_ : ndarray of shape (n_features, n_components)
+        The pseudo-inverse of ``components_``. It is the linear operator
+        that maps independent sources to the data.
+
+    mean_ : ndarray of shape(n_features,)
+        The mean over features. Only set if `self.whiten` is True.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_iter_ : int
+        If the algorithm is "deflation", n_iter is the
+        maximum number of iterations run across all components. Else
+        they are just the number of iterations taken to converge.
+
+    whitening_ : ndarray of shape (n_components, n_features)
+        Only set if whiten is 'True'. This is the pre-whitening matrix
+        that projects data onto the first `n_components` principal components.
+
+    See Also
+    --------
+    PCA : Principal component analysis (PCA).
+    IncrementalPCA : Incremental principal components analysis (IPCA).
+    KernelPCA : Kernel Principal component analysis (KPCA).
+    MiniBatchSparsePCA : Mini-batch Sparse Principal Components Analysis.
+    SparsePCA : Sparse Principal Components Analysis (SparsePCA).
+
+    References
+    ----------
+    .. [1] A. Hyvarinen and E. Oja, Independent Component Analysis:
+           Algorithms and Applications, Neural Networks, 13(4-5), 2000,
+           pp. 411-430.
+
+    Examples
+    --------
+    >>> from sklearn.datasets import load_digits
+    >>> from sklearn.decomposition import FastICA
+    >>> X, _ = load_digits(return_X_y=True)
+    >>> transformer = FastICA(n_components=7,
+    ...         random_state=0,
+    ...         whiten='unit-variance')
+    >>> X_transformed = transformer.fit_transform(X)
+    >>> X_transformed.shape
+    (1797, 7)
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        algorithm="parallel",
+        whiten="warn",
+        fun="logcosh",
+        fun_args=None,
+        max_iter=200,
+        tol=1e-4,
+        w_init=None,
+        random_state=None,
+    ):
+        super().__init__()
+        self.n_components = n_components
+        self.algorithm = algorithm
+        self.whiten = whiten
+        self.fun = fun
+        self.fun_args = fun_args
+        self.max_iter = max_iter
+        self.tol = tol
+        self.w_init = w_init
+        self.random_state = random_state
+
+    def _fit(self, X, compute_sources=False):
+        """Fit the model.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        compute_sources : bool, default=False
+            If False, sources are not computes but only the rotation matrix.
+            This can save memory when working with big data. Defaults to False.
+
+        Returns
+        -------
+        S : ndarray of shape (n_samples, n_components) or None
+            Sources matrix. `None` if `compute_sources` is `False`.
+        """
+        self._whiten = self.whiten
+
+        if self._whiten == "warn":
+            warnings.warn(
+                "From version 1.3 whiten='unit-variance' will be used by default.",
+                FutureWarning,
+            )
+            self._whiten = "arbitrary-variance"
+
+        if self._whiten is True:
+            warnings.warn(
+                "From version 1.3 whiten=True should be specified as "
+                "whiten='arbitrary-variance' (its current behaviour). This "
+                "behavior is deprecated in 1.1 and will raise ValueError in 1.3.",
+                FutureWarning,
+                stacklevel=2,
+            )
+            self._whiten = "arbitrary-variance"
+
+        XT = self._validate_data(
+            X, copy=self._whiten, dtype=[np.float64, np.float32], ensure_min_samples=2
+        ).T
+        fun_args = {} if self.fun_args is None else self.fun_args
+        random_state = check_random_state(self.random_state)
+
+        alpha = fun_args.get("alpha", 1.0)
+        if not 1 <= alpha <= 2:
+            raise ValueError("alpha must be in [1,2]")
+
+        if self.fun == "logcosh":
+            g = _logcosh
+        elif self.fun == "exp":
+            g = _exp
+        elif self.fun == "cube":
+            g = _cube
+        elif callable(self.fun):
+
+            def g(x, fun_args):
+                return self.fun(x, **fun_args)
+
+        else:
+            exc = ValueError if isinstance(self.fun, str) else TypeError
+            raise exc(
+                "Unknown function %r;"
+                " should be one of 'logcosh', 'exp', 'cube' or callable"
+                % self.fun
+            )
+
+        n_features, n_samples = XT.shape
+
+        n_components = self.n_components
+        if not self._whiten and n_components is not None:
+            n_components = None
+            warnings.warn("Ignoring n_components with whiten=False.")
+
+        if n_components is None:
+            n_components = min(n_samples, n_features)
+        if n_components > min(n_samples, n_features):
+            n_components = min(n_samples, n_features)
+            warnings.warn(
+                "n_components is too large: it will be set to %s" % n_components
+            )
+
+        if self._whiten:
+            # Centering the features of X
+            X_mean = XT.mean(axis=-1)
+            XT -= X_mean[:, np.newaxis]
+
+            # Whitening and preprocessing by PCA
+            u, d, _ = linalg.svd(XT, full_matrices=False, check_finite=False)
+
+            del _
+            K = (u / d).T[:n_components]  # see (6.33) p.140
+            del u, d
+            X1 = np.dot(K, XT)
+            # see (13.6) p.267 Here X1 is white and data
+            # in X has been projected onto a subspace by PCA
+            X1 *= np.sqrt(n_samples)
+        else:
+            # X must be casted to floats to avoid typing issues with numpy
+            # 2.0 and the line below
+            X1 = as_float_array(XT, copy=False)  # copy has been taken care of
+
+        w_init = self.w_init
+        if w_init is None:
+            w_init = np.asarray(
+                random_state.normal(size=(n_components, n_components)), dtype=X1.dtype
+            )
+
+        else:
+            w_init = np.asarray(w_init)
+            if w_init.shape != (n_components, n_components):
+                raise ValueError(
+                    "w_init has invalid shape -- should be %(shape)s"
+                    % {"shape": (n_components, n_components)}
+                )
+
+        if self.max_iter < 1:
+            raise ValueError(
+                "max_iter should be greater than 1, got (max_iter={})".format(
+                    self.max_iter
+                )
+            )
+
+        kwargs = {
+            "tol": self.tol,
+            "g": g,
+            "fun_args": fun_args,
+            "max_iter": self.max_iter,
+            "w_init": w_init,
+        }
+
+        if self.algorithm == "parallel":
+            W, n_iter = _ica_par(X1, **kwargs)
+        elif self.algorithm == "deflation":
+            W, n_iter = _ica_def(X1, **kwargs)
+        else:
+            raise ValueError(
+                "Invalid algorithm: must be either `parallel` or `deflation`."
+            )
+        del X1
+
+        self.n_iter_ = n_iter
+
+        if compute_sources:
+            if self._whiten:
+                S = np.linalg.multi_dot([W, K, XT]).T
+            else:
+                S = np.dot(W, XT).T
+        else:
+            S = None
+
+        if self._whiten:
+            if self._whiten == "unit-variance":
+                if not compute_sources:
+                    S = np.linalg.multi_dot([W, K, XT]).T
+                S_std = np.std(S, axis=0, keepdims=True)
+                S /= S_std
+                W /= S_std.T
+
+            self.components_ = np.dot(W, K)
+            self.mean_ = X_mean
+            self.whitening_ = K
+        else:
+            self.components_ = W
+
+        self.mixing_ = linalg.pinv(self.components_, check_finite=False)
+        self._unmixing = W
+
+        return S
+
+    def fit_transform(self, X, y=None):
+        """Fit the model and recover the sources from X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Estimated sources obtained by transforming the data with the
+            estimated unmixing matrix.
+        """
+        return self._fit(X, compute_sources=True)
+
+    def fit(self, X, y=None):
+        """Fit the model to X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        self._fit(X, compute_sources=False)
+        return self
+
+    def transform(self, X, copy=True):
+        """Recover the sources from X (apply the unmixing matrix).
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Data to transform, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        copy : bool, default=True
+            If False, data passed to fit can be overwritten. Defaults to True.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Estimated sources obtained by transforming the data with the
+            estimated unmixing matrix.
+        """
+        check_is_fitted(self)
+
+        X = self._validate_data(
+            X, copy=(copy and self._whiten), dtype=[np.float64, np.float32], reset=False
+        )
+        if self._whiten:
+            X -= self.mean_
+
+        return np.dot(X, self.components_.T)
+
+    def inverse_transform(self, X, copy=True):
+        """Transform the sources back to the mixed data (apply mixing matrix).
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_components)
+            Sources, where `n_samples` is the number of samples
+            and `n_components` is the number of components.
+        copy : bool, default=True
+            If False, data passed to fit are overwritten. Defaults to True.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_features)
+            Reconstructed data obtained with the mixing matrix.
+        """
+        check_is_fitted(self)
+
+        X = check_array(X, copy=(copy and self._whiten), dtype=[np.float64, np.float32])
+        X = np.dot(X, self.mixing_.T)
+        if self._whiten:
+            X += self.mean_
+
+        return X
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]
+
+    def _more_tags(self):
+        return {"preserves_dtype": [np.float32, np.float64]}

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_incremental_pca.py

@@ -0,0 +1,393 @@
+"""Incremental Principal Components Analysis."""
+
+# Author: Kyle Kastner <kastnerkyle@gmail.com>
+#         Giorgio Patrini
+# License: BSD 3 clause
+
+import numpy as np
+from scipy import linalg, sparse
+
+from ._base import _BasePCA
+from ..utils import gen_batches
+from ..utils.extmath import svd_flip, _incremental_mean_and_var
+
+
+class IncrementalPCA(_BasePCA):
+    """Incremental principal components analysis (IPCA).
+
+    Linear dimensionality reduction using Singular Value Decomposition of
+    the data, keeping only the most significant singular vectors to
+    project the data to a lower dimensional space. The input data is centered
+    but not scaled for each feature before applying the SVD.
+
+    Depending on the size of the input data, this algorithm can be much more
+    memory efficient than a PCA, and allows sparse input.
+
+    This algorithm has constant memory complexity, on the order
+    of ``batch_size * n_features``, enabling use of np.memmap files without
+    loading the entire file into memory. For sparse matrices, the input
+    is converted to dense in batches (in order to be able to subtract the
+    mean) which avoids storing the entire dense matrix at any one time.
+
+    The computational overhead of each SVD is
+    ``O(batch_size * n_features ** 2)``, but only 2 * batch_size samples
+    remain in memory at a time. There will be ``n_samples / batch_size`` SVD
+    computations to get the principal components, versus 1 large SVD of
+    complexity ``O(n_samples * n_features ** 2)`` for PCA.
+
+    Read more in the :ref:`User Guide <IncrementalPCA>`.
+
+    .. versionadded:: 0.16
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Number of components to keep. If ``n_components`` is ``None``,
+        then ``n_components`` is set to ``min(n_samples, n_features)``.
+
+    whiten : bool, default=False
+        When True (False by default) the ``components_`` vectors are divided
+        by ``n_samples`` times ``components_`` to ensure uncorrelated outputs
+        with unit component-wise variances.
+
+        Whitening will remove some information from the transformed signal
+        (the relative variance scales of the components) but can sometimes
+        improve the predictive accuracy of the downstream estimators by
+        making data respect some hard-wired assumptions.
+
+    copy : bool, default=True
+        If False, X will be overwritten. ``copy=False`` can be used to
+        save memory but is unsafe for general use.
+
+    batch_size : int, default=None
+        The number of samples to use for each batch. Only used when calling
+        ``fit``. If ``batch_size`` is ``None``, then ``batch_size``
+        is inferred from the data and set to ``5 * n_features``, to provide a
+        balance between approximation accuracy and memory consumption.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Principal axes in feature space, representing the directions of
+        maximum variance in the data. Equivalently, the right singular
+        vectors of the centered input data, parallel to its eigenvectors.
+        The components are sorted by ``explained_variance_``.
+
+    explained_variance_ : ndarray of shape (n_components,)
+        Variance explained by each of the selected components.
+
+    explained_variance_ratio_ : ndarray of shape (n_components,)
+        Percentage of variance explained by each of the selected components.
+        If all components are stored, the sum of explained variances is equal
+        to 1.0.
+
+    singular_values_ : ndarray of shape (n_components,)
+        The singular values corresponding to each of the selected components.
+        The singular values are equal to the 2-norms of the ``n_components``
+        variables in the lower-dimensional space.
+
+    mean_ : ndarray of shape (n_features,)
+        Per-feature empirical mean, aggregate over calls to ``partial_fit``.
+
+    var_ : ndarray of shape (n_features,)
+        Per-feature empirical variance, aggregate over calls to
+        ``partial_fit``.
+
+    noise_variance_ : float
+        The estimated noise covariance following the Probabilistic PCA model
+        from Tipping and Bishop 1999. See "Pattern Recognition and
+        Machine Learning" by C. Bishop, 12.2.1 p. 574 or
+        http://www.miketipping.com/papers/met-mppca.pdf.
+
+    n_components_ : int
+        The estimated number of components. Relevant when
+        ``n_components=None``.
+
+    n_samples_seen_ : int
+        The number of samples processed by the estimator. Will be reset on
+        new calls to fit, but increments across ``partial_fit`` calls.
+
+    batch_size_ : int
+        Inferred batch size from ``batch_size``.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    PCA : Principal component analysis (PCA).
+    KernelPCA : Kernel Principal component analysis (KPCA).
+    SparsePCA : Sparse Principal Components Analysis (SparsePCA).
+    TruncatedSVD : Dimensionality reduction using truncated SVD.
+
+    Notes
+    -----
+    Implements the incremental PCA model from:
+    *D. Ross, J. Lim, R. Lin, M. Yang, Incremental Learning for Robust Visual
+    Tracking, International Journal of Computer Vision, Volume 77, Issue 1-3,
+    pp. 125-141, May 2008.*
+    See https://www.cs.toronto.edu/~dross/ivt/RossLimLinYang_ijcv.pdf
+
+    This model is an extension of the Sequential Karhunen-Loeve Transform from:
+    *A. Levy and M. Lindenbaum, Sequential Karhunen-Loeve Basis Extraction and
+    its Application to Images, IEEE Transactions on Image Processing, Volume 9,
+    Number 8, pp. 1371-1374, August 2000.*
+    See https://www.cs.technion.ac.il/~mic/doc/skl-ip.pdf
+
+    We have specifically abstained from an optimization used by authors of both
+    papers, a QR decomposition used in specific situations to reduce the
+    algorithmic complexity of the SVD. The source for this technique is
+    *Matrix Computations, Third Edition, G. Holub and C. Van Loan, Chapter 5,
+    section 5.4.4, pp 252-253.*. This technique has been omitted because it is
+    advantageous only when decomposing a matrix with ``n_samples`` (rows)
+    >= 5/3 * ``n_features`` (columns), and hurts the readability of the
+    implemented algorithm. This would be a good opportunity for future
+    optimization, if it is deemed necessary.
+
+    References
+    ----------
+    D. Ross, J. Lim, R. Lin, M. Yang. Incremental Learning for Robust Visual
+    Tracking, International Journal of Computer Vision, Volume 77,
+    Issue 1-3, pp. 125-141, May 2008.
+
+    G. Golub and C. Van Loan. Matrix Computations, Third Edition, Chapter 5,
+    Section 5.4.4, pp. 252-253.
+
+    Examples
+    --------
+    >>> from sklearn.datasets import load_digits
+    >>> from sklearn.decomposition import IncrementalPCA
+    >>> from scipy import sparse
+    >>> X, _ = load_digits(return_X_y=True)
+    >>> transformer = IncrementalPCA(n_components=7, batch_size=200)
+    >>> # either partially fit on smaller batches of data
+    >>> transformer.partial_fit(X[:100, :])
+    IncrementalPCA(batch_size=200, n_components=7)
+    >>> # or let the fit function itself divide the data into batches
+    >>> X_sparse = sparse.csr_matrix(X)
+    >>> X_transformed = transformer.fit_transform(X_sparse)
+    >>> X_transformed.shape
+    (1797, 7)
+    """
+
+    def __init__(self, n_components=None, *, whiten=False, copy=True, batch_size=None):
+        self.n_components = n_components
+        self.whiten = whiten
+        self.copy = copy
+        self.batch_size = batch_size
+
+    def fit(self, X, y=None):
+        """Fit the model with X, using minibatches of size batch_size.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        self.components_ = None
+        self.n_samples_seen_ = 0
+        self.mean_ = 0.0
+        self.var_ = 0.0
+        self.singular_values_ = None
+        self.explained_variance_ = None
+        self.explained_variance_ratio_ = None
+        self.noise_variance_ = None
+
+        X = self._validate_data(
+            X,
+            accept_sparse=["csr", "csc", "lil"],
+            copy=self.copy,
+            dtype=[np.float64, np.float32],
+        )
+        n_samples, n_features = X.shape
+
+        if self.batch_size is None:
+            self.batch_size_ = 5 * n_features
+        else:
+            self.batch_size_ = self.batch_size
+
+        for batch in gen_batches(
+            n_samples, self.batch_size_, min_batch_size=self.n_components or 0
+        ):
+            X_batch = X[batch]
+            if sparse.issparse(X_batch):
+                X_batch = X_batch.toarray()
+            self.partial_fit(X_batch, check_input=False)
+
+        return self
+
+    def partial_fit(self, X, y=None, check_input=True):
+        """Incremental fit with X. All of X is processed as a single batch.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        check_input : bool, default=True
+            Run check_array on X.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        first_pass = not hasattr(self, "components_")
+        if check_input:
+            if sparse.issparse(X):
+                raise TypeError(
+                    "IncrementalPCA.partial_fit does not support "
+                    "sparse input. Either convert data to dense "
+                    "or use IncrementalPCA.fit to do so in batches."
+                )
+            X = self._validate_data(
+                X, copy=self.copy, dtype=[np.float64, np.float32], reset=first_pass
+            )
+        n_samples, n_features = X.shape
+        if first_pass:
+            self.components_ = None
+
+        if self.n_components is None:
+            if self.components_ is None:
+                self.n_components_ = min(n_samples, n_features)
+            else:
+                self.n_components_ = self.components_.shape[0]
+        elif not 1 <= self.n_components <= n_features:
+            raise ValueError(
+                "n_components=%r invalid for n_features=%d, need "
+                "more rows than columns for IncrementalPCA "
+                "processing" % (self.n_components, n_features)
+            )
+        elif not self.n_components <= n_samples:
+            raise ValueError(
+                "n_components=%r must be less or equal to "
+                "the batch number of samples "
+                "%d." % (self.n_components, n_samples)
+            )
+        else:
+            self.n_components_ = self.n_components
+
+        if (self.components_ is not None) and (
+            self.components_.shape[0] != self.n_components_
+        ):
+            raise ValueError(
+                "Number of input features has changed from %i "
+                "to %i between calls to partial_fit! Try "
+                "setting n_components to a fixed value."
+                % (self.components_.shape[0], self.n_components_)
+            )
+
+        # This is the first partial_fit
+        if not hasattr(self, "n_samples_seen_"):
+            self.n_samples_seen_ = 0
+            self.mean_ = 0.0
+            self.var_ = 0.0
+
+        # Update stats - they are 0 if this is the first step
+        col_mean, col_var, n_total_samples = _incremental_mean_and_var(
+            X,
+            last_mean=self.mean_,
+            last_variance=self.var_,
+            last_sample_count=np.repeat(self.n_samples_seen_, X.shape[1]),
+        )
+        n_total_samples = n_total_samples[0]
+
+        # Whitening
+        if self.n_samples_seen_ == 0:
+            # If it is the first step, simply whiten X
+            X -= col_mean
+        else:
+            col_batch_mean = np.mean(X, axis=0)
+            X -= col_batch_mean
+            # Build matrix of combined previous basis and new data
+            mean_correction = np.sqrt(
+                (self.n_samples_seen_ / n_total_samples) * n_samples
+            ) * (self.mean_ - col_batch_mean)
+            X = np.vstack(
+                (
+                    self.singular_values_.reshape((-1, 1)) * self.components_,
+                    X,
+                    mean_correction,
+                )
+            )
+
+        U, S, Vt = linalg.svd(X, full_matrices=False, check_finite=False)
+        U, Vt = svd_flip(U, Vt, u_based_decision=False)
+        explained_variance = S**2 / (n_total_samples - 1)
+        explained_variance_ratio = S**2 / np.sum(col_var * n_total_samples)
+
+        self.n_samples_seen_ = n_total_samples
+        self.components_ = Vt[: self.n_components_]
+        self.singular_values_ = S[: self.n_components_]
+        self.mean_ = col_mean
+        self.var_ = col_var
+        self.explained_variance_ = explained_variance[: self.n_components_]
+        self.explained_variance_ratio_ = explained_variance_ratio[: self.n_components_]
+        # we already checked `self.n_components <= n_samples` above
+        if self.n_components_ not in (n_samples, n_features):
+            self.noise_variance_ = explained_variance[self.n_components_ :].mean()
+        else:
+            self.noise_variance_ = 0.0
+        return self
+
+    def transform(self, X):
+        """Apply dimensionality reduction to X.
+
+        X is projected on the first principal components previously extracted
+        from a training set, using minibatches of size batch_size if X is
+        sparse.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Projection of X in the first principal components.
+
+        Examples
+        --------
+
+        >>> import numpy as np
+        >>> from sklearn.decomposition import IncrementalPCA
+        >>> X = np.array([[-1, -1], [-2, -1], [-3, -2],
+        ...               [1, 1], [2, 1], [3, 2]])
+        >>> ipca = IncrementalPCA(n_components=2, batch_size=3)
+        >>> ipca.fit(X)
+        IncrementalPCA(batch_size=3, n_components=2)
+        >>> ipca.transform(X) # doctest: +SKIP
+        """
+        if sparse.issparse(X):
+            n_samples = X.shape[0]
+            output = []
+            for batch in gen_batches(
+                n_samples, self.batch_size_, min_batch_size=self.n_components or 0
+            ):
+                output.append(super().transform(X[batch].toarray()))
+            return np.vstack(output)
+        else:
+            return super().transform(X)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_kernel_pca.py

@@ -0,0 +1,556 @@
+"""Kernel Principal Components Analysis."""
+
+# Author: Mathieu Blondel <mathieu@mblondel.org>
+#         Sylvain Marie <sylvain.marie@schneider-electric.com>
+# License: BSD 3 clause
+
+import numpy as np
+import numbers
+from scipy import linalg
+from scipy.sparse.linalg import eigsh
+
+from ..utils._arpack import _init_arpack_v0
+from ..utils.extmath import svd_flip, _randomized_eigsh
+from ..utils.validation import (
+    check_is_fitted,
+    _check_psd_eigenvalues,
+    check_scalar,
+)
+from ..utils.deprecation import deprecated
+from ..exceptions import NotFittedError
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..preprocessing import KernelCenterer
+from ..metrics.pairwise import pairwise_kernels
+
+
+class KernelPCA(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
+    """Kernel Principal component analysis (KPCA) [1]_.
+
+    Non-linear dimensionality reduction through the use of kernels (see
+    :ref:`metrics`).
+
+    It uses the :func:`scipy.linalg.eigh` LAPACK implementation of the full SVD
+    or the :func:`scipy.sparse.linalg.eigsh` ARPACK implementation of the
+    truncated SVD, depending on the shape of the input data and the number of
+    components to extract. It can also use a randomized truncated SVD by the
+    method proposed in [3]_, see `eigen_solver`.
+
+    Read more in the :ref:`User Guide <kernel_PCA>`.
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Number of components. If None, all non-zero components are kept.
+
+    kernel : {'linear', 'poly', \
+            'rbf', 'sigmoid', 'cosine', 'precomputed'}, default='linear'
+        Kernel used for PCA.
+
+    gamma : float, default=None
+        Kernel coefficient for rbf, poly and sigmoid kernels. Ignored by other
+        kernels. If ``gamma`` is ``None``, then it is set to ``1/n_features``.
+
+    degree : int, default=3
+        Degree for poly kernels. Ignored by other kernels.
+
+    coef0 : float, default=1
+        Independent term in poly and sigmoid kernels.
+        Ignored by other kernels.
+
+    kernel_params : dict, default=None
+        Parameters (keyword arguments) and
+        values for kernel passed as callable object.
+        Ignored by other kernels.
+
+    alpha : float, default=1.0
+        Hyperparameter of the ridge regression that learns the
+        inverse transform (when fit_inverse_transform=True).
+
+    fit_inverse_transform : bool, default=False
+        Learn the inverse transform for non-precomputed kernels
+        (i.e. learn to find the pre-image of a point). This method is based
+        on [2]_.
+
+    eigen_solver : {'auto', 'dense', 'arpack', 'randomized'}, \
+            default='auto'
+        Select eigensolver to use. If `n_components` is much
+        less than the number of training samples, randomized (or arpack to a
+        smaller extent) may be more efficient than the dense eigensolver.
+        Randomized SVD is performed according to the method of Halko et al
+        [3]_.
+
+        auto :
+            the solver is selected by a default policy based on n_samples
+            (the number of training samples) and `n_components`:
+            if the number of components to extract is less than 10 (strict) and
+            the number of samples is more than 200 (strict), the 'arpack'
+            method is enabled. Otherwise the exact full eigenvalue
+            decomposition is computed and optionally truncated afterwards
+            ('dense' method).
+        dense :
+            run exact full eigenvalue decomposition calling the standard
+            LAPACK solver via `scipy.linalg.eigh`, and select the components
+            by postprocessing
+        arpack :
+            run SVD truncated to n_components calling ARPACK solver using
+            `scipy.sparse.linalg.eigsh`. It requires strictly
+            0 < n_components < n_samples
+        randomized :
+            run randomized SVD by the method of Halko et al. [3]_. The current
+            implementation selects eigenvalues based on their module; therefore
+            using this method can lead to unexpected results if the kernel is
+            not positive semi-definite. See also [4]_.
+
+        .. versionchanged:: 1.0
+           `'randomized'` was added.
+
+    tol : float, default=0
+        Convergence tolerance for arpack.
+        If 0, optimal value will be chosen by arpack.
+
+    max_iter : int, default=None
+        Maximum number of iterations for arpack.
+        If None, optimal value will be chosen by arpack.
+
+    iterated_power : int >= 0, or 'auto', default='auto'
+        Number of iterations for the power method computed by
+        svd_solver == 'randomized'. When 'auto', it is set to 7 when
+        `n_components < 0.1 * min(X.shape)`, other it is set to 4.
+
+        .. versionadded:: 1.0
+
+    remove_zero_eig : bool, default=False
+        If True, then all components with zero eigenvalues are removed, so
+        that the number of components in the output may be < n_components
+        (and sometimes even zero due to numerical instability).
+        When n_components is None, this parameter is ignored and components
+        with zero eigenvalues are removed regardless.
+
+    random_state : int, RandomState instance or None, default=None
+        Used when ``eigen_solver`` == 'arpack' or 'randomized'. Pass an int
+        for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+        .. versionadded:: 0.18
+
+    copy_X : bool, default=True
+        If True, input X is copied and stored by the model in the `X_fit_`
+        attribute. If no further changes will be done to X, setting
+        `copy_X=False` saves memory by storing a reference.
+
+        .. versionadded:: 0.18
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+        .. versionadded:: 0.18
+
+    Attributes
+    ----------
+    eigenvalues_ : ndarray of shape (n_components,)
+        Eigenvalues of the centered kernel matrix in decreasing order.
+        If `n_components` and `remove_zero_eig` are not set,
+        then all values are stored.
+
+    lambdas_ : ndarray of shape (n_components,)
+        Same as `eigenvalues_` but this attribute is deprecated.
+
+        .. deprecated:: 1.0
+           `lambdas_` was renamed to `eigenvalues_` in version 1.0 and will be
+           removed in 1.2.
+
+    eigenvectors_ : ndarray of shape (n_samples, n_components)
+        Eigenvectors of the centered kernel matrix. If `n_components` and
+        `remove_zero_eig` are not set, then all components are stored.
+
+    alphas_ : ndarray of shape (n_samples, n_components)
+        Same as `eigenvectors_` but this attribute is deprecated.
+
+        .. deprecated:: 1.0
+           `alphas_` was renamed to `eigenvectors_` in version 1.0 and will be
+           removed in 1.2.
+
+    dual_coef_ : ndarray of shape (n_samples, n_features)
+        Inverse transform matrix. Only available when
+        ``fit_inverse_transform`` is True.
+
+    X_transformed_fit_ : ndarray of shape (n_samples, n_components)
+        Projection of the fitted data on the kernel principal components.
+        Only available when ``fit_inverse_transform`` is True.
+
+    X_fit_ : ndarray of shape (n_samples, n_features)
+        The data used to fit the model. If `copy_X=False`, then `X_fit_` is
+        a reference. This attribute is used for the calls to transform.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    FastICA : A fast algorithm for Independent Component Analysis.
+    IncrementalPCA : Incremental Principal Component Analysis.
+    NMF : Non-Negative Matrix Factorization.
+    PCA : Principal Component Analysis.
+    SparsePCA : Sparse Principal Component Analysis.
+    TruncatedSVD : Dimensionality reduction using truncated SVD.
+
+    References
+    ----------
+    .. [1] `Schölkopf, Bernhard, Alexander Smola, and Klaus-Robert Müller.
+       "Kernel principal component analysis."
+       International conference on artificial neural networks.
+       Springer, Berlin, Heidelberg, 1997.
+       <https://people.eecs.berkeley.edu/~wainwrig/stat241b/scholkopf_kernel.pdf>`_
+
+    .. [2] `Bakır, Gökhan H., Jason Weston, and Bernhard Schölkopf.
+       "Learning to find pre-images."
+       Advances in neural information processing systems 16 (2004): 449-456.
+       <https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.68.5164&rep=rep1&type=pdf>`_
+
+    .. [3] :arxiv:`Halko, Nathan, Per-Gunnar Martinsson, and Joel A. Tropp.
+       "Finding structure with randomness: Probabilistic algorithms for
+       constructing approximate matrix decompositions."
+       SIAM review 53.2 (2011): 217-288. <0909.4061>`
+
+    .. [4] `Martinsson, Per-Gunnar, Vladimir Rokhlin, and Mark Tygert.
+       "A randomized algorithm for the decomposition of matrices."
+       Applied and Computational Harmonic Analysis 30.1 (2011): 47-68.
+       <https://www.sciencedirect.com/science/article/pii/S1063520310000242>`_
+
+    Examples
+    --------
+    >>> from sklearn.datasets import load_digits
+    >>> from sklearn.decomposition import KernelPCA
+    >>> X, _ = load_digits(return_X_y=True)
+    >>> transformer = KernelPCA(n_components=7, kernel='linear')
+    >>> X_transformed = transformer.fit_transform(X)
+    >>> X_transformed.shape
+    (1797, 7)
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        kernel="linear",
+        gamma=None,
+        degree=3,
+        coef0=1,
+        kernel_params=None,
+        alpha=1.0,
+        fit_inverse_transform=False,
+        eigen_solver="auto",
+        tol=0,
+        max_iter=None,
+        iterated_power="auto",
+        remove_zero_eig=False,
+        random_state=None,
+        copy_X=True,
+        n_jobs=None,
+    ):
+        self.n_components = n_components
+        self.kernel = kernel
+        self.kernel_params = kernel_params
+        self.gamma = gamma
+        self.degree = degree
+        self.coef0 = coef0
+        self.alpha = alpha
+        self.fit_inverse_transform = fit_inverse_transform
+        self.eigen_solver = eigen_solver
+        self.tol = tol
+        self.max_iter = max_iter
+        self.iterated_power = iterated_power
+        self.remove_zero_eig = remove_zero_eig
+        self.random_state = random_state
+        self.n_jobs = n_jobs
+        self.copy_X = copy_X
+
+    # TODO: Remove in 1.2
+    # mypy error: Decorated property not supported
+    @deprecated(  # type: ignore
+        "Attribute `lambdas_` was deprecated in version 1.0 and will be "
+        "removed in 1.2. Use `eigenvalues_` instead."
+    )
+    @property
+    def lambdas_(self):
+        return self.eigenvalues_
+
+    # mypy error: Decorated property not supported
+    @deprecated(  # type: ignore
+        "Attribute `alphas_` was deprecated in version 1.0 and will be "
+        "removed in 1.2. Use `eigenvectors_` instead."
+    )
+    @property
+    def alphas_(self):
+        return self.eigenvectors_
+
+    def _get_kernel(self, X, Y=None):
+        if callable(self.kernel):
+            params = self.kernel_params or {}
+        else:
+            params = {"gamma": self.gamma, "degree": self.degree, "coef0": self.coef0}
+        return pairwise_kernels(
+            X, Y, metric=self.kernel, filter_params=True, n_jobs=self.n_jobs, **params
+        )
+
+    def _fit_transform(self, K):
+        """Fit's using kernel K"""
+        # center kernel
+        K = self._centerer.fit_transform(K)
+
+        # adjust n_components according to user inputs
+        if self.n_components is None:
+            n_components = K.shape[0]  # use all dimensions
+        else:
+            check_scalar(self.n_components, "n_components", numbers.Integral, min_val=1)
+            n_components = min(K.shape[0], self.n_components)
+
+        # compute eigenvectors
+        if self.eigen_solver == "auto":
+            if K.shape[0] > 200 and n_components < 10:
+                eigen_solver = "arpack"
+            else:
+                eigen_solver = "dense"
+        else:
+            eigen_solver = self.eigen_solver
+
+        if eigen_solver == "dense":
+            # Note: eigvals specifies the indices of smallest/largest to return
+            self.eigenvalues_, self.eigenvectors_ = linalg.eigh(
+                K, eigvals=(K.shape[0] - n_components, K.shape[0] - 1)
+            )
+        elif eigen_solver == "arpack":
+            v0 = _init_arpack_v0(K.shape[0], self.random_state)
+            self.eigenvalues_, self.eigenvectors_ = eigsh(
+                K, n_components, which="LA", tol=self.tol, maxiter=self.max_iter, v0=v0
+            )
+        elif eigen_solver == "randomized":
+            self.eigenvalues_, self.eigenvectors_ = _randomized_eigsh(
+                K,
+                n_components=n_components,
+                n_iter=self.iterated_power,
+                random_state=self.random_state,
+                selection="module",
+            )
+        else:
+            raise ValueError("Unsupported value for `eigen_solver`: %r" % eigen_solver)
+
+        # make sure that the eigenvalues are ok and fix numerical issues
+        self.eigenvalues_ = _check_psd_eigenvalues(
+            self.eigenvalues_, enable_warnings=False
+        )
+
+        # flip eigenvectors' sign to enforce deterministic output
+        self.eigenvectors_, _ = svd_flip(
+            self.eigenvectors_, np.zeros_like(self.eigenvectors_).T
+        )
+
+        # sort eigenvectors in descending order
+        indices = self.eigenvalues_.argsort()[::-1]
+        self.eigenvalues_ = self.eigenvalues_[indices]
+        self.eigenvectors_ = self.eigenvectors_[:, indices]
+
+        # remove eigenvectors with a zero eigenvalue (null space) if required
+        if self.remove_zero_eig or self.n_components is None:
+            self.eigenvectors_ = self.eigenvectors_[:, self.eigenvalues_ > 0]
+            self.eigenvalues_ = self.eigenvalues_[self.eigenvalues_ > 0]
+
+        # Maintenance note on Eigenvectors normalization
+        # ----------------------------------------------
+        # there is a link between
+        # the eigenvectors of K=Phi(X)'Phi(X) and the ones of Phi(X)Phi(X)'
+        # if v is an eigenvector of K
+        #     then Phi(X)v  is an eigenvector of Phi(X)Phi(X)'
+        # if u is an eigenvector of Phi(X)Phi(X)'
+        #     then Phi(X)'u is an eigenvector of Phi(X)'Phi(X)
+        #
+        # At this stage our self.eigenvectors_ (the v) have norm 1, we need to scale
+        # them so that eigenvectors in kernel feature space (the u) have norm=1
+        # instead
+        #
+        # We COULD scale them here:
+        #       self.eigenvectors_ = self.eigenvectors_ / np.sqrt(self.eigenvalues_)
+        #
+        # But choose to perform that LATER when needed, in `fit()` and in
+        # `transform()`.
+
+        return K
+
+    def _fit_inverse_transform(self, X_transformed, X):
+        if hasattr(X, "tocsr"):
+            raise NotImplementedError(
+                "Inverse transform not implemented for sparse matrices!"
+            )
+
+        n_samples = X_transformed.shape[0]
+        K = self._get_kernel(X_transformed)
+        K.flat[:: n_samples + 1] += self.alpha
+        self.dual_coef_ = linalg.solve(K, X, sym_pos=True, overwrite_a=True)
+        self.X_transformed_fit_ = X_transformed
+
+    def fit(self, X, y=None):
+        """Fit the model from data in X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        if self.fit_inverse_transform and self.kernel == "precomputed":
+            raise ValueError("Cannot fit_inverse_transform with a precomputed kernel.")
+        X = self._validate_data(X, accept_sparse="csr", copy=self.copy_X)
+        self._centerer = KernelCenterer()
+        K = self._get_kernel(X)
+        self._fit_transform(K)
+
+        if self.fit_inverse_transform:
+            # no need to use the kernel to transform X, use shortcut expression
+            X_transformed = self.eigenvectors_ * np.sqrt(self.eigenvalues_)
+
+            self._fit_inverse_transform(X_transformed, X)
+
+        self.X_fit_ = X
+        return self
+
+    def fit_transform(self, X, y=None, **params):
+        """Fit the model from data in X and transform X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        **params : kwargs
+            Parameters (keyword arguments) and values passed to
+            the fit_transform instance.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Returns the instance itself.
+        """
+        self.fit(X, **params)
+
+        # no need to use the kernel to transform X, use shortcut expression
+        X_transformed = self.eigenvectors_ * np.sqrt(self.eigenvalues_)
+
+        if self.fit_inverse_transform:
+            self._fit_inverse_transform(X_transformed, X)
+
+        return X_transformed
+
+    def transform(self, X):
+        """Transform X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Returns the instance itself.
+        """
+        check_is_fitted(self)
+        X = self._validate_data(X, accept_sparse="csr", reset=False)
+
+        # Compute centered gram matrix between X and training data X_fit_
+        K = self._centerer.transform(self._get_kernel(X, self.X_fit_))
+
+        # scale eigenvectors (properly account for null-space for dot product)
+        non_zeros = np.flatnonzero(self.eigenvalues_)
+        scaled_alphas = np.zeros_like(self.eigenvectors_)
+        scaled_alphas[:, non_zeros] = self.eigenvectors_[:, non_zeros] / np.sqrt(
+            self.eigenvalues_[non_zeros]
+        )
+
+        # Project with a scalar product between K and the scaled eigenvectors
+        return np.dot(K, scaled_alphas)
+
+    def inverse_transform(self, X):
+        """Transform X back to original space.
+
+        ``inverse_transform`` approximates the inverse transformation using
+        a learned pre-image. The pre-image is learned by kernel ridge
+        regression of the original data on their low-dimensional representation
+        vectors.
+
+        .. note:
+            :meth:`~sklearn.decomposition.fit` internally uses a centered
+            kernel. As the centered kernel no longer contains the information
+            of the mean of kernel features, such information is not taken into
+            account in reconstruction.
+
+        .. note::
+            When users want to compute inverse transformation for 'linear'
+            kernel, it is recommended that they use
+            :class:`~sklearn.decomposition.PCA` instead. Unlike
+            :class:`~sklearn.decomposition.PCA`,
+            :class:`~sklearn.decomposition.KernelPCA`'s ``inverse_transform``
+            does not reconstruct the mean of data when 'linear' kernel is used
+            due to the use of centered kernel.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_components)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_features)
+            Returns the instance itself.
+
+        References
+        ----------
+        `Bakır, Gökhan H., Jason Weston, and Bernhard Schölkopf.
+        "Learning to find pre-images."
+        Advances in neural information processing systems 16 (2004): 449-456.
+        <https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.68.5164&rep=rep1&type=pdf>`_
+        """
+        if not self.fit_inverse_transform:
+            raise NotFittedError(
+                "The fit_inverse_transform parameter was not"
+                " set to True when instantiating and hence "
+                "the inverse transform is not available."
+            )
+
+        K = self._get_kernel(X, self.X_transformed_fit_)
+        return np.dot(K, self.dual_coef_)
+
+    def _more_tags(self):
+        return {
+            "preserves_dtype": [np.float64, np.float32],
+            "pairwise": self.kernel == "precomputed",
+        }
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.eigenvalues_.shape[0]

