first commit

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/__init__.py

@@ -0,0 +1,481 @@
+"""
+.. _statsrefmanual:
+
+==========================================
+Statistical functions (:mod:`scipy.stats`)
+==========================================
+
+.. currentmodule:: scipy.stats
+
+This module contains a large number of probability distributions,
+summary and frequency statistics, correlation functions and statistical
+tests, masked statistics, kernel density estimation, quasi-Monte Carlo
+functionality, and more.
+
+Statistics is a very large area, and there are topics that are out of scope
+for SciPy and are covered by other packages. Some of the most important ones
+are:
+
+- `statsmodels <https://www.statsmodels.org/stable/index.html>`__:
+  regression, linear models, time series analysis, extensions to topics
+  also covered by ``scipy.stats``.
+- `Pandas <https://pandas.pydata.org/>`__: tabular data, time series
+  functionality, interfaces to other statistical languages.
+- `PyMC <https://docs.pymc.io/>`__: Bayesian statistical
+  modeling, probabilistic machine learning.
+- `scikit-learn <https://scikit-learn.org/>`__: classification, regression,
+  model selection.
+- `Seaborn <https://seaborn.pydata.org/>`__: statistical data visualization.
+- `rpy2 <https://rpy2.github.io/>`__: Python to R bridge.
+
+
+Probability distributions
+=========================
+
+Each univariate distribution is an instance of a subclass of `rv_continuous`
+(`rv_discrete` for discrete distributions):
+
+.. autosummary::
+   :toctree: generated/
+
+   rv_continuous
+   rv_discrete
+   rv_histogram
+
+Continuous distributions
+------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   alpha             -- Alpha
+   anglit            -- Anglit
+   arcsine           -- Arcsine
+   argus             -- Argus
+   beta              -- Beta
+   betaprime         -- Beta Prime
+   bradford          -- Bradford
+   burr              -- Burr (Type III)
+   burr12            -- Burr (Type XII)
+   cauchy            -- Cauchy
+   chi               -- Chi
+   chi2              -- Chi-squared
+   cosine            -- Cosine
+   crystalball       -- Crystalball
+   dgamma            -- Double Gamma
+   dweibull          -- Double Weibull
+   erlang            -- Erlang
+   expon             -- Exponential
+   exponnorm         -- Exponentially Modified Normal
+   exponweib         -- Exponentiated Weibull
+   exponpow          -- Exponential Power
+   f                 -- F (Snecdor F)
+   fatiguelife       -- Fatigue Life (Birnbaum-Saunders)
+   fisk              -- Fisk
+   foldcauchy        -- Folded Cauchy
+   foldnorm          -- Folded Normal
+   genlogistic       -- Generalized Logistic
+   gennorm           -- Generalized normal
+   genpareto         -- Generalized Pareto
+   genexpon          -- Generalized Exponential
+   genextreme        -- Generalized Extreme Value
+   gausshyper        -- Gauss Hypergeometric
+   gamma             -- Gamma
+   gengamma          -- Generalized gamma
+   genhalflogistic   -- Generalized Half Logistic
+   genhyperbolic     -- Generalized Hyperbolic
+   geninvgauss       -- Generalized Inverse Gaussian
+   gilbrat           -- Gilbrat
+   gompertz          -- Gompertz (Truncated Gumbel)
+   gumbel_r          -- Right Sided Gumbel, Log-Weibull, Fisher-Tippett, Extreme Value Type I
+   gumbel_l          -- Left Sided Gumbel, etc.
+   halfcauchy        -- Half Cauchy
+   halflogistic      -- Half Logistic
+   halfnorm          -- Half Normal
+   halfgennorm       -- Generalized Half Normal
+   hypsecant         -- Hyperbolic Secant
+   invgamma          -- Inverse Gamma
+   invgauss          -- Inverse Gaussian
+   invweibull        -- Inverse Weibull
+   johnsonsb         -- Johnson SB
+   johnsonsu         -- Johnson SU
+   kappa4            -- Kappa 4 parameter
+   kappa3            -- Kappa 3 parameter
+   ksone             -- Distribution of Kolmogorov-Smirnov one-sided test statistic
+   kstwo             -- Distribution of Kolmogorov-Smirnov two-sided test statistic
+   kstwobign         -- Limiting Distribution of scaled Kolmogorov-Smirnov two-sided test statistic.
+   laplace           -- Laplace
+   laplace_asymmetric    -- Asymmetric Laplace
+   levy              -- Levy
+   levy_l
+   levy_stable
+   logistic          -- Logistic
+   loggamma          -- Log-Gamma
+   loglaplace        -- Log-Laplace (Log Double Exponential)
+   lognorm           -- Log-Normal
+   loguniform        -- Log-Uniform
+   lomax             -- Lomax (Pareto of the second kind)
+   maxwell           -- Maxwell
+   mielke            -- Mielke's Beta-Kappa
+   moyal             -- Moyal
+   nakagami          -- Nakagami
+   ncx2              -- Non-central chi-squared
+   ncf               -- Non-central F
+   nct               -- Non-central Student's T
+   norm              -- Normal (Gaussian)
+   norminvgauss      -- Normal Inverse Gaussian
+   pareto            -- Pareto
+   pearson3          -- Pearson type III
+   powerlaw          -- Power-function
+   powerlognorm      -- Power log normal
+   powernorm         -- Power normal
+   rdist             -- R-distribution
+   rayleigh          -- Rayleigh
+   rice              -- Rice
+   recipinvgauss     -- Reciprocal Inverse Gaussian
+   semicircular      -- Semicircular
+   skewcauchy        -- Skew Cauchy
+   skewnorm          -- Skew normal
+   studentized_range    -- Studentized Range
+   t                 -- Student's T
+   trapezoid         -- Trapezoidal
+   triang            -- Triangular
+   truncexpon        -- Truncated Exponential
+   truncnorm         -- Truncated Normal
+   tukeylambda       -- Tukey-Lambda
+   uniform           -- Uniform
+   vonmises          -- Von-Mises (Circular)
+   vonmises_line     -- Von-Mises (Line)
+   wald              -- Wald
+   weibull_min       -- Minimum Weibull (see Frechet)
+   weibull_max       -- Maximum Weibull (see Frechet)
+   wrapcauchy        -- Wrapped Cauchy
+
+Multivariate distributions
+--------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   multivariate_normal    -- Multivariate normal distribution
+   matrix_normal          -- Matrix normal distribution
+   dirichlet              -- Dirichlet
+   wishart                -- Wishart
+   invwishart             -- Inverse Wishart
+   multinomial            -- Multinomial distribution
+   special_ortho_group    -- SO(N) group
+   ortho_group            -- O(N) group
+   unitary_group          -- U(N) group
+   random_correlation     -- random correlation matrices
+   multivariate_t         -- Multivariate t-distribution
+   multivariate_hypergeom -- Multivariate hypergeometric distribution
+
+Discrete distributions
+----------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   bernoulli                -- Bernoulli
+   betabinom                -- Beta-Binomial
+   binom                    -- Binomial
+   boltzmann                -- Boltzmann (Truncated Discrete Exponential)
+   dlaplace                 -- Discrete Laplacian
+   geom                     -- Geometric
+   hypergeom                -- Hypergeometric
+   logser                   -- Logarithmic (Log-Series, Series)
+   nbinom                   -- Negative Binomial
+   nchypergeom_fisher       -- Fisher's Noncentral Hypergeometric
+   nchypergeom_wallenius    -- Wallenius's Noncentral Hypergeometric
+   nhypergeom               -- Negative Hypergeometric
+   planck                   -- Planck (Discrete Exponential)
+   poisson                  -- Poisson
+   randint                  -- Discrete Uniform
+   skellam                  -- Skellam
+   yulesimon                -- Yule-Simon
+   zipf                     -- Zipf (Zeta)
+   zipfian                  -- Zipfian
+
+An overview of statistical functions is given below.  Many of these functions
+have a similar version in `scipy.stats.mstats` which work for masked arrays.
+
+Summary statistics
+==================
+
+.. autosummary::
+   :toctree: generated/
+
+   describe          -- Descriptive statistics
+   gmean             -- Geometric mean
+   hmean             -- Harmonic mean
+   kurtosis          -- Fisher or Pearson kurtosis
+   mode              -- Modal value
+   moment            -- Central moment
+   skew              -- Skewness
+   kstat             --
+   kstatvar          --
+   tmean             -- Truncated arithmetic mean
+   tvar              -- Truncated variance
+   tmin              --
+   tmax              --
+   tstd              --
+   tsem              --
+   variation         -- Coefficient of variation
+   find_repeats
+   trim_mean
+   gstd              -- Geometric Standard Deviation
+   iqr
+   sem
+   bayes_mvs
+   mvsdist
+   entropy
+   differential_entropy
+   median_absolute_deviation
+   median_abs_deviation
+   bootstrap
+
+Frequency statistics
+====================
+
+.. autosummary::
+   :toctree: generated/
+
+   cumfreq
+   itemfreq
+   percentileofscore
+   scoreatpercentile
+   relfreq
+
+.. autosummary::
+   :toctree: generated/
+
+   binned_statistic     -- Compute a binned statistic for a set of data.
+   binned_statistic_2d  -- Compute a 2-D binned statistic for a set of data.
+   binned_statistic_dd  -- Compute a d-D binned statistic for a set of data.
+
+Correlation functions
+=====================
+
+.. autosummary::
+   :toctree: generated/
+
+   f_oneway
+   alexandergovern
+   pearsonr
+   spearmanr
+   pointbiserialr
+   kendalltau
+   weightedtau
+   somersd
+   linregress
+   siegelslopes
+   theilslopes
+   multiscale_graphcorr
+
+Statistical tests
+=================
+
+.. autosummary::
+   :toctree: generated/
+
+   ttest_1samp
+   ttest_ind
+   ttest_ind_from_stats
+   ttest_rel
+   chisquare
+   cramervonmises
+   cramervonmises_2samp
+   power_divergence
+   kstest
+   ks_1samp
+   ks_2samp
+   epps_singleton_2samp
+   mannwhitneyu
+   tiecorrect
+   rankdata
+   ranksums
+   wilcoxon
+   kruskal
+   friedmanchisquare
+   brunnermunzel
+   combine_pvalues
+   jarque_bera
+   page_trend_test
+   permutation_test
+   tukey_hsd
+
+.. autosummary::
+   :toctree: generated/
+
+   ansari
+   bartlett
+   levene
+   shapiro
+   anderson
+   anderson_ksamp
+   binom_test
+   binomtest
+   fligner
+   median_test
+   mood
+   skewtest
+   kurtosistest
+   normaltest
+
+
+Quasi-Monte Carlo
+=================
+
+.. toctree::
+   :maxdepth: 4
+
+   stats.qmc
+
+
+Masked statistics functions
+===========================
+
+.. toctree::
+
+   stats.mstats
+
+
+Other statistical functionality
+===============================
+
+Transformations
+---------------
+
+.. autosummary::
+   :toctree: generated/
+
+   boxcox
+   boxcox_normmax
+   boxcox_llf
+   yeojohnson
+   yeojohnson_normmax
+   yeojohnson_llf
+   obrientransform
+   sigmaclip
+   trimboth
+   trim1
+   zmap
+   zscore
+   gzscore
+
+Statistical distances
+---------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   wasserstein_distance
+   energy_distance
+
+Sampling
+--------
+
+.. toctree::
+   :maxdepth: 4
+
+   stats.sampling
+
+Random variate generation / CDF Inversion
+-----------------------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   rvs_ratio_uniforms
+   NumericalInverseHermite
+
+Circular statistical functions
+------------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   circmean
+   circvar
+   circstd
+
+Contingency table functions
+---------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   chi2_contingency
+   contingency.crosstab
+   contingency.expected_freq
+   contingency.margins
+   contingency.relative_risk
+   contingency.association
+   fisher_exact
+   barnard_exact
+   boschloo_exact
+
+Plot-tests
+----------
+
+.. autosummary::
+   :toctree: generated/
+
+   ppcc_max
+   ppcc_plot
+   probplot
+   boxcox_normplot
+   yeojohnson_normplot
+
+Univariate and multivariate kernel density estimation
+-----------------------------------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   gaussian_kde
+
+Warnings / Errors used in :mod:`scipy.stats`
+--------------------------------------------
+
+.. autosummary::
+   :toctree: generated/
+
+   F_onewayConstantInputWarning
+   F_onewayBadInputSizesWarning
+   PearsonRConstantInputWarning
+   PearsonRNearConstantInputWarning
+   SpearmanRConstantInputWarning
+   BootstrapDegenerateDistributionWarning
+
+"""
+
+from ._stats_py import *
+from ._variation import variation
+from .distributions import *
+from ._morestats import *
+from ._binomtest import binomtest
+from ._binned_statistic import *
+from ._kde import gaussian_kde
+from . import mstats
+from . import qmc
+from ._multivariate import *
+from . import contingency
+from .contingency import chi2_contingency
+from ._bootstrap import bootstrap, BootstrapDegenerateDistributionWarning
+from ._entropy import *
+from ._hypotests import *
+from ._rvs_sampling import rvs_ratio_uniforms, NumericalInverseHermite  # noqa
+from ._page_trend_test import page_trend_test
+from ._mannwhitneyu import mannwhitneyu
+
+# Deprecated namespaces, to be removed in v2.0.0
+from . import (
+    biasedurn, kde, morestats, mstats_basic, mstats_extras, mvn, statlib, stats
+)
+
+__all__ = [s for s in dir() if not s.startswith("_")]  # Remove dunders.
+
+from scipy._lib._testutils import PytestTester
+test = PytestTester(__name__)
+del PytestTester

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_axis_nan_policy.py

@@ -0,0 +1,347 @@
+# Many scipy.stats functions support `axis` and `nan_policy` parameters.
+# When the two are combined, it can be tricky to get all the behavior just
+# right. This file contains utility functions useful for scipy.stats functions
+# that support `axis` and `nan_policy`, including a decorator that
+# automatically adds `axis` and `nan_policy` arguments to a function.
+
+import numpy as np
+import scipy.stats
+import scipy.stats._stats_py
+from functools import wraps
+from scipy._lib._docscrape import FunctionDoc, Parameter
+import inspect
+
+
+def _broadcast_array_shapes_remove_axis(arrays, axis=None):
+    """
+    Broadcast shapes of arrays, dropping specified axes
+
+    Given a sequence of arrays `arrays` and an integer or tuple `axis`, find
+    the shape of the broadcast result after consuming/dropping `axis`.
+    In other words, return output shape of a typical hypothesis test on
+    `arrays` vectorized along `axis`.
+
+    Examples
+    --------
+    >>> a = np.zeros((5, 2, 1))
+    >>> b = np.zeros((9, 3))
+    >>> _broadcast_array_shapes((a, b), 1)
+    (5, 3)
+    """
+    # Note that here, `axis=None` means do not consume/drop any axes - _not_
+    # ravel arrays before broadcasting.
+    shapes = [arr.shape for arr in arrays]
+    return _broadcast_shapes_remove_axis(shapes, axis)
+
+
+def _broadcast_shapes_remove_axis(shapes, axis=None):
+    """
+    Broadcast shapes, dropping specified axes
+
+    Same as _broadcast_array_shapes, but given a sequence
+    of array shapes `shapes` instead of the arrays themselves.
+    """
+    n_dims = max([len(shape) for shape in shapes])
+    new_shapes = np.ones((len(shapes), n_dims), dtype=int)
+    for row, shape in zip(new_shapes, shapes):
+        row[len(row)-len(shape):] = shape  # can't use negative indices (-0:)
+    if axis is not None:
+        new_shapes = np.delete(new_shapes, axis, axis=1)
+    new_shape = np.max(new_shapes, axis=0)
+    new_shape *= new_shapes.all(axis=0)
+    if np.any(~((new_shapes == 1) | (new_shapes == new_shape))):
+        raise ValueError("Array shapes are incompatible for broadcasting.")
+    return tuple(new_shape)
+
+
+def _broadcast_concatenate(xs, axis):
+    """Concatenate arrays along an axis with broadcasting."""
+    # prepend 1s to array shapes as needed
+    ndim = max([x.ndim for x in xs])
+    xs = [x.reshape([1]*(ndim-x.ndim) + list(x.shape)) for x in xs]
+    # move the axis we're concatenating along to the end
+    xs = [np.swapaxes(x, axis, -1) for x in xs]
+    # determine final shape of all but the last axis
+    shape = _broadcast_array_shapes_remove_axis(xs, axis=-1)
+    # broadcast along all but the last axis
+    xs = [np.broadcast_to(x, shape + (x.shape[-1],)) for x in xs]
+    # concatenate along last axis
+    res = np.concatenate(xs, axis=-1)
+    # move the last axis back to where it was
+    res = np.swapaxes(res, axis, -1)
+    return res
+
+
+# TODO: add support for `axis` tuples
+def _remove_nans(samples, paired):
+    "Remove nans from paired or unpaired samples"
+    # potential optimization: don't copy arrays that don't contain nans
+    if not paired:
+        return [sample[~np.isnan(sample)] for sample in samples]
+
+    # for paired samples, we need to remove the whole pair when any part
+    # has a nan
+    nans = np.isnan(samples[0])
+    for sample in samples[1:]:
+        nans = nans | np.isnan(sample)
+    not_nans = ~nans
+    return [sample[not_nans] for sample in samples]
+
+
+def _check_empty_inputs(samples, axis):
+    """
+    Check for empty sample; return appropriate output for a vectorized hypotest
+    """
+    # if none of the samples are empty, we need to perform the test
+    if not any((sample.size == 0 for sample in samples)):
+        return None
+    # otherwise, the statistic and p-value will be either empty arrays or
+    # arrays with NaNs. Produce the appropriate array and return it.
+    output_shape = _broadcast_array_shapes_remove_axis(samples, axis)
+    output = np.ones(output_shape) * np.nan
+    return output
+
+
+# Standard docstring / signature entries for `axis` and `nan_policy`
+_name = 'axis'
+_type = "int or None, default: 0"
+_desc = (
+    """If an int, the axis of the input along which to compute the statistic.
+The statistic of each axis-slice (e.g. row) of the input will appear in a
+corresponding element of the output.
+If ``None``, the input will be raveled before computing the statistic."""
+    .split('\n'))
+_axis_parameter_doc = Parameter(_name, _type, _desc)
+_axis_parameter = inspect.Parameter(_name,
+                                    inspect.Parameter.KEYWORD_ONLY,
+                                    default=0)
+
+_name = 'nan_policy'
+_type = "{'propagate', 'omit', 'raise'}"
+_desc = (
+    """Defines how to handle input NaNs.
+
+- ``propagate``: if a NaN is present in the axis slice (e.g. row) along
+  which the  statistic is computed, the corresponding entry of the output
+  will be NaN.
+- ``omit``: NaNs will be omitted when performing the calculation.
+  If insufficient data remains in the axis slice along which the
+  statistic is computed, the corresponding entry of the output will be
+  NaN.
+- ``raise``: if a NaN is present, a ``ValueError`` will be raised."""
+    .split('\n'))
+_nan_policy_parameter_doc = Parameter(_name, _type, _desc)
+_nan_policy_parameter = inspect.Parameter(_name,
+                                          inspect.Parameter.KEYWORD_ONLY,
+                                          default='propagate')
+
+
+def _axis_nan_policy_factory(result_object, default_axis=0,
+                             n_samples=1, paired=False,
+                             result_unpacker=None, too_small=0):
+    """Factory for a wrapper that adds axis/nan_policy params to a function.
+
+    Parameters
+    ----------
+    result_object : callable
+        Callable that returns an object of the type returned by the function
+        being wrapped (e.g. the namedtuple or dataclass returned by a
+        statistical test) provided the separate components (e.g. statistic,
+        pvalue).
+    default_axis : int, default: 0
+        The default value of the axis argument. Standard is 0 except when
+        backwards compatibility demands otherwise (e.g. `None`).
+    n_samples : int or callable, default: 1
+        The number of data samples accepted by the function
+        (e.g. `mannwhitneyu`), a callable that accepts a dictionary of
+        parameters passed into the function and returns the number of data
+        samples (e.g. `wilcoxon`), or `None` to indicate an arbitrary number
+        of samples (e.g. `kruskal`).
+    paired : {False, True}
+        Whether the function being wrapped treats the samples as paired (i.e.
+        corresponding elements of each sample should be considered as different
+        components of the same sample.)
+    result_unpacker : callable, optional
+        Function that unpacks the results of the function being wrapped into
+        a tuple. This is essentially the inverse of `result_object`. Default
+        is `None`, which is appropriate for statistical tests that return a
+        statistic, pvalue tuple (rather than, e.g., a non-iterable datalass).