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_lda.py

@@ -0,0 +1,896 @@
+"""
+
+=============================================================
+Online Latent Dirichlet Allocation with variational inference
+=============================================================
+
+This implementation is modified from Matthew D. Hoffman's onlineldavb code
+Link: https://github.com/blei-lab/onlineldavb
+"""
+
+# Author: Chyi-Kwei Yau
+# Author: Matthew D. Hoffman (original onlineldavb implementation)
+
+import numpy as np
+import scipy.sparse as sp
+from scipy.special import gammaln, logsumexp
+from joblib import Parallel, effective_n_jobs
+
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..utils import check_random_state, gen_batches, gen_even_slices
+from ..utils.validation import check_non_negative
+from ..utils.validation import check_is_fitted
+from ..utils.fixes import delayed
+
+from ._online_lda_fast import (
+    mean_change,
+    _dirichlet_expectation_1d,
+    _dirichlet_expectation_2d,
+)
+
+EPS = np.finfo(float).eps
+
+
+def _update_doc_distribution(
+    X,
+    exp_topic_word_distr,
+    doc_topic_prior,
+    max_doc_update_iter,
+    mean_change_tol,
+    cal_sstats,
+    random_state,
+):
+    """E-step: update document-topic distribution.
+
+    Parameters
+    ----------
+    X : {array-like, sparse matrix} of shape (n_samples, n_features)
+        Document word matrix.
+
+    exp_topic_word_distr : ndarray of shape (n_topics, n_features)
+        Exponential value of expectation of log topic word distribution.
+        In the literature, this is `exp(E[log(beta)])`.
+
+    doc_topic_prior : float
+        Prior of document topic distribution `theta`.
+
+    max_doc_update_iter : int
+        Max number of iterations for updating document topic distribution in
+        the E-step.
+
+    mean_change_tol : float
+        Stopping tolerance for updating document topic distribution in E-step.
+
+    cal_sstats : bool
+        Parameter that indicate to calculate sufficient statistics or not.
+        Set `cal_sstats` to `True` when we need to run M-step.
+
+    random_state : RandomState instance or None
+        Parameter that indicate how to initialize document topic distribution.
+        Set `random_state` to None will initialize document topic distribution
+        to a constant number.
+
+    Returns
+    -------
+    (doc_topic_distr, suff_stats) :
+        `doc_topic_distr` is unnormalized topic distribution for each document.
+        In the literature, this is `gamma`. we can calculate `E[log(theta)]`
+        from it.
+        `suff_stats` is expected sufficient statistics for the M-step.
+            When `cal_sstats == False`, this will be None.
+
+    """
+    is_sparse_x = sp.issparse(X)
+    n_samples, n_features = X.shape
+    n_topics = exp_topic_word_distr.shape[0]
+
+    if random_state:
+        doc_topic_distr = random_state.gamma(100.0, 0.01, (n_samples, n_topics))
+    else:
+        doc_topic_distr = np.ones((n_samples, n_topics))
+
+    # In the literature, this is `exp(E[log(theta)])`
+    exp_doc_topic = np.exp(_dirichlet_expectation_2d(doc_topic_distr))
+
+    # diff on `component_` (only calculate it when `cal_diff` is True)
+    suff_stats = np.zeros(exp_topic_word_distr.shape) if cal_sstats else None
+
+    if is_sparse_x:
+        X_data = X.data
+        X_indices = X.indices
+        X_indptr = X.indptr
+
+    for idx_d in range(n_samples):
+        if is_sparse_x:
+            ids = X_indices[X_indptr[idx_d] : X_indptr[idx_d + 1]]
+            cnts = X_data[X_indptr[idx_d] : X_indptr[idx_d + 1]]
+        else:
+            ids = np.nonzero(X[idx_d, :])[0]
+            cnts = X[idx_d, ids]
+
+        doc_topic_d = doc_topic_distr[idx_d, :]
+        # The next one is a copy, since the inner loop overwrites it.
+        exp_doc_topic_d = exp_doc_topic[idx_d, :].copy()
+        exp_topic_word_d = exp_topic_word_distr[:, ids]
+
+        # Iterate between `doc_topic_d` and `norm_phi` until convergence
+        for _ in range(0, max_doc_update_iter):
+            last_d = doc_topic_d
+
+            # The optimal phi_{dwk} is proportional to
+            # exp(E[log(theta_{dk})]) * exp(E[log(beta_{dw})]).
+            norm_phi = np.dot(exp_doc_topic_d, exp_topic_word_d) + EPS
+
+            doc_topic_d = exp_doc_topic_d * np.dot(cnts / norm_phi, exp_topic_word_d.T)
+            # Note: adds doc_topic_prior to doc_topic_d, in-place.
+            _dirichlet_expectation_1d(doc_topic_d, doc_topic_prior, exp_doc_topic_d)
+
+            if mean_change(last_d, doc_topic_d) < mean_change_tol:
+                break
+        doc_topic_distr[idx_d, :] = doc_topic_d
+
+        # Contribution of document d to the expected sufficient
+        # statistics for the M step.
+        if cal_sstats:
+            norm_phi = np.dot(exp_doc_topic_d, exp_topic_word_d) + EPS
+            suff_stats[:, ids] += np.outer(exp_doc_topic_d, cnts / norm_phi)
+
+    return (doc_topic_distr, suff_stats)
+
+
+class LatentDirichletAllocation(
+    _ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator
+):
+    """Latent Dirichlet Allocation with online variational Bayes algorithm.
+
+    The implementation is based on [1]_ and [2]_.
+
+    .. versionadded:: 0.17
+
+    Read more in the :ref:`User Guide <LatentDirichletAllocation>`.
+
+    Parameters
+    ----------
+    n_components : int, default=10
+        Number of topics.
+
+        .. versionchanged:: 0.19
+            ``n_topics`` was renamed to ``n_components``
+
+    doc_topic_prior : float, default=None
+        Prior of document topic distribution `theta`. If the value is None,
+        defaults to `1 / n_components`.
+        In [1]_, this is called `alpha`.
+
+    topic_word_prior : float, default=None
+        Prior of topic word distribution `beta`. If the value is None, defaults
+        to `1 / n_components`.
+        In [1]_, this is called `eta`.
+
+    learning_method : {'batch', 'online'}, default='batch'
+        Method used to update `_component`. Only used in :meth:`fit` method.
+        In general, if the data size is large, the online update will be much
+        faster than the batch update.
+
+        Valid options::
+
+            'batch': Batch variational Bayes method. Use all training data in
+                each EM update.
+                Old `components_` will be overwritten in each iteration.
+            'online': Online variational Bayes method. In each EM update, use
+                mini-batch of training data to update the ``components_``
+                variable incrementally. The learning rate is controlled by the
+                ``learning_decay`` and the ``learning_offset`` parameters.
+
+        .. versionchanged:: 0.20
+            The default learning method is now ``"batch"``.
+
+    learning_decay : float, default=0.7
+        It is a parameter that control learning rate in the online learning
+        method. The value should be set between (0.5, 1.0] to guarantee
+        asymptotic convergence. When the value is 0.0 and batch_size is
+        ``n_samples``, the update method is same as batch learning. In the
+        literature, this is called kappa.
+
+    learning_offset : float, default=10.0
+        A (positive) parameter that downweights early iterations in online
+        learning.  It should be greater than 1.0. In the literature, this is
+        called tau_0.
+
+    max_iter : int, default=10
+        The maximum number of passes over the training data (aka epochs).
+        It only impacts the behavior in the :meth:`fit` method, and not the
+        :meth:`partial_fit` method.
+
+    batch_size : int, default=128
+        Number of documents to use in each EM iteration. Only used in online
+        learning.
+
+    evaluate_every : int, default=-1
+        How often to evaluate perplexity. Only used in `fit` method.
+        set it to 0 or negative number to not evaluate perplexity in
+        training at all. Evaluating perplexity can help you check convergence
+        in training process, but it will also increase total training time.
+        Evaluating perplexity in every iteration might increase training time
+        up to two-fold.
+
+    total_samples : int, default=1e6
+        Total number of documents. Only used in the :meth:`partial_fit` method.
+
+    perp_tol : float, default=1e-1
+        Perplexity tolerance in batch learning. Only used when
+        ``evaluate_every`` is greater than 0.
+
+    mean_change_tol : float, default=1e-3
+        Stopping tolerance for updating document topic distribution in E-step.
+
+    max_doc_update_iter : int, default=100
+        Max number of iterations for updating document topic distribution in
+        the E-step.
+
+    n_jobs : int, default=None
+        The number of jobs to use in the E-step.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    verbose : int, default=0
+        Verbosity level.
+
+    random_state : int, RandomState instance or None, default=None
+        Pass an int for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Variational parameters for topic word distribution. Since the complete
+        conditional for topic word distribution is a Dirichlet,
+        ``components_[i, j]`` can be viewed as pseudocount that represents the
+        number of times word `j` was assigned to topic `i`.
+        It can also be viewed as distribution over the words for each topic
+        after normalization:
+        ``model.components_ / model.components_.sum(axis=1)[:, np.newaxis]``.
+
+    exp_dirichlet_component_ : ndarray of shape (n_components, n_features)
+        Exponential value of expectation of log topic word distribution.
+        In the literature, this is `exp(E[log(beta)])`.
+
+    n_batch_iter_ : int
+        Number of iterations of the EM step.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_iter_ : int
+        Number of passes over the dataset.
+
+    bound_ : float
+        Final perplexity score on training set.
+
+    doc_topic_prior_ : float
+        Prior of document topic distribution `theta`. If the value is None,
+        it is `1 / n_components`.
+
+    random_state_ : RandomState instance
+        RandomState instance that is generated either from a seed, the random
+        number generator or by `np.random`.
+
+    topic_word_prior_ : float
+        Prior of topic word distribution `beta`. If the value is None, it is
+        `1 / n_components`.
+
+    See Also
+    --------
+    sklearn.discriminant_analysis.LinearDiscriminantAnalysis:
+        A classifier with a linear decision boundary, generated by fitting
+        class conditional densities to the data and using Bayes’ rule.
+
+    References
+    ----------
+    .. [1] "Online Learning for Latent Dirichlet Allocation", Matthew D.
+           Hoffman, David M. Blei, Francis Bach, 2010
+           https://github.com/blei-lab/onlineldavb
+
+    .. [2] "Stochastic Variational Inference", Matthew D. Hoffman,
+           David M. Blei, Chong Wang, John Paisley, 2013
+
+    Examples
+    --------
+    >>> from sklearn.decomposition import LatentDirichletAllocation
+    >>> from sklearn.datasets import make_multilabel_classification
+    >>> # This produces a feature matrix of token counts, similar to what
+    >>> # CountVectorizer would produce on text.
+    >>> X, _ = make_multilabel_classification(random_state=0)
+    >>> lda = LatentDirichletAllocation(n_components=5,
+    ...     random_state=0)
+    >>> lda.fit(X)
+    LatentDirichletAllocation(...)
+    >>> # get topics for some given samples:
+    >>> lda.transform(X[-2:])
+    array([[0.00360392, 0.25499205, 0.0036211 , 0.64236448, 0.09541846],
+           [0.15297572, 0.00362644, 0.44412786, 0.39568399, 0.003586  ]])
+    """
+
+    def __init__(
+        self,
+        n_components=10,
+        *,
+        doc_topic_prior=None,
+        topic_word_prior=None,
+        learning_method="batch",
+        learning_decay=0.7,
+        learning_offset=10.0,
+        max_iter=10,
+        batch_size=128,
+        evaluate_every=-1,
+        total_samples=1e6,
+        perp_tol=1e-1,
+        mean_change_tol=1e-3,
+        max_doc_update_iter=100,
+        n_jobs=None,
+        verbose=0,
+        random_state=None,
+    ):
+        self.n_components = n_components
+        self.doc_topic_prior = doc_topic_prior
+        self.topic_word_prior = topic_word_prior
+        self.learning_method = learning_method
+        self.learning_decay = learning_decay
+        self.learning_offset = learning_offset
+        self.max_iter = max_iter
+        self.batch_size = batch_size
+        self.evaluate_every = evaluate_every
+        self.total_samples = total_samples
+        self.perp_tol = perp_tol
+        self.mean_change_tol = mean_change_tol
+        self.max_doc_update_iter = max_doc_update_iter
+        self.n_jobs = n_jobs
+        self.verbose = verbose
+        self.random_state = random_state
+
+    def _check_params(self):
+        """Check model parameters."""
+        if self.n_components <= 0:
+            raise ValueError("Invalid 'n_components' parameter: %r" % self.n_components)
+
+        if self.total_samples <= 0:
+            raise ValueError(
+                "Invalid 'total_samples' parameter: %r" % self.total_samples
+            )
+
+        if self.learning_offset < 0:
+            raise ValueError(
+                "Invalid 'learning_offset' parameter: %r" % self.learning_offset
+            )
+
+        if self.learning_method not in ("batch", "online"):
+            raise ValueError(
+                "Invalid 'learning_method' parameter: %r" % self.learning_method
+            )
+
+    def _init_latent_vars(self, n_features):
+        """Initialize latent variables."""
+
+        self.random_state_ = check_random_state(self.random_state)
+        self.n_batch_iter_ = 1
+        self.n_iter_ = 0
+
+        if self.doc_topic_prior is None:
+            self.doc_topic_prior_ = 1.0 / self.n_components
+        else:
+            self.doc_topic_prior_ = self.doc_topic_prior
+
+        if self.topic_word_prior is None:
+            self.topic_word_prior_ = 1.0 / self.n_components
+        else:
+            self.topic_word_prior_ = self.topic_word_prior
+
+        init_gamma = 100.0
+        init_var = 1.0 / init_gamma
+        # In the literature, this is called `lambda`
+        self.components_ = self.random_state_.gamma(
+            init_gamma, init_var, (self.n_components, n_features)
+        )
+
+        # In the literature, this is `exp(E[log(beta)])`
+        self.exp_dirichlet_component_ = np.exp(
+            _dirichlet_expectation_2d(self.components_)
+        )
+
+    def _e_step(self, X, cal_sstats, random_init, parallel=None):
+        """E-step in EM update.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        cal_sstats : bool
+            Parameter that indicate whether to calculate sufficient statistics
+            or not. Set ``cal_sstats`` to True when we need to run M-step.
+
+        random_init : bool
+            Parameter that indicate whether to initialize document topic
+            distribution randomly in the E-step. Set it to True in training
+            steps.
+
+        parallel : joblib.Parallel, default=None
+            Pre-initialized instance of joblib.Parallel.
+
+        Returns
+        -------
+        (doc_topic_distr, suff_stats) :
+            `doc_topic_distr` is unnormalized topic distribution for each
+            document. In the literature, this is called `gamma`.
+            `suff_stats` is expected sufficient statistics for the M-step.
+            When `cal_sstats == False`, it will be None.
+
+        """
+
+        # Run e-step in parallel
+        random_state = self.random_state_ if random_init else None
+
+        # TODO: make Parallel._effective_n_jobs public instead?
+        n_jobs = effective_n_jobs(self.n_jobs)
+        if parallel is None:
+            parallel = Parallel(n_jobs=n_jobs, verbose=max(0, self.verbose - 1))
+        results = parallel(
+            delayed(_update_doc_distribution)(
+                X[idx_slice, :],
+                self.exp_dirichlet_component_,
+                self.doc_topic_prior_,
+                self.max_doc_update_iter,
+                self.mean_change_tol,
+                cal_sstats,
+                random_state,
+            )
+            for idx_slice in gen_even_slices(X.shape[0], n_jobs)
+        )
+
+        # merge result
+        doc_topics, sstats_list = zip(*results)
+        doc_topic_distr = np.vstack(doc_topics)
+
+        if cal_sstats:
+            # This step finishes computing the sufficient statistics for the
+            # M-step.
+            suff_stats = np.zeros(self.components_.shape)
+            for sstats in sstats_list:
+                suff_stats += sstats
+            suff_stats *= self.exp_dirichlet_component_
+        else:
+            suff_stats = None
+
+        return (doc_topic_distr, suff_stats)
+
+    def _em_step(self, X, total_samples, batch_update, parallel=None):
+        """EM update for 1 iteration.
+
+        update `_component` by batch VB or online VB.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        total_samples : int
+            Total number of documents. It is only used when
+            batch_update is `False`.
+
+        batch_update : bool
+            Parameter that controls updating method.
+            `True` for batch learning, `False` for online learning.
+
+        parallel : joblib.Parallel, default=None
+            Pre-initialized instance of joblib.Parallel
+
+        Returns
+        -------
+        doc_topic_distr : ndarray of shape (n_samples, n_components)
+            Unnormalized document topic distribution.
+        """
+
+        # E-step
+        _, suff_stats = self._e_step(
+            X, cal_sstats=True, random_init=True, parallel=parallel
+        )
+
+        # M-step
+        if batch_update:
+            self.components_ = self.topic_word_prior_ + suff_stats
+        else:
+            # online update
+            # In the literature, the weight is `rho`
+            weight = np.power(
+                self.learning_offset + self.n_batch_iter_, -self.learning_decay
+            )
+            doc_ratio = float(total_samples) / X.shape[0]
+            self.components_ *= 1 - weight
+            self.components_ += weight * (
+                self.topic_word_prior_ + doc_ratio * suff_stats
+            )
+
+        # update `component_` related variables
+        self.exp_dirichlet_component_ = np.exp(
+            _dirichlet_expectation_2d(self.components_)
+        )
+        self.n_batch_iter_ += 1
+        return
+
+    def _more_tags(self):
+        return {"requires_positive_X": True}
+
+    def _check_non_neg_array(self, X, reset_n_features, whom):
+        """check X format
+
+        check X format and make sure no negative value in X.
+
+        Parameters
+        ----------
+        X :  array-like or sparse matrix
+
+        """
+        X = self._validate_data(X, reset=reset_n_features, accept_sparse="csr")
+        check_non_negative(X, whom)
+        return X
+
+    def partial_fit(self, X, y=None):
+        """Online VB with Mini-Batch update.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        self
+            Partially fitted estimator.
+        """
+        self._check_params()
+        first_time = not hasattr(self, "components_")
+        X = self._check_non_neg_array(
+            X, reset_n_features=first_time, whom="LatentDirichletAllocation.partial_fit"
+        )
+        n_samples, n_features = X.shape
+        batch_size = self.batch_size
+
+        # initialize parameters or check
+        if first_time:
+            self._init_latent_vars(n_features)
+
+        if n_features != self.components_.shape[1]:
+            raise ValueError(
+                "The provided data has %d dimensions while "
+                "the model was trained with feature size %d."
+                % (n_features, self.components_.shape[1])
+            )
+
+        n_jobs = effective_n_jobs(self.n_jobs)
+        with Parallel(n_jobs=n_jobs, verbose=max(0, self.verbose - 1)) as parallel:
+            for idx_slice in gen_batches(n_samples, batch_size):
+                self._em_step(
+                    X[idx_slice, :],
+                    total_samples=self.total_samples,
+                    batch_update=False,
+                    parallel=parallel,
+                )
+
+        return self
+
+    def fit(self, X, y=None):
+        """Learn model for the data X with variational Bayes method.
+
+        When `learning_method` is 'online', use mini-batch update.
+        Otherwise, use batch update.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        self
+            Fitted estimator.
+        """
+        self._check_params()
+        X = self._check_non_neg_array(
+            X, reset_n_features=True, whom="LatentDirichletAllocation.fit"
+        )
+        n_samples, n_features = X.shape
+        max_iter = self.max_iter
+        evaluate_every = self.evaluate_every
+        learning_method = self.learning_method
+
+        batch_size = self.batch_size
+
+        # initialize parameters
+        self._init_latent_vars(n_features)
+        # change to perplexity later
+        last_bound = None
+        n_jobs = effective_n_jobs(self.n_jobs)
+        with Parallel(n_jobs=n_jobs, verbose=max(0, self.verbose - 1)) as parallel:
+            for i in range(max_iter):
+                if learning_method == "online":
+                    for idx_slice in gen_batches(n_samples, batch_size):
+                        self._em_step(
+                            X[idx_slice, :],
+                            total_samples=n_samples,
+                            batch_update=False,
+                            parallel=parallel,
+                        )
+                else:
+                    # batch update
+                    self._em_step(
+                        X, total_samples=n_samples, batch_update=True, parallel=parallel
+                    )
+
+                # check perplexity
+                if evaluate_every > 0 and (i + 1) % evaluate_every == 0:
+                    doc_topics_distr, _ = self._e_step(
+                        X, cal_sstats=False, random_init=False, parallel=parallel
+                    )
+                    bound = self._perplexity_precomp_distr(
+                        X, doc_topics_distr, sub_sampling=False
+                    )
+                    if self.verbose:
+                        print(
+                            "iteration: %d of max_iter: %d, perplexity: %.4f"
+                            % (i + 1, max_iter, bound)
+                        )
+
+                    if last_bound and abs(last_bound - bound) < self.perp_tol:
+                        break
+                    last_bound = bound
+
+                elif self.verbose:
+                    print("iteration: %d of max_iter: %d" % (i + 1, max_iter))
+                self.n_iter_ += 1
+
+        # calculate final perplexity value on train set
+        doc_topics_distr, _ = self._e_step(
+            X, cal_sstats=False, random_init=False, parallel=parallel
+        )
+        self.bound_ = self._perplexity_precomp_distr(
+            X, doc_topics_distr, sub_sampling=False
+        )
+
+        return self
+
+    def _unnormalized_transform(self, X):
+        """Transform data X according to fitted model.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        Returns
+        -------
+        doc_topic_distr : ndarray of shape (n_samples, n_components)
+            Document topic distribution for X.
+        """
+        doc_topic_distr, _ = self._e_step(X, cal_sstats=False, random_init=False)
+
+        return doc_topic_distr
+
+    def transform(self, X):
+        """Transform data X according to the fitted model.
+
+           .. versionchanged:: 0.18
+              *doc_topic_distr* is now normalized
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        Returns
+        -------
+        doc_topic_distr : ndarray of shape (n_samples, n_components)
+            Document topic distribution for X.
+        """
+        check_is_fitted(self)
+        X = self._check_non_neg_array(
+            X, reset_n_features=False, whom="LatentDirichletAllocation.transform"
+        )
+        doc_topic_distr = self._unnormalized_transform(X)
+        doc_topic_distr /= doc_topic_distr.sum(axis=1)[:, np.newaxis]
+        return doc_topic_distr
+
+    def _approx_bound(self, X, doc_topic_distr, sub_sampling):
+        """Estimate the variational bound.
+
+        Estimate the variational bound over "all documents" using only the
+        documents passed in as X. Since log-likelihood of each word cannot
+        be computed directly, we use this bound to estimate it.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        doc_topic_distr : ndarray of shape (n_samples, n_components)
+            Document topic distribution. In the literature, this is called
+            gamma.
+
+        sub_sampling : bool, default=False
+            Compensate for subsampling of documents.
+            It is used in calculate bound in online learning.
+
+        Returns
+        -------
+        score : float
+
+        """
+
+        def _loglikelihood(prior, distr, dirichlet_distr, size):
+            # calculate log-likelihood
+            score = np.sum((prior - distr) * dirichlet_distr)
+            score += np.sum(gammaln(distr) - gammaln(prior))
+            score += np.sum(gammaln(prior * size) - gammaln(np.sum(distr, 1)))
+            return score
+
+        is_sparse_x = sp.issparse(X)
+        n_samples, n_components = doc_topic_distr.shape
+        n_features = self.components_.shape[1]
+        score = 0
+
+        dirichlet_doc_topic = _dirichlet_expectation_2d(doc_topic_distr)
+        dirichlet_component_ = _dirichlet_expectation_2d(self.components_)
+        doc_topic_prior = self.doc_topic_prior_
+        topic_word_prior = self.topic_word_prior_
+
+        if is_sparse_x:
+            X_data = X.data
+            X_indices = X.indices
+            X_indptr = X.indptr
+
+        # E[log p(docs | theta, beta)]
+        for idx_d in range(0, n_samples):
+            if is_sparse_x:
+                ids = X_indices[X_indptr[idx_d] : X_indptr[idx_d + 1]]
+                cnts = X_data[X_indptr[idx_d] : X_indptr[idx_d + 1]]
+            else:
+                ids = np.nonzero(X[idx_d, :])[0]
+                cnts = X[idx_d, ids]
+            temp = (
+                dirichlet_doc_topic[idx_d, :, np.newaxis] + dirichlet_component_[:, ids]
+            )
+            norm_phi = logsumexp(temp, axis=0)
+            score += np.dot(cnts, norm_phi)
+
+        # compute E[log p(theta | alpha) - log q(theta | gamma)]
+        score += _loglikelihood(
+            doc_topic_prior, doc_topic_distr, dirichlet_doc_topic, self.n_components
+        )
+
+        # Compensate for the subsampling of the population of documents
+        if sub_sampling:
+            doc_ratio = float(self.total_samples) / n_samples
+            score *= doc_ratio
+
+        # E[log p(beta | eta) - log q (beta | lambda)]
+        score += _loglikelihood(
+            topic_word_prior, self.components_, dirichlet_component_, n_features
+        )
+
+        return score
+
+    def score(self, X, y=None):
+        """Calculate approximate log-likelihood as score.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        score : float
+            Use approximate bound as score.
+        """
+        check_is_fitted(self)
+        X = self._check_non_neg_array(
+            X, reset_n_features=False, whom="LatentDirichletAllocation.score"
+        )
+
+        doc_topic_distr = self._unnormalized_transform(X)
+        score = self._approx_bound(X, doc_topic_distr, sub_sampling=False)
+        return score
+
+    def _perplexity_precomp_distr(self, X, doc_topic_distr=None, sub_sampling=False):
+        """Calculate approximate perplexity for data X with ability to accept
+        precomputed doc_topic_distr
+
+        Perplexity is defined as exp(-1. * log-likelihood per word)
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        doc_topic_distr : ndarray of shape (n_samples, n_components), \
+                default=None
+            Document topic distribution.
+            If it is None, it will be generated by applying transform on X.
+
+        Returns
+        -------
+        score : float
+            Perplexity score.
+        """
+        if doc_topic_distr is None:
+            doc_topic_distr = self._unnormalized_transform(X)
+        else:
+            n_samples, n_components = doc_topic_distr.shape
+            if n_samples != X.shape[0]:
+                raise ValueError(
+                    "Number of samples in X and doc_topic_distr do not match."
+                )
+
+            if n_components != self.n_components:
+                raise ValueError("Number of topics does not match.")
+
+        current_samples = X.shape[0]
+        bound = self._approx_bound(X, doc_topic_distr, sub_sampling)
+
+        if sub_sampling:
+            word_cnt = X.sum() * (float(self.total_samples) / current_samples)
+        else:
+            word_cnt = X.sum()
+        perword_bound = bound / word_cnt
+
+        return np.exp(-1.0 * perword_bound)
+
+    def perplexity(self, X, sub_sampling=False):
+        """Calculate approximate perplexity for data X.
+
+        Perplexity is defined as exp(-1. * log-likelihood per word)
+
+        .. versionchanged:: 0.19
+           *doc_topic_distr* argument has been deprecated and is ignored
+           because user no longer has access to unnormalized distribution
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Document word matrix.
+
+        sub_sampling : bool
+            Do sub-sampling or not.
+
+        Returns
+        -------
+        score : float
+            Perplexity score.
+        """
+        check_is_fitted(self)
+        X = self._check_non_neg_array(
+            X, reset_n_features=True, whom="LatentDirichletAllocation.perplexity"
+        )
+        return self._perplexity_precomp_distr(X, sub_sampling=sub_sampling)
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_pca.py