+    too_small : int, default: 0
+        The largest unnacceptably small sample for the function being wrapped.
+        For example, some functions require samples of size two or more or they
+        raise an error. This argument prevents the error from being raised when
+        input is not 1D and instead places a NaN in the corresponding element
+        of the result.
+    """
+
+    if result_unpacker is None:
+        def result_unpacker(res):
+            return res[..., 0], res[..., 1]
+
+    def is_too_small(samples):
+        for sample in samples:
+            if len(sample) <= too_small:
+                return True
+        return False
+
+    def axis_nan_policy_decorator(hypotest_fun_in):
+        @wraps(hypotest_fun_in)
+        def axis_nan_policy_wrapper(*args, _no_deco=False, **kwds):
+
+            if _no_deco:  # for testing, decorator does nothing
+                return hypotest_fun_in(*args, **kwds)
+
+            # We need to be flexible about whether position or keyword
+            # arguments are used, but we need to make sure users don't pass
+            # both for the same parameter. To complicate matters, some
+            # functions accept samples with *args, and some functions already
+            # accept `axis` and `nan_policy` as positional arguments.
+            # The strategy is to make sure that there is no duplication
+            # between `args` and `kwds`, combine the two into `kwds`, then
+            # the samples, `nan_policy`, and `axis` from `kwds`, as they are
+            # dealt with separately.
+
+            # Check for intersection between positional and keyword args
+            params = list(inspect.signature(hypotest_fun_in).parameters)
+            if n_samples is None:
+                # Give unique names to each positional sample argument
+                # Note that *args can't be provided as a keyword argument
+                params = [f"arg{i}" for i in range(len(args))] + params[1:]
+
+            d_args = dict(zip(params, args))
+            intersection = set(d_args) & set(kwds)
+            if intersection:
+                message = (f"{hypotest_fun_in.__name__}() got multiple values "
+                           f"for argument '{list(intersection)[0]}'")
+                raise TypeError(message)
+
+            # Consolidate other positional and keyword args into `kwds`
+            kwds.update(d_args)
+
+            # rename avoids UnboundLocalError
+            if callable(n_samples):
+                n_samp = n_samples(kwds)
+            else:
+                n_samp = n_samples or len(args)
+
+            # Extract the things we need here
+            samples = [np.atleast_1d(kwds.pop(param))
+                       for param in params[:n_samp]]
+            vectorized = True if 'axis' in params else False
+            axis = kwds.pop('axis', default_axis)
+            nan_policy = kwds.pop('nan_policy', 'propagate')
+            del args  # avoid the possibility of passing both `args` and `kwds`
+
+            if axis is None:
+                samples = [sample.ravel() for sample in samples]
+                axis = 0
+            elif axis != int(axis):
+                raise ValueError('`axis` must be an integer')
+            axis = int(axis)
+
+            # if axis is not needed, just handle nan_policy and return
+            ndims = np.array([sample.ndim for sample in samples])
+            if np.all(ndims <= 1):
+                # Addresses nan_policy == "raise"
+                contains_nans = []
+                for sample in samples:
+                    contains_nan, _ = (
+                        scipy.stats._stats_py._contains_nan(sample, nan_policy))
+                    contains_nans.append(contains_nan)
+
+                # Addresses nan_policy == "propagate"
+                # Consider adding option to let function propagate nans, but
+                # currently the hypothesis tests this is applied to do not
+                # propagate nans in a sensible way
+                if any(contains_nans) and nan_policy == 'propagate':
+                    return result_object(np.nan, np.nan)
+
+                # Addresses nan_policy == "omit"
+                if any(contains_nans) and nan_policy == 'omit':
+                    # consider passing in contains_nans
+                    samples = _remove_nans(samples, paired)
+
+                # ideally, this is what the behavior would be, but some
+                # existing functions raise exceptions, so overriding it
+                # would break backward compatibility.
+                # if is_too_small(samples):
+                #     return result_object(np.nan, np.nan)
+
+                return hypotest_fun_in(*samples, **kwds)
+
+            # check for empty input
+            # ideally, move this to the top, but some existing functions raise
+            # exceptions for empty input, so overriding it would break
+            # backward compatibility.
+            empty_output = _check_empty_inputs(samples, axis)
+            if empty_output is not None:
+                statistic = empty_output
+                pvalue = empty_output.copy()
+                return result_object(statistic, pvalue)
+
+            # otherwise, concatenate all samples along axis, remembering where
+            # each separate sample begins
+            lengths = np.array([sample.shape[axis] for sample in samples])
+            split_indices = np.cumsum(lengths)
+            x = _broadcast_concatenate(samples, axis)
+
+            # Addresses nan_policy == "raise"
+            contains_nan, _ = (
+                scipy.stats._stats_py._contains_nan(x, nan_policy))
+
+            if vectorized and not contains_nan:
+                return hypotest_fun_in(*samples, axis=axis, **kwds)
+
+            # Addresses nan_policy == "omit"
+            if contains_nan and nan_policy == 'omit':
+                def hypotest_fun(x):
+                    samples = np.split(x, split_indices)[:n_samp]
+                    samples = _remove_nans(samples, paired)
+                    if is_too_small(samples):
+                        return result_object(np.nan, np.nan)
+                    return hypotest_fun_in(*samples, **kwds)
+
+            # Addresses nan_policy == "propagate"
+            elif contains_nan and nan_policy == 'propagate':
+                def hypotest_fun(x):
+                    if np.isnan(x).any():
+                        return result_object(np.nan, np.nan)
+                    samples = np.split(x, split_indices)[:n_samp]
+                    return hypotest_fun_in(*samples, **kwds)
+
+            else:
+                def hypotest_fun(x):
+                    samples = np.split(x, split_indices)[:n_samp]
+                    return hypotest_fun_in(*samples, **kwds)
+
+            x = np.moveaxis(x, axis, -1)
+            res = np.apply_along_axis(hypotest_fun, axis=-1, arr=x)
+            return result_object(*result_unpacker(res))
+
+        doc = FunctionDoc(axis_nan_policy_wrapper)
+        parameter_names = [param.name for param in doc['Parameters']]
+        if 'axis' in parameter_names:
+            doc['Parameters'][parameter_names.index('axis')] = (
+                _axis_parameter_doc)
+        else:
+            doc['Parameters'].append(_axis_parameter_doc)
+        if 'nan_policy' in parameter_names:
+            doc['Parameters'][parameter_names.index('nan_policy')] = (
+                _nan_policy_parameter_doc)
+        else:
+            doc['Parameters'].append(_nan_policy_parameter_doc)
+        doc = str(doc).split("\n", 1)[1]  # remove signature
+        axis_nan_policy_wrapper.__doc__ = str(doc)
+
+        sig = inspect.signature(axis_nan_policy_wrapper)
+        parameters = sig.parameters
+        parameter_list = list(parameters.values())
+        if 'axis' not in parameters:
+            parameter_list.append(_axis_parameter)
+        if 'nan_policy' not in parameters:
+            parameter_list.append(_nan_policy_parameter)
+        sig = sig.replace(parameters=parameter_list)
+        axis_nan_policy_wrapper.__signature__ = sig
+
+        return axis_nan_policy_wrapper
+    return axis_nan_policy_decorator

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_biasedurn.pxd

@@ -0,0 +1,27 @@
+# Declare the class with cdef
+cdef extern from "biasedurn/stocc.h" nogil:
+    cdef cppclass CFishersNCHypergeometric:
+        CFishersNCHypergeometric(int, int, int, double, double) except +
+        int mode()
+        double mean()
+        double variance()
+        double probability(int x)
+        double moments(double * mean, double * var)
+
+    cdef cppclass CWalleniusNCHypergeometric:
+        CWalleniusNCHypergeometric() except +
+        CWalleniusNCHypergeometric(int, int, int, double, double) except +
+        int mode()
+        double mean()
+        double variance()
+        double probability(int x)
+        double moments(double * mean, double * var)
+
+    cdef cppclass StochasticLib3:
+        StochasticLib3(int seed) except +
+        double Random() except +
+        void SetAccuracy(double accur)
+        int FishersNCHyp (int n, int m, int N, double odds) except +
+        int WalleniusNCHyp (int n, int m, int N, double odds) except +
+        double(*next_double)()
+        double(*next_normal)(const double m, const double s)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_binned_statistic.py

@@ -0,0 +1,763 @@
+import builtins
+import numpy as np
+from numpy.testing import suppress_warnings
+from operator import index
+from collections import namedtuple
+
+__all__ = ['binned_statistic',
+           'binned_statistic_2d',
+           'binned_statistic_dd']
+
+
+BinnedStatisticResult = namedtuple('BinnedStatisticResult',
+                                   ('statistic', 'bin_edges', 'binnumber'))
+
+
+def binned_statistic(x, values, statistic='mean',
+                     bins=10, range=None):
+    """
+    Compute a binned statistic for one or more sets of data.
+
+    This is a generalization of a histogram function.  A histogram divides
+    the space into bins, and returns the count of the number of points in
+    each bin.  This function allows the computation of the sum, mean, median,
+    or other statistic of the values (or set of values) within each bin.
+
+    Parameters
+    ----------
+    x : (N,) array_like
+        A sequence of values to be binned.
+    values : (N,) array_like or list of (N,) array_like
+        The data on which the statistic will be computed.  This must be
+        the same shape as `x`, or a set of sequences - each the same shape as
+        `x`.  If `values` is a set of sequences, the statistic will be computed
+        on each independently.
+    statistic : string or callable, optional
+        The statistic to compute (default is 'mean').
+        The following statistics are available:
+
+          * 'mean' : compute the mean of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'std' : compute the standard deviation within each bin. This
+            is implicitly calculated with ddof=0.
+          * 'median' : compute the median of values for points within each
+            bin. Empty bins will be represented by NaN.
+          * 'count' : compute the count of points within each bin.  This is
+            identical to an unweighted histogram.  `values` array is not
+            referenced.
+          * 'sum' : compute the sum of values for points within each bin.
+            This is identical to a weighted histogram.
+          * 'min' : compute the minimum of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'max' : compute the maximum of values for point within each bin.
+            Empty bins will be represented by NaN.
+          * function : a user-defined function which takes a 1D array of
+            values, and outputs a single numerical statistic. This function
+            will be called on the values in each bin.  Empty bins will be
+            represented by function([]), or NaN if this returns an error.