@@ -0,0 +1,691 @@
+""" Principal Component Analysis.
+"""
+
+# Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
+#         Olivier Grisel <olivier.grisel@ensta.org>
+#         Mathieu Blondel <mathieu@mblondel.org>
+#         Denis A. Engemann <denis-alexander.engemann@inria.fr>
+#         Michael Eickenberg <michael.eickenberg@inria.fr>
+#         Giorgio Patrini <giorgio.patrini@anu.edu.au>
+#
+# License: BSD 3 clause
+
+from math import log, sqrt
+import numbers
+
+import numpy as np
+from scipy import linalg
+from scipy.special import gammaln
+from scipy.sparse import issparse
+from scipy.sparse.linalg import svds
+
+from ._base import _BasePCA
+from ..utils import check_random_state, check_scalar
+from ..utils._arpack import _init_arpack_v0
+from ..utils.extmath import fast_logdet, randomized_svd, svd_flip
+from ..utils.extmath import stable_cumsum
+from ..utils.validation import check_is_fitted
+
+
+def _assess_dimension(spectrum, rank, n_samples):
+    """Compute the log-likelihood of a rank ``rank`` dataset.
+
+    The dataset is assumed to be embedded in gaussian noise of shape(n,
+    dimf) having spectrum ``spectrum``. This implements the method of
+    T. P. Minka.
+
+    Parameters
+    ----------
+    spectrum : ndarray of shape (n_features,)
+        Data spectrum.
+    rank : int
+        Tested rank value. It should be strictly lower than n_features,
+        otherwise the method isn't specified (division by zero in equation
+        (31) from the paper).
+    n_samples : int
+        Number of samples.
+
+    Returns
+    -------
+    ll : float
+        The log-likelihood.
+
+    References
+    ----------
+    This implements the method of `Thomas P. Minka:
+    Automatic Choice of Dimensionality for PCA. NIPS 2000: 598-604
+    <https://proceedings.neurips.cc/paper/2000/file/7503cfacd12053d309b6bed5c89de212-Paper.pdf>`_
+    """
+
+    n_features = spectrum.shape[0]
+    if not 1 <= rank < n_features:
+        raise ValueError("the tested rank should be in [1, n_features - 1]")
+
+    eps = 1e-15
+
+    if spectrum[rank - 1] < eps:
+        # When the tested rank is associated with a small eigenvalue, there's
+        # no point in computing the log-likelihood: it's going to be very
+        # small and won't be the max anyway. Also, it can lead to numerical
+        # issues below when computing pa, in particular in log((spectrum[i] -
+        # spectrum[j]) because this will take the log of something very small.
+        return -np.inf
+
+    pu = -rank * log(2.0)
+    for i in range(1, rank + 1):
+        pu += (
+            gammaln((n_features - i + 1) / 2.0)
+            - log(np.pi) * (n_features - i + 1) / 2.0
+        )
+
+    pl = np.sum(np.log(spectrum[:rank]))
+    pl = -pl * n_samples / 2.0
+
+    v = max(eps, np.sum(spectrum[rank:]) / (n_features - rank))
+    pv = -np.log(v) * n_samples * (n_features - rank) / 2.0
+
+    m = n_features * rank - rank * (rank + 1.0) / 2.0
+    pp = log(2.0 * np.pi) * (m + rank) / 2.0
+
+    pa = 0.0
+    spectrum_ = spectrum.copy()
+    spectrum_[rank:n_features] = v
+    for i in range(rank):
+        for j in range(i + 1, len(spectrum)):
+            pa += log(
+                (spectrum[i] - spectrum[j]) * (1.0 / spectrum_[j] - 1.0 / spectrum_[i])
+            ) + log(n_samples)
+
+    ll = pu + pl + pv + pp - pa / 2.0 - rank * log(n_samples) / 2.0
+
+    return ll
+
+
+def _infer_dimension(spectrum, n_samples):
+    """Infers the dimension of a dataset with a given spectrum.
+
+    The returned value will be in [1, n_features - 1].
+    """
+    ll = np.empty_like(spectrum)
+    ll[0] = -np.inf  # we don't want to return n_components = 0
+    for rank in range(1, spectrum.shape[0]):
+        ll[rank] = _assess_dimension(spectrum, rank, n_samples)
+    return ll.argmax()
+
+
+class PCA(_BasePCA):
+    """Principal component analysis (PCA).
+
+    Linear dimensionality reduction using Singular Value Decomposition of the
+    data to project it to a lower dimensional space. The input data is centered
+    but not scaled for each feature before applying the SVD.
+
+    It uses the LAPACK implementation of the full SVD or a randomized truncated
+    SVD by the method of Halko et al. 2009, depending on the shape of the input
+    data and the number of components to extract.
+
+    It can also use the scipy.sparse.linalg ARPACK implementation of the
+    truncated SVD.
+
+    Notice that this class does not support sparse input. See
+    :class:`TruncatedSVD` for an alternative with sparse data.
+
+    Read more in the :ref:`User Guide <PCA>`.
+
+    Parameters
+    ----------
+    n_components : int, float or 'mle', default=None
+        Number of components to keep.
+        if n_components is not set all components are kept::
+
+            n_components == min(n_samples, n_features)
+
+        If ``n_components == 'mle'`` and ``svd_solver == 'full'``, Minka's
+        MLE is used to guess the dimension. Use of ``n_components == 'mle'``
+        will interpret ``svd_solver == 'auto'`` as ``svd_solver == 'full'``.
+
+        If ``0 < n_components < 1`` and ``svd_solver == 'full'``, select the
+        number of components such that the amount of variance that needs to be
+        explained is greater than the percentage specified by n_components.
+
+        If ``svd_solver == 'arpack'``, the number of components must be
+        strictly less than the minimum of n_features and n_samples.
+
+        Hence, the None case results in::
+
+            n_components == min(n_samples, n_features) - 1
+
+    copy : bool, default=True
+        If False, data passed to fit are overwritten and running
+        fit(X).transform(X) will not yield the expected results,
+        use fit_transform(X) instead.
+
+    whiten : bool, default=False
+        When True (False by default) the `components_` vectors are multiplied
+        by the square root of n_samples and then divided by the singular values
+        to ensure uncorrelated outputs with unit component-wise variances.
+
+        Whitening will remove some information from the transformed signal
+        (the relative variance scales of the components) but can sometime
+        improve the predictive accuracy of the downstream estimators by
+        making their data respect some hard-wired assumptions.
+
+    svd_solver : {'auto', 'full', 'arpack', 'randomized'}, default='auto'
+        If auto :
+            The solver is selected by a default policy based on `X.shape` and
+            `n_components`: if the input data is larger than 500x500 and the
+            number of components to extract is lower than 80% of the smallest
+            dimension of the data, then the more efficient 'randomized'
+            method is enabled. Otherwise the exact full SVD is computed and
+            optionally truncated afterwards.
+        If full :
+            run exact full SVD calling the standard LAPACK solver via
+            `scipy.linalg.svd` and select the components by postprocessing
+        If arpack :
+            run SVD truncated to n_components calling ARPACK solver via
+            `scipy.sparse.linalg.svds`. It requires strictly
+            0 < n_components < min(X.shape)
+        If randomized :
+            run randomized SVD by the method of Halko et al.
+
+        .. versionadded:: 0.18.0
+
+    tol : float, default=0.0
+        Tolerance for singular values computed by svd_solver == 'arpack'.
+        Must be of range [0.0, infinity).
+
+        .. versionadded:: 0.18.0
+
+    iterated_power : int or 'auto', default='auto'
+        Number of iterations for the power method computed by
+        svd_solver == 'randomized'.
+        Must be of range [0, infinity).
+
+        .. versionadded:: 0.18.0
+
+    n_oversamples : int, default=10
+        This parameter is only relevant when `svd_solver="randomized"`.
+        It corresponds to the additional number of random vectors to sample the
+        range of `X` so as to ensure proper conditioning. See
+        :func:`~sklearn.utils.extmath.randomized_svd` for more details.
+
+        .. versionadded:: 1.1
+
+    power_iteration_normalizer : {‘auto’, ‘QR’, ‘LU’, ‘none’}, default=’auto’
+        Power iteration normalizer for randomized SVD solver.
+        Not used by ARPACK. See :func:`~sklearn.utils.extmath.randomized_svd`
+        for more details.
+
+        .. versionadded:: 1.1
+
+    random_state : int, RandomState instance or None, default=None
+        Used when the 'arpack' or 'randomized' solvers are used. Pass an int
+        for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+        .. versionadded:: 0.18.0
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Principal axes in feature space, representing the directions of
+        maximum variance in the data. Equivalently, the right singular
+        vectors of the centered input data, parallel to its eigenvectors.
+        The components are sorted by ``explained_variance_``.
+
+    explained_variance_ : ndarray of shape (n_components,)
+        The amount of variance explained by each of the selected components.
+        The variance estimation uses `n_samples - 1` degrees of freedom.
+
+        Equal to n_components largest eigenvalues
+        of the covariance matrix of X.
+
+        .. versionadded:: 0.18
+
+    explained_variance_ratio_ : ndarray of shape (n_components,)
+        Percentage of variance explained by each of the selected components.
+
+        If ``n_components`` is not set then all components are stored and the
+        sum of the ratios is equal to 1.0.
+
+    singular_values_ : ndarray of shape (n_components,)
+        The singular values corresponding to each of the selected components.
+        The singular values are equal to the 2-norms of the ``n_components``
+        variables in the lower-dimensional space.
+
+        .. versionadded:: 0.19
+
+    mean_ : ndarray of shape (n_features,)
+        Per-feature empirical mean, estimated from the training set.
+
+        Equal to `X.mean(axis=0)`.
+
+    n_components_ : int
+        The estimated number of components. When n_components is set
+        to 'mle' or a number between 0 and 1 (with svd_solver == 'full') this
+        number is estimated from input data. Otherwise it equals the parameter
+        n_components, or the lesser value of n_features and n_samples
+        if n_components is None.
+
+    n_features_ : int
+        Number of features in the training data.
+
+    n_samples_ : int
+        Number of samples in the training data.
+
+    noise_variance_ : float
+        The estimated noise covariance following the Probabilistic PCA model
+        from Tipping and Bishop 1999. See "Pattern Recognition and
+        Machine Learning" by C. Bishop, 12.2.1 p. 574 or
+        http://www.miketipping.com/papers/met-mppca.pdf. It is required to
+        compute the estimated data covariance and score samples.
+
+        Equal to the average of (min(n_features, n_samples) - n_components)
+        smallest eigenvalues of the covariance matrix of X.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    KernelPCA : Kernel Principal Component Analysis.
+    SparsePCA : Sparse Principal Component Analysis.
+    TruncatedSVD : Dimensionality reduction using truncated SVD.
+    IncrementalPCA : Incremental Principal Component Analysis.
+
+    References
+    ----------
+    For n_components == 'mle', this class uses the method from:
+    `Minka, T. P.. "Automatic choice of dimensionality for PCA".
+    In NIPS, pp. 598-604 <https://tminka.github.io/papers/pca/minka-pca.pdf>`_
+
+    Implements the probabilistic PCA model from:
+    `Tipping, M. E., and Bishop, C. M. (1999). "Probabilistic principal
+    component analysis". Journal of the Royal Statistical Society:
+    Series B (Statistical Methodology), 61(3), 611-622.
+    <http://www.miketipping.com/papers/met-mppca.pdf>`_
+    via the score and score_samples methods.
+
+    For svd_solver == 'arpack', refer to `scipy.sparse.linalg.svds`.
+
+    For svd_solver == 'randomized', see:
+    :doi:`Halko, N., Martinsson, P. G., and Tropp, J. A. (2011).
+    "Finding structure with randomness: Probabilistic algorithms for
+    constructing approximate matrix decompositions".
+    SIAM review, 53(2), 217-288.
+    <10.1137/090771806>`
+    and also
+    :doi:`Martinsson, P. G., Rokhlin, V., and Tygert, M. (2011).
+    "A randomized algorithm for the decomposition of matrices".
+    Applied and Computational Harmonic Analysis, 30(1), 47-68.
+    <10.1016/j.acha.2010.02.003>`
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.decomposition import PCA
+    >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
+    >>> pca = PCA(n_components=2)
+    >>> pca.fit(X)
+    PCA(n_components=2)
+    >>> print(pca.explained_variance_ratio_)
+    [0.9924... 0.0075...]
+    >>> print(pca.singular_values_)
+    [6.30061... 0.54980...]
+
+    >>> pca = PCA(n_components=2, svd_solver='full')
+    >>> pca.fit(X)
+    PCA(n_components=2, svd_solver='full')
+    >>> print(pca.explained_variance_ratio_)
+    [0.9924... 0.00755...]
+    >>> print(pca.singular_values_)
+    [6.30061... 0.54980...]
+
+    >>> pca = PCA(n_components=1, svd_solver='arpack')
+    >>> pca.fit(X)
+    PCA(n_components=1, svd_solver='arpack')
+    >>> print(pca.explained_variance_ratio_)
+    [0.99244...]
+    >>> print(pca.singular_values_)
+    [6.30061...]
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        copy=True,
+        whiten=False,
+        svd_solver="auto",
+        tol=0.0,
+        iterated_power="auto",
+        n_oversamples=10,
+        power_iteration_normalizer="auto",
+        random_state=None,
+    ):
+        self.n_components = n_components
+        self.copy = copy
+        self.whiten = whiten
+        self.svd_solver = svd_solver
+        self.tol = tol
+        self.iterated_power = iterated_power
+        self.n_oversamples = n_oversamples
+        self.power_iteration_normalizer = power_iteration_normalizer
+        self.random_state = random_state
+
+    def fit(self, X, y=None):
+        """Fit the model with X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Ignored.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        check_scalar(
+            self.n_oversamples,
+            "n_oversamples",
+            min_val=1,
+            target_type=numbers.Integral,
+        )
+
+        self._fit(X)
+        return self
+
+    def fit_transform(self, X, y=None):
+        """Fit the model with X and apply the dimensionality reduction on X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Ignored.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Transformed values.
+
+        Notes
+        -----
+        This method returns a Fortran-ordered array. To convert it to a
+        C-ordered array, use 'np.ascontiguousarray'.
+        """
+        U, S, Vt = self._fit(X)
+        U = U[:, : self.n_components_]
+
+        if self.whiten:
+            # X_new = X * V / S * sqrt(n_samples) = U * sqrt(n_samples)
+            U *= sqrt(X.shape[0] - 1)
+        else:
+            # X_new = X * V = U * S * Vt * V = U * S
+            U *= S[: self.n_components_]
+
+        return U
+
+    def _fit(self, X):
+        """Dispatch to the right submethod depending on the chosen solver."""
+
+        # Raise an error for sparse input.
+        # This is more informative than the generic one raised by check_array.
+        if issparse(X):
+            raise TypeError(
+                "PCA does not support sparse input. See "
+                "TruncatedSVD for a possible alternative."
+            )
+
+        X = self._validate_data(
+            X, dtype=[np.float64, np.float32], ensure_2d=True, copy=self.copy
+        )
+
+        # Handle n_components==None
+        if self.n_components is None:
+            if self.svd_solver != "arpack":
+                n_components = min(X.shape)
+            else:
+                n_components = min(X.shape) - 1
+        else:
+            n_components = self.n_components
+
+        # Handle svd_solver
+        self._fit_svd_solver = self.svd_solver
+        if self._fit_svd_solver == "auto":
+            # Small problem or n_components == 'mle', just call full PCA
+            if max(X.shape) <= 500 or n_components == "mle":
+                self._fit_svd_solver = "full"
+            elif n_components >= 1 and n_components < 0.8 * min(X.shape):
+                self._fit_svd_solver = "randomized"
+            # This is also the case of n_components in (0,1)
+            else:
+                self._fit_svd_solver = "full"
+
+        # Call different fits for either full or truncated SVD
+        if self._fit_svd_solver == "full":
+            return self._fit_full(X, n_components)
+        elif self._fit_svd_solver in ["arpack", "randomized"]:
+            return self._fit_truncated(X, n_components, self._fit_svd_solver)
+        else:
+            raise ValueError(
+                "Unrecognized svd_solver='{0}'".format(self._fit_svd_solver)
+            )
+
+    def _fit_full(self, X, n_components):
+        """Fit the model by computing full SVD on X."""
+        n_samples, n_features = X.shape
+
+        if n_components == "mle":
+            if n_samples < n_features:
+                raise ValueError(
+                    "n_components='mle' is only supported if n_samples >= n_features"
+                )
+        elif not 0 <= n_components <= min(n_samples, n_features):
+            raise ValueError(
+                "n_components=%r must be between 0 and "
+                "min(n_samples, n_features)=%r with "
+                "svd_solver='full'" % (n_components, min(n_samples, n_features))
+            )
+        elif n_components >= 1:
+            if not isinstance(n_components, numbers.Integral):
+                raise ValueError(
+                    "n_components=%r must be of type int "
+                    "when greater than or equal to 1, "
+                    "was of type=%r" % (n_components, type(n_components))
+                )
+
+        # Center data
+        self.mean_ = np.mean(X, axis=0)
+        X -= self.mean_
+
+        U, S, Vt = linalg.svd(X, full_matrices=False)
+        # flip eigenvectors' sign to enforce deterministic output
+        U, Vt = svd_flip(U, Vt)
+
+        components_ = Vt
+
+        # Get variance explained by singular values
+        explained_variance_ = (S**2) / (n_samples - 1)
+        total_var = explained_variance_.sum()
+        explained_variance_ratio_ = explained_variance_ / total_var
+        singular_values_ = S.copy()  # Store the singular values.
+
+        # Postprocess the number of components required
+        if n_components == "mle":
+            n_components = _infer_dimension(explained_variance_, n_samples)
+        elif 0 < n_components < 1.0:
+            # number of components for which the cumulated explained
+            # variance percentage is superior to the desired threshold
+            # side='right' ensures that number of features selected
+            # their variance is always greater than n_components float
+            # passed. More discussion in issue: #15669
+            ratio_cumsum = stable_cumsum(explained_variance_ratio_)
+            n_components = np.searchsorted(ratio_cumsum, n_components, side="right") + 1
+        # Compute noise covariance using Probabilistic PCA model
+        # The sigma2 maximum likelihood (cf. eq. 12.46)
+        if n_components < min(n_features, n_samples):
+            self.noise_variance_ = explained_variance_[n_components:].mean()
+        else:
+            self.noise_variance_ = 0.0
+
+        self.n_samples_, self.n_features_ = n_samples, n_features
+        self.components_ = components_[:n_components]
+        self.n_components_ = n_components
+        self.explained_variance_ = explained_variance_[:n_components]
+        self.explained_variance_ratio_ = explained_variance_ratio_[:n_components]
+        self.singular_values_ = singular_values_[:n_components]
+
+        return U, S, Vt
+
+    def _fit_truncated(self, X, n_components, svd_solver):
+        """Fit the model by computing truncated SVD (by ARPACK or randomized)
+        on X.
+        """
+        n_samples, n_features = X.shape
+
+        if isinstance(n_components, str):
+            raise ValueError(
+                "n_components=%r cannot be a string with svd_solver='%s'"
+                % (n_components, svd_solver)
+            )
+        elif not 1 <= n_components <= min(n_samples, n_features):
+            raise ValueError(
+                "n_components=%r must be between 1 and "
+                "min(n_samples, n_features)=%r with "
+                "svd_solver='%s'"
+                % (n_components, min(n_samples, n_features), svd_solver)
+            )
+        elif not isinstance(n_components, numbers.Integral):
+            raise ValueError(
+                "n_components=%r must be of type int "
+                "when greater than or equal to 1, was of type=%r"
+                % (n_components, type(n_components))
+            )
+        elif svd_solver == "arpack" and n_components == min(n_samples, n_features):
+            raise ValueError(
+                "n_components=%r must be strictly less than "
+                "min(n_samples, n_features)=%r with "
+                "svd_solver='%s'"
+                % (n_components, min(n_samples, n_features), svd_solver)
+            )
+
+        random_state = check_random_state(self.random_state)
+
+        # Center data
+        self.mean_ = np.mean(X, axis=0)
+        X -= self.mean_
+
+        if svd_solver == "arpack":
+            v0 = _init_arpack_v0(min(X.shape), random_state)
+            U, S, Vt = svds(X, k=n_components, tol=self.tol, v0=v0)
+            # svds doesn't abide by scipy.linalg.svd/randomized_svd
+            # conventions, so reverse its outputs.
+            S = S[::-1]
+            # flip eigenvectors' sign to enforce deterministic output
+            U, Vt = svd_flip(U[:, ::-1], Vt[::-1])
+
+        elif svd_solver == "randomized":
+            # sign flipping is done inside
+            U, S, Vt = randomized_svd(
+                X,
+                n_components=n_components,
+                n_oversamples=self.n_oversamples,
+                n_iter=self.iterated_power,
+                power_iteration_normalizer=self.power_iteration_normalizer,
+                flip_sign=True,
+                random_state=random_state,
+            )
+
+        self.n_samples_, self.n_features_ = n_samples, n_features
+        self.components_ = Vt
+        self.n_components_ = n_components
+
+        # Get variance explained by singular values
+        self.explained_variance_ = (S**2) / (n_samples - 1)
+
+        # Workaround in-place variance calculation since at the time numpy
+        # did not have a way to calculate variance in-place.
+        N = X.shape[0] - 1
+        np.square(X, out=X)
+        np.sum(X, axis=0, out=X[0])
+        total_var = (X[0] / N).sum()
+
+        self.explained_variance_ratio_ = self.explained_variance_ / total_var
+        self.singular_values_ = S.copy()  # Store the singular values.
+
+        if self.n_components_ < min(n_features, n_samples):
+            self.noise_variance_ = total_var - self.explained_variance_.sum()
+            self.noise_variance_ /= min(n_features, n_samples) - n_components
+        else:
+            self.noise_variance_ = 0.0
+
+        return U, S, Vt
+
+    def score_samples(self, X):
+        """Return the log-likelihood of each sample.
+
+        See. "Pattern Recognition and Machine Learning"
+        by C. Bishop, 12.2.1 p. 574
+        or http://www.miketipping.com/papers/met-mppca.pdf
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The data.
+
+        Returns
+        -------
+        ll : ndarray of shape (n_samples,)
+            Log-likelihood of each sample under the current model.
+        """
+        check_is_fitted(self)
+
+        X = self._validate_data(X, dtype=[np.float64, np.float32], reset=False)
+        Xr = X - self.mean_
+        n_features = X.shape[1]
+        precision = self.get_precision()
+        log_like = -0.5 * (Xr * (np.dot(Xr, precision))).sum(axis=1)
+        log_like -= 0.5 * (n_features * log(2.0 * np.pi) - fast_logdet(precision))
+        return log_like
+
+    def score(self, X, y=None):
+        """Return the average log-likelihood of all samples.
+
+        See. "Pattern Recognition and Machine Learning"
+        by C. Bishop, 12.2.1 p. 574
+        or http://www.miketipping.com/papers/met-mppca.pdf
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The data.
+
+        y : Ignored
+            Ignored.
+
+        Returns
+        -------
+        ll : float
+            Average log-likelihood of the samples under the current model.
+        """
+        return np.mean(self.score_samples(X))
+
+    def _more_tags(self):
+        return {"preserves_dtype": [np.float64, np.float32]}

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_sparse_pca.py

@@ -0,0 +1,465 @@
+"""Matrix factorization with Sparse PCA."""
+# Author: Vlad Niculae, Gael Varoquaux, Alexandre Gramfort
+# License: BSD 3 clause
+
+import warnings
+
+import numpy as np
+
+from ..utils import check_random_state
+from ..utils.validation import check_is_fitted
+from ..linear_model import ridge_regression
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ._dict_learning import dict_learning, dict_learning_online
+
+
+class SparsePCA(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
+    """Sparse Principal Components Analysis (SparsePCA).
+
+    Finds the set of sparse components that can optimally reconstruct
+    the data.  The amount of sparseness is controllable by the coefficient
+    of the L1 penalty, given by the parameter alpha.
+
+    Read more in the :ref:`User Guide <SparsePCA>`.
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Number of sparse atoms to extract. If None, then ``n_components``
+        is set to ``n_features``.
+
+    alpha : float, default=1
+        Sparsity controlling parameter. Higher values lead to sparser
+        components.
+
+    ridge_alpha : float, default=0.01
+        Amount of ridge shrinkage to apply in order to improve
+        conditioning when calling the transform method.
+
+    max_iter : int, default=1000
+        Maximum number of iterations to perform.
+
+    tol : float, default=1e-8
+        Tolerance for the stopping condition.
+
+    method : {'lars', 'cd'}, default='lars'
+        Method to be used for optimization.
+        lars: uses the least angle regression method to solve the lasso problem
+        (linear_model.lars_path)
+        cd: uses the coordinate descent method to compute the
+        Lasso solution (linear_model.Lasso). Lars will be faster if
+        the estimated components are sparse.
+
+    n_jobs : int, default=None
+        Number of parallel jobs to run.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    U_init : ndarray of shape (n_samples, n_components), default=None
+        Initial values for the loadings for warm restart scenarios. Only used
+        if `U_init` and `V_init` are not None.
+
+    V_init : ndarray of shape (n_components, n_features), default=None
+        Initial values for the components for warm restart scenarios. Only used
+        if `U_init` and `V_init` are not None.
+
+    verbose : int or bool, default=False
+        Controls the verbosity; the higher, the more messages. Defaults to 0.
+
+    random_state : int, RandomState instance or None, default=None
+        Used during dictionary learning. Pass an int for reproducible results
+        across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Sparse components extracted from the data.
+
+    error_ : ndarray
+        Vector of errors at each iteration.
+
+    n_components_ : int
+        Estimated number of components.
+
+        .. versionadded:: 0.23
+
+    n_iter_ : int
+        Number of iterations run.
+
+    mean_ : ndarray of shape (n_features,)
+        Per-feature empirical mean, estimated from the training set.
+        Equal to ``X.mean(axis=0)``.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    PCA : Principal Component Analysis implementation.
+    MiniBatchSparsePCA : Mini batch variant of `SparsePCA` that is faster but less
+        accurate.
+    DictionaryLearning : Generic dictionary learning problem using a sparse code.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.datasets import make_friedman1
+    >>> from sklearn.decomposition import SparsePCA
+    >>> X, _ = make_friedman1(n_samples=200, n_features=30, random_state=0)
+    >>> transformer = SparsePCA(n_components=5, random_state=0)
+    >>> transformer.fit(X)
+    SparsePCA(...)
+    >>> X_transformed = transformer.transform(X)
+    >>> X_transformed.shape
+    (200, 5)
+    >>> # most values in the components_ are zero (sparsity)
+    >>> np.mean(transformer.components_ == 0)
+    0.9666...
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        alpha=1,
+        ridge_alpha=0.01,
+        max_iter=1000,
+        tol=1e-8,
+        method="lars",
+        n_jobs=None,
+        U_init=None,
+        V_init=None,
+        verbose=False,
+        random_state=None,
+    ):
+        self.n_components = n_components
+        self.alpha = alpha
+        self.ridge_alpha = ridge_alpha
+        self.max_iter = max_iter
+        self.tol = tol
+        self.method = method
+        self.n_jobs = n_jobs
+        self.U_init = U_init
+        self.V_init = V_init
+        self.verbose = verbose
+        self.random_state = random_state
+
+    def fit(self, X, y=None):
+        """Fit the model from data in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        random_state = check_random_state(self.random_state)
+        X = self._validate_data(X)
+
+        self.mean_ = X.mean(axis=0)
+        X = X - self.mean_
+
+        if self.n_components is None:
+            n_components = X.shape[1]
+        else:
+            n_components = self.n_components
+        code_init = self.V_init.T if self.V_init is not None else None
+        dict_init = self.U_init.T if self.U_init is not None else None
+        Vt, _, E, self.n_iter_ = dict_learning(
+            X.T,
+            n_components,
+            alpha=self.alpha,
+            tol=self.tol,
+            max_iter=self.max_iter,
+            method=self.method,
+            n_jobs=self.n_jobs,
+            verbose=self.verbose,
+            random_state=random_state,
+            code_init=code_init,
+            dict_init=dict_init,
+            return_n_iter=True,
+        )
+        self.components_ = Vt.T
+        components_norm = np.linalg.norm(self.components_, axis=1)[:, np.newaxis]
+        components_norm[components_norm == 0] = 1
+        self.components_ /= components_norm
+        self.n_components_ = len(self.components_)
+
+        self.error_ = E
+        return self
+
+    def transform(self, X):
+        """Least Squares projection of the data onto the sparse components.
+
+        To avoid instability issues in case the system is under-determined,
+        regularization can be applied (Ridge regression) via the
+        `ridge_alpha` parameter.
+
+        Note that Sparse PCA components orthogonality is not enforced as in PCA
+        hence one cannot use a simple linear projection.
+
+        Parameters
+        ----------
+        X : ndarray of shape (n_samples, n_features)
+            Test data to be transformed, must have the same number of
+            features as the data used to train the model.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Transformed data.
+        """
+        check_is_fitted(self)
+
+        X = self._validate_data(X, reset=False)
+        X = X - self.mean_
+
+        U = ridge_regression(
+            self.components_.T, X.T, self.ridge_alpha, solver="cholesky"
+        )
+
+        return U
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]
+
+    def _more_tags(self):
+        return {
+            "preserves_dtype": [np.float64, np.float32],
+        }
+
+
+class MiniBatchSparsePCA(SparsePCA):
+    """Mini-batch Sparse Principal Components Analysis.
+
+    Finds the set of sparse components that can optimally reconstruct
+    the data.  The amount of sparseness is controllable by the coefficient
+    of the L1 penalty, given by the parameter alpha.
+
+    Read more in the :ref:`User Guide <SparsePCA>`.
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Number of sparse atoms to extract. If None, then ``n_components``
+        is set to ``n_features``.
+
+    alpha : int, default=1
+        Sparsity controlling parameter. Higher values lead to sparser
+        components.
+
+    ridge_alpha : float, default=0.01
+        Amount of ridge shrinkage to apply in order to improve
+        conditioning when calling the transform method.
+
+    n_iter : int, default=100
+        Number of iterations to perform for each mini batch.
+
+    callback : callable, default=None
+        Callable that gets invoked every five iterations.
+
+    batch_size : int, default=3
+        The number of features to take in each mini batch.
+
+    verbose : int or bool, default=False
+        Controls the verbosity; the higher, the more messages. Defaults to 0.
+
+    shuffle : bool, default=True
+        Whether to shuffle the data before splitting it in batches.
+
+    n_jobs : int, default=None
+        Number of parallel jobs to run.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    method : {'lars', 'cd'}, default='lars'
+        Method to be used for optimization.
+        lars: uses the least angle regression method to solve the lasso problem
+        (linear_model.lars_path)
+        cd: uses the coordinate descent method to compute the
+        Lasso solution (linear_model.Lasso). Lars will be faster if
+        the estimated components are sparse.
+
+    random_state : int, RandomState instance or None, default=None
+        Used for random shuffling when ``shuffle`` is set to ``True``,
+        during online dictionary learning. Pass an int for reproducible results
+        across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        Sparse components extracted from the data.
+
+    n_components_ : int
+        Estimated number of components.
+
+        .. versionadded:: 0.23
+
+    n_iter_ : int
+        Number of iterations run.
+
+    mean_ : ndarray of shape (n_features,)
+        Per-feature empirical mean, estimated from the training set.
+        Equal to ``X.mean(axis=0)``.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    DictionaryLearning : Find a dictionary that sparsely encodes data.
+    IncrementalPCA : Incremental principal components analysis.
+    PCA : Principal component analysis.
+    SparsePCA : Sparse Principal Components Analysis.
+    TruncatedSVD : Dimensionality reduction using truncated SVD.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.datasets import make_friedman1
+    >>> from sklearn.decomposition import MiniBatchSparsePCA
+    >>> X, _ = make_friedman1(n_samples=200, n_features=30, random_state=0)
+    >>> transformer = MiniBatchSparsePCA(n_components=5, batch_size=50,
+    ...                                  random_state=0)
+    >>> transformer.fit(X)
+    MiniBatchSparsePCA(...)
+    >>> X_transformed = transformer.transform(X)
+    >>> X_transformed.shape
+    (200, 5)
+    >>> # most values in the components_ are zero (sparsity)
+    >>> np.mean(transformer.components_ == 0)
+    0.94
+    """
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        alpha=1,
+        ridge_alpha=0.01,
+        n_iter=100,
+        callback=None,
+        batch_size=3,
+        verbose=False,
+        shuffle=True,
+        n_jobs=None,
+        method="lars",
+        random_state=None,
+    ):
+        super().__init__(
+            n_components=n_components,
+            alpha=alpha,
+            verbose=verbose,
+            ridge_alpha=ridge_alpha,
+            n_jobs=n_jobs,
+            method=method,
+            random_state=random_state,
+        )
+        self.n_iter = n_iter
+        self.callback = callback
+        self.batch_size = batch_size
+        self.shuffle = shuffle
+
+    def fit(self, X, y=None):
+        """Fit the model from data in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        random_state = check_random_state(self.random_state)
+        X = self._validate_data(X)
+
+        self.mean_ = X.mean(axis=0)
+        X = X - self.mean_
+
+        if self.n_components is None:
+            n_components = X.shape[1]
+        else:
+            n_components = self.n_components
+
+        with warnings.catch_warnings():
+            # return_n_iter and n_iter are deprecated. TODO Remove in 1.3
+            warnings.filterwarnings(
+                "ignore",
+                message=(
+                    "'return_n_iter' is deprecated in version 1.1 and will be "
+                    "removed in version 1.3. From 1.3 'n_iter' will never be "
+                    "returned. Refer to the 'n_iter_' and 'n_steps_' attributes "
+                    "of the MiniBatchDictionaryLearning object instead."
+                ),
+                category=FutureWarning,
+            )
+            warnings.filterwarnings(
+                "ignore",
+                message=(
+                    "'n_iter' is deprecated in version 1.1 and will be removed in "
+                    "version 1.3. Use 'max_iter' instead."
+                ),
+                category=FutureWarning,
+            )
+            Vt, _, self.n_iter_ = dict_learning_online(
+                X.T,
+                n_components,
+                alpha=self.alpha,
+                n_iter=self.n_iter,
+                return_code=True,
+                dict_init=None,
+                verbose=self.verbose,
+                callback=self.callback,
+                batch_size=self.batch_size,
+                shuffle=self.shuffle,
+                n_jobs=self.n_jobs,
+                method=self.method,
+                random_state=random_state,
+                return_n_iter=True,
+            )
+
+        self.components_ = Vt.T
+
+        components_norm = np.linalg.norm(self.components_, axis=1)[:, np.newaxis]
+        components_norm[components_norm == 0] = 1
+        self.components_ /= components_norm
+        self.n_components_ = len(self.components_)
+
+        return self

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/_truncated_svd.py

@@ -0,0 +1,314 @@
+"""Truncated SVD for sparse matrices, aka latent semantic analysis (LSA).
+"""
+
+# Author: Lars Buitinck
+#         Olivier Grisel <olivier.grisel@ensta.org>
+#         Michael Becker <mike@beckerfuffle.com>
+# License: 3-clause BSD.
+
+from numbers import Integral
+import numpy as np
+import scipy.sparse as sp
+from scipy.sparse.linalg import svds
+
+from ..base import BaseEstimator, TransformerMixin, _ClassNamePrefixFeaturesOutMixin
+from ..utils import check_array, check_random_state
+from ..utils._arpack import _init_arpack_v0
+from ..utils.extmath import randomized_svd, safe_sparse_dot, svd_flip
+from ..utils.sparsefuncs import mean_variance_axis
+from ..utils.validation import check_is_fitted, check_scalar
+
+__all__ = ["TruncatedSVD"]
+
+
+class TruncatedSVD(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
+    """Dimensionality reduction using truncated SVD (aka LSA).
+
+    This transformer performs linear dimensionality reduction by means of
+    truncated singular value decomposition (SVD). Contrary to PCA, this
+    estimator does not center the data before computing the singular value
+    decomposition. This means it can work with sparse matrices
+    efficiently.
+
+    In particular, truncated SVD works on term count/tf-idf matrices as
+    returned by the vectorizers in :mod:`sklearn.feature_extraction.text`. In
+    that context, it is known as latent semantic analysis (LSA).
+
+    This estimator supports two algorithms: a fast randomized SVD solver, and
+    a "naive" algorithm that uses ARPACK as an eigensolver on `X * X.T` or
+    `X.T * X`, whichever is more efficient.
+
+    Read more in the :ref:`User Guide <LSA>`.
+
+    Parameters
+    ----------
+    n_components : int, default=2
+        Desired dimensionality of output data.
+        If algorithm='arpack', must be strictly less than the number of features.
+        If algorithm='randomized', must be less than or equal to the number of features.
+        The default value is useful for visualisation. For LSA, a value of
+        100 is recommended.
+
+    algorithm : {'arpack', 'randomized'}, default='randomized'
+        SVD solver to use. Either "arpack" for the ARPACK wrapper in SciPy
+        (scipy.sparse.linalg.svds), or "randomized" for the randomized
+        algorithm due to Halko (2009).
+
+    n_iter : int, default=5
+        Number of iterations for randomized SVD solver. Not used by ARPACK. The
+        default is larger than the default in
+        :func:`~sklearn.utils.extmath.randomized_svd` to handle sparse
+        matrices that may have large slowly decaying spectrum.
+
+    n_oversamples : int, default=10
+        Number of oversamples for randomized SVD solver. Not used by ARPACK.
+        See :func:`~sklearn.utils.extmath.randomized_svd` for a complete
+        description.
+
+        .. versionadded:: 1.1
+
+    power_iteration_normalizer : {‘auto’, ‘QR’, ‘LU’, ‘none’}, default=’auto’
+        Power iteration normalizer for randomized SVD solver.
+        Not used by ARPACK. See :func:`~sklearn.utils.extmath.randomized_svd`
+        for more details.
+
+        .. versionadded:: 1.1
+
+    random_state : int, RandomState instance or None, default=None
+        Used during randomized svd. Pass an int for reproducible results across
+        multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    tol : float, default=0.0
+        Tolerance for ARPACK. 0 means machine precision. Ignored by randomized
+        SVD solver.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        The right singular vectors of the input data.
+
+    explained_variance_ : ndarray of shape (n_components,)
+        The variance of the training samples transformed by a projection to
+        each component.
+
+    explained_variance_ratio_ : ndarray of shape (n_components,)
+        Percentage of variance explained by each of the selected components.
+
+    singular_values_ : ndarray of shape (n_components,)
+        The singular values corresponding to each of the selected components.
+        The singular values are equal to the 2-norms of the ``n_components``
+        variables in the lower-dimensional space.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    DictionaryLearning : Find a dictionary that sparsely encodes data.
+    FactorAnalysis : A simple linear generative model with
+        Gaussian latent variables.
+    IncrementalPCA : Incremental principal components analysis.
+    KernelPCA : Kernel Principal component analysis.
+    NMF : Non-Negative Matrix Factorization.
+    PCA : Principal component analysis.
+
+    Notes
+    -----
+    SVD suffers from a problem called "sign indeterminacy", which means the
+    sign of the ``components_`` and the output from transform depend on the
+    algorithm and random state. To work around this, fit instances of this
+    class to data once, then keep the instance around to do transformations.
+
+    References
+    ----------
+    :arxiv:`Halko, et al. (2009). "Finding structure with randomness:
+    Stochastic algorithms for constructing approximate matrix decompositions"
+    <0909.4061>`
+
+    Examples
+    --------
+    >>> from sklearn.decomposition import TruncatedSVD
+    >>> from scipy.sparse import csr_matrix
+    >>> import numpy as np
+    >>> np.random.seed(0)
+    >>> X_dense = np.random.rand(100, 100)
+    >>> X_dense[:, 2 * np.arange(50)] = 0
+    >>> X = csr_matrix(X_dense)
+    >>> svd = TruncatedSVD(n_components=5, n_iter=7, random_state=42)
+    >>> svd.fit(X)
+    TruncatedSVD(n_components=5, n_iter=7, random_state=42)
+    >>> print(svd.explained_variance_ratio_)
+    [0.0157... 0.0512... 0.0499... 0.0479... 0.0453...]
+    >>> print(svd.explained_variance_ratio_.sum())
+    0.2102...
+    >>> print(svd.singular_values_)
+    [35.2410...  4.5981...   4.5420...  4.4486...  4.3288...]
+    """
+
+    def __init__(
+        self,
+        n_components=2,
+        *,
+        algorithm="randomized",
+        n_iter=5,
+        n_oversamples=10,
+        power_iteration_normalizer="auto",
+        random_state=None,
+        tol=0.0,
+    ):
+        self.algorithm = algorithm
+        self.n_components = n_components
+        self.n_iter = n_iter
+        self.n_oversamples = n_oversamples
+        self.power_iteration_normalizer = power_iteration_normalizer
+        self.random_state = random_state
+        self.tol = tol
+
+    def fit(self, X, y=None):
+        """Fit model on training data X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training data.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        self : object
+            Returns the transformer object.
+        """
+        self.fit_transform(X)
+        return self
+
+    def fit_transform(self, X, y=None):
+        """Fit model to X and perform dimensionality reduction on X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training data.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Reduced version of X. This will always be a dense array.
+        """
+        check_scalar(
+            self.n_oversamples,
+            "n_oversamples",
+            min_val=1,
+            target_type=Integral,
+        )
+
+        X = self._validate_data(X, accept_sparse=["csr", "csc"], ensure_min_features=2)
+        random_state = check_random_state(self.random_state)
+
+        if self.algorithm == "arpack":
+            v0 = _init_arpack_v0(min(X.shape), random_state)
+            U, Sigma, VT = svds(X, k=self.n_components, tol=self.tol, v0=v0)
+            # svds doesn't abide by scipy.linalg.svd/randomized_svd
+            # conventions, so reverse its outputs.
+            Sigma = Sigma[::-1]
+            U, VT = svd_flip(U[:, ::-1], VT[::-1])
+
+        elif self.algorithm == "randomized":
+            k = self.n_components
+            n_features = X.shape[1]
+            check_scalar(
+                k,
+                "n_components",
+                target_type=Integral,
+                min_val=1,
+                max_val=n_features,
+            )
+            U, Sigma, VT = randomized_svd(
+                X,
+                self.n_components,
+                n_iter=self.n_iter,
+                n_oversamples=self.n_oversamples,
+                power_iteration_normalizer=self.power_iteration_normalizer,
+                random_state=random_state,
+            )
+        else:
+            raise ValueError("unknown algorithm %r" % self.algorithm)
+
+        self.components_ = VT
+
+        # As a result of the SVD approximation error on X ~ U @ Sigma @ V.T,
+        # X @ V is not the same as U @ Sigma
+        if self.algorithm == "randomized" or (
+            self.algorithm == "arpack" and self.tol > 0
+        ):
+            X_transformed = safe_sparse_dot(X, self.components_.T)
+        else:
+            X_transformed = U * Sigma
+
+        # Calculate explained variance & explained variance ratio
+        self.explained_variance_ = exp_var = np.var(X_transformed, axis=0)
+        if sp.issparse(X):
+            _, full_var = mean_variance_axis(X, axis=0)
+            full_var = full_var.sum()
+        else:
+            full_var = np.var(X, axis=0).sum()
+        self.explained_variance_ratio_ = exp_var / full_var
+        self.singular_values_ = Sigma  # Store the singular values.
+
+        return X_transformed
+
+    def transform(self, X):
+        """Perform dimensionality reduction on X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Reduced version of X. This will always be a dense array.
+        """
+        check_is_fitted(self)
+        X = self._validate_data(X, accept_sparse=["csr", "csc"], reset=False)
+        return safe_sparse_dot(X, self.components_.T)
+
+    def inverse_transform(self, X):
+        """Transform X back to its original space.
+
+        Returns an array X_original whose transform would be X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_components)
+            New data.
+
+        Returns
+        -------
+        X_original : ndarray of shape (n_samples, n_features)
+            Note that this is always a dense array.
+        """
+        X = check_array(X)
+        return np.dot(X, self.components_)
+
+    def _more_tags(self):
+        return {"preserves_dtype": [np.float64, np.float32]}
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/setup.py

@@ -0,0 +1,35 @@
+import os
+import numpy
+from numpy.distutils.misc_util import Configuration
+
+
+def configuration(parent_package="", top_path=None):
+    config = Configuration("decomposition", parent_package, top_path)
+
+    libraries = []
+    if os.name == "posix":
+        libraries.append("m")
+
+    config.add_extension(
+        "_online_lda_fast",
+        sources=["_online_lda_fast.pyx"],
+        include_dirs=[numpy.get_include()],
+        libraries=libraries,
+    )
+
+    config.add_extension(
+        "_cdnmf_fast",
+        sources=["_cdnmf_fast.pyx"],
+        include_dirs=[numpy.get_include()],
+        libraries=libraries,
+    )
+
+    config.add_subpackage("tests")
+
+    return config
+
+
+if __name__ == "__main__":
+    from numpy.distutils.core import setup
+
+    setup(**configuration().todict())

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_factor_analysis.py

@@ -0,0 +1,121 @@
+# Author: Christian Osendorfer <osendorf@gmail.com>
+#         Alexandre Gramfort <alexandre.gramfort@inria.fr>
+# License: BSD3
+
+from itertools import combinations
+
+import numpy as np
+import pytest
+
+from sklearn.utils._testing import assert_almost_equal
+from sklearn.utils._testing import assert_array_almost_equal
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.decomposition import FactorAnalysis
+from sklearn.utils._testing import ignore_warnings
+from sklearn.decomposition._factor_analysis import _ortho_rotation
+
+
+# Ignore warnings from switching to more power iterations in randomized_svd
+@ignore_warnings
+def test_factor_analysis():
+    # Test FactorAnalysis ability to recover the data covariance structure
+    rng = np.random.RandomState(0)
+    n_samples, n_features, n_components = 20, 5, 3
+
+    # Some random settings for the generative model
+    W = rng.randn(n_components, n_features)
+    # latent variable of dim 3, 20 of it
+    h = rng.randn(n_samples, n_components)
+    # using gamma to model different noise variance
+    # per component
+    noise = rng.gamma(1, size=n_features) * rng.randn(n_samples, n_features)
+
+    # generate observations
+    # wlog, mean is 0
+    X = np.dot(h, W) + noise
+
+    fa_fail = FactorAnalysis(svd_method="foo")
+    msg = "SVD method 'foo' is not supported"
+    with pytest.raises(ValueError, match=msg):
+        fa_fail.fit(X)
+    fas = []
+    for method in ["randomized", "lapack"]:
+        fa = FactorAnalysis(n_components=n_components, svd_method=method)
+        fa.fit(X)
+        fas.append(fa)
+
+        X_t = fa.transform(X)
+        assert X_t.shape == (n_samples, n_components)
+
+        assert_almost_equal(fa.loglike_[-1], fa.score_samples(X).sum())
+        assert_almost_equal(fa.score_samples(X).mean(), fa.score(X))
+
+        diff = np.all(np.diff(fa.loglike_))
+        assert diff > 0.0, "Log likelihood dif not increase"
+
+        # Sample Covariance
+        scov = np.cov(X, rowvar=0.0, bias=1.0)
+
+        # Model Covariance
+        mcov = fa.get_covariance()
+        diff = np.sum(np.abs(scov - mcov)) / W.size
+        assert diff < 0.1, "Mean absolute difference is %f" % diff
+        fa = FactorAnalysis(
+            n_components=n_components, noise_variance_init=np.ones(n_features)
+        )
+        with pytest.raises(ValueError):
+            fa.fit(X[:, :2])
+
+    def f(x, y):
+        return np.abs(getattr(x, y))  # sign will not be equal
+
+    fa1, fa2 = fas
+    for attr in ["loglike_", "components_", "noise_variance_"]:
+        assert_almost_equal(f(fa1, attr), f(fa2, attr))
+
+    fa1.max_iter = 1
+    fa1.verbose = True
+    with pytest.warns(ConvergenceWarning):
+        fa1.fit(X)
+
+    # Test get_covariance and get_precision with n_components == n_features
+    # with n_components < n_features and with n_components == 0
+    for n_components in [0, 2, X.shape[1]]:
+        fa.n_components = n_components
+        fa.fit(X)
+        cov = fa.get_covariance()
+        precision = fa.get_precision()
+        assert_array_almost_equal(np.dot(cov, precision), np.eye(X.shape[1]), 12)
+
+    # test rotation
+    n_components = 2
+
+    results, projections = {}, {}
+    for method in (None, "varimax", "quartimax"):
+        fa_var = FactorAnalysis(n_components=n_components, rotation=method)
+        results[method] = fa_var.fit_transform(X)
+        projections[method] = fa_var.get_covariance()
+    for rot1, rot2 in combinations([None, "varimax", "quartimax"], 2):
+        assert not np.allclose(results[rot1], results[rot2])
+        assert np.allclose(projections[rot1], projections[rot2], atol=3)
+
+    with pytest.raises(ValueError):
+        FactorAnalysis(rotation="not_implemented").fit_transform(X)
+
+    # test against R's psych::principal with rotate="varimax"
+    # (i.e., the values below stem from rotating the components in R)
+    # R's factor analysis returns quite different values; therefore, we only
+    # test the rotation itself
+    factors = np.array(
+        [
+            [0.89421016, -0.35854928, -0.27770122, 0.03773647],
+            [-0.45081822, -0.89132754, 0.0932195, -0.01787973],
+            [0.99500666, -0.02031465, 0.05426497, -0.11539407],
+            [0.96822861, -0.06299656, 0.24411001, 0.07540887],
+        ]
+    )
+    r_solution = np.array(
+        [[0.962, 0.052], [-0.141, 0.989], [0.949, -0.300], [0.937, -0.251]]
+    )
+    rotated = _ortho_rotation(factors[:, :n_components], method="varimax").T
+    assert_array_almost_equal(np.abs(rotated), np.abs(r_solution), decimal=3)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_fastica.py

@@ -0,0 +1,459 @@
+"""
+Test the fastica algorithm.
+"""
+import itertools
+import pytest
+import warnings
+
+import numpy as np
+from scipy import stats
+
+from sklearn.utils._testing import assert_array_equal
+from sklearn.utils._testing import assert_allclose
+
+from sklearn.decomposition import FastICA, fastica, PCA
+from sklearn.decomposition._fastica import _gs_decorrelation
+from sklearn.exceptions import ConvergenceWarning
+
+
+def center_and_norm(x, axis=-1):
+    """Centers and norms x **in place**
+
+    Parameters
+    -----------
+    x: ndarray
+        Array with an axis of observations (statistical units) measured on
+        random variables.
+    axis: int, optional
+        Axis along which the mean and variance are calculated.
+    """
+    x = np.rollaxis(x, axis)
+    x -= x.mean(axis=0)
+    x /= x.std(axis=0)
+
+
+def test_gs():
+    # Test gram schmidt orthonormalization
+    # generate a random orthogonal  matrix
+    rng = np.random.RandomState(0)
+    W, _, _ = np.linalg.svd(rng.randn(10, 10))
+    w = rng.randn(10)
+    _gs_decorrelation(w, W, 10)
+    assert (w**2).sum() < 1.0e-10
+    w = rng.randn(10)
+    u = _gs_decorrelation(w, W, 5)
+    tmp = np.dot(u, W.T)
+    assert (tmp[:5] ** 2).sum() < 1.0e-10
+
+
+def test_fastica_attributes_dtypes(global_dtype):
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((100, 10)).astype(global_dtype, copy=False)
+    fica = FastICA(
+        n_components=5, max_iter=1000, whiten="unit-variance", random_state=0
+    ).fit(X)
+    assert fica.components_.dtype == global_dtype
+    assert fica.mixing_.dtype == global_dtype
+    assert fica.mean_.dtype == global_dtype
+    assert fica.whitening_.dtype == global_dtype
+
+
+def test_fastica_return_dtypes(global_dtype):
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((100, 10)).astype(global_dtype, copy=False)
+    k_, mixing_, s_ = fastica(
+        X, max_iter=1000, whiten="unit-variance", random_state=rng
+    )
+    assert k_.dtype == global_dtype
+    assert mixing_.dtype == global_dtype
+    assert s_.dtype == global_dtype
+
+
+# FIXME remove filter in 1.3
+@pytest.mark.filterwarnings(
+    "ignore:From version 1.3 whiten='unit-variance' will be used by default."
+)
+@pytest.mark.parametrize("add_noise", [True, False])
+def test_fastica_simple(add_noise, global_random_seed, global_dtype):
+    # Test the FastICA algorithm on very simple data.
+    rng = np.random.RandomState(global_random_seed)
+    n_samples = 1000
+    # Generate two sources:
+    s1 = (2 * np.sin(np.linspace(0, 100, n_samples)) > 0) - 1
+    s2 = stats.t.rvs(1, size=n_samples, random_state=global_random_seed)
+    s = np.c_[s1, s2].T
+    center_and_norm(s)
+    s = s.astype(global_dtype)
+    s1, s2 = s
+
+    # Mixing angle
+    phi = 0.6
+    mixing = np.array([[np.cos(phi), np.sin(phi)], [np.sin(phi), -np.cos(phi)]])
+    mixing = mixing.astype(global_dtype)
+    m = np.dot(mixing, s)
+
+    if add_noise:
+        m += 0.1 * rng.randn(2, 1000)
+
+    center_and_norm(m)
+
+    # function as fun arg
+    def g_test(x):
+        return x**3, (3 * x**2).mean(axis=-1)
+
+    algos = ["parallel", "deflation"]
+    nls = ["logcosh", "exp", "cube", g_test]
+    whitening = ["arbitrary-variance", "unit-variance", False]
+    for algo, nl, whiten in itertools.product(algos, nls, whitening):
+        if whiten:
+            k_, mixing_, s_ = fastica(
+                m.T, fun=nl, whiten=whiten, algorithm=algo, random_state=rng
+            )
+            with pytest.raises(ValueError):
+                fastica(m.T, fun=np.tanh, whiten=whiten, algorithm=algo)
+        else:
+            pca = PCA(n_components=2, whiten=True, random_state=rng)
+            X = pca.fit_transform(m.T)
+            k_, mixing_, s_ = fastica(
+                X, fun=nl, algorithm=algo, whiten=False, random_state=rng
+            )
+            with pytest.raises(ValueError):
+                fastica(X, fun=np.tanh, algorithm=algo)
+        s_ = s_.T
+        # Check that the mixing model described in the docstring holds:
+        if whiten:
+            # XXX: exact reconstruction to standard relative tolerance is not
+            # possible. This is probably expected when add_noise is True but we
+            # also need a non-trivial atol in float32 when add_noise is False.
+            #
+            # Note that the 2 sources are non-Gaussian in this test.
+            atol = 1e-5 if global_dtype == np.float32 else 0
+            assert_allclose(np.dot(np.dot(mixing_, k_), m), s_, atol=atol)
+
+        center_and_norm(s_)
+        s1_, s2_ = s_
+        # Check to see if the sources have been estimated
+        # in the wrong order
+        if abs(np.dot(s1_, s2)) > abs(np.dot(s1_, s1)):
+            s2_, s1_ = s_
+        s1_ *= np.sign(np.dot(s1_, s1))
+        s2_ *= np.sign(np.dot(s2_, s2))
+
+        # Check that we have estimated the original sources
+        if not add_noise:
+            assert_allclose(np.dot(s1_, s1) / n_samples, 1, atol=1e-2)
+            assert_allclose(np.dot(s2_, s2) / n_samples, 1, atol=1e-2)
+        else:
+            assert_allclose(np.dot(s1_, s1) / n_samples, 1, atol=1e-1)
+            assert_allclose(np.dot(s2_, s2) / n_samples, 1, atol=1e-1)
+
+    # Test FastICA class
+    _, _, sources_fun = fastica(
+        m.T, fun=nl, algorithm=algo, random_state=global_random_seed
+    )
+    ica = FastICA(fun=nl, algorithm=algo, random_state=global_random_seed)
+    sources = ica.fit_transform(m.T)
+    assert ica.components_.shape == (2, 2)
+    assert sources.shape == (1000, 2)
+
+    assert_allclose(sources_fun, sources)
+    assert_allclose(sources, ica.transform(m.T))
+
+    assert ica.mixing_.shape == (2, 2)
+
+    for fn in [np.tanh, "exp(-.5(x^2))"]:
+        ica = FastICA(fun=fn, algorithm=algo)
+        with pytest.raises(ValueError):
+            ica.fit(m.T)
+
+    with pytest.raises(TypeError):
+        FastICA(fun=range(10)).fit(m.T)
+
+
+def test_fastica_nowhiten():
+    m = [[0, 1], [1, 0]]
+
+    # test for issue #697
+    ica = FastICA(n_components=1, whiten=False, random_state=0)
+    warn_msg = "Ignoring n_components with whiten=False."
+    with pytest.warns(UserWarning, match=warn_msg):
+        ica.fit(m)
+    assert hasattr(ica, "mixing_")
+
+
+def test_fastica_convergence_fail():
+    # Test the FastICA algorithm on very simple data
+    # (see test_non_square_fastica).
+    # Ensure a ConvergenceWarning raised if the tolerance is sufficiently low.
+    rng = np.random.RandomState(0)
+
+    n_samples = 1000
+    # Generate two sources:
+    t = np.linspace(0, 100, n_samples)
+    s1 = np.sin(t)
+    s2 = np.ceil(np.sin(np.pi * t))
+    s = np.c_[s1, s2].T
+    center_and_norm(s)
+
+    # Mixing matrix
+    mixing = rng.randn(6, 2)
+    m = np.dot(mixing, s)
+
+    # Do fastICA with tolerance 0. to ensure failing convergence
+    warn_msg = (
+        "FastICA did not converge. Consider increasing tolerance "
+        "or the maximum number of iterations."
+    )
+    with pytest.warns(ConvergenceWarning, match=warn_msg):
+        ica = FastICA(
+            algorithm="parallel", n_components=2, random_state=rng, max_iter=2, tol=0.0
+        )
+        ica.fit(m.T)
+
+
+@pytest.mark.parametrize("add_noise", [True, False])
+def test_non_square_fastica(add_noise):
+    # Test the FastICA algorithm on very simple data.
+    rng = np.random.RandomState(0)
+
+    n_samples = 1000
+    # Generate two sources:
+    t = np.linspace(0, 100, n_samples)
+    s1 = np.sin(t)
+    s2 = np.ceil(np.sin(np.pi * t))
+    s = np.c_[s1, s2].T
+    center_and_norm(s)
+    s1, s2 = s
+
+    # Mixing matrix
+    mixing = rng.randn(6, 2)
+    m = np.dot(mixing, s)
+
+    if add_noise:
+        m += 0.1 * rng.randn(6, n_samples)
+
+    center_and_norm(m)
+
+    k_, mixing_, s_ = fastica(
+        m.T, n_components=2, whiten="unit-variance", random_state=rng
+    )
+    s_ = s_.T
+
+    # Check that the mixing model described in the docstring holds:
+    assert_allclose(s_, np.dot(np.dot(mixing_, k_), m))
+
+    center_and_norm(s_)
+    s1_, s2_ = s_
+    # Check to see if the sources have been estimated
+    # in the wrong order
+    if abs(np.dot(s1_, s2)) > abs(np.dot(s1_, s1)):
+        s2_, s1_ = s_
+    s1_ *= np.sign(np.dot(s1_, s1))
+    s2_ *= np.sign(np.dot(s2_, s2))
+
+    # Check that we have estimated the original sources
+    if not add_noise:
+        assert_allclose(np.dot(s1_, s1) / n_samples, 1, atol=1e-3)
+        assert_allclose(np.dot(s2_, s2) / n_samples, 1, atol=1e-3)
+
+
+def test_fit_transform(global_random_seed, global_dtype):
+    """Test unit variance of transformed data using FastICA algorithm.
+
+    Check that `fit_transform` gives the same result as applying
+    `fit` and then `transform`.
+
+    Bug #13056
+    """
+    # multivariate uniform data in [0, 1]
+    rng = np.random.RandomState(global_random_seed)
+    X = rng.random_sample((100, 10)).astype(global_dtype)
+    max_iter = 300
+    for whiten, n_components in [["unit-variance", 5], [False, None]]:
+        n_components_ = n_components if n_components is not None else X.shape[1]
+
+        ica = FastICA(
+            n_components=n_components, max_iter=max_iter, whiten=whiten, random_state=0
+        )
+        with warnings.catch_warnings():
+            # make sure that numerical errors do not cause sqrt of negative
+            # values
+            warnings.simplefilter("error", RuntimeWarning)
+            # XXX: for some seeds, the model does not converge.
+            # However this is not what we test here.
+            warnings.simplefilter("ignore", ConvergenceWarning)
+            Xt = ica.fit_transform(X)
+        assert ica.components_.shape == (n_components_, 10)
+        assert Xt.shape == (X.shape[0], n_components_)
+
+        ica2 = FastICA(
+            n_components=n_components, max_iter=max_iter, whiten=whiten, random_state=0
+        )
+        with warnings.catch_warnings():
+            # make sure that numerical errors do not cause sqrt of negative
+            # values
+            warnings.simplefilter("error", RuntimeWarning)
+            warnings.simplefilter("ignore", ConvergenceWarning)
+            ica2.fit(X)
+        assert ica2.components_.shape == (n_components_, 10)
+        Xt2 = ica2.transform(X)
+
+        # XXX: we have to set atol for this test to pass for all seeds when
+        # fitting with float32 data. Is this revealing a bug?
+        if global_dtype:
+            atol = np.abs(Xt2).mean() / 1e6
+        else:
+            atol = 0.0  # the default rtol is enough for float64 data
+        assert_allclose(Xt, Xt2, atol=atol)
+
+
+@pytest.mark.filterwarnings("ignore:Ignoring n_components with whiten=False.")
+@pytest.mark.parametrize(
+    "whiten, n_components, expected_mixing_shape",
+    [
+        ("arbitrary-variance", 5, (10, 5)),
+        ("arbitrary-variance", 10, (10, 10)),
+        ("unit-variance", 5, (10, 5)),
+        ("unit-variance", 10, (10, 10)),
+        (False, 5, (10, 10)),
+        (False, 10, (10, 10)),
+    ],
+)
+def test_inverse_transform(
+    whiten, n_components, expected_mixing_shape, global_random_seed, global_dtype
+):
+    # Test FastICA.inverse_transform
+    n_samples = 100
+    rng = np.random.RandomState(global_random_seed)
+    X = rng.random_sample((n_samples, 10)).astype(global_dtype)
+
+    ica = FastICA(n_components=n_components, random_state=rng, whiten=whiten)
+    with warnings.catch_warnings():
+        # For some dataset (depending on the value of global_dtype) the model
+        # can fail to converge but this should not impact the definition of
+        # a valid inverse transform.
+        warnings.simplefilter("ignore", ConvergenceWarning)
+        Xt = ica.fit_transform(X)
+    assert ica.mixing_.shape == expected_mixing_shape
+    X2 = ica.inverse_transform(Xt)
+    assert X.shape == X2.shape
+
+    # reversibility test in non-reduction case
+    if n_components == X.shape[1]:
+        # XXX: we have to set atol for this test to pass for all seeds when
+        # fitting with float32 data. Is this revealing a bug?
+        if global_dtype:
+            # XXX: dividing by a smaller number makes
+            # tests fail for some seeds.
+            atol = np.abs(X2).mean() / 1e5
+        else:
+            atol = 0.0  # the default rtol is enough for float64 data
+        assert_allclose(X, X2, atol=atol)
+
+
+# FIXME remove filter in 1.3
+@pytest.mark.filterwarnings(
+    "ignore:From version 1.3 whiten='unit-variance' will be used by default."
+)
+def test_fastica_errors():
+    n_features = 3
+    n_samples = 10
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((n_samples, n_features))
+    w_init = rng.randn(n_features + 1, n_features + 1)
+    fastica_estimator = FastICA(max_iter=0)
+    with pytest.raises(ValueError, match="max_iter should be greater than 1"):
+        fastica_estimator.fit(X)
+    with pytest.raises(ValueError, match=r"alpha must be in \[1,2\]"):
+        fastica(X, fun_args={"alpha": 0})
+    with pytest.raises(
+        ValueError, match="w_init has invalid shape.+" r"should be \(3L?, 3L?\)"
+    ):
+        fastica(X, w_init=w_init)
+    with pytest.raises(
+        ValueError, match="Invalid algorithm.+must be.+parallel.+or.+deflation"
+    ):
+        fastica(X, algorithm="pizza")
+
+
+def test_fastica_whiten_unit_variance():
+    """Test unit variance of transformed data using FastICA algorithm.
+
+    Bug #13056
+    """
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((100, 10))
+    n_components = X.shape[1]
+    ica = FastICA(n_components=n_components, whiten="unit-variance", random_state=0)
+    Xt = ica.fit_transform(X)
+
+    assert np.var(Xt) == pytest.approx(1.0)
+
+
+@pytest.mark.parametrize("ica", [FastICA(), FastICA(whiten=True)])
+def test_fastica_whiten_default_value_deprecation(ica):
+    """Test FastICA whiten default value deprecation.
+
+    Regression test for #19490
+    """
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((100, 10))
+    with pytest.warns(FutureWarning, match=r"From version 1.3 whiten="):
+        ica.fit(X)
+        assert ica._whiten == "arbitrary-variance"
+
+
+def test_fastica_whiten_backwards_compatibility():
+    """Test previous behavior for FastICA whitening (whiten=True)
+
+    Regression test for #19490
+    """
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((100, 10))
+    n_components = X.shape[1]
+
+    default_ica = FastICA(n_components=n_components, random_state=0)
+    with pytest.warns(FutureWarning):
+        Xt_on_default = default_ica.fit_transform(X)
+
+    ica = FastICA(n_components=n_components, whiten=True, random_state=0)
+    with pytest.warns(FutureWarning):
+        Xt = ica.fit_transform(X)
+
+    # No warning must be raised in this case.
+    av_ica = FastICA(
+        n_components=n_components, whiten="arbitrary-variance", random_state=0
+    )
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", FutureWarning)
+        Xt_av = av_ica.fit_transform(X)
+
+    # The whitening strategy must be "arbitrary-variance" in all the cases.
+    assert default_ica._whiten == "arbitrary-variance"
+    assert ica._whiten == "arbitrary-variance"
+    assert av_ica._whiten == "arbitrary-variance"
+
+    assert_array_equal(Xt, Xt_on_default)
+    assert_array_equal(Xt, Xt_av)
+
+    assert np.var(Xt) == pytest.approx(1.0 / 100)
+
+
+@pytest.mark.parametrize("whiten", ["arbitrary-variance", "unit-variance", False])
+@pytest.mark.parametrize("return_X_mean", [True, False])
+@pytest.mark.parametrize("return_n_iter", [True, False])
+def test_fastica_output_shape(whiten, return_X_mean, return_n_iter):
+    n_features = 3
+    n_samples = 10
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((n_samples, n_features))
+
+    expected_len = 3 + return_X_mean + return_n_iter
+
+    out = fastica(
+        X, whiten=whiten, return_n_iter=return_n_iter, return_X_mean=return_X_mean
+    )
+
+    assert len(out) == expected_len
+    if not whiten:
+        assert out[0] is None