+
+    bins : int or sequence of scalars, optional
+        If `bins` is an int, it defines the number of equal-width bins in the
+        given range (10 by default).  If `bins` is a sequence, it defines the
+        bin edges, including the rightmost edge, allowing for non-uniform bin
+        widths.  Values in `x` that are smaller than lowest bin edge are
+        assigned to bin number 0, values beyond the highest bin are assigned to
+        ``bins[-1]``.  If the bin edges are specified, the number of bins will
+        be, (nx = len(bins)-1).
+    range : (float, float) or [(float, float)], optional
+        The lower and upper range of the bins.  If not provided, range
+        is simply ``(x.min(), x.max())``.  Values outside the range are
+        ignored.
+
+    Returns
+    -------
+    statistic : array
+        The values of the selected statistic in each bin.
+    bin_edges : array of dtype float
+        Return the bin edges ``(length(statistic)+1)``.
+    binnumber: 1-D ndarray of ints
+        Indices of the bins (corresponding to `bin_edges`) in which each value
+        of `x` belongs.  Same length as `values`.  A binnumber of `i` means the
+        corresponding value is between (bin_edges[i-1], bin_edges[i]).
+
+    See Also
+    --------
+    numpy.digitize, numpy.histogram, binned_statistic_2d, binned_statistic_dd
+
+    Notes
+    -----
+    All but the last (righthand-most) bin is half-open.  In other words, if
+    `bins` is ``[1, 2, 3, 4]``, then the first bin is ``[1, 2)`` (including 1,
+    but excluding 2) and the second ``[2, 3)``.  The last bin, however, is
+    ``[3, 4]``, which *includes* 4.
+
+    .. versionadded:: 0.11.0
+
+    Examples
+    --------
+    >>> from scipy import stats
+    >>> import matplotlib.pyplot as plt
+
+    First some basic examples:
+
+    Create two evenly spaced bins in the range of the given sample, and sum the
+    corresponding values in each of those bins:
+
+    >>> values = [1.0, 1.0, 2.0, 1.5, 3.0]
+    >>> stats.binned_statistic([1, 1, 2, 5, 7], values, 'sum', bins=2)
+    BinnedStatisticResult(statistic=array([4. , 4.5]),
+            bin_edges=array([1., 4., 7.]), binnumber=array([1, 1, 1, 2, 2]))
+
+    Multiple arrays of values can also be passed.  The statistic is calculated
+    on each set independently:
+
+    >>> values = [[1.0, 1.0, 2.0, 1.5, 3.0], [2.0, 2.0, 4.0, 3.0, 6.0]]
+    >>> stats.binned_statistic([1, 1, 2, 5, 7], values, 'sum', bins=2)
+    BinnedStatisticResult(statistic=array([[4. , 4.5],
+           [8. , 9. ]]), bin_edges=array([1., 4., 7.]),
+           binnumber=array([1, 1, 1, 2, 2]))
+
+    >>> stats.binned_statistic([1, 2, 1, 2, 4], np.arange(5), statistic='mean',
+    ...                        bins=3)
+    BinnedStatisticResult(statistic=array([1., 2., 4.]),
+            bin_edges=array([1., 2., 3., 4.]),
+            binnumber=array([1, 2, 1, 2, 3]))
+
+    As a second example, we now generate some random data of sailing boat speed
+    as a function of wind speed, and then determine how fast our boat is for
+    certain wind speeds:
+
+    >>> rng = np.random.default_rng()
+    >>> windspeed = 8 * rng.random(500)
+    >>> boatspeed = .3 * windspeed**.5 + .2 * rng.random(500)
+    >>> bin_means, bin_edges, binnumber = stats.binned_statistic(windspeed,
+    ...                 boatspeed, statistic='median', bins=[1,2,3,4,5,6,7])
+    >>> plt.figure()
+    >>> plt.plot(windspeed, boatspeed, 'b.', label='raw data')
+    >>> plt.hlines(bin_means, bin_edges[:-1], bin_edges[1:], colors='g', lw=5,
+    ...            label='binned statistic of data')
+    >>> plt.legend()
+
+    Now we can use ``binnumber`` to select all datapoints with a windspeed
+    below 1:
+
+    >>> low_boatspeed = boatspeed[binnumber == 0]
+
+    As a final example, we will use ``bin_edges`` and ``binnumber`` to make a
+    plot of a distribution that shows the mean and distribution around that
+    mean per bin, on top of a regular histogram and the probability
+    distribution function:
+
+    >>> x = np.linspace(0, 5, num=500)
+    >>> x_pdf = stats.maxwell.pdf(x)
+    >>> samples = stats.maxwell.rvs(size=10000)
+
+    >>> bin_means, bin_edges, binnumber = stats.binned_statistic(x, x_pdf,
+    ...         statistic='mean', bins=25)
+    >>> bin_width = (bin_edges[1] - bin_edges[0])
+    >>> bin_centers = bin_edges[1:] - bin_width/2
+
+    >>> plt.figure()
+    >>> plt.hist(samples, bins=50, density=True, histtype='stepfilled',
+    ...          alpha=0.2, label='histogram of data')
+    >>> plt.plot(x, x_pdf, 'r-', label='analytical pdf')
+    >>> plt.hlines(bin_means, bin_edges[:-1], bin_edges[1:], colors='g', lw=2,
+    ...            label='binned statistic of data')
+    >>> plt.plot((binnumber - 0.5) * bin_width, x_pdf, 'g.', alpha=0.5)
+    >>> plt.legend(fontsize=10)
+    >>> plt.show()
+
+    """
+    try:
+        N = len(bins)
+    except TypeError:
+        N = 1
+
+    if N != 1:
+        bins = [np.asarray(bins, float)]
+
+    if range is not None:
+        if len(range) == 2:
+            range = [range]
+
+    medians, edges, binnumbers = binned_statistic_dd(
+        [x], values, statistic, bins, range)
+
+    return BinnedStatisticResult(medians, edges[0], binnumbers)
+
+
+BinnedStatistic2dResult = namedtuple('BinnedStatistic2dResult',
+                                     ('statistic', 'x_edge', 'y_edge',
+                                      'binnumber'))
+
+
+def binned_statistic_2d(x, y, values, statistic='mean',
+                        bins=10, range=None, expand_binnumbers=False):
+    """
+    Compute a bidimensional binned statistic for one or more sets of data.
+
+    This is a generalization of a histogram2d function.  A histogram divides
+    the space into bins, and returns the count of the number of points in
+    each bin.  This function allows the computation of the sum, mean, median,
+    or other statistic of the values (or set of values) within each bin.
+
+    Parameters
+    ----------
+    x : (N,) array_like
+        A sequence of values to be binned along the first dimension.
+    y : (N,) array_like
+        A sequence of values to be binned along the second dimension.
+    values : (N,) array_like or list of (N,) array_like
+        The data on which the statistic will be computed.  This must be
+        the same shape as `x`, or a list of sequences - each with the same
+        shape as `x`.  If `values` is such a list, the statistic will be
+        computed on each independently.
+    statistic : string or callable, optional
+        The statistic to compute (default is 'mean').
+        The following statistics are available:
+
+          * 'mean' : compute the mean of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'std' : compute the standard deviation within each bin. This
+            is implicitly calculated with ddof=0.
+          * 'median' : compute the median of values for points within each
+            bin. Empty bins will be represented by NaN.
+          * 'count' : compute the count of points within each bin.  This is
+            identical to an unweighted histogram.  `values` array is not
+            referenced.
+          * 'sum' : compute the sum of values for points within each bin.
+            This is identical to a weighted histogram.
+          * 'min' : compute the minimum of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'max' : compute the maximum of values for point within each bin.
+            Empty bins will be represented by NaN.
+          * function : a user-defined function which takes a 1D array of
+            values, and outputs a single numerical statistic. This function
+            will be called on the values in each bin.  Empty bins will be
+            represented by function([]), or NaN if this returns an error.
+
+    bins : int or [int, int] or array_like or [array, array], optional
+        The bin specification:
+
+          * the number of bins for the two dimensions (nx = ny = bins),
+          * the number of bins in each dimension (nx, ny = bins),
+          * the bin edges for the two dimensions (x_edge = y_edge = bins),
+          * the bin edges in each dimension (x_edge, y_edge = bins).
+
+        If the bin edges are specified, the number of bins will be,
+        (nx = len(x_edge)-1, ny = len(y_edge)-1).
+
+    range : (2,2) array_like, optional
+        The leftmost and rightmost edges of the bins along each dimension
+        (if not specified explicitly in the `bins` parameters):
+        [[xmin, xmax], [ymin, ymax]]. All values outside of this range will be
+        considered outliers and not tallied in the histogram.
+    expand_binnumbers : bool, optional
+        'False' (default): the returned `binnumber` is a shape (N,) array of
+        linearized bin indices.
+        'True': the returned `binnumber` is 'unraveled' into a shape (2,N)
+        ndarray, where each row gives the bin numbers in the corresponding
+        dimension.
+        See the `binnumber` returned value, and the `Examples` section.
+
+        .. versionadded:: 0.17.0
+
+    Returns
+    -------
+    statistic : (nx, ny) ndarray
+        The values of the selected statistic in each two-dimensional bin.
+    x_edge : (nx + 1) ndarray
+        The bin edges along the first dimension.
+    y_edge : (ny + 1) ndarray
+        The bin edges along the second dimension.
+    binnumber : (N,) array of ints or (2,N) ndarray of ints
+        This assigns to each element of `sample` an integer that represents the
+        bin in which this observation falls.  The representation depends on the
+        `expand_binnumbers` argument.  See `Notes` for details.
+
+
+    See Also
+    --------
+    numpy.digitize, numpy.histogram2d, binned_statistic, binned_statistic_dd
+
+    Notes
+    -----
+    Binedges:
+    All but the last (righthand-most) bin is half-open.  In other words, if
+    `bins` is ``[1, 2, 3, 4]``, then the first bin is ``[1, 2)`` (including 1,
+    but excluding 2) and the second ``[2, 3)``.  The last bin, however, is
+    ``[3, 4]``, which *includes* 4.
+
+    `binnumber`:
+    This returned argument assigns to each element of `sample` an integer that
+    represents the bin in which it belongs.  The representation depends on the
+    `expand_binnumbers` argument. If 'False' (default): The returned
+    `binnumber` is a shape (N,) array of linearized indices mapping each
+    element of `sample` to its corresponding bin (using row-major ordering).