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_incremental_pca.py

@@ -0,0 +1,451 @@
+"""Tests for Incremental PCA."""
+import numpy as np
+import pytest
+import warnings
+
+from sklearn.utils._testing import assert_almost_equal
+from sklearn.utils._testing import assert_array_almost_equal
+from sklearn.utils._testing import assert_allclose_dense_sparse
+from numpy.testing import assert_array_equal
+
+from sklearn import datasets
+from sklearn.decomposition import PCA, IncrementalPCA
+
+from scipy import sparse
+
+iris = datasets.load_iris()
+
+
+def test_incremental_pca():
+    # Incremental PCA on dense arrays.
+    X = iris.data
+    batch_size = X.shape[0] // 3
+    ipca = IncrementalPCA(n_components=2, batch_size=batch_size)
+    pca = PCA(n_components=2)
+    pca.fit_transform(X)
+
+    X_transformed = ipca.fit_transform(X)
+
+    assert X_transformed.shape == (X.shape[0], 2)
+    np.testing.assert_allclose(
+        ipca.explained_variance_ratio_.sum(),
+        pca.explained_variance_ratio_.sum(),
+        rtol=1e-3,
+    )
+
+    for n_components in [1, 2, X.shape[1]]:
+        ipca = IncrementalPCA(n_components, batch_size=batch_size)
+        ipca.fit(X)
+        cov = ipca.get_covariance()
+        precision = ipca.get_precision()
+        np.testing.assert_allclose(
+            np.dot(cov, precision), np.eye(X.shape[1]), atol=1e-13
+        )
+
+
+@pytest.mark.parametrize(
+    "matrix_class", [sparse.csc_matrix, sparse.csr_matrix, sparse.lil_matrix]
+)
+def test_incremental_pca_sparse(matrix_class):
+    # Incremental PCA on sparse arrays.
+    X = iris.data
+    pca = PCA(n_components=2)
+    pca.fit_transform(X)
+    X_sparse = matrix_class(X)
+    batch_size = X_sparse.shape[0] // 3
+    ipca = IncrementalPCA(n_components=2, batch_size=batch_size)
+
+    X_transformed = ipca.fit_transform(X_sparse)
+
+    assert X_transformed.shape == (X_sparse.shape[0], 2)
+    np.testing.assert_allclose(
+        ipca.explained_variance_ratio_.sum(),
+        pca.explained_variance_ratio_.sum(),
+        rtol=1e-3,
+    )
+
+    for n_components in [1, 2, X.shape[1]]:
+        ipca = IncrementalPCA(n_components, batch_size=batch_size)
+        ipca.fit(X_sparse)
+        cov = ipca.get_covariance()
+        precision = ipca.get_precision()
+        np.testing.assert_allclose(
+            np.dot(cov, precision), np.eye(X_sparse.shape[1]), atol=1e-13
+        )
+
+    with pytest.raises(
+        TypeError,
+        match=(
+            "IncrementalPCA.partial_fit does not support "
+            "sparse input. Either convert data to dense "
+            "or use IncrementalPCA.fit to do so in batches."
+        ),
+    ):
+        ipca.partial_fit(X_sparse)
+
+
+def test_incremental_pca_check_projection():
+    # Test that the projection of data is correct.
+    rng = np.random.RandomState(1999)
+    n, p = 100, 3
+    X = rng.randn(n, p) * 0.1
+    X[:10] += np.array([3, 4, 5])
+    Xt = 0.1 * rng.randn(1, p) + np.array([3, 4, 5])
+
+    # Get the reconstruction of the generated data X
+    # Note that Xt has the same "components" as X, just separated
+    # This is what we want to ensure is recreated correctly
+    Yt = IncrementalPCA(n_components=2).fit(X).transform(Xt)
+
+    # Normalize
+    Yt /= np.sqrt((Yt**2).sum())
+
+    # Make sure that the first element of Yt is ~1, this means
+    # the reconstruction worked as expected
+    assert_almost_equal(np.abs(Yt[0][0]), 1.0, 1)
+
+
+def test_incremental_pca_inverse():
+    # Test that the projection of data can be inverted.
+    rng = np.random.RandomState(1999)
+    n, p = 50, 3
+    X = rng.randn(n, p)  # spherical data
+    X[:, 1] *= 0.00001  # make middle component relatively small
+    X += [5, 4, 3]  # make a large mean
+
+    # same check that we can find the original data from the transformed
+    # signal (since the data is almost of rank n_components)
+    ipca = IncrementalPCA(n_components=2, batch_size=10).fit(X)
+    Y = ipca.transform(X)
+    Y_inverse = ipca.inverse_transform(Y)
+    assert_almost_equal(X, Y_inverse, decimal=3)
+
+
+def test_incremental_pca_validation():
+    # Test that n_components is >=1 and <= n_features.
+    X = np.array([[0, 1, 0], [1, 0, 0]])
+    n_samples, n_features = X.shape
+    for n_components in [-1, 0, 0.99, 4]:
+        with pytest.raises(
+            ValueError,
+            match=(
+                "n_components={} invalid"
+                " for n_features={}, need more rows than"
+                " columns for IncrementalPCA"
+                " processing".format(n_components, n_features)
+            ),
+        ):
+            IncrementalPCA(n_components, batch_size=10).fit(X)
+
+    # Tests that n_components is also <= n_samples.
+    n_components = 3
+    with pytest.raises(
+        ValueError,
+        match=(
+            "n_components={} must be"
+            " less or equal to the batch number of"
+            " samples {}".format(n_components, n_samples)
+        ),
+    ):
+        IncrementalPCA(n_components=n_components).partial_fit(X)
+
+
+def test_n_samples_equal_n_components():
+    # Ensures no warning is raised when n_samples==n_components
+    # Non-regression test for gh-19050
+    ipca = IncrementalPCA(n_components=5)
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", RuntimeWarning)
+        ipca.partial_fit(np.random.randn(5, 7))
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", RuntimeWarning)
+        ipca.fit(np.random.randn(5, 7))
+
+
+def test_n_components_none():
+    # Ensures that n_components == None is handled correctly
+    rng = np.random.RandomState(1999)
+    for n_samples, n_features in [(50, 10), (10, 50)]:
+        X = rng.rand(n_samples, n_features)
+        ipca = IncrementalPCA(n_components=None)
+
+        # First partial_fit call, ipca.n_components_ is inferred from
+        # min(X.shape)
+        ipca.partial_fit(X)
+        assert ipca.n_components_ == min(X.shape)
+
+        # Second partial_fit call, ipca.n_components_ is inferred from
+        # ipca.components_ computed from the first partial_fit call
+        ipca.partial_fit(X)
+        assert ipca.n_components_ == ipca.components_.shape[0]
+
+
+def test_incremental_pca_set_params():
+    # Test that components_ sign is stable over batch sizes.
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    n_features = 20
+    X = rng.randn(n_samples, n_features)
+    X2 = rng.randn(n_samples, n_features)
+    X3 = rng.randn(n_samples, n_features)
+    ipca = IncrementalPCA(n_components=20)
+    ipca.fit(X)
+    # Decreasing number of components
+    ipca.set_params(n_components=10)
+    with pytest.raises(ValueError):
+        ipca.partial_fit(X2)
+    # Increasing number of components
+    ipca.set_params(n_components=15)
+    with pytest.raises(ValueError):
+        ipca.partial_fit(X3)
+    # Returning to original setting
+    ipca.set_params(n_components=20)
+    ipca.partial_fit(X)
+
+
+def test_incremental_pca_num_features_change():
+    # Test that changing n_components will raise an error.
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    X = rng.randn(n_samples, 20)
+    X2 = rng.randn(n_samples, 50)
+    ipca = IncrementalPCA(n_components=None)
+    ipca.fit(X)
+    with pytest.raises(ValueError):
+        ipca.partial_fit(X2)
+
+
+def test_incremental_pca_batch_signs():
+    # Test that components_ sign is stable over batch sizes.
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    n_features = 3
+    X = rng.randn(n_samples, n_features)
+    all_components = []
+    batch_sizes = np.arange(10, 20)
+    for batch_size in batch_sizes:
+        ipca = IncrementalPCA(n_components=None, batch_size=batch_size).fit(X)
+        all_components.append(ipca.components_)
+
+    for i, j in zip(all_components[:-1], all_components[1:]):
+        assert_almost_equal(np.sign(i), np.sign(j), decimal=6)
+
+
+def test_incremental_pca_batch_values():
+    # Test that components_ values are stable over batch sizes.
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    n_features = 3
+    X = rng.randn(n_samples, n_features)
+    all_components = []
+    batch_sizes = np.arange(20, 40, 3)
+    for batch_size in batch_sizes:
+        ipca = IncrementalPCA(n_components=None, batch_size=batch_size).fit(X)
+        all_components.append(ipca.components_)
+
+    for i, j in zip(all_components[:-1], all_components[1:]):
+        assert_almost_equal(i, j, decimal=1)
+
+
+def test_incremental_pca_batch_rank():
+    # Test sample size in each batch is always larger or equal to n_components
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    n_features = 20
+    X = rng.randn(n_samples, n_features)
+    all_components = []
+    batch_sizes = np.arange(20, 90, 3)
+    for batch_size in batch_sizes:
+        ipca = IncrementalPCA(n_components=20, batch_size=batch_size).fit(X)
+        all_components.append(ipca.components_)
+
+    for components_i, components_j in zip(all_components[:-1], all_components[1:]):
+        assert_allclose_dense_sparse(components_i, components_j)
+
+
+def test_incremental_pca_partial_fit():
+    # Test that fit and partial_fit get equivalent results.
+    rng = np.random.RandomState(1999)
+    n, p = 50, 3
+    X = rng.randn(n, p)  # spherical data
+    X[:, 1] *= 0.00001  # make middle component relatively small
+    X += [5, 4, 3]  # make a large mean
+
+    # same check that we can find the original data from the transformed
+    # signal (since the data is almost of rank n_components)
+    batch_size = 10
+    ipca = IncrementalPCA(n_components=2, batch_size=batch_size).fit(X)
+    pipca = IncrementalPCA(n_components=2, batch_size=batch_size)
+    # Add one to make sure endpoint is included
+    batch_itr = np.arange(0, n + 1, batch_size)
+    for i, j in zip(batch_itr[:-1], batch_itr[1:]):
+        pipca.partial_fit(X[i:j, :])
+    assert_almost_equal(ipca.components_, pipca.components_, decimal=3)
+
+
+def test_incremental_pca_against_pca_iris():
+    # Test that IncrementalPCA and PCA are approximate (to a sign flip).
+    X = iris.data
+
+    Y_pca = PCA(n_components=2).fit_transform(X)
+    Y_ipca = IncrementalPCA(n_components=2, batch_size=25).fit_transform(X)
+
+    assert_almost_equal(np.abs(Y_pca), np.abs(Y_ipca), 1)
+
+
+def test_incremental_pca_against_pca_random_data():
+    # Test that IncrementalPCA and PCA are approximate (to a sign flip).
+    rng = np.random.RandomState(1999)
+    n_samples = 100
+    n_features = 3
+    X = rng.randn(n_samples, n_features) + 5 * rng.rand(1, n_features)
+
+    Y_pca = PCA(n_components=3).fit_transform(X)
+    Y_ipca = IncrementalPCA(n_components=3, batch_size=25).fit_transform(X)
+
+    assert_almost_equal(np.abs(Y_pca), np.abs(Y_ipca), 1)
+
+
+def test_explained_variances():
+    # Test that PCA and IncrementalPCA calculations match
+    X = datasets.make_low_rank_matrix(
+        1000, 100, tail_strength=0.0, effective_rank=10, random_state=1999
+    )
+    prec = 3
+    n_samples, n_features = X.shape
+    for nc in [None, 99]:
+        pca = PCA(n_components=nc).fit(X)
+        ipca = IncrementalPCA(n_components=nc, batch_size=100).fit(X)
+        assert_almost_equal(
+            pca.explained_variance_, ipca.explained_variance_, decimal=prec
+        )
+        assert_almost_equal(
+            pca.explained_variance_ratio_, ipca.explained_variance_ratio_, decimal=prec
+        )
+        assert_almost_equal(pca.noise_variance_, ipca.noise_variance_, decimal=prec)
+
+
+def test_singular_values():
+    # Check that the IncrementalPCA output has the correct singular values
+
+    rng = np.random.RandomState(0)
+    n_samples = 1000
+    n_features = 100
+
+    X = datasets.make_low_rank_matrix(
+        n_samples, n_features, tail_strength=0.0, effective_rank=10, random_state=rng
+    )
+
+    pca = PCA(n_components=10, svd_solver="full", random_state=rng).fit(X)
+    ipca = IncrementalPCA(n_components=10, batch_size=100).fit(X)
+    assert_array_almost_equal(pca.singular_values_, ipca.singular_values_, 2)
+
+    # Compare to the Frobenius norm
+    X_pca = pca.transform(X)
+    X_ipca = ipca.transform(X)
+    assert_array_almost_equal(
+        np.sum(pca.singular_values_**2.0), np.linalg.norm(X_pca, "fro") ** 2.0, 12
+    )
+    assert_array_almost_equal(
+        np.sum(ipca.singular_values_**2.0), np.linalg.norm(X_ipca, "fro") ** 2.0, 2
+    )
+
+    # Compare to the 2-norms of the score vectors
+    assert_array_almost_equal(
+        pca.singular_values_, np.sqrt(np.sum(X_pca**2.0, axis=0)), 12
+    )
+    assert_array_almost_equal(
+        ipca.singular_values_, np.sqrt(np.sum(X_ipca**2.0, axis=0)), 2
+    )
+
+    # Set the singular values and see what we get back
+    rng = np.random.RandomState(0)
+    n_samples = 100
+    n_features = 110
+
+    X = datasets.make_low_rank_matrix(
+        n_samples, n_features, tail_strength=0.0, effective_rank=3, random_state=rng
+    )
+
+    pca = PCA(n_components=3, svd_solver="full", random_state=rng)
+    ipca = IncrementalPCA(n_components=3, batch_size=100)
+
+    X_pca = pca.fit_transform(X)
+    X_pca /= np.sqrt(np.sum(X_pca**2.0, axis=0))
+    X_pca[:, 0] *= 3.142
+    X_pca[:, 1] *= 2.718
+
+    X_hat = np.dot(X_pca, pca.components_)
+    pca.fit(X_hat)
+    ipca.fit(X_hat)
+    assert_array_almost_equal(pca.singular_values_, [3.142, 2.718, 1.0], 14)
+    assert_array_almost_equal(ipca.singular_values_, [3.142, 2.718, 1.0], 14)
+
+
+def test_whitening():
+    # Test that PCA and IncrementalPCA transforms match to sign flip.
+    X = datasets.make_low_rank_matrix(
+        1000, 10, tail_strength=0.0, effective_rank=2, random_state=1999
+    )
+    prec = 3
+    n_samples, n_features = X.shape
+    for nc in [None, 9]:
+        pca = PCA(whiten=True, n_components=nc).fit(X)
+        ipca = IncrementalPCA(whiten=True, n_components=nc, batch_size=250).fit(X)
+
+        Xt_pca = pca.transform(X)
+        Xt_ipca = ipca.transform(X)
+        assert_almost_equal(np.abs(Xt_pca), np.abs(Xt_ipca), decimal=prec)
+        Xinv_ipca = ipca.inverse_transform(Xt_ipca)
+        Xinv_pca = pca.inverse_transform(Xt_pca)
+        assert_almost_equal(X, Xinv_ipca, decimal=prec)
+        assert_almost_equal(X, Xinv_pca, decimal=prec)
+        assert_almost_equal(Xinv_pca, Xinv_ipca, decimal=prec)
+
+
+def test_incremental_pca_partial_fit_float_division():
+    # Test to ensure float division is used in all versions of Python
+    # (non-regression test for issue #9489)
+
+    rng = np.random.RandomState(0)
+    A = rng.randn(5, 3) + 2
+    B = rng.randn(7, 3) + 5
+
+    pca = IncrementalPCA(n_components=2)
+    pca.partial_fit(A)
+    # Set n_samples_seen_ to be a floating point number instead of an int
+    pca.n_samples_seen_ = float(pca.n_samples_seen_)
+    pca.partial_fit(B)
+    singular_vals_float_samples_seen = pca.singular_values_
+
+    pca2 = IncrementalPCA(n_components=2)
+    pca2.partial_fit(A)
+    pca2.partial_fit(B)
+    singular_vals_int_samples_seen = pca2.singular_values_
+
+    np.testing.assert_allclose(
+        singular_vals_float_samples_seen, singular_vals_int_samples_seen
+    )
+
+
+def test_incremental_pca_fit_overflow_error():
+    # Test for overflow error on Windows OS
+    # (non-regression test for issue #17693)
+    rng = np.random.RandomState(0)
+    A = rng.rand(500000, 2)
+
+    ipca = IncrementalPCA(n_components=2, batch_size=10000)
+    ipca.fit(A)
+
+    pca = PCA(n_components=2)
+    pca.fit(A)
+
+    np.testing.assert_allclose(ipca.singular_values_, pca.singular_values_)
+
+
+def test_incremental_pca_feature_names_out():
+    """Check feature names out for IncrementalPCA."""
+    ipca = IncrementalPCA(n_components=2).fit(iris.data)
+
+    names = ipca.get_feature_names_out()
+    assert_array_equal([f"incrementalpca{i}" for i in range(2)], names)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_kernel_pca.py

@@ -0,0 +1,571 @@
+import numpy as np
+import scipy.sparse as sp
+import pytest
+import warnings
+
+from sklearn.utils._testing import (
+    assert_array_almost_equal,
+    assert_array_equal,
+    assert_allclose,
+)
+
+from sklearn.decomposition import PCA, KernelPCA
+from sklearn.datasets import make_circles
+from sklearn.datasets import make_blobs
+from sklearn.exceptions import NotFittedError
+from sklearn.linear_model import Perceptron
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import GridSearchCV
+from sklearn.metrics.pairwise import rbf_kernel
+from sklearn.utils.validation import _check_psd_eigenvalues
+
+
+def test_kernel_pca():
+    """Nominal test for all solvers and all known kernels + a custom one
+
+    It tests
+     - that fit_transform is equivalent to fit+transform
+     - that the shapes of transforms and inverse transforms are correct
+    """
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((5, 4))
+    X_pred = rng.random_sample((2, 4))
+
+    def histogram(x, y, **kwargs):
+        # Histogram kernel implemented as a callable.
+        assert kwargs == {}  # no kernel_params that we didn't ask for
+        return np.minimum(x, y).sum()
+
+    for eigen_solver in ("auto", "dense", "arpack", "randomized"):
+        for kernel in ("linear", "rbf", "poly", histogram):
+            # histogram kernel produces singular matrix inside linalg.solve
+            # XXX use a least-squares approximation?
+            inv = not callable(kernel)
+
+            # transform fit data
+            kpca = KernelPCA(
+                4, kernel=kernel, eigen_solver=eigen_solver, fit_inverse_transform=inv
+            )
+            X_fit_transformed = kpca.fit_transform(X_fit)
+            X_fit_transformed2 = kpca.fit(X_fit).transform(X_fit)
+            assert_array_almost_equal(
+                np.abs(X_fit_transformed), np.abs(X_fit_transformed2)
+            )
+
+            # non-regression test: previously, gamma would be 0 by default,
+            # forcing all eigenvalues to 0 under the poly kernel
+            assert X_fit_transformed.size != 0
+
+            # transform new data
+            X_pred_transformed = kpca.transform(X_pred)
+            assert X_pred_transformed.shape[1] == X_fit_transformed.shape[1]
+
+            # inverse transform
+            if inv:
+                X_pred2 = kpca.inverse_transform(X_pred_transformed)
+                assert X_pred2.shape == X_pred.shape
+
+
+def test_kernel_pca_invalid_solver():
+    """Check that kPCA raises an error if the solver parameter is invalid"""
+    with pytest.raises(ValueError):
+        KernelPCA(eigen_solver="unknown").fit(np.random.randn(10, 10))
+
+
+def test_kernel_pca_invalid_parameters():
+    """Check that kPCA raises an error if the parameters are invalid
+
+    Tests fitting inverse transform with a precomputed kernel raises a
+    ValueError.
+    """
+    estimator = KernelPCA(
+        n_components=10, fit_inverse_transform=True, kernel="precomputed"
+    )
+    err_ms = "Cannot fit_inverse_transform with a precomputed kernel"
+    with pytest.raises(ValueError, match=err_ms):
+        estimator.fit(np.random.randn(10, 10))
+
+
+def test_kernel_pca_consistent_transform():
+    """Check robustness to mutations in the original training array
+
+    Test that after fitting a kPCA model, it stays independent of any
+    mutation of the values of the original data object by relying on an
+    internal copy.
+    """
+    # X_fit_ needs to retain the old, unmodified copy of X
+    state = np.random.RandomState(0)
+    X = state.rand(10, 10)
+    kpca = KernelPCA(random_state=state).fit(X)
+    transformed1 = kpca.transform(X)
+
+    X_copy = X.copy()
+    X[:, 0] = 666
+    transformed2 = kpca.transform(X_copy)
+    assert_array_almost_equal(transformed1, transformed2)
+
+
+def test_kernel_pca_deterministic_output():
+    """Test that Kernel PCA produces deterministic output
+
+    Tests that the same inputs and random state produce the same output.
+    """
+    rng = np.random.RandomState(0)
+    X = rng.rand(10, 10)
+    eigen_solver = ("arpack", "dense")
+
+    for solver in eigen_solver:
+        transformed_X = np.zeros((20, 2))
+        for i in range(20):
+            kpca = KernelPCA(n_components=2, eigen_solver=solver, random_state=rng)
+            transformed_X[i, :] = kpca.fit_transform(X)[0]
+        assert_allclose(transformed_X, np.tile(transformed_X[0, :], 20).reshape(20, 2))
+
+
+def test_kernel_pca_sparse():
+    """Test that kPCA works on a sparse data input.
+
+    Same test as ``test_kernel_pca except inverse_transform`` since it's not
+    implemented for sparse matrices.
+    """
+    rng = np.random.RandomState(0)
+    X_fit = sp.csr_matrix(rng.random_sample((5, 4)))
+    X_pred = sp.csr_matrix(rng.random_sample((2, 4)))
+
+    for eigen_solver in ("auto", "arpack", "randomized"):
+        for kernel in ("linear", "rbf", "poly"):
+            # transform fit data
+            kpca = KernelPCA(
+                4,
+                kernel=kernel,
+                eigen_solver=eigen_solver,
+                fit_inverse_transform=False,
+                random_state=0,
+            )
+            X_fit_transformed = kpca.fit_transform(X_fit)
+            X_fit_transformed2 = kpca.fit(X_fit).transform(X_fit)
+            assert_array_almost_equal(
+                np.abs(X_fit_transformed), np.abs(X_fit_transformed2)
+            )
+
+            # transform new data
+            X_pred_transformed = kpca.transform(X_pred)
+            assert X_pred_transformed.shape[1] == X_fit_transformed.shape[1]
+
+            # inverse transform: not available for sparse matrices
+            # XXX: should we raise another exception type here? For instance:
+            # NotImplementedError.
+            with pytest.raises(NotFittedError):
+                kpca.inverse_transform(X_pred_transformed)
+
+
+@pytest.mark.parametrize("solver", ["auto", "dense", "arpack", "randomized"])
+@pytest.mark.parametrize("n_features", [4, 10])
+def test_kernel_pca_linear_kernel(solver, n_features):
+    """Test that kPCA with linear kernel is equivalent to PCA for all solvers.
+
+    KernelPCA with linear kernel should produce the same output as PCA.
+    """
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((5, n_features))
+    X_pred = rng.random_sample((2, n_features))
+
+    # for a linear kernel, kernel PCA should find the same projection as PCA
+    # modulo the sign (direction)
+    # fit only the first four components: fifth is near zero eigenvalue, so
+    # can be trimmed due to roundoff error
+    n_comps = 3 if solver == "arpack" else 4
+    assert_array_almost_equal(
+        np.abs(KernelPCA(n_comps, eigen_solver=solver).fit(X_fit).transform(X_pred)),
+        np.abs(
+            PCA(n_comps, svd_solver=solver if solver != "dense" else "full")
+            .fit(X_fit)
+            .transform(X_pred)
+        ),
+    )
+
+
+def test_kernel_pca_n_components():
+    """Test that `n_components` is correctly taken into account for projections
+
+    For all solvers this tests that the output has the correct shape depending
+    on the selected number of components.
+    """
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((5, 4))
+    X_pred = rng.random_sample((2, 4))
+
+    for eigen_solver in ("dense", "arpack", "randomized"):
+        for c in [1, 2, 4]:
+            kpca = KernelPCA(n_components=c, eigen_solver=eigen_solver)
+            shape = kpca.fit(X_fit).transform(X_pred).shape
+
+            assert shape == (2, c)
+
+
+@pytest.mark.parametrize("n_components", [-1, 0])
+def test_kernal_pca_too_few_components(n_components):
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((5, 4))
+    kpca = KernelPCA(n_components=n_components)
+    msg = "n_components.* must be >= 1"
+    with pytest.raises(ValueError, match=msg):
+        kpca.fit(X_fit)
+
+
+def test_remove_zero_eig():
+    """Check that the ``remove_zero_eig`` parameter works correctly.
+
+    Tests that the null-space (Zero) eigenvalues are removed when
+    remove_zero_eig=True, whereas they are not by default.
+    """
+    X = np.array([[1 - 1e-30, 1], [1, 1], [1, 1 - 1e-20]])
+
+    # n_components=None (default) => remove_zero_eig is True
+    kpca = KernelPCA()
+    Xt = kpca.fit_transform(X)
+    assert Xt.shape == (3, 0)
+
+    kpca = KernelPCA(n_components=2)
+    Xt = kpca.fit_transform(X)
+    assert Xt.shape == (3, 2)
+
+    kpca = KernelPCA(n_components=2, remove_zero_eig=True)
+    Xt = kpca.fit_transform(X)
+    assert Xt.shape == (3, 0)
+
+
+def test_leave_zero_eig():
+    """Non-regression test for issue #12141 (PR #12143)
+
+    This test checks that fit().transform() returns the same result as
+    fit_transform() in case of non-removed zero eigenvalue.
+    """
+    X_fit = np.array([[1, 1], [0, 0]])
+
+    # Assert that even with all np warnings on, there is no div by zero warning
+    with warnings.catch_warnings():
+        # There might be warnings about the kernel being badly conditioned,
+        # but there should not be warnings about division by zero.
+        # (Numpy division by zero warning can have many message variants, but
+        # at least we know that it is a RuntimeWarning so lets check only this)
+        warnings.simplefilter("error", RuntimeWarning)
+        with np.errstate(all="warn"):
+            k = KernelPCA(n_components=2, remove_zero_eig=False, eigen_solver="dense")
+            # Fit, then transform
+            A = k.fit(X_fit).transform(X_fit)
+            # Do both at once
+            B = k.fit_transform(X_fit)
+            # Compare
+            assert_array_almost_equal(np.abs(A), np.abs(B))
+
+
+def test_kernel_pca_precomputed():
+    """Test that kPCA works with a precomputed kernel, for all solvers"""
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((5, 4))
+    X_pred = rng.random_sample((2, 4))
+
+    for eigen_solver in ("dense", "arpack", "randomized"):
+        X_kpca = (
+            KernelPCA(4, eigen_solver=eigen_solver, random_state=0)
+            .fit(X_fit)
+            .transform(X_pred)
+        )
+
+        X_kpca2 = (
+            KernelPCA(
+                4, eigen_solver=eigen_solver, kernel="precomputed", random_state=0
+            )
+            .fit(np.dot(X_fit, X_fit.T))
+            .transform(np.dot(X_pred, X_fit.T))
+        )
+
+        X_kpca_train = KernelPCA(
+            4, eigen_solver=eigen_solver, kernel="precomputed", random_state=0
+        ).fit_transform(np.dot(X_fit, X_fit.T))
+
+        X_kpca_train2 = (
+            KernelPCA(
+                4, eigen_solver=eigen_solver, kernel="precomputed", random_state=0
+            )
+            .fit(np.dot(X_fit, X_fit.T))
+            .transform(np.dot(X_fit, X_fit.T))
+        )
+
+        assert_array_almost_equal(np.abs(X_kpca), np.abs(X_kpca2))
+
+        assert_array_almost_equal(np.abs(X_kpca_train), np.abs(X_kpca_train2))
+
+
+@pytest.mark.parametrize("solver", ["auto", "dense", "arpack", "randomized"])
+def test_kernel_pca_precomputed_non_symmetric(solver):
+    """Check that the kernel centerer works.
+
+    Tests that a non symmetric precomputed kernel is actually accepted
+    because the kernel centerer does its job correctly.
+    """
+
+    # a non symmetric gram matrix
+    K = [[1, 2], [3, 40]]
+    kpca = KernelPCA(
+        kernel="precomputed", eigen_solver=solver, n_components=1, random_state=0
+    )
+    kpca.fit(K)  # no error
+
+    # same test with centered kernel
+    Kc = [[9, -9], [-9, 9]]
+    kpca_c = KernelPCA(
+        kernel="precomputed", eigen_solver=solver, n_components=1, random_state=0
+    )
+    kpca_c.fit(Kc)
+
+    # comparison between the non-centered and centered versions
+    assert_array_equal(kpca.eigenvectors_, kpca_c.eigenvectors_)
+    assert_array_equal(kpca.eigenvalues_, kpca_c.eigenvalues_)
+
+
+def test_kernel_pca_invalid_kernel():
+    """Tests that using an invalid kernel name raises a ValueError
+
+    An invalid kernel name should raise a ValueError at fit time.
+    """
+    rng = np.random.RandomState(0)
+    X_fit = rng.random_sample((2, 4))
+    kpca = KernelPCA(kernel="tototiti")
+    with pytest.raises(ValueError):
+        kpca.fit(X_fit)
+
+
+def test_gridsearch_pipeline():
+    """Check that kPCA works as expected in a grid search pipeline
+
+    Test if we can do a grid-search to find parameters to separate
+    circles with a perceptron model.
+    """
+    X, y = make_circles(n_samples=400, factor=0.3, noise=0.05, random_state=0)
+    kpca = KernelPCA(kernel="rbf", n_components=2)
+    pipeline = Pipeline([("kernel_pca", kpca), ("Perceptron", Perceptron(max_iter=5))])
+    param_grid = dict(kernel_pca__gamma=2.0 ** np.arange(-2, 2))
+    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
+    grid_search.fit(X, y)
+    assert grid_search.best_score_ == 1
+
+
+def test_gridsearch_pipeline_precomputed():
+    """Check that kPCA works as expected in a grid search pipeline (2)
+
+    Test if we can do a grid-search to find parameters to separate
+    circles with a perceptron model. This test uses a precomputed kernel.
+    """
+    X, y = make_circles(n_samples=400, factor=0.3, noise=0.05, random_state=0)
+    kpca = KernelPCA(kernel="precomputed", n_components=2)
+    pipeline = Pipeline([("kernel_pca", kpca), ("Perceptron", Perceptron(max_iter=5))])
+    param_grid = dict(Perceptron__max_iter=np.arange(1, 5))
+    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
+    X_kernel = rbf_kernel(X, gamma=2.0)
+    grid_search.fit(X_kernel, y)
+    assert grid_search.best_score_ == 1
+
+
+def test_nested_circles():
+    """Check that kPCA projects in a space where nested circles are separable
+
+    Tests that 2D nested circles become separable with a perceptron when
+    projected in the first 2 kPCA using an RBF kernel, while raw samples
+    are not directly separable in the original space.
+    """
+    X, y = make_circles(n_samples=400, factor=0.3, noise=0.05, random_state=0)
+
+    # 2D nested circles are not linearly separable
+    train_score = Perceptron(max_iter=5).fit(X, y).score(X, y)
+    assert train_score < 0.8
+
+    # Project the circles data into the first 2 components of a RBF Kernel
+    # PCA model.
+    # Note that the gamma value is data dependent. If this test breaks
+    # and the gamma value has to be updated, the Kernel PCA example will
+    # have to be updated too.
+    kpca = KernelPCA(
+        kernel="rbf", n_components=2, fit_inverse_transform=True, gamma=2.0
+    )
+    X_kpca = kpca.fit_transform(X)
+
+    # The data is perfectly linearly separable in that space
+    train_score = Perceptron(max_iter=5).fit(X_kpca, y).score(X_kpca, y)
+    assert train_score == 1.0
+
+
+def test_kernel_conditioning():
+    """Check that ``_check_psd_eigenvalues`` is correctly called in kPCA
+
+    Non-regression test for issue #12140 (PR #12145).
+    """
+
+    # create a pathological X leading to small non-zero eigenvalue
+    X = [[5, 1], [5 + 1e-8, 1e-8], [5 + 1e-8, 0]]
+    kpca = KernelPCA(kernel="linear", n_components=2, fit_inverse_transform=True)
+    kpca.fit(X)
+
+    # check that the small non-zero eigenvalue was correctly set to zero
+    assert kpca.eigenvalues_.min() == 0
+    assert np.all(kpca.eigenvalues_ == _check_psd_eigenvalues(kpca.eigenvalues_))
+
+
+@pytest.mark.parametrize("solver", ["auto", "dense", "arpack", "randomized"])
+def test_precomputed_kernel_not_psd(solver):
+    """Check how KernelPCA works with non-PSD kernels depending on n_components
+
+    Tests for all methods what happens with a non PSD gram matrix (this
+    can happen in an isomap scenario, or with custom kernel functions, or
+    maybe with ill-posed datasets).
+
+    When ``n_component`` is large enough to capture a negative eigenvalue, an
+    error should be raised. Otherwise, KernelPCA should run without error
+    since the negative eigenvalues are not selected.
+    """
+
+    # a non PSD kernel with large eigenvalues, already centered
+    # it was captured from an isomap call and multiplied by 100 for compacity
+    K = [
+        [4.48, -1.0, 8.07, 2.33, 2.33, 2.33, -5.76, -12.78],
+        [-1.0, -6.48, 4.5, -1.24, -1.24, -1.24, -0.81, 7.49],
+        [8.07, 4.5, 15.48, 2.09, 2.09, 2.09, -11.1, -23.23],
+        [2.33, -1.24, 2.09, 4.0, -3.65, -3.65, 1.02, -0.9],
+        [2.33, -1.24, 2.09, -3.65, 4.0, -3.65, 1.02, -0.9],
+        [2.33, -1.24, 2.09, -3.65, -3.65, 4.0, 1.02, -0.9],
+        [-5.76, -0.81, -11.1, 1.02, 1.02, 1.02, 4.86, 9.75],
+        [-12.78, 7.49, -23.23, -0.9, -0.9, -0.9, 9.75, 21.46],
+    ]
+    # this gram matrix has 5 positive eigenvalues and 3 negative ones
+    # [ 52.72,   7.65,   7.65,   5.02,   0.  ,  -0.  ,  -6.13, -15.11]
+
+    # 1. ask for enough components to get a significant negative one
+    kpca = KernelPCA(kernel="precomputed", eigen_solver=solver, n_components=7)
+    # make sure that the appropriate error is raised
+    with pytest.raises(ValueError, match="There are significant negative eigenvalues"):
+        kpca.fit(K)
+
+    # 2. ask for a small enough n_components to get only positive ones
+    kpca = KernelPCA(kernel="precomputed", eigen_solver=solver, n_components=2)
+    if solver == "randomized":
+        # the randomized method is still inconsistent with the others on this
+        # since it selects the eigenvalues based on the largest 2 modules, not
+        # on the largest 2 values.
+        #
+        # At least we can ensure that we return an error instead of returning
+        # the wrong eigenvalues
+        with pytest.raises(
+            ValueError, match="There are significant negative eigenvalues"
+        ):
+            kpca.fit(K)
+    else:
+        # general case: make sure that it works
+        kpca.fit(K)
+
+
+@pytest.mark.parametrize("n_components", [4, 10, 20])
+def test_kernel_pca_solvers_equivalence(n_components):
+    """Check that 'dense' 'arpack' & 'randomized' solvers give similar results"""
+
+    # Generate random data
+    n_train, n_test = 1_000, 100
+    X, _ = make_circles(
+        n_samples=(n_train + n_test), factor=0.3, noise=0.05, random_state=0
+    )
+    X_fit, X_pred = X[:n_train, :], X[n_train:, :]
+
+    # reference (full)
+    ref_pred = (
+        KernelPCA(n_components, eigen_solver="dense", random_state=0)
+        .fit(X_fit)
+        .transform(X_pred)
+    )
+
+    # arpack
+    a_pred = (
+        KernelPCA(n_components, eigen_solver="arpack", random_state=0)
+        .fit(X_fit)
+        .transform(X_pred)
+    )
+    # check that the result is still correct despite the approx
+    assert_array_almost_equal(np.abs(a_pred), np.abs(ref_pred))
+
+    # randomized
+    r_pred = (
+        KernelPCA(n_components, eigen_solver="randomized", random_state=0)
+        .fit(X_fit)
+        .transform(X_pred)
+    )
+    # check that the result is still correct despite the approximation
+    assert_array_almost_equal(np.abs(r_pred), np.abs(ref_pred))
+
+
+def test_kernel_pca_inverse_transform_reconstruction():
+    """Test if the reconstruction is a good approximation.
+
+    Note that in general it is not possible to get an arbitrarily good
+    reconstruction because of kernel centering that does not
+    preserve all the information of the original data.
+    """
+    X, *_ = make_blobs(n_samples=100, n_features=4, random_state=0)
+
+    kpca = KernelPCA(
+        n_components=20, kernel="rbf", fit_inverse_transform=True, alpha=1e-3
+    )
+    X_trans = kpca.fit_transform(X)
+    X_reconst = kpca.inverse_transform(X_trans)
+    assert np.linalg.norm(X - X_reconst) / np.linalg.norm(X) < 1e-1
+
+
+def test_kernel_pca_raise_not_fitted_error():
+    X = np.random.randn(15).reshape(5, 3)
+    kpca = KernelPCA()
+    kpca.fit(X)
+    with pytest.raises(NotFittedError):
+        kpca.inverse_transform(X)
+
+
+def test_32_64_decomposition_shape():
+    """Test that the decomposition is similar for 32 and 64 bits data
+
+    Non regression test for
+    https://github.com/scikit-learn/scikit-learn/issues/18146
+    """
+    X, y = make_blobs(
+        n_samples=30, centers=[[0, 0, 0], [1, 1, 1]], random_state=0, cluster_std=0.1
+    )
+    X = StandardScaler().fit_transform(X)
+    X -= X.min()
+
+    # Compare the shapes (corresponds to the number of non-zero eigenvalues)
+    kpca = KernelPCA()
+    assert kpca.fit_transform(X).shape == kpca.fit_transform(X.astype(np.float32)).shape
+
+
+# TODO: Remove in 1.2
+def test_kernel_pca_lambdas_deprecated():
+    kp = KernelPCA()
+    kp.eigenvalues_ = None
+    msg = r"Attribute `lambdas_` was deprecated in version 1\.0"
+    with pytest.warns(FutureWarning, match=msg):
+        kp.lambdas_
+
+
+# TODO: Remove in 1.2
+def test_kernel_pca_alphas_deprecated():
+    kp = KernelPCA(kernel="precomputed")
+    kp.eigenvectors_ = None
+    msg = r"Attribute `alphas_` was deprecated in version 1\.0"
+    with pytest.warns(FutureWarning, match=msg):
+        kp.alphas_
+
+
+def test_kernel_pca_feature_names_out():
+    """Check feature names out for KernelPCA."""
+    X, *_ = make_blobs(n_samples=100, n_features=4, random_state=0)
+    kpca = KernelPCA(n_components=2).fit(X)
+
+    names = kpca.get_feature_names_out()
+    assert_array_equal([f"kernelpca{i}" for i in range(2)], names)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_nmf.py