+    Note that the returned linearized bin indices are used for an array with
+    extra bins on the outer binedges to capture values outside of the defined
+    bin bounds.
+    If 'True': The returned `binnumber` is a shape (2,N) ndarray where
+    each row indicates bin placements for each dimension respectively.  In each
+    dimension, a binnumber of `i` means the corresponding value is between
+    (D_edge[i-1], D_edge[i]), where 'D' is either 'x' or 'y'.
+
+    .. versionadded:: 0.11.0
+
+    Examples
+    --------
+    >>> from scipy import stats
+
+    Calculate the counts with explicit bin-edges:
+
+    >>> x = [0.1, 0.1, 0.1, 0.6]
+    >>> y = [2.1, 2.6, 2.1, 2.1]
+    >>> binx = [0.0, 0.5, 1.0]
+    >>> biny = [2.0, 2.5, 3.0]
+    >>> ret = stats.binned_statistic_2d(x, y, None, 'count', bins=[binx, biny])
+    >>> ret.statistic
+    array([[2., 1.],
+           [1., 0.]])
+
+    The bin in which each sample is placed is given by the `binnumber`
+    returned parameter.  By default, these are the linearized bin indices:
+
+    >>> ret.binnumber
+    array([5, 6, 5, 9])
+
+    The bin indices can also be expanded into separate entries for each
+    dimension using the `expand_binnumbers` parameter:
+
+    >>> ret = stats.binned_statistic_2d(x, y, None, 'count', bins=[binx, biny],
+    ...                                 expand_binnumbers=True)
+    >>> ret.binnumber
+    array([[1, 1, 1, 2],
+           [1, 2, 1, 1]])
+
+    Which shows that the first three elements belong in the xbin 1, and the
+    fourth into xbin 2; and so on for y.
+
+    """
+
+    # This code is based on np.histogram2d
+    try:
+        N = len(bins)
+    except TypeError:
+        N = 1
+
+    if N != 1 and N != 2:
+        xedges = yedges = np.asarray(bins, float)
+        bins = [xedges, yedges]
+
+    medians, edges, binnumbers = binned_statistic_dd(
+        [x, y], values, statistic, bins, range,
+        expand_binnumbers=expand_binnumbers)
+
+    return BinnedStatistic2dResult(medians, edges[0], edges[1], binnumbers)
+
+
+BinnedStatisticddResult = namedtuple('BinnedStatisticddResult',
+                                     ('statistic', 'bin_edges',
+                                      'binnumber'))
+
+
+def binned_statistic_dd(sample, values, statistic='mean',
+                        bins=10, range=None, expand_binnumbers=False,
+                        binned_statistic_result=None):
+    """
+    Compute a multidimensional binned statistic for a set of data.
+
+    This is a generalization of a histogramdd function.  A histogram divides
+    the space into bins, and returns the count of the number of points in
+    each bin.  This function allows the computation of the sum, mean, median,
+    or other statistic of the values within each bin.
+
+    Parameters
+    ----------
+    sample : array_like
+        Data to histogram passed as a sequence of N arrays of length D, or
+        as an (N,D) array.
+    values : (N,) array_like or list of (N,) array_like
+        The data on which the statistic will be computed.  This must be
+        the same shape as `sample`, or a list of sequences - each with the
+        same shape as `sample`.  If `values` is such a list, the statistic
+        will be computed on each independently.
+    statistic : string or callable, optional
+        The statistic to compute (default is 'mean').
+        The following statistics are available:
+
+          * 'mean' : compute the mean of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'median' : compute the median of values for points within each
+            bin. Empty bins will be represented by NaN.
+          * 'count' : compute the count of points within each bin.  This is
+            identical to an unweighted histogram.  `values` array is not
+            referenced.
+          * 'sum' : compute the sum of values for points within each bin.
+            This is identical to a weighted histogram.
+          * 'std' : compute the standard deviation within each bin. This
+            is implicitly calculated with ddof=0. If the number of values
+            within a given bin is 0 or 1, the computed standard deviation value
+            will be 0 for the bin.
+          * 'min' : compute the minimum of values for points within each bin.
+            Empty bins will be represented by NaN.
+          * 'max' : compute the maximum of values for point within each bin.
+            Empty bins will be represented by NaN.
+          * function : a user-defined function which takes a 1D array of
+            values, and outputs a single numerical statistic. This function
+            will be called on the values in each bin.  Empty bins will be
+            represented by function([]), or NaN if this returns an error.
+
+    bins : sequence or positive int, optional
+        The bin specification must be in one of the following forms:
+
+          * A sequence of arrays describing the bin edges along each dimension.
+          * The number of bins for each dimension (nx, ny, ... = bins).
+          * The number of bins for all dimensions (nx = ny = ... = bins).
+    range : sequence, optional
+        A sequence of lower and upper bin edges to be used if the edges are
+        not given explicitly in `bins`. Defaults to the minimum and maximum
+        values along each dimension.
+    expand_binnumbers : bool, optional
+        'False' (default): the returned `binnumber` is a shape (N,) array of
+        linearized bin indices.
+        'True': the returned `binnumber` is 'unraveled' into a shape (D,N)
+        ndarray, where each row gives the bin numbers in the corresponding
+        dimension.
+        See the `binnumber` returned value, and the `Examples` section of
+        `binned_statistic_2d`.
+    binned_statistic_result : binnedStatisticddResult
+        Result of a previous call to the function in order to reuse bin edges
+        and bin numbers with new values and/or a different statistic.
+        To reuse bin numbers, `expand_binnumbers` must have been set to False
+        (the default)
+
+        .. versionadded:: 0.17.0
+
+    Returns
+    -------
+    statistic : ndarray, shape(nx1, nx2, nx3,...)
+        The values of the selected statistic in each two-dimensional bin.
+    bin_edges : list of ndarrays
+        A list of D arrays describing the (nxi + 1) bin edges for each
+        dimension.
+    binnumber : (N,) array of ints or (D,N) ndarray of ints
+        This assigns to each element of `sample` an integer that represents the
+        bin in which this observation falls.  The representation depends on the
+        `expand_binnumbers` argument.  See `Notes` for details.
+
+
+    See Also
+    --------
+    numpy.digitize, numpy.histogramdd, binned_statistic, binned_statistic_2d
+
+    Notes
+    -----
+    Binedges:
+    All but the last (righthand-most) bin is half-open in each dimension.  In
+    other words, if `bins` is ``[1, 2, 3, 4]``, then the first bin is
+    ``[1, 2)`` (including 1, but excluding 2) and the second ``[2, 3)``.  The
+    last bin, however, is ``[3, 4]``, which *includes* 4.
+
+    `binnumber`:
+    This returned argument assigns to each element of `sample` an integer that
+    represents the bin in which it belongs.  The representation depends on the
+    `expand_binnumbers` argument. If 'False' (default): The returned
+    `binnumber` is a shape (N,) array of linearized indices mapping each
+    element of `sample` to its corresponding bin (using row-major ordering).
+    If 'True': The returned `binnumber` is a shape (D,N) ndarray where
+    each row indicates bin placements for each dimension respectively.  In each
+    dimension, a binnumber of `i` means the corresponding value is between
+    (bin_edges[D][i-1], bin_edges[D][i]), for each dimension 'D'.
+
+    .. versionadded:: 0.11.0
+
+    Examples
+    --------
+    >>> from scipy import stats
+    >>> import matplotlib.pyplot as plt
+    >>> from mpl_toolkits.mplot3d import Axes3D
+
+    Take an array of 600 (x, y) coordinates as an example.
+    `binned_statistic_dd` can handle arrays of higher dimension `D`. But a plot
+    of dimension `D+1` is required.
+
+    >>> mu = np.array([0., 1.])
+    >>> sigma = np.array([[1., -0.5],[-0.5, 1.5]])
+    >>> multinormal = stats.multivariate_normal(mu, sigma)
+    >>> data = multinormal.rvs(size=600, random_state=235412)
+    >>> data.shape
+    (600, 2)
+
+    Create bins and count how many arrays fall in each bin:
+
+    >>> N = 60
+    >>> x = np.linspace(-3, 3, N)
+    >>> y = np.linspace(-3, 4, N)
+    >>> ret = stats.binned_statistic_dd(data, np.arange(600), bins=[x, y],
+    ...                                 statistic='count')
+    >>> bincounts = ret.statistic
+
+    Set the volume and the location of bars:
+
+    >>> dx = x[1] - x[0]
+    >>> dy = y[1] - y[0]
+    >>> x, y = np.meshgrid(x[:-1]+dx/2, y[:-1]+dy/2)
+    >>> z = 0
+
+    >>> bincounts = bincounts.ravel()
+    >>> x = x.ravel()
+    >>> y = y.ravel()
+
+    >>> fig = plt.figure()
+    >>> ax = fig.add_subplot(111, projection='3d')
+    >>> with np.errstate(divide='ignore'):   # silence random axes3d warning
+    ...     ax.bar3d(x, y, z, dx, dy, bincounts)
+
+    Reuse bin numbers and bin edges with new values:
+
+    >>> ret2 = stats.binned_statistic_dd(data, -np.arange(600),
+    ...                                  binned_statistic_result=ret,
+    ...                                  statistic='mean')
+    """
+    known_stats = ['mean', 'median', 'count', 'sum', 'std', 'min', 'max']
+    if not callable(statistic) and statistic not in known_stats:
+        raise ValueError('invalid statistic %r' % (statistic,))
+
+    try:
+        bins = index(bins)
+    except TypeError:
+        # bins is not an integer
+        pass
+    # If bins was an integer-like object, now it is an actual Python int.
+
+    # NOTE: for _bin_edges(), see e.g. gh-11365
+    if isinstance(bins, int) and not np.isfinite(sample).all():
+        raise ValueError('%r contains non-finite values.' % (sample,))
+
+    # `Ndim` is the number of dimensions (e.g. `2` for `binned_statistic_2d`)
+    # `Dlen` is the length of elements along each dimension.
+    # This code is based on np.histogramdd
+    try:
+        # `sample` is an ND-array.
+        Dlen, Ndim = sample.shape
+    except (AttributeError, ValueError):
+        # `sample` is a sequence of 1D arrays.