@@ -0,0 +1,970 @@
+import re
+import sys
+from io import StringIO
+
+import numpy as np
+import scipy.sparse as sp
+
+from scipy import linalg
+from sklearn.decomposition import NMF, MiniBatchNMF
+from sklearn.decomposition import non_negative_factorization
+from sklearn.decomposition import _nmf as nmf  # For testing internals
+from scipy.sparse import csc_matrix
+
+import pytest
+
+from sklearn.utils._testing import assert_array_equal
+from sklearn.utils._testing import assert_array_almost_equal
+from sklearn.utils._testing import assert_almost_equal
+from sklearn.utils._testing import assert_allclose
+from sklearn.utils._testing import ignore_warnings
+from sklearn.utils.extmath import squared_norm
+from sklearn.base import clone
+from sklearn.exceptions import ConvergenceWarning
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_convergence_warning(Estimator, solver):
+    convergence_warning = (
+        "Maximum number of iterations 1 reached. Increase it to improve convergence."
+    )
+    A = np.ones((2, 2))
+    with pytest.warns(ConvergenceWarning, match=convergence_warning):
+        Estimator(max_iter=1, **solver).fit(A)
+
+
+def test_initialize_nn_output():
+    # Test that initialization does not return negative values
+    rng = np.random.mtrand.RandomState(42)
+    data = np.abs(rng.randn(10, 10))
+    for init in ("random", "nndsvd", "nndsvda", "nndsvdar"):
+        W, H = nmf._initialize_nmf(data, 10, init=init, random_state=0)
+        assert not ((W < 0).any() or (H < 0).any())
+
+
+@pytest.mark.filterwarnings(
+    r"ignore:The multiplicative update \('mu'\) solver cannot update zeros present in"
+    r" the initialization"
+)
+def test_parameter_checking():
+    A = np.ones((2, 2))
+    name = "spam"
+
+    with ignore_warnings(category=FutureWarning):
+        # TODO remove in 1.2
+        msg = "Invalid regularization parameter: got 'spam' instead of one of"
+        with pytest.raises(ValueError, match=msg):
+            NMF(regularization=name).fit(A)
+
+    msg = "Invalid beta_loss parameter: solver 'cd' does not handle beta_loss = 1.0"
+    with pytest.raises(ValueError, match=msg):
+        NMF(solver="cd", beta_loss=1.0).fit(A)
+    msg = "Negative values in data passed to"
+    with pytest.raises(ValueError, match=msg):
+        NMF().fit(-A)
+    clf = NMF(2, tol=0.1).fit(A)
+    with pytest.raises(ValueError, match=msg):
+        clf.transform(-A)
+    with pytest.raises(ValueError, match=msg):
+        nmf._initialize_nmf(-A, 2, "nndsvd")
+
+    for init in ["nndsvd", "nndsvda", "nndsvdar"]:
+        msg = re.escape(
+            "init = '{}' can only be used when "
+            "n_components <= min(n_samples, n_features)".format(init)
+        )
+        with pytest.raises(ValueError, match=msg):
+            NMF(3, init=init).fit(A)
+        with pytest.raises(ValueError, match=msg):
+            MiniBatchNMF(3, init=init).fit(A)
+        with pytest.raises(ValueError, match=msg):
+            nmf._initialize_nmf(A, 3, init)
+
+
+@pytest.mark.parametrize(
+    "param, match",
+    [
+        ({"n_components": 0}, "Number of components must be a positive integer"),
+        ({"max_iter": -1}, "Maximum number of iterations must be a positive integer"),
+        ({"tol": -1}, "Tolerance for stopping criteria must be positive"),
+        ({"init": "wrong"}, "Invalid init parameter"),
+        ({"beta_loss": "wrong"}, "Invalid beta_loss parameter"),
+    ],
+)
+@pytest.mark.parametrize("Estimator", [NMF, MiniBatchNMF])
+def test_nmf_common_wrong_params(Estimator, param, match):
+    # Check that appropriate errors are raised for invalid values of parameters common
+    # to NMF and MiniBatchNMF.
+    A = np.ones((2, 2))
+    with pytest.raises(ValueError, match=match):
+        Estimator(**param).fit(A)
+
+
+@pytest.mark.parametrize(
+    "param, match",
+    [
+        ({"solver": "wrong"}, "Invalid solver parameter"),
+    ],
+)
+def test_nmf_wrong_params(param, match):
+    # Check that appropriate errors are raised for invalid values specific to NMF
+    # parameters
+    A = np.ones((2, 2))
+    with pytest.raises(ValueError, match=match):
+        NMF(**param).fit(A)
+
+
+@pytest.mark.parametrize(
+    "param, match",
+    [
+        ({"batch_size": 0}, "batch_size must be a positive integer"),
+    ],
+)
+def test_minibatch_nmf_wrong_params(param, match):
+    # Check that appropriate errors are raised for invalid values specific to
+    # MiniBatchNMF parameters
+    A = np.ones((2, 2))
+    with pytest.raises(ValueError, match=match):
+        MiniBatchNMF(**param).fit(A)
+
+
+def test_initialize_close():
+    # Test NNDSVD error
+    # Test that _initialize_nmf error is less than the standard deviation of
+    # the entries in the matrix.
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(10, 10))
+    W, H = nmf._initialize_nmf(A, 10, init="nndsvd")
+    error = linalg.norm(np.dot(W, H) - A)
+    sdev = linalg.norm(A - A.mean())
+    assert error <= sdev
+
+
+def test_initialize_variants():
+    # Test NNDSVD variants correctness
+    # Test that the variants 'nndsvda' and 'nndsvdar' differ from basic
+    # 'nndsvd' only where the basic version has zeros.
+    rng = np.random.mtrand.RandomState(42)
+    data = np.abs(rng.randn(10, 10))
+    W0, H0 = nmf._initialize_nmf(data, 10, init="nndsvd")
+    Wa, Ha = nmf._initialize_nmf(data, 10, init="nndsvda")
+    War, Har = nmf._initialize_nmf(data, 10, init="nndsvdar", random_state=0)
+
+    for ref, evl in ((W0, Wa), (W0, War), (H0, Ha), (H0, Har)):
+        assert_almost_equal(evl[ref != 0], ref[ref != 0])
+
+
+# ignore UserWarning raised when both solver='mu' and init='nndsvd'
+@ignore_warnings(category=UserWarning)
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+@pytest.mark.parametrize("init", (None, "nndsvd", "nndsvda", "nndsvdar", "random"))
+@pytest.mark.parametrize("alpha_W", (0.0, 1.0))
+@pytest.mark.parametrize("alpha_H", (0.0, 1.0, "same"))
+def test_nmf_fit_nn_output(Estimator, solver, init, alpha_W, alpha_H):
+    # Test that the decomposition does not contain negative values
+    A = np.c_[5.0 - np.arange(1, 6), 5.0 + np.arange(1, 6)]
+    model = Estimator(
+        n_components=2,
+        init=init,
+        alpha_W=alpha_W,
+        alpha_H=alpha_H,
+        random_state=0,
+        **solver,
+    )
+    transf = model.fit_transform(A)
+    assert not ((model.components_ < 0).any() or (transf < 0).any())
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_fit_close(Estimator, solver):
+    rng = np.random.mtrand.RandomState(42)
+    # Test that the fit is not too far away
+    pnmf = Estimator(
+        5,
+        init="nndsvdar",
+        random_state=0,
+        max_iter=600,
+        **solver,
+    )
+    X = np.abs(rng.randn(6, 5))
+    assert pnmf.fit(X).reconstruction_err_ < 0.1
+
+
+def test_nmf_true_reconstruction():
+    # Test that the fit is not too far away from an exact solution
+    # (by construction)
+    n_samples = 15
+    n_features = 10
+    n_components = 5
+    beta_loss = 1
+    batch_size = 3
+    max_iter = 1000
+
+    rng = np.random.mtrand.RandomState(42)
+    W_true = np.zeros([n_samples, n_components])
+    W_array = np.abs(rng.randn(n_samples))
+    for j in range(n_components):
+        W_true[j % n_samples, j] = W_array[j % n_samples]
+    H_true = np.zeros([n_components, n_features])
+    H_array = np.abs(rng.randn(n_components))
+    for j in range(n_features):
+        H_true[j % n_components, j] = H_array[j % n_components]
+    X = np.dot(W_true, H_true)
+
+    model = NMF(
+        n_components=n_components,
+        solver="mu",
+        beta_loss=beta_loss,
+        max_iter=max_iter,
+        random_state=0,
+    )
+    transf = model.fit_transform(X)
+    X_calc = np.dot(transf, model.components_)
+
+    assert model.reconstruction_err_ < 0.1
+    assert_allclose(X, X_calc)
+
+    mbmodel = MiniBatchNMF(
+        n_components=n_components,
+        beta_loss=beta_loss,
+        batch_size=batch_size,
+        random_state=0,
+        max_iter=max_iter,
+    )
+    transf = mbmodel.fit_transform(X)
+    X_calc = np.dot(transf, mbmodel.components_)
+
+    assert mbmodel.reconstruction_err_ < 0.1
+    assert_allclose(X, X_calc, atol=1)
+
+
+@pytest.mark.parametrize("solver", ["cd", "mu"])
+def test_nmf_transform(solver):
+    # Test that fit_transform is equivalent to fit.transform for NMF
+    # Test that NMF.transform returns close values
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(6, 5))
+    m = NMF(
+        solver=solver,
+        n_components=3,
+        init="random",
+        random_state=0,
+        tol=1e-6,
+    )
+    ft = m.fit_transform(A)
+    t = m.transform(A)
+    assert_allclose(ft, t, atol=1e-1)
+
+
+def test_minibatch_nmf_transform():
+    # Test that fit_transform is equivalent to fit.transform for MiniBatchNMF
+    # Only guaranteed with fresh restarts
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(6, 5))
+    m = MiniBatchNMF(
+        n_components=3,
+        random_state=0,
+        tol=1e-3,
+        fresh_restarts=True,
+    )
+    ft = m.fit_transform(A)
+    t = m.transform(A)
+    assert_allclose(ft, t)
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_transform_custom_init(Estimator, solver):
+    # Smoke test that checks if NMF.transform works with custom initialization
+    random_state = np.random.RandomState(0)
+    A = np.abs(random_state.randn(6, 5))
+    n_components = 4
+    avg = np.sqrt(A.mean() / n_components)
+    H_init = np.abs(avg * random_state.randn(n_components, 5))
+    W_init = np.abs(avg * random_state.randn(6, n_components))
+
+    m = Estimator(
+        n_components=n_components, init="custom", random_state=0, tol=1e-3, **solver
+    )
+    m.fit_transform(A, W=W_init, H=H_init)
+    m.transform(A)
+
+
+@pytest.mark.parametrize("solver", ("cd", "mu"))
+def test_nmf_inverse_transform(solver):
+    # Test that NMF.inverse_transform returns close values
+    random_state = np.random.RandomState(0)
+    A = np.abs(random_state.randn(6, 4))
+    m = NMF(
+        solver=solver,
+        n_components=4,
+        init="random",
+        random_state=0,
+        max_iter=1000,
+    )
+    ft = m.fit_transform(A)
+    A_new = m.inverse_transform(ft)
+    assert_array_almost_equal(A, A_new, decimal=2)
+
+
+def test_mbnmf_inverse_transform():
+    # Test that MiniBatchNMF.transform followed by MiniBatchNMF.inverse_transform
+    # is close to the identity
+    rng = np.random.RandomState(0)
+    A = np.abs(rng.randn(6, 4))
+    nmf = MiniBatchNMF(
+        random_state=rng,
+        max_iter=500,
+        init="nndsvdar",
+        fresh_restarts=True,
+    )
+    ft = nmf.fit_transform(A)
+    A_new = nmf.inverse_transform(ft)
+    assert_allclose(A, A_new, rtol=1e-3, atol=1e-2)
+
+
+@pytest.mark.parametrize("Estimator", [NMF, MiniBatchNMF])
+def test_n_components_greater_n_features(Estimator):
+    # Smoke test for the case of more components than features.
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(30, 10))
+    Estimator(n_components=15, random_state=0, tol=1e-2).fit(A)
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+@pytest.mark.parametrize("alpha_W", (0.0, 1.0))
+@pytest.mark.parametrize("alpha_H", (0.0, 1.0, "same"))
+def test_nmf_sparse_input(Estimator, solver, alpha_W, alpha_H):
+    # Test that sparse matrices are accepted as input
+    from scipy.sparse import csc_matrix
+
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(10, 10))
+    A[:, 2 * np.arange(5)] = 0
+    A_sparse = csc_matrix(A)
+
+    est1 = Estimator(
+        n_components=5,
+        init="random",
+        alpha_W=alpha_W,
+        alpha_H=alpha_H,
+        random_state=0,
+        tol=0,
+        max_iter=100,
+        **solver,
+    )
+    est2 = clone(est1)
+
+    W1 = est1.fit_transform(A)
+    W2 = est2.fit_transform(A_sparse)
+    H1 = est1.components_
+    H2 = est2.components_
+
+    assert_allclose(W1, W2)
+    assert_allclose(H1, H2)
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_sparse_transform(Estimator, solver):
+    # Test that transform works on sparse data.  Issue #2124
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(3, 2))
+    A[1, 1] = 0
+    A = csc_matrix(A)
+
+    model = Estimator(random_state=0, n_components=2, max_iter=400, **solver)
+    A_fit_tr = model.fit_transform(A)
+    A_tr = model.transform(A)
+    assert_allclose(A_fit_tr, A_tr, atol=1e-1)
+
+
+@pytest.mark.parametrize("init", ["random", "nndsvd"])
+@pytest.mark.parametrize("solver", ("cd", "mu"))
+@pytest.mark.parametrize("alpha_W", (0.0, 1.0))
+@pytest.mark.parametrize("alpha_H", (0.0, 1.0, "same"))
+def test_non_negative_factorization_consistency(init, solver, alpha_W, alpha_H):
+    # Test that the function is called in the same way, either directly
+    # or through the NMF class
+    max_iter = 500
+    rng = np.random.mtrand.RandomState(42)
+    A = np.abs(rng.randn(10, 10))
+    A[:, 2 * np.arange(5)] = 0
+
+    W_nmf, H, _ = non_negative_factorization(
+        A,
+        init=init,
+        solver=solver,
+        max_iter=max_iter,
+        alpha_W=alpha_W,
+        alpha_H=alpha_H,
+        random_state=1,
+        tol=1e-2,
+    )
+    W_nmf_2, H, _ = non_negative_factorization(
+        A,
+        H=H,
+        update_H=False,
+        init=init,
+        solver=solver,
+        max_iter=max_iter,
+        alpha_W=alpha_W,
+        alpha_H=alpha_H,
+        random_state=1,
+        tol=1e-2,
+    )
+
+    model_class = NMF(
+        init=init,
+        solver=solver,
+        max_iter=max_iter,
+        alpha_W=alpha_W,
+        alpha_H=alpha_H,
+        random_state=1,
+        tol=1e-2,
+    )
+    W_cls = model_class.fit_transform(A)
+    W_cls_2 = model_class.transform(A)
+
+    assert_allclose(W_nmf, W_cls)
+    assert_allclose(W_nmf_2, W_cls_2)
+
+
+def test_non_negative_factorization_checking():
+    A = np.ones((2, 2))
+    # Test parameters checking is public function
+    nnmf = non_negative_factorization
+    msg = re.escape(
+        "Number of components must be a positive integer; got (n_components=1.5)"
+    )
+    with pytest.raises(ValueError, match=msg):
+        nnmf(A, A, A, 1.5, init="random")
+    msg = re.escape(
+        "Number of components must be a positive integer; got (n_components='2')"
+    )
+    with pytest.raises(ValueError, match=msg):
+        nnmf(A, A, A, "2", init="random")
+    msg = re.escape("Negative values in data passed to NMF (input H)")
+    with pytest.raises(ValueError, match=msg):
+        nnmf(A, A, -A, 2, init="custom")
+    msg = re.escape("Negative values in data passed to NMF (input W)")
+    with pytest.raises(ValueError, match=msg):
+        nnmf(A, -A, A, 2, init="custom")
+    msg = re.escape("Array passed to NMF (input H) is full of zeros")
+    with pytest.raises(ValueError, match=msg):
+        nnmf(A, A, 0 * A, 2, init="custom")
+
+    with ignore_warnings(category=FutureWarning):
+        # TODO remove in 1.2
+        msg = "Invalid regularization parameter: got 'spam' instead of one of"
+        with pytest.raises(ValueError, match=msg):
+            nnmf(A, A, 0 * A, 2, init="custom", regularization="spam")
+
+
+def _beta_divergence_dense(X, W, H, beta):
+    """Compute the beta-divergence of X and W.H for dense array only.
+
+    Used as a reference for testing nmf._beta_divergence.
+    """
+    WH = np.dot(W, H)
+
+    if beta == 2:
+        return squared_norm(X - WH) / 2
+
+    WH_Xnonzero = WH[X != 0]
+    X_nonzero = X[X != 0]
+    np.maximum(WH_Xnonzero, 1e-9, out=WH_Xnonzero)
+
+    if beta == 1:
+        res = np.sum(X_nonzero * np.log(X_nonzero / WH_Xnonzero))
+        res += WH.sum() - X.sum()
+
+    elif beta == 0:
+        div = X_nonzero / WH_Xnonzero
+        res = np.sum(div) - X.size - np.sum(np.log(div))
+    else:
+        res = (X_nonzero**beta).sum()
+        res += (beta - 1) * (WH**beta).sum()
+        res -= beta * (X_nonzero * (WH_Xnonzero ** (beta - 1))).sum()
+        res /= beta * (beta - 1)
+
+    return res
+
+
+def test_beta_divergence():
+    # Compare _beta_divergence with the reference _beta_divergence_dense
+    n_samples = 20
+    n_features = 10
+    n_components = 5
+    beta_losses = [0.0, 0.5, 1.0, 1.5, 2.0, 3.0]
+
+    # initialization
+    rng = np.random.mtrand.RandomState(42)
+    X = rng.randn(n_samples, n_features)
+    np.clip(X, 0, None, out=X)
+    X_csr = sp.csr_matrix(X)
+    W, H = nmf._initialize_nmf(X, n_components, init="random", random_state=42)
+
+    for beta in beta_losses:
+        ref = _beta_divergence_dense(X, W, H, beta)
+        loss = nmf._beta_divergence(X, W, H, beta)
+        loss_csr = nmf._beta_divergence(X_csr, W, H, beta)
+
+        assert_almost_equal(ref, loss, decimal=7)
+        assert_almost_equal(ref, loss_csr, decimal=7)
+
+
+def test_special_sparse_dot():
+    # Test the function that computes np.dot(W, H), only where X is non zero.
+    n_samples = 10
+    n_features = 5
+    n_components = 3
+    rng = np.random.mtrand.RandomState(42)
+    X = rng.randn(n_samples, n_features)
+    np.clip(X, 0, None, out=X)
+    X_csr = sp.csr_matrix(X)
+
+    W = np.abs(rng.randn(n_samples, n_components))
+    H = np.abs(rng.randn(n_components, n_features))
+
+    WH_safe = nmf._special_sparse_dot(W, H, X_csr)
+    WH = nmf._special_sparse_dot(W, H, X)
+
+    # test that both results have same values, in X_csr nonzero elements
+    ii, jj = X_csr.nonzero()
+    WH_safe_data = np.asarray(WH_safe[ii, jj]).ravel()
+    assert_array_almost_equal(WH_safe_data, WH[ii, jj], decimal=10)
+
+    # test that WH_safe and X_csr have the same sparse structure
+    assert_array_equal(WH_safe.indices, X_csr.indices)
+    assert_array_equal(WH_safe.indptr, X_csr.indptr)
+    assert_array_equal(WH_safe.shape, X_csr.shape)
+
+
+@ignore_warnings(category=ConvergenceWarning)
+def test_nmf_multiplicative_update_sparse():
+    # Compare sparse and dense input in multiplicative update NMF
+    # Also test continuity of the results with respect to beta_loss parameter
+    n_samples = 20
+    n_features = 10
+    n_components = 5
+    alpha = 0.1
+    l1_ratio = 0.5
+    n_iter = 20
+
+    # initialization
+    rng = np.random.mtrand.RandomState(1337)
+    X = rng.randn(n_samples, n_features)
+    X = np.abs(X)
+    X_csr = sp.csr_matrix(X)
+    W0, H0 = nmf._initialize_nmf(X, n_components, init="random", random_state=42)
+
+    for beta_loss in (-1.2, 0, 0.2, 1.0, 2.0, 2.5):
+        # Reference with dense array X
+        W, H = W0.copy(), H0.copy()
+        W1, H1, _ = non_negative_factorization(
+            X,
+            W,
+            H,
+            n_components,
+            init="custom",
+            update_H=True,
+            solver="mu",
+            beta_loss=beta_loss,
+            max_iter=n_iter,
+            alpha_W=alpha,
+            l1_ratio=l1_ratio,
+            random_state=42,
+        )
+
+        # Compare with sparse X
+        W, H = W0.copy(), H0.copy()
+        W2, H2, _ = non_negative_factorization(
+            X_csr,
+            W,
+            H,
+            n_components,
+            init="custom",
+            update_H=True,
+            solver="mu",
+            beta_loss=beta_loss,
+            max_iter=n_iter,
+            alpha_W=alpha,
+            l1_ratio=l1_ratio,
+            random_state=42,
+        )
+
+        assert_allclose(W1, W2, atol=1e-7)
+        assert_allclose(H1, H2, atol=1e-7)
+
+        # Compare with almost same beta_loss, since some values have a specific
+        # behavior, but the results should be continuous w.r.t beta_loss
+        beta_loss -= 1.0e-5
+        W, H = W0.copy(), H0.copy()
+        W3, H3, _ = non_negative_factorization(
+            X_csr,
+            W,
+            H,
+            n_components,
+            init="custom",
+            update_H=True,
+            solver="mu",
+            beta_loss=beta_loss,
+            max_iter=n_iter,
+            alpha_W=alpha,
+            l1_ratio=l1_ratio,
+            random_state=42,
+        )
+
+        assert_allclose(W1, W3, atol=1e-4)
+        assert_allclose(H1, H3, atol=1e-4)
+
+
+def test_nmf_negative_beta_loss():
+    # Test that an error is raised if beta_loss < 0 and X contains zeros.
+    # Test that the output has not NaN values when the input contains zeros.
+    n_samples = 6
+    n_features = 5
+    n_components = 3
+
+    rng = np.random.mtrand.RandomState(42)
+    X = rng.randn(n_samples, n_features)
+    np.clip(X, 0, None, out=X)
+    X_csr = sp.csr_matrix(X)
+
+    def _assert_nmf_no_nan(X, beta_loss):
+        W, H, _ = non_negative_factorization(
+            X,
+            init="random",
+            n_components=n_components,
+            solver="mu",
+            beta_loss=beta_loss,
+            random_state=0,
+            max_iter=1000,
+        )
+        assert not np.any(np.isnan(W))
+        assert not np.any(np.isnan(H))
+
+    msg = "When beta_loss <= 0 and X contains zeros, the solver may diverge."
+    for beta_loss in (-0.6, 0.0):
+        with pytest.raises(ValueError, match=msg):
+            _assert_nmf_no_nan(X, beta_loss)
+        _assert_nmf_no_nan(X + 1e-9, beta_loss)
+
+    for beta_loss in (0.2, 1.0, 1.2, 2.0, 2.5):
+        _assert_nmf_no_nan(X, beta_loss)
+        _assert_nmf_no_nan(X_csr, beta_loss)
+
+
+@pytest.mark.parametrize("beta_loss", [-0.5, 0.0])
+def test_minibatch_nmf_negative_beta_loss(beta_loss):
+    """Check that an error is raised if beta_loss < 0 and X contains zeros."""
+    rng = np.random.RandomState(0)
+    X = rng.normal(size=(6, 5))
+    X[X < 0] = 0
+
+    nmf = MiniBatchNMF(beta_loss=beta_loss, random_state=0)
+
+    msg = "When beta_loss <= 0 and X contains zeros, the solver may diverge."
+    with pytest.raises(ValueError, match=msg):
+        nmf.fit(X)
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_regularization(Estimator, solver):
+    # Test the effect of L1 and L2 regularizations
+    n_samples = 6
+    n_features = 5
+    n_components = 3
+    rng = np.random.mtrand.RandomState(42)
+    X = np.abs(rng.randn(n_samples, n_features))
+
+    # L1 regularization should increase the number of zeros
+    l1_ratio = 1.0
+    regul = Estimator(
+        n_components=n_components,
+        alpha_W=0.5,
+        l1_ratio=l1_ratio,
+        random_state=42,
+        **solver,
+    )
+    model = Estimator(
+        n_components=n_components,
+        alpha_W=0.0,
+        l1_ratio=l1_ratio,
+        random_state=42,
+        **solver,
+    )
+
+    W_regul = regul.fit_transform(X)
+    W_model = model.fit_transform(X)
+
+    H_regul = regul.components_
+    H_model = model.components_
+
+    eps = np.finfo(np.float64).eps
+    W_regul_n_zeros = W_regul[W_regul <= eps].size
+    W_model_n_zeros = W_model[W_model <= eps].size
+    H_regul_n_zeros = H_regul[H_regul <= eps].size
+    H_model_n_zeros = H_model[H_model <= eps].size
+
+    assert W_regul_n_zeros > W_model_n_zeros
+    assert H_regul_n_zeros > H_model_n_zeros
+
+    # L2 regularization should decrease the sum of the squared norm
+    # of the matrices W and H
+    l1_ratio = 0.0
+    regul = Estimator(
+        n_components=n_components,
+        alpha_W=0.5,
+        l1_ratio=l1_ratio,
+        random_state=42,
+        **solver,
+    )
+    model = Estimator(
+        n_components=n_components,
+        alpha_W=0.0,
+        l1_ratio=l1_ratio,
+        random_state=42,
+        **solver,
+    )
+
+    W_regul = regul.fit_transform(X)
+    W_model = model.fit_transform(X)
+
+    H_regul = regul.components_
+    H_model = model.components_
+
+    assert (linalg.norm(W_model)) ** 2.0 + (linalg.norm(H_model)) ** 2.0 > (
+        linalg.norm(W_regul)
+    ) ** 2.0 + (linalg.norm(H_regul)) ** 2.0
+
+
+@ignore_warnings(category=ConvergenceWarning)
+@pytest.mark.parametrize("solver", ("cd", "mu"))
+def test_nmf_decreasing(solver):
+    # test that the objective function is decreasing at each iteration
+    n_samples = 20
+    n_features = 15
+    n_components = 10
+    alpha = 0.1
+    l1_ratio = 0.5
+    tol = 0.0
+
+    # initialization
+    rng = np.random.mtrand.RandomState(42)
+    X = rng.randn(n_samples, n_features)
+    np.abs(X, X)
+    W0, H0 = nmf._initialize_nmf(X, n_components, init="random", random_state=42)
+
+    for beta_loss in (-1.2, 0, 0.2, 1.0, 2.0, 2.5):
+        if solver != "mu" and beta_loss != 2:
+            # not implemented
+            continue
+        W, H = W0.copy(), H0.copy()
+        previous_loss = None
+        for _ in range(30):
+            # one more iteration starting from the previous results
+            W, H, _ = non_negative_factorization(
+                X,
+                W,
+                H,
+                beta_loss=beta_loss,
+                init="custom",
+                n_components=n_components,
+                max_iter=1,
+                alpha_W=alpha,
+                solver=solver,
+                tol=tol,
+                l1_ratio=l1_ratio,
+                verbose=0,
+                random_state=0,
+                update_H=True,
+            )
+
+            loss = (
+                nmf._beta_divergence(X, W, H, beta_loss)
+                + alpha * l1_ratio * n_features * W.sum()
+                + alpha * l1_ratio * n_samples * H.sum()
+                + alpha * (1 - l1_ratio) * n_features * (W**2).sum()
+                + alpha * (1 - l1_ratio) * n_samples * (H**2).sum()
+            )
+            if previous_loss is not None:
+                assert previous_loss > loss
+            previous_loss = loss
+
+
+def test_nmf_underflow():
+    # Regression test for an underflow issue in _beta_divergence
+    rng = np.random.RandomState(0)
+    n_samples, n_features, n_components = 10, 2, 2
+    X = np.abs(rng.randn(n_samples, n_features)) * 10
+    W = np.abs(rng.randn(n_samples, n_components)) * 10
+    H = np.abs(rng.randn(n_components, n_features))
+
+    X[0, 0] = 0
+    ref = nmf._beta_divergence(X, W, H, beta=1.0)
+    X[0, 0] = 1e-323
+    res = nmf._beta_divergence(X, W, H, beta=1.0)
+    assert_almost_equal(res, ref)
+
+
+@pytest.mark.parametrize(
+    "dtype_in, dtype_out",
+    [
+        (np.float32, np.float32),
+        (np.float64, np.float64),
+        (np.int32, np.float64),
+        (np.int64, np.float64),
+    ],
+)
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_dtype_match(Estimator, solver, dtype_in, dtype_out):
+    # Check that NMF preserves dtype (float32 and float64)
+    X = np.random.RandomState(0).randn(20, 15).astype(dtype_in, copy=False)
+    np.abs(X, out=X)
+
+    nmf = Estimator(alpha_W=1.0, alpha_H=1.0, tol=1e-2, random_state=0, **solver)
+
+    assert nmf.fit(X).transform(X).dtype == dtype_out
+    assert nmf.fit_transform(X).dtype == dtype_out
+    assert nmf.components_.dtype == dtype_out
+
+
+@pytest.mark.parametrize(
+    ["Estimator", "solver"],
+    [[NMF, {"solver": "cd"}], [NMF, {"solver": "mu"}], [MiniBatchNMF, {}]],
+)
+def test_nmf_float32_float64_consistency(Estimator, solver):
+    # Check that the result of NMF is the same between float32 and float64
+    X = np.random.RandomState(0).randn(50, 7)
+    np.abs(X, out=X)
+    nmf32 = Estimator(random_state=0, tol=1e-3, **solver)
+    W32 = nmf32.fit_transform(X.astype(np.float32))
+    nmf64 = Estimator(random_state=0, tol=1e-3, **solver)
+    W64 = nmf64.fit_transform(X)
+
+    assert_allclose(W32, W64, atol=1e-5)
+
+
+@pytest.mark.parametrize("Estimator", [NMF, MiniBatchNMF])
+def test_nmf_custom_init_dtype_error(Estimator):
+    # Check that an error is raise if custom H and/or W don't have the same
+    # dtype as X.
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((20, 15))
+    H = rng.random_sample((15, 15)).astype(np.float32)
+    W = rng.random_sample((20, 15))
+
+    with pytest.raises(TypeError, match="should have the same dtype as X"):
+        Estimator(init="custom").fit(X, H=H, W=W)
+
+    with pytest.raises(TypeError, match="should have the same dtype as X"):
+        non_negative_factorization(X, H=H, update_H=False)
+
+
+@pytest.mark.parametrize("beta_loss", [-0.5, 0, 0.5, 1, 1.5, 2, 2.5])
+def test_nmf_minibatchnmf_equivalence(beta_loss):
+    # Test that MiniBatchNMF is equivalent to NMF when batch_size = n_samples and
+    # forget_factor 0.0 (stopping criterion put aside)
+    rng = np.random.mtrand.RandomState(42)
+    X = np.abs(rng.randn(48, 5))
+
+    nmf = NMF(
+        n_components=5,
+        beta_loss=beta_loss,
+        solver="mu",
+        random_state=0,
+        tol=0,
+    )
+    mbnmf = MiniBatchNMF(
+        n_components=5,
+        beta_loss=beta_loss,
+        random_state=0,
+        tol=0,
+        max_no_improvement=None,
+        batch_size=X.shape[0],
+        forget_factor=0.0,
+    )
+    W = nmf.fit_transform(X)
+    mbW = mbnmf.fit_transform(X)
+    assert_allclose(W, mbW)
+
+
+def test_minibatch_nmf_partial_fit():
+    # Check fit / partial_fit equivalence. Applicable only with fresh restarts.
+    rng = np.random.mtrand.RandomState(42)
+    X = np.abs(rng.randn(100, 5))
+
+    n_components = 5
+    batch_size = 10
+    max_iter = 2
+
+    mbnmf1 = MiniBatchNMF(
+        n_components=n_components,
+        init="custom",
+        random_state=0,
+        max_iter=max_iter,
+        batch_size=batch_size,
+        tol=0,
+        max_no_improvement=None,
+        fresh_restarts=False,
+    )
+    mbnmf2 = MiniBatchNMF(n_components=n_components, init="custom", random_state=0)
+
+    # Force the same init of H (W is recomputed anyway) to be able to compare results.
+    W, H = nmf._initialize_nmf(
+        X, n_components=n_components, init="random", random_state=0
+    )
+
+    mbnmf1.fit(X, W=W, H=H)
+    for i in range(max_iter):
+        for j in range(batch_size):
+            mbnmf2.partial_fit(X[j : j + batch_size], W=W[:batch_size], H=H)
+
+    assert mbnmf1.n_steps_ == mbnmf2.n_steps_
+    assert_allclose(mbnmf1.components_, mbnmf2.components_)
+
+
+def test_feature_names_out():
+    """Check feature names out for NMF."""
+    random_state = np.random.RandomState(0)
+    X = np.abs(random_state.randn(10, 4))
+    nmf = NMF(n_components=3).fit(X)
+
+    names = nmf.get_feature_names_out()
+    assert_array_equal([f"nmf{i}" for i in range(3)], names)
+
+
+def test_minibatch_nmf_verbose():
+    # Check verbose mode of MiniBatchNMF for better coverage.
+    A = np.random.RandomState(0).random_sample((100, 10))
+    nmf = MiniBatchNMF(tol=1e-2, random_state=0, verbose=1)
+    old_stdout = sys.stdout
+    sys.stdout = StringIO()
+    try:
+        nmf.fit(A)
+    finally:
+        sys.stdout = old_stdout