+        sample = np.atleast_2d(sample).T
+        Dlen, Ndim = sample.shape
+
+    # Store initial shape of `values` to preserve it in the output
+    values = np.asarray(values)
+    input_shape = list(values.shape)
+    # Make sure that `values` is 2D to iterate over rows
+    values = np.atleast_2d(values)
+    Vdim, Vlen = values.shape
+
+    # Make sure `values` match `sample`
+    if(statistic != 'count' and Vlen != Dlen):
+        raise AttributeError('The number of `values` elements must match the '
+                             'length of each `sample` dimension.')
+
+    try:
+        M = len(bins)
+        if M != Ndim:
+            raise AttributeError('The dimension of bins must be equal '
+                                 'to the dimension of the sample x.')
+    except TypeError:
+        bins = Ndim * [bins]
+
+    if binned_statistic_result is None:
+        nbin, edges, dedges = _bin_edges(sample, bins, range)
+        binnumbers = _bin_numbers(sample, nbin, edges, dedges)
+    else:
+        edges = binned_statistic_result.bin_edges
+        nbin = np.array([len(edges[i]) + 1 for i in builtins.range(Ndim)])
+        # +1 for outlier bins
+        dedges = [np.diff(edges[i]) for i in builtins.range(Ndim)]
+        binnumbers = binned_statistic_result.binnumber
+
+    result = np.empty([Vdim, nbin.prod()], float)
+
+    if statistic == 'mean':
+        result.fill(np.nan)
+        flatcount = np.bincount(binnumbers, None)
+        a = flatcount.nonzero()
+        for vv in builtins.range(Vdim):
+            flatsum = np.bincount(binnumbers, values[vv])
+            result[vv, a] = flatsum[a] / flatcount[a]
+    elif statistic == 'std':
+        result.fill(np.nan)
+        flatcount = np.bincount(binnumbers, None)
+        a = flatcount.nonzero()
+        for vv in builtins.range(Vdim):
+            flatsum = np.bincount(binnumbers, values[vv])
+            delta = values[vv] - flatsum[binnumbers] / flatcount[binnumbers]
+            std = np.sqrt(np.bincount(binnumbers, delta**2)[a] / flatcount[a])
+            result[vv, a] = std
+    elif statistic == 'count':
+        result.fill(0)
+        flatcount = np.bincount(binnumbers, None)
+        a = np.arange(len(flatcount))
+        result[:, a] = flatcount[np.newaxis, :]
+    elif statistic == 'sum':
+        result.fill(0)
+        for vv in builtins.range(Vdim):
+            flatsum = np.bincount(binnumbers, values[vv])
+            a = np.arange(len(flatsum))
+            result[vv, a] = flatsum
+    elif statistic == 'median':
+        result.fill(np.nan)
+        for vv in builtins.range(Vdim):
+            i = np.lexsort((values[vv], binnumbers))
+            _, j, counts = np.unique(binnumbers[i],
+                                     return_index=True, return_counts=True)
+            mid = j + (counts - 1) / 2
+            mid_a = values[vv, i][np.floor(mid).astype(int)]
+            mid_b = values[vv, i][np.ceil(mid).astype(int)]
+            medians = (mid_a + mid_b) / 2
+            result[vv, binnumbers[i][j]] = medians
+    elif statistic == 'min':
+        result.fill(np.nan)
+        for vv in builtins.range(Vdim):
+            i = np.argsort(values[vv])[::-1]  # Reversed so the min is last
+            result[vv, binnumbers[i]] = values[vv, i]
+    elif statistic == 'max':
+        result.fill(np.nan)
+        for vv in builtins.range(Vdim):
+            i = np.argsort(values[vv])
+            result[vv, binnumbers[i]] = values[vv, i]
+    elif callable(statistic):
+        with np.errstate(invalid='ignore'), suppress_warnings() as sup:
+            sup.filter(RuntimeWarning)
+            try:
+                null = statistic([])
+            except Exception:
+                null = np.nan
+        result.fill(null)
+        _calc_binned_statistic(Vdim, binnumbers, result, values, statistic)
+
+    # Shape into a proper matrix
+    result = result.reshape(np.append(Vdim, nbin))
+
+    # Remove outliers (indices 0 and -1 for each bin-dimension).
+    core = tuple([slice(None)] + Ndim * [slice(1, -1)])
+    result = result[core]
+
+    # Unravel binnumbers into an ndarray, each row the bins for each dimension
+    if(expand_binnumbers and Ndim > 1):
+        binnumbers = np.asarray(np.unravel_index(binnumbers, nbin))
+
+    if np.any(result.shape[1:] != nbin - 2):
+        raise RuntimeError('Internal Shape Error')
+
+    # Reshape to have output (`result`) match input (`values`) shape
+    result = result.reshape(input_shape[:-1] + list(nbin-2))
+
+    return BinnedStatisticddResult(result, edges, binnumbers)
+
+
+def _calc_binned_statistic(Vdim, bin_numbers, result, values, stat_func):
+    unique_bin_numbers = np.unique(bin_numbers)
+    for vv in builtins.range(Vdim):
+        bin_map = _create_binned_data(bin_numbers, unique_bin_numbers,
+                                      values, vv)
+        for i in unique_bin_numbers:
+            result[vv, i] = stat_func(np.array(bin_map[i]))
+
+
+def _create_binned_data(bin_numbers, unique_bin_numbers, values, vv):
+    """ Create hashmap of bin ids to values in bins
+    key: bin number
+    value: list of binned data
+    """
+    bin_map = dict()
+    for i in unique_bin_numbers:
+        bin_map[i] = []
+    for i in builtins.range(len(bin_numbers)):
+        bin_map[bin_numbers[i]].append(values[vv, i])
+    return bin_map
+
+
+def _bin_edges(sample, bins=None, range=None):
+    """ Create edge arrays
+    """
+    Dlen, Ndim = sample.shape
+
+    nbin = np.empty(Ndim, int)    # Number of bins in each dimension
+    edges = Ndim * [None]         # Bin edges for each dim (will be 2D array)
+    dedges = Ndim * [None]        # Spacing between edges (will be 2D array)
+
+    # Select range for each dimension
+    # Used only if number of bins is given.
+    if range is None:
+        smin = np.atleast_1d(np.array(sample.min(axis=0), float))
+        smax = np.atleast_1d(np.array(sample.max(axis=0), float))
+    else:
+        if len(range) != Ndim:
+            raise ValueError(
+                f"range given for {len(range)} dimensions; {Ndim} required")
+        smin = np.empty(Ndim)
+        smax = np.empty(Ndim)
+        for i in builtins.range(Ndim):
+            if range[i][1] < range[i][0]:
+                raise ValueError(
+                    "In {}range, start must be <= stop".format(
+                        f"dimension {i + 1} of " if Ndim > 1 else ""))
+            smin[i], smax[i] = range[i]
+
+    # Make sure the bins have a finite width.
+    for i in builtins.range(len(smin)):
+        if smin[i] == smax[i]:
+            smin[i] = smin[i] - .5
+            smax[i] = smax[i] + .5
+
+    # Preserve sample floating point precision in bin edges
+    edges_dtype = (sample.dtype if np.issubdtype(sample.dtype, np.floating)
+                   else float)
+
+    # Create edge arrays
+    for i in builtins.range(Ndim):
+        if np.isscalar(bins[i]):
+            nbin[i] = bins[i] + 2  # +2 for outlier bins
+            edges[i] = np.linspace(smin[i], smax[i], nbin[i] - 1,
+                                   dtype=edges_dtype)
+        else:
+            edges[i] = np.asarray(bins[i], edges_dtype)
+            nbin[i] = len(edges[i]) + 1  # +1 for outlier bins
+        dedges[i] = np.diff(edges[i])
+
+    nbin = np.asarray(nbin)
+
+    return nbin, edges, dedges
+
+
+def _bin_numbers(sample, nbin, edges, dedges):
+    """Compute the bin number each sample falls into, in each dimension
+    """
+    Dlen, Ndim = sample.shape
+
+    sampBin = [
+        np.digitize(sample[:, i], edges[i])
+        for i in range(Ndim)
+    ]
+
+    # Using `digitize`, values that fall on an edge are put in the right bin.
+    # For the rightmost bin, we want values equal to the right
+    # edge to be counted in the last bin, and not as an outlier.
+    for i in range(Ndim):
+        # Find the rounding precision
+        dedges_min = dedges[i].min()
+        if dedges_min == 0:
+            raise ValueError('The smallest edge difference is numerically 0.')
+        decimal = int(-np.log10(dedges_min)) + 6
+        # Find which points are on the rightmost edge.
+        on_edge = np.where((sample[:, i] >= edges[i][-1]) &
+                           (np.around(sample[:, i], decimal) ==
+                            np.around(edges[i][-1], decimal)))[0]
+        # Shift these points one bin to the left.
+        sampBin[i][on_edge] -= 1
+
+    # Compute the sample indices in the flattened statistic matrix.
+    binnumbers = np.ravel_multi_index(sampBin, nbin)
+
+    return binnumbers

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_binomtest.py

@@ -0,0 +1,371 @@
+from math import sqrt
+import numpy as np
+from scipy._lib._util import _validate_int
+from scipy.optimize import brentq
+from scipy.special import ndtri
+from ._discrete_distns import binom
+from ._common import ConfidenceInterval
+
+
+class BinomTestResult:
+    """
+    Result of `scipy.stats.binomtest`.
+
+    Attributes
+    ----------
+    k : int
+        The number of successes (copied from `binomtest` input).
+    n : int
+        The number of trials (copied from `binomtest` input).
+    alternative : str
+        Indicates the alternative hypothesis specified in the input
+        to `binomtest`.  It will be one of ``'two-sided'``, ``'greater'``,
+        or ``'less'``.
+    pvalue : float
+        The p-value of the hypothesis test.
+    proportion_estimate : float
+        The estimate of the proportion of successes.
+
+    """
+    def __init__(self, k, n, alternative, pvalue, proportion_estimate):
+        self.k = k
+        self.n = n
+        self.alternative = alternative
+        self.proportion_estimate = proportion_estimate
+        self.pvalue = pvalue
+
+    def __repr__(self):
+        s = ("BinomTestResult("
+             f"k={self.k}, "
+             f"n={self.n}, "
+             f"alternative={self.alternative!r}, "
+             f"proportion_estimate={self.proportion_estimate}, "
+             f"pvalue={self.pvalue})")
+        return s
+
+    def proportion_ci(self, confidence_level=0.95, method='exact'):
+        """
+        Compute the confidence interval for the estimated proportion.
+
+        Parameters
+        ----------
+        confidence_level : float, optional
+            Confidence level for the computed confidence interval
+            of the estimated proportion. Default is 0.95.
+        method : {'exact', 'wilson', 'wilsoncc'}, optional
+            Selects the method used to compute the confidence interval
+            for the estimate of the proportion:
+
+            'exact' :
+                Use the Clopper-Pearson exact method [1]_.
+            'wilson' :
+                Wilson's method, without continuity correction ([2]_, [3]_).
+            'wilsoncc' :
+                Wilson's method, with continuity correction ([2]_, [3]_).
+
+            Default is ``'exact'``.
+
+        Returns
+        -------
+        ci : ``ConfidenceInterval`` object
+            The object has attributes ``low`` and ``high`` that hold the
+            lower and upper bounds of the confidence interval.
+
+        References
+        ----------
+        .. [1] C. J. Clopper and E. S. Pearson, The use of confidence or
+               fiducial limits illustrated in the case of the binomial,
+               Biometrika, Vol. 26, No. 4, pp 404-413 (Dec. 1934).
+        .. [2] E. B. Wilson, Probable inference, the law of succession, and
+               statistical inference, J. Amer. Stat. Assoc., 22, pp 209-212
+               (1927).
+        .. [3] Robert G. Newcombe, Two-sided confidence intervals for the
+               single proportion: comparison of seven methods, Statistics
+               in Medicine, 17, pp 857-872 (1998).
+
+        Examples
+        --------
+        >>> from scipy.stats import binomtest
+        >>> result = binomtest(k=7, n=50, p=0.1)
+        >>> result.proportion_estimate
+        0.14
+        >>> result.proportion_ci()
+        ConfidenceInterval(low=0.05819170033997342, high=0.26739600249700846)
+        """
+        if method not in ('exact', 'wilson', 'wilsoncc'):
+            raise ValueError("method must be one of 'exact', 'wilson' or "
+                             "'wilsoncc'.")
+        if not (0 <= confidence_level <= 1):
+            raise ValueError('confidence_level must be in the interval '
+                             '[0, 1].')
+        if method == 'exact':
+            low, high = _binom_exact_conf_int(self.k, self.n,
+                                              confidence_level,
+                                              self.alternative)
+        else:
+            # method is 'wilson' or 'wilsoncc'
+            low, high = _binom_wilson_conf_int(self.k, self.n,
+                                               confidence_level,
+                                               self.alternative,
+                                               correction=method == 'wilsoncc')
+        return ConfidenceInterval(low=low, high=high)
+
+
+def _findp(func):
+    try:
+        p = brentq(func, 0, 1)
+    except RuntimeError:
+        raise RuntimeError('numerical solver failed to converge when '
+                           'computing the confidence limits') from None
+    except ValueError as exc:
+        raise ValueError('brentq raised a ValueError; report this to the '
+                         'SciPy developers') from exc
+    return p
+
+
+def _binom_exact_conf_int(k, n, confidence_level, alternative):
+    """
+    Compute the estimate and confidence interval for the binomial test.
+
+    Returns proportion, prop_low, prop_high
+    """
+    if alternative == 'two-sided':
+        alpha = (1 - confidence_level) / 2
+        if k == 0:
+            plow = 0.0
+        else:
+            plow = _findp(lambda p: binom.sf(k-1, n, p) - alpha)
+        if k == n:
+            phigh = 1.0
+        else:
+            phigh = _findp(lambda p: binom.cdf(k, n, p) - alpha)
+    elif alternative == 'less':
+        alpha = 1 - confidence_level
+        plow = 0.0
+        if k == n:
+            phigh = 1.0
+        else:
+            phigh = _findp(lambda p: binom.cdf(k, n, p) - alpha)
+    elif alternative == 'greater':
+        alpha = 1 - confidence_level
+        if k == 0:
+            plow = 0.0
+        else:
+            plow = _findp(lambda p: binom.sf(k-1, n, p) - alpha)
+        phigh = 1.0
+    return plow, phigh
+
+
+def _binom_wilson_conf_int(k, n, confidence_level, alternative, correction):
+    # This function assumes that the arguments have already been validated.
+    # In particular, `alternative` must be one of 'two-sided', 'less' or
+    # 'greater'.
+    p = k / n
+    if alternative == 'two-sided':
+        z = ndtri(0.5 + 0.5*confidence_level)
+    else:
+        z = ndtri(confidence_level)
+
+    # For reference, the formulas implemented here are from
+    # Newcombe (1998) (ref. [3] in the proportion_ci docstring).
+    denom = 2*(n + z**2)
+    center = (2*n*p + z**2)/denom
+    q = 1 - p
+    if correction:
+        if alternative == 'less' or k == 0:
+            lo = 0.0
+        else:
+            dlo = (1 + z*sqrt(z**2 - 2 - 1/n + 4*p*(n*q + 1))) / denom
+            lo = center - dlo
+        if alternative == 'greater' or k == n:
+            hi = 1.0
+        else:
+            dhi = (1 + z*sqrt(z**2 + 2 - 1/n + 4*p*(n*q - 1))) / denom
+            hi = center + dhi
+    else:
+        delta = z/denom * sqrt(4*n*p*q + z**2)
+        if alternative == 'less' or k == 0:
+            lo = 0.0
+        else:
+            lo = center - delta
+        if alternative == 'greater' or k == n:
+            hi = 1.0
+        else:
+            hi = center + delta
+
+    return lo, hi
+
+
+def binomtest(k, n, p=0.5, alternative='two-sided'):
+    """
+    Perform a test that the probability of success is p.
+
+    The binomial test [1]_ is a test of the null hypothesis that the
+    probability of success in a Bernoulli experiment is `p`.
+
+    Details of the test can be found in many texts on statistics, such
+    as section 24.5 of [2]_.
+
+    Parameters
+    ----------
+    k : int
+        The number of successes.
+    n : int
+        The number of trials.
+    p : float, optional
+        The hypothesized probability of success, i.e. the expected
+        proportion of successes.  The value must be in the interval
+        ``0 <= p <= 1``. The default value is ``p = 0.5``.
+    alternative : {'two-sided', 'greater', 'less'}, optional
+        Indicates the alternative hypothesis. The default value is
+        'two-sided'.
+
+    Returns
+    -------
+    result : `~scipy.stats._result_classes.BinomTestResult` instance
+        The return value is an object with the following attributes:
+
+        k : int
+            The number of successes (copied from `binomtest` input).
+        n : int
+            The number of trials (copied from `binomtest` input).
+        alternative : str
+            Indicates the alternative hypothesis specified in the input
+            to `binomtest`.  It will be one of ``'two-sided'``, ``'greater'``,
+            or ``'less'``.
+        pvalue : float
+            The p-value of the hypothesis test.
+        proportion_estimate : float
+            The estimate of the proportion of successes.
+
+        The object has the following methods:
+
+        proportion_ci(confidence_level=0.95, method='exact') :
+            Compute the confidence interval for ``proportion_estimate``.
+
+    Notes
+    -----
+    .. versionadded:: 1.7.0
+
+    References
+    ----------
+    .. [1] Binomial test, https://en.wikipedia.org/wiki/Binomial_test
+    .. [2] Jerrold H. Zar, Biostatistical Analysis (fifth edition),
+           Prentice Hall, Upper Saddle River, New Jersey USA (2010)
+
+    Examples
+    --------
+    >>> from scipy.stats import binomtest
+
+    A car manufacturer claims that no more than 10% of their cars are unsafe.
+    15 cars are inspected for safety, 3 were found to be unsafe. Test the
+    manufacturer's claim:
+
+    >>> result = binomtest(3, n=15, p=0.1, alternative='greater')
+    >>> result.pvalue
+    0.18406106910639114
+
+    The null hypothesis cannot be rejected at the 5% level of significance
+    because the returned p-value is greater than the critical value of 5%.
+
+    The estimated proportion is simply ``3/15``:
+
+    >>> result.proportion_estimate
+    0.2
+
+    We can use the `proportion_ci()` method of the result to compute the
+    confidence interval of the estimate:
+
+    >>> result.proportion_ci(confidence_level=0.95)
+    ConfidenceInterval(low=0.05684686759024681, high=1.0)
+
+    """
+    k = _validate_int(k, 'k', minimum=0)
+    n = _validate_int(n, 'n', minimum=1)
+    if k > n:
+        raise ValueError('k must not be greater than n.')
+
+    if not (0 <= p <= 1):
+        raise ValueError("p must be in range [0,1]")
+
+    if alternative not in ('two-sided', 'less', 'greater'):
+        raise ValueError("alternative not recognized; \n"
+                         "must be 'two-sided', 'less' or 'greater'")
+    if alternative == 'less':
+        pval = binom.cdf(k, n, p)
+    elif alternative == 'greater':
+        pval = binom.sf(k-1, n, p)
+    else:
+        # alternative is 'two-sided'
+        d = binom.pmf(k, n, p)
+        rerr = 1 + 1e-7
+        if k == p * n:
+            # special case as shortcut, would also be handled by `else` below
+            pval = 1.
+        elif k < p * n:
+            ix = _binary_search_for_binom_tst(lambda x1: -binom.pmf(x1, n, p),
+                                              -d*rerr, np.ceil(p * n), n)
+            # y is the number of terms between mode and n that are <= d*rerr.
+            # ix gave us the first term where a(ix) <= d*rerr < a(ix-1)
+            # if the first equality doesn't hold, y=n-ix. Otherwise, we
+            # need to include ix as well as the equality holds. Note that
+            # the equality will hold in very very rare situations due to rerr.
+            y = n - ix + int(d*rerr == binom.pmf(ix, n, p))
+            pval = binom.cdf(k, n, p) + binom.sf(n - y, n, p)
+        else:
+            ix = _binary_search_for_binom_tst(lambda x1: binom.pmf(x1, n, p),
+                                              d*rerr, 0, np.floor(p * n))
+            # y is the number of terms between 0 and mode that are <= d*rerr.
+            # we need to add a 1 to account for the 0 index.
+            # For comparing this with old behavior, see
+            # tst_binary_srch_for_binom_tst method in test_morestats.
+            y = ix + 1
+            pval = binom.cdf(y-1, n, p) + binom.sf(k-1, n, p)
+
+        pval = min(1.0, pval)
+
+    result = BinomTestResult(k=k, n=n, alternative=alternative,
+                             proportion_estimate=k/n, pvalue=pval)
+    return result
+
+
+def _binary_search_for_binom_tst(a, d, lo, hi):
+    """
+    Conducts an implicit binary search on a function specified by `a`.