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_online_lda.py

@@ -0,0 +1,441 @@
+import sys
+
+import numpy as np
+from scipy.linalg import block_diag
+from scipy.sparse import csr_matrix
+from scipy.special import psi
+from numpy.testing import assert_array_equal
+
+import pytest
+
+from sklearn.decomposition import LatentDirichletAllocation
+from sklearn.decomposition._lda import (
+    _dirichlet_expectation_1d,
+    _dirichlet_expectation_2d,
+)
+
+from sklearn.utils._testing import assert_allclose
+from sklearn.utils._testing import assert_array_almost_equal
+from sklearn.utils._testing import assert_almost_equal
+from sklearn.utils._testing import if_safe_multiprocessing_with_blas
+
+from sklearn.exceptions import NotFittedError
+from io import StringIO
+
+
+def _build_sparse_mtx():
+    # Create 3 topics and each topic has 3 distinct words.
+    # (Each word only belongs to a single topic.)
+    n_components = 3
+    block = np.full((3, 3), n_components, dtype=int)
+    blocks = [block] * n_components
+    X = block_diag(*blocks)
+    X = csr_matrix(X)
+    return (n_components, X)
+
+
+def test_lda_default_prior_params():
+    # default prior parameter should be `1 / topics`
+    # and verbose params should not affect result
+    n_components, X = _build_sparse_mtx()
+    prior = 1.0 / n_components
+    lda_1 = LatentDirichletAllocation(
+        n_components=n_components,
+        doc_topic_prior=prior,
+        topic_word_prior=prior,
+        random_state=0,
+    )
+    lda_2 = LatentDirichletAllocation(n_components=n_components, random_state=0)
+    topic_distr_1 = lda_1.fit_transform(X)
+    topic_distr_2 = lda_2.fit_transform(X)
+    assert_almost_equal(topic_distr_1, topic_distr_2)
+
+
+def test_lda_fit_batch():
+    # Test LDA batch learning_offset (`fit` method with 'batch' learning)
+    rng = np.random.RandomState(0)
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        evaluate_every=1,
+        learning_method="batch",
+        random_state=rng,
+    )
+    lda.fit(X)
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for component in lda.components_:
+        # Find top 3 words in each LDA component
+        top_idx = set(component.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+def test_lda_fit_online():
+    # Test LDA online learning (`fit` method with 'online' learning)
+    rng = np.random.RandomState(0)
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        learning_offset=10.0,
+        evaluate_every=1,
+        learning_method="online",
+        random_state=rng,
+    )
+    lda.fit(X)
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for component in lda.components_:
+        # Find top 3 words in each LDA component
+        top_idx = set(component.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+def test_lda_partial_fit():
+    # Test LDA online learning (`partial_fit` method)
+    # (same as test_lda_batch)
+    rng = np.random.RandomState(0)
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        learning_offset=10.0,
+        total_samples=100,
+        random_state=rng,
+    )
+    for i in range(3):
+        lda.partial_fit(X)
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for c in lda.components_:
+        top_idx = set(c.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+def test_lda_dense_input():
+    # Test LDA with dense input.
+    rng = np.random.RandomState(0)
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components, learning_method="batch", random_state=rng
+    )
+    lda.fit(X.toarray())
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for component in lda.components_:
+        # Find top 3 words in each LDA component
+        top_idx = set(component.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+def test_lda_transform():
+    # Test LDA transform.
+    # Transform result cannot be negative and should be normalized
+    rng = np.random.RandomState(0)
+    X = rng.randint(5, size=(20, 10))
+    n_components = 3
+    lda = LatentDirichletAllocation(n_components=n_components, random_state=rng)
+    X_trans = lda.fit_transform(X)
+    assert (X_trans > 0.0).any()
+    assert_array_almost_equal(np.sum(X_trans, axis=1), np.ones(X_trans.shape[0]))
+
+
+@pytest.mark.parametrize("method", ("online", "batch"))
+def test_lda_fit_transform(method):
+    # Test LDA fit_transform & transform
+    # fit_transform and transform result should be the same
+    rng = np.random.RandomState(0)
+    X = rng.randint(10, size=(50, 20))
+    lda = LatentDirichletAllocation(
+        n_components=5, learning_method=method, random_state=rng
+    )
+    X_fit = lda.fit_transform(X)
+    X_trans = lda.transform(X)
+    assert_array_almost_equal(X_fit, X_trans, 4)
+
+
+def test_invalid_params():
+    # test `_check_params` method
+    X = np.ones((5, 10))
+
+    invalid_models = (
+        ("n_components", LatentDirichletAllocation(n_components=0)),
+        ("learning_method", LatentDirichletAllocation(learning_method="unknown")),
+        ("total_samples", LatentDirichletAllocation(total_samples=0)),
+        ("learning_offset", LatentDirichletAllocation(learning_offset=-1)),
+    )
+    for param, model in invalid_models:
+        regex = r"^Invalid %r parameter" % param
+        with pytest.raises(ValueError, match=regex):
+            model.fit(X)
+
+
+def test_lda_negative_input():
+    # test pass dense matrix with sparse negative input.
+    X = np.full((5, 10), -1.0)
+    lda = LatentDirichletAllocation()
+    regex = r"^Negative values in data passed"
+    with pytest.raises(ValueError, match=regex):
+        lda.fit(X)
+
+
+def test_lda_no_component_error():
+    # test `perplexity` before `fit`
+    rng = np.random.RandomState(0)
+    X = rng.randint(4, size=(20, 10))
+    lda = LatentDirichletAllocation()
+    regex = (
+        "This LatentDirichletAllocation instance is not fitted yet. "
+        "Call 'fit' with appropriate arguments before using this "
+        "estimator."
+    )
+    with pytest.raises(NotFittedError, match=regex):
+        lda.perplexity(X)
+
+
+@if_safe_multiprocessing_with_blas
+@pytest.mark.parametrize("method", ("online", "batch"))
+def test_lda_multi_jobs(method):
+    n_components, X = _build_sparse_mtx()
+    # Test LDA batch training with multi CPU
+    rng = np.random.RandomState(0)
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        n_jobs=2,
+        learning_method=method,
+        evaluate_every=1,
+        random_state=rng,
+    )
+    lda.fit(X)
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for c in lda.components_:
+        top_idx = set(c.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+@if_safe_multiprocessing_with_blas
+def test_lda_partial_fit_multi_jobs():
+    # Test LDA online training with multi CPU
+    rng = np.random.RandomState(0)
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        n_jobs=2,
+        learning_offset=5.0,
+        total_samples=30,
+        random_state=rng,
+    )
+    for i in range(2):
+        lda.partial_fit(X)
+
+    correct_idx_grps = [(0, 1, 2), (3, 4, 5), (6, 7, 8)]
+    for c in lda.components_:
+        top_idx = set(c.argsort()[-3:][::-1])
+        assert tuple(sorted(top_idx)) in correct_idx_grps
+
+
+def test_lda_preplexity_mismatch():
+    # test dimension mismatch in `perplexity` method
+    rng = np.random.RandomState(0)
+    n_components = rng.randint(3, 6)
+    n_samples = rng.randint(6, 10)
+    X = np.random.randint(4, size=(n_samples, 10))
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        learning_offset=5.0,
+        total_samples=20,
+        random_state=rng,
+    )
+    lda.fit(X)
+    # invalid samples
+    invalid_n_samples = rng.randint(4, size=(n_samples + 1, n_components))
+    with pytest.raises(ValueError, match=r"Number of samples"):
+        lda._perplexity_precomp_distr(X, invalid_n_samples)
+    # invalid topic number
+    invalid_n_components = rng.randint(4, size=(n_samples, n_components + 1))
+    with pytest.raises(ValueError, match=r"Number of topics"):
+        lda._perplexity_precomp_distr(X, invalid_n_components)
+
+
+@pytest.mark.parametrize("method", ("online", "batch"))
+def test_lda_perplexity(method):
+    # Test LDA perplexity for batch training
+    # perplexity should be lower after each iteration
+    n_components, X = _build_sparse_mtx()
+    lda_1 = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=1,
+        learning_method=method,
+        total_samples=100,
+        random_state=0,
+    )
+    lda_2 = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=10,
+        learning_method=method,
+        total_samples=100,
+        random_state=0,
+    )
+    lda_1.fit(X)
+    perp_1 = lda_1.perplexity(X, sub_sampling=False)
+
+    lda_2.fit(X)
+    perp_2 = lda_2.perplexity(X, sub_sampling=False)
+    assert perp_1 >= perp_2
+
+    perp_1_subsampling = lda_1.perplexity(X, sub_sampling=True)
+    perp_2_subsampling = lda_2.perplexity(X, sub_sampling=True)
+    assert perp_1_subsampling >= perp_2_subsampling
+
+
+@pytest.mark.parametrize("method", ("online", "batch"))
+def test_lda_score(method):
+    # Test LDA score for batch training
+    # score should be higher after each iteration
+    n_components, X = _build_sparse_mtx()
+    lda_1 = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=1,
+        learning_method=method,
+        total_samples=100,
+        random_state=0,
+    )
+    lda_2 = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=10,
+        learning_method=method,
+        total_samples=100,
+        random_state=0,
+    )
+    lda_1.fit_transform(X)
+    score_1 = lda_1.score(X)
+
+    lda_2.fit_transform(X)
+    score_2 = lda_2.score(X)
+    assert score_2 >= score_1
+
+
+def test_perplexity_input_format():
+    # Test LDA perplexity for sparse and dense input
+    # score should be the same for both dense and sparse input
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=1,
+        learning_method="batch",
+        total_samples=100,
+        random_state=0,
+    )
+    lda.fit(X)
+    perp_1 = lda.perplexity(X)
+    perp_2 = lda.perplexity(X.toarray())
+    assert_almost_equal(perp_1, perp_2)
+
+
+def test_lda_score_perplexity():
+    # Test the relationship between LDA score and perplexity
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components, max_iter=10, random_state=0
+    )
+    lda.fit(X)
+    perplexity_1 = lda.perplexity(X, sub_sampling=False)
+
+    score = lda.score(X)
+    perplexity_2 = np.exp(-1.0 * (score / np.sum(X.data)))
+    assert_almost_equal(perplexity_1, perplexity_2)
+
+
+def test_lda_fit_perplexity():
+    # Test that the perplexity computed during fit is consistent with what is
+    # returned by the perplexity method
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=1,
+        learning_method="batch",
+        random_state=0,
+        evaluate_every=1,
+    )
+    lda.fit(X)
+
+    # Perplexity computed at end of fit method
+    perplexity1 = lda.bound_
+
+    # Result of perplexity method on the train set
+    perplexity2 = lda.perplexity(X)
+
+    assert_almost_equal(perplexity1, perplexity2)
+
+
+def test_lda_empty_docs():
+    """Test LDA on empty document (all-zero rows)."""
+    Z = np.zeros((5, 4))
+    for X in [Z, csr_matrix(Z)]:
+        lda = LatentDirichletAllocation(max_iter=750).fit(X)
+        assert_almost_equal(
+            lda.components_.sum(axis=0), np.ones(lda.components_.shape[1])
+        )
+
+
+def test_dirichlet_expectation():
+    """Test Cython version of Dirichlet expectation calculation."""
+    x = np.logspace(-100, 10, 10000)
+    expectation = np.empty_like(x)
+    _dirichlet_expectation_1d(x, 0, expectation)
+    assert_allclose(expectation, np.exp(psi(x) - psi(np.sum(x))), atol=1e-19)
+
+    x = x.reshape(100, 100)
+    assert_allclose(
+        _dirichlet_expectation_2d(x),
+        psi(x) - psi(np.sum(x, axis=1)[:, np.newaxis]),
+        rtol=1e-11,
+        atol=3e-9,
+    )
+
+
+def check_verbosity(verbose, evaluate_every, expected_lines, expected_perplexities):
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(
+        n_components=n_components,
+        max_iter=3,
+        learning_method="batch",
+        verbose=verbose,
+        evaluate_every=evaluate_every,
+        random_state=0,
+    )
+    out = StringIO()
+    old_out, sys.stdout = sys.stdout, out
+    try:
+        lda.fit(X)
+    finally:
+        sys.stdout = old_out
+
+    n_lines = out.getvalue().count("\n")
+    n_perplexity = out.getvalue().count("perplexity")
+    assert expected_lines == n_lines
+    assert expected_perplexities == n_perplexity
+
+
+@pytest.mark.parametrize(
+    "verbose,evaluate_every,expected_lines,expected_perplexities",
+    [
+        (False, 1, 0, 0),
+        (False, 0, 0, 0),
+        (True, 0, 3, 0),
+        (True, 1, 3, 3),
+        (True, 2, 3, 1),
+    ],
+)
+def test_verbosity(verbose, evaluate_every, expected_lines, expected_perplexities):
+    check_verbosity(verbose, evaluate_every, expected_lines, expected_perplexities)
+
+
+def test_lda_feature_names_out():
+    """Check feature names out for LatentDirichletAllocation."""
+    n_components, X = _build_sparse_mtx()
+    lda = LatentDirichletAllocation(n_components=n_components).fit(X)
+
+    names = lda.get_feature_names_out()
+    assert_array_equal(
+        [f"latentdirichletallocation{i}" for i in range(n_components)], names
+    )

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_pca.py

@@ -0,0 +1,734 @@
+import numpy as np
+import scipy as sp
+from numpy.testing import assert_array_equal
+
+import pytest
+import warnings
+
+from sklearn.utils._testing import assert_allclose
+
+from sklearn import datasets
+from sklearn.decomposition import PCA
+from sklearn.datasets import load_iris
+from sklearn.decomposition._pca import _assess_dimension
+from sklearn.decomposition._pca import _infer_dimension
+
+iris = datasets.load_iris()
+PCA_SOLVERS = ["full", "arpack", "randomized", "auto"]
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+@pytest.mark.parametrize("n_components", range(1, iris.data.shape[1]))
+def test_pca(svd_solver, n_components):
+    X = iris.data
+    pca = PCA(n_components=n_components, svd_solver=svd_solver)
+
+    # check the shape of fit.transform
+    X_r = pca.fit(X).transform(X)
+    assert X_r.shape[1] == n_components
+
+    # check the equivalence of fit.transform and fit_transform
+    X_r2 = pca.fit_transform(X)
+    assert_allclose(X_r, X_r2)
+    X_r = pca.transform(X)
+    assert_allclose(X_r, X_r2)
+
+    # Test get_covariance and get_precision
+    cov = pca.get_covariance()
+    precision = pca.get_precision()
+    assert_allclose(np.dot(cov, precision), np.eye(X.shape[1]), atol=1e-12)
+
+
+def test_no_empty_slice_warning():
+    # test if we avoid numpy warnings for computing over empty arrays
+    n_components = 10
+    n_features = n_components + 2  # anything > n_comps triggered it in 0.16
+    X = np.random.uniform(-1, 1, size=(n_components, n_features))
+    pca = PCA(n_components=n_components)
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", RuntimeWarning)
+        pca.fit(X)
+
+
+@pytest.mark.parametrize("copy", [True, False])
+@pytest.mark.parametrize("solver", PCA_SOLVERS)
+def test_whitening(solver, copy):
+    # Check that PCA output has unit-variance
+    rng = np.random.RandomState(0)
+    n_samples = 100
+    n_features = 80
+    n_components = 30
+    rank = 50
+
+    # some low rank data with correlated features
+    X = np.dot(
+        rng.randn(n_samples, rank),
+        np.dot(np.diag(np.linspace(10.0, 1.0, rank)), rng.randn(rank, n_features)),
+    )
+    # the component-wise variance of the first 50 features is 3 times the
+    # mean component-wise variance of the remaining 30 features
+    X[:, :50] *= 3
+
+    assert X.shape == (n_samples, n_features)
+
+    # the component-wise variance is thus highly varying:
+    assert X.std(axis=0).std() > 43.8
+
+    # whiten the data while projecting to the lower dim subspace
+    X_ = X.copy()  # make sure we keep an original across iterations.
+    pca = PCA(
+        n_components=n_components,
+        whiten=True,
+        copy=copy,
+        svd_solver=solver,
+        random_state=0,
+        iterated_power=7,
+    )
+    # test fit_transform
+    X_whitened = pca.fit_transform(X_.copy())
+    assert X_whitened.shape == (n_samples, n_components)
+    X_whitened2 = pca.transform(X_)
+    assert_allclose(X_whitened, X_whitened2, rtol=5e-4)
+
+    assert_allclose(X_whitened.std(ddof=1, axis=0), np.ones(n_components))
+    assert_allclose(X_whitened.mean(axis=0), np.zeros(n_components), atol=1e-12)
+
+    X_ = X.copy()
+    pca = PCA(
+        n_components=n_components, whiten=False, copy=copy, svd_solver=solver
+    ).fit(X_.copy())
+    X_unwhitened = pca.transform(X_)
+    assert X_unwhitened.shape == (n_samples, n_components)
+
+    # in that case the output components still have varying variances
+    assert X_unwhitened.std(axis=0).std() == pytest.approx(74.1, rel=1e-1)
+    # we always center, so no test for non-centering.
+
+
+@pytest.mark.parametrize("svd_solver", ["arpack", "randomized"])
+def test_pca_explained_variance_equivalence_solver(svd_solver):
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 100, 80
+    X = rng.randn(n_samples, n_features)
+
+    pca_full = PCA(n_components=2, svd_solver="full")
+    pca_other = PCA(n_components=2, svd_solver=svd_solver, random_state=0)
+
+    pca_full.fit(X)
+    pca_other.fit(X)
+
+    assert_allclose(
+        pca_full.explained_variance_, pca_other.explained_variance_, rtol=5e-2
+    )
+    assert_allclose(
+        pca_full.explained_variance_ratio_,
+        pca_other.explained_variance_ratio_,
+        rtol=5e-2,
+    )
+
+
+@pytest.mark.parametrize(
+    "X",
+    [
+        np.random.RandomState(0).randn(100, 80),
+        datasets.make_classification(100, 80, n_informative=78, random_state=0)[0],
+    ],
+    ids=["random-data", "correlated-data"],
+)
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_explained_variance_empirical(X, svd_solver):
+    pca = PCA(n_components=2, svd_solver=svd_solver, random_state=0)
+    X_pca = pca.fit_transform(X)
+    assert_allclose(pca.explained_variance_, np.var(X_pca, ddof=1, axis=0))
+
+    expected_result = np.linalg.eig(np.cov(X, rowvar=False))[0]
+    expected_result = sorted(expected_result, reverse=True)[:2]
+    assert_allclose(pca.explained_variance_, expected_result, rtol=5e-3)
+
+
+@pytest.mark.parametrize("svd_solver", ["arpack", "randomized"])
+def test_pca_singular_values_consistency(svd_solver):
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 100, 80
+    X = rng.randn(n_samples, n_features)
+
+    pca_full = PCA(n_components=2, svd_solver="full", random_state=rng)
+    pca_other = PCA(n_components=2, svd_solver=svd_solver, random_state=rng)
+
+    pca_full.fit(X)
+    pca_other.fit(X)
+
+    assert_allclose(pca_full.singular_values_, pca_other.singular_values_, rtol=5e-3)
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_singular_values(svd_solver):
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 100, 80
+    X = rng.randn(n_samples, n_features)
+
+    pca = PCA(n_components=2, svd_solver=svd_solver, random_state=rng)
+    X_trans = pca.fit_transform(X)
+
+    # compare to the Frobenius norm
+    assert_allclose(
+        np.sum(pca.singular_values_**2), np.linalg.norm(X_trans, "fro") ** 2
+    )
+    # Compare to the 2-norms of the score vectors
+    assert_allclose(pca.singular_values_, np.sqrt(np.sum(X_trans**2, axis=0)))
+
+    # set the singular values and see what er get back
+    n_samples, n_features = 100, 110
+    X = rng.randn(n_samples, n_features)
+
+    pca = PCA(n_components=3, svd_solver=svd_solver, random_state=rng)
+    X_trans = pca.fit_transform(X)
+    X_trans /= np.sqrt(np.sum(X_trans**2, axis=0))
+    X_trans[:, 0] *= 3.142
+    X_trans[:, 1] *= 2.718
+    X_hat = np.dot(X_trans, pca.components_)
+    pca.fit(X_hat)
+    assert_allclose(pca.singular_values_, [3.142, 2.718, 1.0])
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_check_projection(svd_solver):
+    # Test that the projection of data is correct
+    rng = np.random.RandomState(0)
+    n, p = 100, 3
+    X = rng.randn(n, p) * 0.1
+    X[:10] += np.array([3, 4, 5])
+    Xt = 0.1 * rng.randn(1, p) + np.array([3, 4, 5])
+
+    Yt = PCA(n_components=2, svd_solver=svd_solver).fit(X).transform(Xt)
+    Yt /= np.sqrt((Yt**2).sum())
+
+    assert_allclose(np.abs(Yt[0][0]), 1.0, rtol=5e-3)
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_check_projection_list(svd_solver):
+    # Test that the projection of data is correct
+    X = [[1.0, 0.0], [0.0, 1.0]]
+    pca = PCA(n_components=1, svd_solver=svd_solver, random_state=0)
+    X_trans = pca.fit_transform(X)
+    assert X_trans.shape, (2, 1)
+    assert_allclose(X_trans.mean(), 0.00, atol=1e-12)
+    assert_allclose(X_trans.std(), 0.71, rtol=5e-3)
+
+
+@pytest.mark.parametrize("svd_solver", ["full", "arpack", "randomized"])
+@pytest.mark.parametrize("whiten", [False, True])
+def test_pca_inverse(svd_solver, whiten):
+    # Test that the projection of data can be inverted
+    rng = np.random.RandomState(0)
+    n, p = 50, 3
+    X = rng.randn(n, p)  # spherical data
+    X[:, 1] *= 0.00001  # make middle component relatively small
+    X += [5, 4, 3]  # make a large mean
+
+    # same check that we can find the original data from the transformed
+    # signal (since the data is almost of rank n_components)
+    pca = PCA(n_components=2, svd_solver=svd_solver, whiten=whiten).fit(X)
+    Y = pca.transform(X)
+    Y_inverse = pca.inverse_transform(Y)
+    assert_allclose(X, Y_inverse, rtol=5e-6)
+
+
+@pytest.mark.parametrize(
+    "data", [np.array([[0, 1, 0], [1, 0, 0]]), np.array([[0, 1, 0], [1, 0, 0]]).T]
+)
+@pytest.mark.parametrize(
+    "svd_solver, n_components, err_msg",
+    [
+        ("arpack", 0, r"must be between 1 and min\(n_samples, n_features\)"),
+        ("randomized", 0, r"must be between 1 and min\(n_samples, n_features\)"),
+        ("arpack", 2, r"must be strictly less than min"),
+        (
+            "auto",
+            -1,
+            (
+                r"n_components={}L? must be between {}L? and "
+                r"min\(n_samples, n_features\)={}L? with "
+                r"svd_solver=\'{}\'"
+            ),
+        ),
+        (
+            "auto",
+            3,
+            (
+                r"n_components={}L? must be between {}L? and "
+                r"min\(n_samples, n_features\)={}L? with "
+                r"svd_solver=\'{}\'"
+            ),
+        ),
+        ("auto", 1.0, "must be of type int"),
+    ],
+)
+def test_pca_validation(svd_solver, data, n_components, err_msg):
+    # Ensures that solver-specific extreme inputs for the n_components
+    # parameter raise errors
+    smallest_d = 2  # The smallest dimension
+    lower_limit = {"randomized": 1, "arpack": 1, "full": 0, "auto": 0}
+    pca_fitted = PCA(n_components, svd_solver=svd_solver)
+
+    solver_reported = "full" if svd_solver == "auto" else svd_solver
+    err_msg = err_msg.format(
+        n_components, lower_limit[svd_solver], smallest_d, solver_reported
+    )
+    with pytest.raises(ValueError, match=err_msg):
+        pca_fitted.fit(data)
+
+    # Additional case for arpack
+    if svd_solver == "arpack":
+        n_components = smallest_d
+
+        err_msg = (
+            "n_components={}L? must be strictly less than "
+            r"min\(n_samples, n_features\)={}L? with "
+            "svd_solver='arpack'".format(n_components, smallest_d)
+        )
+        with pytest.raises(ValueError, match=err_msg):
+            PCA(n_components, svd_solver=svd_solver).fit(data)
+
+
+@pytest.mark.parametrize(
+    "solver, n_components_",
+    [
+        ("full", min(iris.data.shape)),
+        ("arpack", min(iris.data.shape) - 1),
+        ("randomized", min(iris.data.shape)),
+    ],
+)
+@pytest.mark.parametrize("data", [iris.data, iris.data.T])
+def test_n_components_none(data, solver, n_components_):
+    pca = PCA(svd_solver=solver)
+    pca.fit(data)
+    assert pca.n_components_ == n_components_
+
+
+@pytest.mark.parametrize("svd_solver", ["auto", "full"])
+def test_n_components_mle(svd_solver):
+    # Ensure that n_components == 'mle' doesn't raise error for auto/full
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 600, 10
+    X = rng.randn(n_samples, n_features)
+    pca = PCA(n_components="mle", svd_solver=svd_solver)
+    pca.fit(X)
+    assert pca.n_components_ == 1
+
+
+@pytest.mark.parametrize("svd_solver", ["arpack", "randomized"])
+def test_n_components_mle_error(svd_solver):
+    # Ensure that n_components == 'mle' will raise an error for unsupported
+    # solvers
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 600, 10
+    X = rng.randn(n_samples, n_features)
+    pca = PCA(n_components="mle", svd_solver=svd_solver)
+    err_msg = "n_components='mle' cannot be a string with svd_solver='{}'".format(
+        svd_solver
+    )
+    with pytest.raises(ValueError, match=err_msg):
+        pca.fit(X)
+
+
+def test_pca_dim():
+    # Check automated dimensionality setting
+    rng = np.random.RandomState(0)
+    n, p = 100, 5
+    X = rng.randn(n, p) * 0.1
+    X[:10] += np.array([3, 4, 5, 1, 2])
+    pca = PCA(n_components="mle", svd_solver="full").fit(X)
+    assert pca.n_components == "mle"
+    assert pca.n_components_ == 1
+
+
+def test_infer_dim_1():
+    # TODO: explain what this is testing
+    # Or at least use explicit variable names...
+    n, p = 1000, 5
+    rng = np.random.RandomState(0)
+    X = (
+        rng.randn(n, p) * 0.1
+        + rng.randn(n, 1) * np.array([3, 4, 5, 1, 2])
+        + np.array([1, 0, 7, 4, 6])
+    )
+    pca = PCA(n_components=p, svd_solver="full")
+    pca.fit(X)
+    spect = pca.explained_variance_
+    ll = np.array([_assess_dimension(spect, k, n) for k in range(1, p)])
+    assert ll[1] > ll.max() - 0.01 * n
+
+
+def test_infer_dim_2():
+    # TODO: explain what this is testing
+    # Or at least use explicit variable names...
+    n, p = 1000, 5
+    rng = np.random.RandomState(0)
+    X = rng.randn(n, p) * 0.1
+    X[:10] += np.array([3, 4, 5, 1, 2])
+    X[10:20] += np.array([6, 0, 7, 2, -1])
+    pca = PCA(n_components=p, svd_solver="full")
+    pca.fit(X)
+    spect = pca.explained_variance_
+    assert _infer_dimension(spect, n) > 1
+
+
+def test_infer_dim_3():
+    n, p = 100, 5
+    rng = np.random.RandomState(0)
+    X = rng.randn(n, p) * 0.1
+    X[:10] += np.array([3, 4, 5, 1, 2])
+    X[10:20] += np.array([6, 0, 7, 2, -1])
+    X[30:40] += 2 * np.array([-1, 1, -1, 1, -1])
+    pca = PCA(n_components=p, svd_solver="full")
+    pca.fit(X)
+    spect = pca.explained_variance_
+    assert _infer_dimension(spect, n) > 2
+
+
+@pytest.mark.parametrize(
+    "X, n_components, n_components_validated",
+    [
+        (iris.data, 0.95, 2),  # row > col
+        (iris.data, 0.01, 1),  # row > col
+        (np.random.RandomState(0).rand(5, 20), 0.5, 2),
+    ],  # row < col
+)
+def test_infer_dim_by_explained_variance(X, n_components, n_components_validated):
+    pca = PCA(n_components=n_components, svd_solver="full")
+    pca.fit(X)
+    assert pca.n_components == pytest.approx(n_components)
+    assert pca.n_components_ == n_components_validated
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_score(svd_solver):
+    # Test that probabilistic PCA scoring yields a reasonable score
+    n, p = 1000, 3
+    rng = np.random.RandomState(0)
+    X = rng.randn(n, p) * 0.1 + np.array([3, 4, 5])
+    pca = PCA(n_components=2, svd_solver=svd_solver)
+    pca.fit(X)
+
+    ll1 = pca.score(X)
+    h = -0.5 * np.log(2 * np.pi * np.exp(1) * 0.1**2) * p
+    assert_allclose(ll1 / h, 1, rtol=5e-2)
+
+    ll2 = pca.score(rng.randn(n, p) * 0.2 + np.array([3, 4, 5]))
+    assert ll1 > ll2
+
+    pca = PCA(n_components=2, whiten=True, svd_solver=svd_solver)
+    pca.fit(X)
+    ll2 = pca.score(X)
+    assert ll1 > ll2
+
+
+def test_pca_score3():
+    # Check that probabilistic PCA selects the right model
+    n, p = 200, 3
+    rng = np.random.RandomState(0)
+    Xl = rng.randn(n, p) + rng.randn(n, 1) * np.array([3, 4, 5]) + np.array([1, 0, 7])
+    Xt = rng.randn(n, p) + rng.randn(n, 1) * np.array([3, 4, 5]) + np.array([1, 0, 7])
+    ll = np.zeros(p)
+    for k in range(p):
+        pca = PCA(n_components=k, svd_solver="full")
+        pca.fit(Xl)
+        ll[k] = pca.score(Xt)
+
+    assert ll.argmax() == 1
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_sanity_noise_variance(svd_solver):
+    # Sanity check for the noise_variance_. For more details see
+    # https://github.com/scikit-learn/scikit-learn/issues/7568
+    # https://github.com/scikit-learn/scikit-learn/issues/8541
+    # https://github.com/scikit-learn/scikit-learn/issues/8544
+    X, _ = datasets.load_digits(return_X_y=True)
+    pca = PCA(n_components=30, svd_solver=svd_solver, random_state=0)
+    pca.fit(X)
+    assert np.all((pca.explained_variance_ - pca.noise_variance_) >= 0)
+
+
+@pytest.mark.parametrize("svd_solver", ["arpack", "randomized"])
+def test_pca_score_consistency_solvers(svd_solver):
+    # Check the consistency of score between solvers
+    X, _ = datasets.load_digits(return_X_y=True)
+    pca_full = PCA(n_components=30, svd_solver="full", random_state=0)
+    pca_other = PCA(n_components=30, svd_solver=svd_solver, random_state=0)
+    pca_full.fit(X)
+    pca_other.fit(X)
+    assert_allclose(pca_full.score(X), pca_other.score(X), rtol=5e-6)
+
+
+# arpack raises ValueError for n_components == min(n_samples,  n_features)
+@pytest.mark.parametrize("svd_solver", ["full", "randomized"])
+def test_pca_zero_noise_variance_edge_cases(svd_solver):
+    # ensure that noise_variance_ is 0 in edge cases
+    # when n_components == min(n_samples, n_features)
+    n, p = 100, 3
+    rng = np.random.RandomState(0)
+    X = rng.randn(n, p) * 0.1 + np.array([3, 4, 5])
+
+    pca = PCA(n_components=p, svd_solver=svd_solver)
+    pca.fit(X)
+    assert pca.noise_variance_ == 0
+    # Non-regression test for gh-12489
+    # ensure no divide-by-zero error for n_components == n_features < n_samples
+    pca.score(X)
+
+    pca.fit(X.T)
+    assert pca.noise_variance_ == 0
+    # Non-regression test for gh-12489
+    # ensure no divide-by-zero error for n_components == n_samples < n_features
+    pca.score(X.T)
+
+
+@pytest.mark.parametrize(
+    "data, n_components, expected_solver",
+    [  # case: n_components in (0,1) => 'full'
+        (np.random.RandomState(0).uniform(size=(1000, 50)), 0.5, "full"),
+        # case: max(X.shape) <= 500 => 'full'
+        (np.random.RandomState(0).uniform(size=(10, 50)), 5, "full"),
+        # case: n_components >= .8 * min(X.shape) => 'full'
+        (np.random.RandomState(0).uniform(size=(1000, 50)), 50, "full"),
+        # n_components >= 1 and n_components < .8*min(X.shape) => 'randomized'
+        (np.random.RandomState(0).uniform(size=(1000, 50)), 10, "randomized"),
+    ],
+)
+def test_pca_svd_solver_auto(data, n_components, expected_solver):
+    pca_auto = PCA(n_components=n_components, random_state=0)
+    pca_test = PCA(
+        n_components=n_components, svd_solver=expected_solver, random_state=0
+    )
+    pca_auto.fit(data)
+    pca_test.fit(data)
+    assert_allclose(pca_auto.components_, pca_test.components_)
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_sparse_input(svd_solver):
+    X = np.random.RandomState(0).rand(5, 4)
+    X = sp.sparse.csr_matrix(X)
+    assert sp.sparse.issparse(X)
+
+    pca = PCA(n_components=3, svd_solver=svd_solver)
+    with pytest.raises(TypeError):
+        pca.fit(X)
+
+
+def test_pca_bad_solver():
+    X = np.random.RandomState(0).rand(5, 4)
+    pca = PCA(n_components=3, svd_solver="bad_argument")
+    with pytest.raises(ValueError):
+        pca.fit(X)
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_deterministic_output(svd_solver):
+    rng = np.random.RandomState(0)
+    X = rng.rand(10, 10)
+
+    transformed_X = np.zeros((20, 2))
+    for i in range(20):
+        pca = PCA(n_components=2, svd_solver=svd_solver, random_state=rng)
+        transformed_X[i, :] = pca.fit_transform(X)[0]
+    assert_allclose(transformed_X, np.tile(transformed_X[0, :], 20).reshape(20, 2))
+
+
+@pytest.mark.parametrize("svd_solver", PCA_SOLVERS)
+def test_pca_dtype_preservation(svd_solver):
+    check_pca_float_dtype_preservation(svd_solver)
+    check_pca_int_dtype_upcast_to_double(svd_solver)
+
+
+def check_pca_float_dtype_preservation(svd_solver):
+    # Ensure that PCA does not upscale the dtype when input is float32
+    X_64 = np.random.RandomState(0).rand(1000, 4).astype(np.float64, copy=False)
+    X_32 = X_64.astype(np.float32)
+
+    pca_64 = PCA(n_components=3, svd_solver=svd_solver, random_state=0).fit(X_64)
+    pca_32 = PCA(n_components=3, svd_solver=svd_solver, random_state=0).fit(X_32)
+
+    assert pca_64.components_.dtype == np.float64
+    assert pca_32.components_.dtype == np.float32
+    assert pca_64.transform(X_64).dtype == np.float64
+    assert pca_32.transform(X_32).dtype == np.float32
+
+    # the rtol is set such that the test passes on all platforms tested on
+    # conda-forge: PR#15775
+    # see: https://github.com/conda-forge/scikit-learn-feedstock/pull/113
+    assert_allclose(pca_64.components_, pca_32.components_, rtol=2e-4)
+
+
+def check_pca_int_dtype_upcast_to_double(svd_solver):
+    # Ensure that all int types will be upcast to float64
+    X_i64 = np.random.RandomState(0).randint(0, 1000, (1000, 4))
+    X_i64 = X_i64.astype(np.int64, copy=False)
+    X_i32 = X_i64.astype(np.int32, copy=False)
+
+    pca_64 = PCA(n_components=3, svd_solver=svd_solver, random_state=0).fit(X_i64)
+    pca_32 = PCA(n_components=3, svd_solver=svd_solver, random_state=0).fit(X_i32)
+
+    assert pca_64.components_.dtype == np.float64
+    assert pca_32.components_.dtype == np.float64
+    assert pca_64.transform(X_i64).dtype == np.float64
+    assert pca_32.transform(X_i32).dtype == np.float64
+
+    assert_allclose(pca_64.components_, pca_32.components_, rtol=1e-4)
+
+
+def test_pca_n_components_mostly_explained_variance_ratio():
+    # when n_components is the second highest cumulative sum of the
+    # explained_variance_ratio_, then n_components_ should equal the
+    # number of features in the dataset #15669
+    X, y = load_iris(return_X_y=True)
+    pca1 = PCA().fit(X, y)
+
+    n_components = pca1.explained_variance_ratio_.cumsum()[-2]
+    pca2 = PCA(n_components=n_components).fit(X, y)
+    assert pca2.n_components_ == X.shape[1]
+
+
+def test_assess_dimension_bad_rank():
+    # Test error when tested rank not in [1, n_features - 1]
+    spectrum = np.array([1, 1e-30, 1e-30, 1e-30])
+    n_samples = 10
+    for rank in (0, 5):
+        with pytest.raises(ValueError, match=r"should be in \[1, n_features - 1\]"):
+            _assess_dimension(spectrum, rank, n_samples)
+
+
+def test_small_eigenvalues_mle():
+    # Test rank associated with tiny eigenvalues are given a log-likelihood of
+    # -inf. The inferred rank will be 1
+    spectrum = np.array([1, 1e-30, 1e-30, 1e-30])
+
+    assert _assess_dimension(spectrum, rank=1, n_samples=10) > -np.inf
+
+    for rank in (2, 3):
+        assert _assess_dimension(spectrum, rank, 10) == -np.inf
+
+    assert _infer_dimension(spectrum, 10) == 1
+
+
+def test_mle_redundant_data():
+    # Test 'mle' with pathological X: only one relevant feature should give a
+    # rank of 1
+    X, _ = datasets.make_classification(
+        n_features=20,
+        n_informative=1,
+        n_repeated=18,
+        n_redundant=1,
+        n_clusters_per_class=1,
+        random_state=42,
+    )
+    pca = PCA(n_components="mle").fit(X)
+    assert pca.n_components_ == 1
+
+
+def test_fit_mle_too_few_samples():
+    # Tests that an error is raised when the number of samples is smaller
+    # than the number of features during an mle fit
+    X, _ = datasets.make_classification(n_samples=20, n_features=21, random_state=42)
+
+    pca = PCA(n_components="mle", svd_solver="full")
+    with pytest.raises(
+        ValueError,
+        match="n_components='mle' is only supported if n_samples >= n_features",
+    ):
+        pca.fit(X)
+
+
+def test_mle_simple_case():
+    # non-regression test for issue
+    # https://github.com/scikit-learn/scikit-learn/issues/16730
+    n_samples, n_dim = 1000, 10
+    X = np.random.RandomState(0).randn(n_samples, n_dim)
+    X[:, -1] = np.mean(X[:, :-1], axis=-1)  # true X dim is ndim - 1
+    pca_skl = PCA("mle", svd_solver="full")
+    pca_skl.fit(X)
+    assert pca_skl.n_components_ == n_dim - 1
+
+
+def test_assess_dimesion_rank_one():
+    # Make sure assess_dimension works properly on a matrix of rank 1
+    n_samples, n_features = 9, 6
+    X = np.ones((n_samples, n_features))  # rank 1 matrix
+    _, s, _ = np.linalg.svd(X, full_matrices=True)
+    # except for rank 1, all eigenvalues are 0 resp. close to 0 (FP)
+    assert_allclose(s[1:], np.zeros(n_features - 1), atol=1e-12)
+
+    assert np.isfinite(_assess_dimension(s, rank=1, n_samples=n_samples))
+    for rank in range(2, n_features):
+        assert _assess_dimension(s, rank, n_samples) == -np.inf
+
+
+def test_pca_randomized_svd_n_oversamples():
+    """Check that exposing and setting `n_oversamples` will provide accurate results
+    even when `X` as a large number of features.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/20589
+    """
+    rng = np.random.RandomState(0)
+    n_features = 100
+    X = rng.randn(1_000, n_features)
+
+    # The default value of `n_oversamples` will lead to inaccurate results
+    # We force it to the number of features.
+    pca_randomized = PCA(
+        n_components=1,
+        svd_solver="randomized",
+        n_oversamples=n_features,
+        random_state=0,
+    ).fit(X)
+    pca_full = PCA(n_components=1, svd_solver="full").fit(X)
+    pca_arpack = PCA(n_components=1, svd_solver="arpack", random_state=0).fit(X)
+
+    assert_allclose(np.abs(pca_full.components_), np.abs(pca_arpack.components_))
+    assert_allclose(np.abs(pca_randomized.components_), np.abs(pca_arpack.components_))
+
+
+@pytest.mark.parametrize(
+    "params, err_type, err_msg",
+    [
+        (
+            {"n_oversamples": 0},
+            ValueError,
+            "n_oversamples == 0, must be >= 1.",
+        ),
+        (
+            {"n_oversamples": 1.5},
+            TypeError,
+            "n_oversamples must be an instance of int",
+        ),
+    ],
+)
+def test_pca_params_validation(params, err_type, err_msg):
+    """Check the parameters validation in `PCA`."""
+    rng = np.random.RandomState(0)
+    X = rng.randn(100, 20)
+    with pytest.raises(err_type, match=err_msg):
+        PCA(**params).fit(X)
+
+
+def test_feature_names_out():
+    """Check feature names out for PCA."""
+    pca = PCA(n_components=2).fit(iris.data)
+
+    names = pca.get_feature_names_out()
+    assert_array_equal([f"pca{i}" for i in range(2)], names)
+
+
+@pytest.mark.parametrize("copy", [True, False])
+def test_variance_correctness(copy):
+    """Check the accuracy of PCA's internal variance calculation"""
+    rng = np.random.RandomState(0)
+    X = rng.randn(1000, 200)
+    pca = PCA().fit(X)
+    pca_var = pca.explained_variance_ / pca.explained_variance_ratio_
+    true_var = np.var(X, ddof=1, axis=0).sum()
+    np.testing.assert_allclose(pca_var, true_var)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_sparse_pca.py

@@ -0,0 +1,267 @@
+# Author: Vlad Niculae
+# License: BSD 3 clause
+
+import sys
+import pytest
+
+import numpy as np
+from numpy.testing import assert_array_equal
+
+from sklearn.utils._testing import assert_array_almost_equal
+from sklearn.utils._testing import assert_allclose
+from sklearn.utils._testing import if_safe_multiprocessing_with_blas
+
+from sklearn.decomposition import SparsePCA, MiniBatchSparsePCA, PCA
+from sklearn.utils import check_random_state
+
+
+def generate_toy_data(n_components, n_samples, image_size, random_state=None):
+    n_features = image_size[0] * image_size[1]
+
+    rng = check_random_state(random_state)
+    U = rng.randn(n_samples, n_components)
+    V = rng.randn(n_components, n_features)
+
+    centers = [(3, 3), (6, 7), (8, 1)]
+    sz = [1, 2, 1]
+    for k in range(n_components):
+        img = np.zeros(image_size)
+        xmin, xmax = centers[k][0] - sz[k], centers[k][0] + sz[k]
+        ymin, ymax = centers[k][1] - sz[k], centers[k][1] + sz[k]
+        img[xmin:xmax][:, ymin:ymax] = 1.0
+        V[k, :] = img.ravel()
+
+    # Y is defined by : Y = UV + noise
+    Y = np.dot(U, V)
+    Y += 0.1 * rng.randn(Y.shape[0], Y.shape[1])  # Add noise
+    return Y, U, V
+
+
+# SparsePCA can be a bit slow. To avoid having test times go up, we
+# test different aspects of the code in the same test
+
+
+def test_correct_shapes():
+    rng = np.random.RandomState(0)
+    X = rng.randn(12, 10)
+    spca = SparsePCA(n_components=8, random_state=rng)
+    U = spca.fit_transform(X)
+    assert spca.components_.shape == (8, 10)
+    assert U.shape == (12, 8)
+    # test overcomplete decomposition
+    spca = SparsePCA(n_components=13, random_state=rng)
+    U = spca.fit_transform(X)
+    assert spca.components_.shape == (13, 10)
+    assert U.shape == (12, 13)
+
+
+def test_fit_transform():
+    alpha = 1
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
+    spca_lars = SparsePCA(n_components=3, method="lars", alpha=alpha, random_state=0)
+    spca_lars.fit(Y)
+
+    # Test that CD gives similar results
+    spca_lasso = SparsePCA(n_components=3, method="cd", random_state=0, alpha=alpha)
+    spca_lasso.fit(Y)
+    assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)
+
+
+@if_safe_multiprocessing_with_blas
+def test_fit_transform_parallel():
+    alpha = 1
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
+    spca_lars = SparsePCA(n_components=3, method="lars", alpha=alpha, random_state=0)
+    spca_lars.fit(Y)
+    U1 = spca_lars.transform(Y)
+    # Test multiple CPUs
+    spca = SparsePCA(
+        n_components=3, n_jobs=2, method="lars", alpha=alpha, random_state=0
+    ).fit(Y)
+    U2 = spca.transform(Y)
+    assert not np.all(spca_lars.components_ == 0)
+    assert_array_almost_equal(U1, U2)
+
+
+def test_transform_nan():
+    # Test that SparsePCA won't return NaN when there is 0 feature in all
+    # samples.
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
+    Y[:, 0] = 0
+    estimator = SparsePCA(n_components=8)
+    assert not np.any(np.isnan(estimator.fit_transform(Y)))
+
+
+def test_fit_transform_tall():
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 65, (8, 8), random_state=rng)  # tall array
+    spca_lars = SparsePCA(n_components=3, method="lars", random_state=rng)
+    U1 = spca_lars.fit_transform(Y)
+    spca_lasso = SparsePCA(n_components=3, method="cd", random_state=rng)
+    U2 = spca_lasso.fit(Y).transform(Y)
+    assert_array_almost_equal(U1, U2)
+
+
+def test_initialization():
+    rng = np.random.RandomState(0)
+    U_init = rng.randn(5, 3)
+    V_init = rng.randn(3, 4)
+    model = SparsePCA(
+        n_components=3, U_init=U_init, V_init=V_init, max_iter=0, random_state=rng
+    )
+    model.fit(rng.randn(5, 4))
+    assert_allclose(model.components_, V_init / np.linalg.norm(V_init, axis=1)[:, None])
+
+
+def test_mini_batch_correct_shapes():
+    rng = np.random.RandomState(0)
+    X = rng.randn(12, 10)
+    pca = MiniBatchSparsePCA(n_components=8, random_state=rng)
+    U = pca.fit_transform(X)
+    assert pca.components_.shape == (8, 10)
+    assert U.shape == (12, 8)
+    # test overcomplete decomposition
+    pca = MiniBatchSparsePCA(n_components=13, random_state=rng)
+    U = pca.fit_transform(X)
+    assert pca.components_.shape == (13, 10)
+    assert U.shape == (12, 13)
+
+
+# XXX: test always skipped
+@pytest.mark.skipif(True, reason="skipping mini_batch_fit_transform.")
+def test_mini_batch_fit_transform():
+    alpha = 1
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
+    spca_lars = MiniBatchSparsePCA(n_components=3, random_state=0, alpha=alpha).fit(Y)
+    U1 = spca_lars.transform(Y)
+    # Test multiple CPUs
+    if sys.platform == "win32":  # fake parallelism for win32
+        import joblib
+
+        _mp = joblib.parallel.multiprocessing
+        joblib.parallel.multiprocessing = None
+        try:
+            spca = MiniBatchSparsePCA(
+                n_components=3, n_jobs=2, alpha=alpha, random_state=0
+            )
+            U2 = spca.fit(Y).transform(Y)
+        finally:
+            joblib.parallel.multiprocessing = _mp
+    else:  # we can efficiently use parallelism
+        spca = MiniBatchSparsePCA(n_components=3, n_jobs=2, alpha=alpha, random_state=0)
+        U2 = spca.fit(Y).transform(Y)
+    assert not np.all(spca_lars.components_ == 0)
+    assert_array_almost_equal(U1, U2)
+    # Test that CD gives similar results
+    spca_lasso = MiniBatchSparsePCA(
+        n_components=3, method="cd", alpha=alpha, random_state=0
+    ).fit(Y)
+    assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)
+
+
+def test_scaling_fit_transform():
+    alpha = 1
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
+    spca_lars = SparsePCA(n_components=3, method="lars", alpha=alpha, random_state=rng)
+    results_train = spca_lars.fit_transform(Y)
+    results_test = spca_lars.transform(Y[:10])
+    assert_allclose(results_train[0], results_test[0])
+
+
+def test_pca_vs_spca():
+    rng = np.random.RandomState(0)
+    Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
+    Z, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)
+    spca = SparsePCA(alpha=0, ridge_alpha=0, n_components=2)
+    pca = PCA(n_components=2)
+    pca.fit(Y)
+    spca.fit(Y)
+    results_test_pca = pca.transform(Z)
+    results_test_spca = spca.transform(Z)
+    assert_allclose(
+        np.abs(spca.components_.dot(pca.components_.T)), np.eye(2), atol=1e-5
+    )
+    results_test_pca *= np.sign(results_test_pca[0, :])
+    results_test_spca *= np.sign(results_test_spca[0, :])
+    assert_allclose(results_test_pca, results_test_spca)
+
+
+@pytest.mark.parametrize("SPCA", [SparsePCA, MiniBatchSparsePCA])
+@pytest.mark.parametrize("n_components", [None, 3])
+def test_spca_n_components_(SPCA, n_components):
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 12, 10
+    X = rng.randn(n_samples, n_features)
+
+    model = SPCA(n_components=n_components).fit(X)
+
+    if n_components is not None:
+        assert model.n_components_ == n_components
+    else:
+        assert model.n_components_ == n_features
+
+
+@pytest.mark.parametrize("SPCA", (SparsePCA, MiniBatchSparsePCA))
+@pytest.mark.parametrize("method", ("lars", "cd"))
+@pytest.mark.parametrize(
+    "data_type, expected_type",
+    (
+        (np.float32, np.float32),
+        (np.float64, np.float64),
+        (np.int32, np.float64),
+        (np.int64, np.float64),
+    ),
+)
+def test_sparse_pca_dtype_match(SPCA, method, data_type, expected_type):
+    # Verify output matrix dtype
+    n_samples, n_features, n_components = 12, 10, 3
+    rng = np.random.RandomState(0)
+    input_array = rng.randn(n_samples, n_features).astype(data_type)
+    model = SPCA(n_components=n_components, method=method)
+    transformed = model.fit_transform(input_array)
+
+    assert transformed.dtype == expected_type
+    assert model.components_.dtype == expected_type
+
+
+@pytest.mark.parametrize("SPCA", (SparsePCA, MiniBatchSparsePCA))
+@pytest.mark.parametrize("method", ("lars", "cd"))
+def test_sparse_pca_numerical_consistency(SPCA, method):
+    # Verify numericall consistentency among np.float32 and np.float64
+    rtol = 1e-3
+    alpha = 2
+    n_samples, n_features, n_components = 12, 10, 3
+    rng = np.random.RandomState(0)
+    input_array = rng.randn(n_samples, n_features)
+
+    model_32 = SPCA(
+        n_components=n_components, alpha=alpha, method=method, random_state=0
+    )
+    transformed_32 = model_32.fit_transform(input_array.astype(np.float32))
+
+    model_64 = SPCA(
+        n_components=n_components, alpha=alpha, method=method, random_state=0
+    )
+    transformed_64 = model_64.fit_transform(input_array.astype(np.float64))
+
+    assert_allclose(transformed_64, transformed_32, rtol=rtol)
+    assert_allclose(model_64.components_, model_32.components_, rtol=rtol)
+
+
+@pytest.mark.parametrize("SPCA", [SparsePCA, MiniBatchSparsePCA])
+def test_spca_feature_names_out(SPCA):
+    """Check feature names out for *SparsePCA."""
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 12, 10
+    X = rng.randn(n_samples, n_features)
+
+    model = SPCA(n_components=4).fit(X)
+    names = model.get_feature_names_out()
+
+    estimator_name = SPCA.__name__.lower()
+    assert_array_equal([f"{estimator_name}{i}" for i in range(4)], names)

dashboard/flask-server/venv/Lib/site-packages/sklearn/decomposition/tests/test_truncated_svd.py

@@ -0,0 +1,213 @@
+"""Test truncated SVD transformer."""
+
+import numpy as np
+import scipy.sparse as sp
+
+import pytest
+
+from sklearn.decomposition import TruncatedSVD, PCA
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import assert_array_less, assert_allclose
+
+SVD_SOLVERS = ["arpack", "randomized"]
+
+
+@pytest.fixture(scope="module")
+def X_sparse():
+    # Make an X that looks somewhat like a small tf-idf matrix.
+    rng = check_random_state(42)
+    X = sp.random(60, 55, density=0.2, format="csr", random_state=rng)
+    X.data[:] = 1 + np.log(X.data)
+    return X
+
+
+@pytest.mark.parametrize("solver", ["randomized"])
+@pytest.mark.parametrize("kind", ("dense", "sparse"))
+def test_solvers(X_sparse, solver, kind):
+    X = X_sparse if kind == "sparse" else X_sparse.toarray()
+    svd_a = TruncatedSVD(30, algorithm="arpack")
+    svd = TruncatedSVD(30, algorithm=solver, random_state=42, n_oversamples=100)
+
+    Xa = svd_a.fit_transform(X)[:, :6]
+    Xr = svd.fit_transform(X)[:, :6]
+    assert_allclose(Xa, Xr, rtol=2e-3)
+
+    comp_a = np.abs(svd_a.components_)
+    comp = np.abs(svd.components_)
+    # All elements are equal, but some elements are more equal than others.
+    assert_allclose(comp_a[:9], comp[:9], rtol=1e-3)
+    assert_allclose(comp_a[9:], comp[9:], atol=1e-2)
+
+
+@pytest.mark.parametrize("n_components", (10, 25, 41, 55))
+def test_attributes(n_components, X_sparse):
+    n_features = X_sparse.shape[1]
+    tsvd = TruncatedSVD(n_components).fit(X_sparse)
+    assert tsvd.n_components == n_components
+    assert tsvd.components_.shape == (n_components, n_features)
+
+
+@pytest.mark.parametrize(
+    "algorithm, n_components",
+    [
+        ("arpack", 55),
+        ("arpack", 56),
+        ("randomized", 56),
+    ],
+)
+def test_too_many_components(X_sparse, algorithm, n_components):
+    tsvd = TruncatedSVD(n_components=n_components, algorithm=algorithm)
+    with pytest.raises(ValueError):
+        tsvd.fit(X_sparse)
+
+
+@pytest.mark.parametrize("fmt", ("array", "csr", "csc", "coo", "lil"))
+def test_sparse_formats(fmt, X_sparse):
+    n_samples = X_sparse.shape[0]
+    Xfmt = X_sparse.toarray() if fmt == "dense" else getattr(X_sparse, "to" + fmt)()
+    tsvd = TruncatedSVD(n_components=11)
+    Xtrans = tsvd.fit_transform(Xfmt)
+    assert Xtrans.shape == (n_samples, 11)
+    Xtrans = tsvd.transform(Xfmt)
+    assert Xtrans.shape == (n_samples, 11)
+
+
+@pytest.mark.parametrize("algo", SVD_SOLVERS)
+def test_inverse_transform(algo, X_sparse):
+    # We need a lot of components for the reconstruction to be "almost
+    # equal" in all positions. XXX Test means or sums instead?
+    tsvd = TruncatedSVD(n_components=52, random_state=42, algorithm=algo)
+    Xt = tsvd.fit_transform(X_sparse)
+    Xinv = tsvd.inverse_transform(Xt)
+    assert_allclose(Xinv, X_sparse.toarray(), rtol=1e-1, atol=2e-1)
+
+
+def test_integers(X_sparse):
+    n_samples = X_sparse.shape[0]
+    Xint = X_sparse.astype(np.int64)
+    tsvd = TruncatedSVD(n_components=6)
+    Xtrans = tsvd.fit_transform(Xint)
+    assert Xtrans.shape == (n_samples, tsvd.n_components)
+
+
+@pytest.mark.parametrize("kind", ("dense", "sparse"))
+@pytest.mark.parametrize("n_components", [10, 20])
+@pytest.mark.parametrize("solver", SVD_SOLVERS)
+def test_explained_variance(X_sparse, kind, n_components, solver):
+    X = X_sparse if kind == "sparse" else X_sparse.toarray()
+    svd = TruncatedSVD(n_components, algorithm=solver)
+    X_tr = svd.fit_transform(X)
+    # Assert that all the values are greater than 0
+    assert_array_less(0.0, svd.explained_variance_ratio_)
+
+    # Assert that total explained variance is less than 1
+    assert_array_less(svd.explained_variance_ratio_.sum(), 1.0)
+
+    # Test that explained_variance is correct
+    total_variance = np.var(X_sparse.toarray(), axis=0).sum()
+    variances = np.var(X_tr, axis=0)
+    true_explained_variance_ratio = variances / total_variance
+
+    assert_allclose(
+        svd.explained_variance_ratio_,
+        true_explained_variance_ratio,
+    )
+
+
+@pytest.mark.parametrize("kind", ("dense", "sparse"))
+@pytest.mark.parametrize("solver", SVD_SOLVERS)
+def test_explained_variance_components_10_20(X_sparse, kind, solver):
+    X = X_sparse if kind == "sparse" else X_sparse.toarray()
+    svd_10 = TruncatedSVD(10, algorithm=solver, n_iter=10).fit(X)
+    svd_20 = TruncatedSVD(20, algorithm=solver, n_iter=10).fit(X)
+
+    # Assert the 1st component is equal
+    assert_allclose(
+        svd_10.explained_variance_ratio_,
+        svd_20.explained_variance_ratio_[:10],
+        rtol=5e-3,
+    )
+
+    # Assert that 20 components has higher explained variance than 10
+    assert (
+        svd_20.explained_variance_ratio_.sum() > svd_10.explained_variance_ratio_.sum()
+    )
+
+
+@pytest.mark.parametrize("solver", SVD_SOLVERS)
+def test_singular_values_consistency(solver):
+    # Check that the TruncatedSVD output has the correct singular values
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 100, 80
+    X = rng.randn(n_samples, n_features)
+
+    pca = TruncatedSVD(n_components=2, algorithm=solver, random_state=rng).fit(X)
+
+    # Compare to the Frobenius norm
+    X_pca = pca.transform(X)
+    assert_allclose(
+        np.sum(pca.singular_values_**2.0),
+        np.linalg.norm(X_pca, "fro") ** 2.0,
+        rtol=1e-2,
+    )
+
+    # Compare to the 2-norms of the score vectors
+    assert_allclose(
+        pca.singular_values_, np.sqrt(np.sum(X_pca**2.0, axis=0)), rtol=1e-2
+    )
+
+
+@pytest.mark.parametrize("solver", SVD_SOLVERS)
+def test_singular_values_expected(solver):
+    # Set the singular values and see what we get back
+    rng = np.random.RandomState(0)
+    n_samples = 100
+    n_features = 110
+
+    X = rng.randn(n_samples, n_features)
+
+    pca = TruncatedSVD(n_components=3, algorithm=solver, random_state=rng)
+    X_pca = pca.fit_transform(X)
+
+    X_pca /= np.sqrt(np.sum(X_pca**2.0, axis=0))
+    X_pca[:, 0] *= 3.142
+    X_pca[:, 1] *= 2.718
+
+    X_hat_pca = np.dot(X_pca, pca.components_)
+    pca.fit(X_hat_pca)
+    assert_allclose(pca.singular_values_, [3.142, 2.718, 1.0], rtol=1e-14)
+
+
+def test_truncated_svd_eq_pca(X_sparse):
+    # TruncatedSVD should be equal to PCA on centered data
+
+    X_dense = X_sparse.toarray()
+
+    X_c = X_dense - X_dense.mean(axis=0)
+
+    params = dict(n_components=10, random_state=42)
+
+    svd = TruncatedSVD(algorithm="arpack", **params)
+    pca = PCA(svd_solver="arpack", **params)
+
+    Xt_svd = svd.fit_transform(X_c)
+    Xt_pca = pca.fit_transform(X_c)
+
+    assert_allclose(Xt_svd, Xt_pca, rtol=1e-9)
+    assert_allclose(pca.mean_, 0, atol=1e-9)
+    assert_allclose(svd.components_, pca.components_)
+
+
+@pytest.mark.parametrize(
+    "algorithm, tol", [("randomized", 0.0), ("arpack", 1e-6), ("arpack", 0.0)]
+)
+@pytest.mark.parametrize("kind", ("dense", "sparse"))
+def test_fit_transform(X_sparse, algorithm, tol, kind):
+    # fit_transform(X) should equal fit(X).transform(X)
+    X = X_sparse if kind == "sparse" else X_sparse.toarray()
+    svd = TruncatedSVD(
+        n_components=5, n_iter=7, random_state=42, algorithm=algorithm, tol=tol
+    )
+    X_transformed_1 = svd.fit_transform(X)
+    X_transformed_2 = svd.fit(X).transform(X)
+    assert_allclose(X_transformed_1, X_transformed_2)