+
+    Meant to be used on the binomial PMF for the case of two-sided tests
+    to obtain the value on the other side of the mode where the tail
+    probability should be computed. The values on either side of
+    the mode are always in order, meaning binary search is applicable.
+
+    Parameters
+    ----------
+    a : callable
+      The function over which to perform binary search. Its values
+      for inputs lo and hi should be in ascending order.
+    d : float
+      The value to search.
+    lo : int
+      The lower end of range to search.
+    hi : int
+      The higher end of the range to search.
+
+    Returns
+    ----------
+    int
+      The index, i between lo and hi
+      such that a(i)<=d<a(i+1)
+    """
+    while lo < hi:
+        mid = lo + (hi-lo)//2
+        midval = a(mid)
+        if midval < d:
+            lo = mid+1
+        elif midval > d:
+            hi = mid-1
+        else:
+            return mid
+    if a(lo) <= d:
+        return lo
+    else:
+        return lo-1

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_boost/__init__.py

@@ -0,0 +1,23 @@
+from scipy.stats._boost.beta_ufunc import (
+    _beta_pdf, _beta_cdf, _beta_sf, _beta_ppf,
+    _beta_isf, _beta_mean, _beta_variance,
+    _beta_skewness, _beta_kurtosis_excess,
+)
+
+from scipy.stats._boost.binom_ufunc import (
+    _binom_pdf, _binom_cdf, _binom_sf, _binom_ppf,
+    _binom_isf, _binom_mean, _binom_variance,
+    _binom_skewness, _binom_kurtosis_excess,
+)
+
+from scipy.stats._boost.nbinom_ufunc import (
+    _nbinom_pdf, _nbinom_cdf, _nbinom_sf, _nbinom_ppf,
+    _nbinom_isf, _nbinom_mean, _nbinom_variance,
+    _nbinom_skewness, _nbinom_kurtosis_excess,
+)
+
+from scipy.stats._boost.hypergeom_ufunc import (
+    _hypergeom_pdf, _hypergeom_cdf, _hypergeom_sf, _hypergeom_ppf,
+    _hypergeom_isf, _hypergeom_mean, _hypergeom_variance,
+    _hypergeom_skewness, _hypergeom_kurtosis_excess,
+)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_boost/setup.py

@@ -0,0 +1,60 @@
+import pathlib
+import sys
+
+
+def pre_build_hook(build_ext, ext):
+    from scipy._build_utils.compiler_helper import get_cxx_std_flag
+    std_flag = get_cxx_std_flag(build_ext._cxx_compiler)
+    if std_flag is not None:
+        ext.extra_compile_args.append(std_flag)
+
+
+def configuration(parent_package='', top_path=None):
+    from scipy._lib._boost_utils import _boost_dir
+    from scipy._build_utils import import_file
+    from numpy.distutils.misc_util import Configuration
+    import numpy as np
+    config = Configuration('_boost', parent_package, top_path)
+
+    DEFINES = [
+        # return nan instead of throwing
+        ('BOOST_MATH_DOMAIN_ERROR_POLICY', 'ignore_error'),
+        ('BOOST_MATH_EVALUATION_ERROR_POLICY', 'user_error'),
+        ('BOOST_MATH_OVERFLOW_ERROR_POLICY', 'user_error'),
+    ]
+    if sys.maxsize > 2**32:
+        # 32-bit machines lose too much precision with no promotion,
+        # so only set this policy for 64-bit machines
+        DEFINES += [('BOOST_MATH_PROMOTE_DOUBLE_POLICY', 'false')]
+    INCLUDES = [
+        'include/',
+        'src/',
+        np.get_include(),
+        _boost_dir(),
+    ]
+
+    # generate the PXD and PYX wrappers
+    boost_dir = pathlib.Path(__file__).parent
+    src_dir = boost_dir / 'src'
+    _klass_mapper = import_file(boost_dir / 'include', '_info')._klass_mapper
+    for s in _klass_mapper.values():
+        ext = config.add_extension(
+            f'{s.scipy_name}_ufunc',
+            sources=[f'{src_dir}/{s.scipy_name}_ufunc.cxx'],
+            include_dirs=INCLUDES,
+            define_macros=DEFINES,
+            language='c++',
+            depends=[
+                'include/func_defs.hpp',
+                'include/Templated_PyUFunc.hpp',
+            ],
+        )
+        # Add c++11/14 support:
+        ext._pre_build_hook = pre_build_hook
+
+    return config
+
+
+if __name__ == '__main__':
+    from numpy.distutils.core import setup
+    setup(**configuration(top_path='').todict())

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_bootstrap.py

@@ -0,0 +1,488 @@
+import warnings
+import numpy as np
+from scipy._lib._util import check_random_state
+from scipy.special import ndtr, ndtri
+from scipy._lib._util import rng_integers
+from dataclasses import make_dataclass
+from ._common import ConfidenceInterval
+from ._axis_nan_policy import _broadcast_concatenate
+
+
+class BootstrapDegenerateDistributionWarning(RuntimeWarning):
+    """
+    Warning generated by `bootstrap` when BCa method is used and
+    the bootstrap distribution is degenerate.
+    """
+
+    def __init__(self, msg=None):
+        if msg is None:
+            msg = ("The bootstrap distribution is degenerate; the "
+                   "confidence interval is not defined.")
+        self.args = (msg,)
+
+
+def _vectorize_statistic(statistic):
+    """Vectorize an n-sample statistic"""
+    # This is a little cleaner than np.nditer at the expense of some data
+    # copying: concatenate samples together, then use np.apply_along_axis
+    def stat_nd(*data, axis=0):
+        lengths = [sample.shape[axis] for sample in data]
+        split_indices = np.cumsum(lengths)[:-1]
+        z = _broadcast_concatenate(data, axis)
+
+        def stat_1d(z):
+            data = np.split(z, split_indices)
+            return statistic(*data)
+
+        return np.apply_along_axis(stat_1d, axis, z)[()]
+    return stat_nd
+
+
+def _jackknife_resample(sample, batch=None):
+    """Jackknife resample the sample. Only one-sample stats for now."""
+    n = sample.shape[-1]
+    batch_nominal = batch or n
+
+    for k in range(0, n, batch_nominal):
+        # col_start:col_end are the observations to remove
+        batch_actual = min(batch_nominal, n-k)
+
+        # jackknife - each row leaves out one observation
+        j = np.ones((batch_actual, n), dtype=bool)
+        np.fill_diagonal(j[:, k:k+batch_actual], False)
+        i = np.arange(n)
+        i = np.broadcast_to(i, (batch_actual, n))
+        i = i[j].reshape((batch_actual, n-1))
+
+        resamples = sample[..., i]
+        yield resamples
+
+
+def _bootstrap_resample(sample, n_resamples=None, random_state=None):
+    """Bootstrap resample the sample."""
+    n = sample.shape[-1]
+
+    # bootstrap - each row is a random resample of original observations
+    i = rng_integers(random_state, 0, n, (n_resamples, n))
+
+    resamples = sample[..., i]
+    return resamples
+
+
+def _percentile_of_score(a, score, axis):
+    """Vectorized, simplified `scipy.stats.percentileofscore`.
+
+    Unlike `stats.percentileofscore`, the percentile returned is a fraction
+    in [0, 1].
+    """
+    B = a.shape[axis]
+    return (a < score).sum(axis=axis) / B
+
+
+def _percentile_along_axis(theta_hat_b, alpha):
+    """`np.percentile` with different percentile for each slice."""
+    # the difference between _percentile_along_axis and np.percentile is that
+    # np.percentile gets _all_ the qs for each axis slice, whereas
+    # _percentile_along_axis gets the q corresponding with each axis slice
+    shape = theta_hat_b.shape[:-1]
+    alpha = np.broadcast_to(alpha, shape)
+    percentiles = np.zeros_like(alpha, dtype=np.float64)
+    for indices, alpha_i in np.ndenumerate(alpha):
+        if np.isnan(alpha_i):
+            # e.g. when bootstrap distribution has only one unique element
+            warnings.warn(BootstrapDegenerateDistributionWarning())
+            percentiles[indices] = np.nan
+        else:
+            theta_hat_b_i = theta_hat_b[indices]
+            percentiles[indices] = np.percentile(theta_hat_b_i, alpha_i)
+    return percentiles[()]  # return scalar instead of 0d array
+
+
+def _bca_interval(data, statistic, axis, alpha, theta_hat_b, batch):
+    """Bias-corrected and accelerated interval."""
+    # closely follows [2] "BCa Bootstrap CIs"
+    sample = data[0]  # only works with 1 sample statistics right now
+
+    # calculate z0_hat
+    theta_hat = np.asarray(statistic(sample, axis=axis))[..., None]
+    percentile = _percentile_of_score(theta_hat_b, theta_hat, axis=-1)
+    z0_hat = ndtri(percentile)
+
+    # calculate a_hat
+    theta_hat_i = []  # would be better to fill pre-allocated array
+    for jackknife_sample in _jackknife_resample(sample, batch):
+        theta_hat_i.append(statistic(jackknife_sample, axis=-1))
+    theta_hat_i = np.concatenate(theta_hat_i, axis=-1)
+    theta_hat_dot = theta_hat_i.mean(axis=-1, keepdims=True)
+    num = ((theta_hat_dot - theta_hat_i)**3).sum(axis=-1)
+    den = 6*((theta_hat_dot - theta_hat_i)**2).sum(axis=-1)**(3/2)
+    a_hat = num / den
+
+    # calculate alpha_1, alpha_2
+    z_alpha = ndtri(alpha)
+    z_1alpha = -z_alpha
+    num1 = z0_hat + z_alpha
+    alpha_1 = ndtr(z0_hat + num1/(1 - a_hat*num1))
+    num2 = z0_hat + z_1alpha
+    alpha_2 = ndtr(z0_hat + num2/(1 - a_hat*num2))
+    return alpha_1, alpha_2
+
+
+def _bootstrap_iv(data, statistic, vectorized, paired, axis, confidence_level,
+                  n_resamples, batch, method, random_state):
+    """Input validation and standardization for `bootstrap`."""
+
+    if vectorized not in {True, False}:
+        raise ValueError("`vectorized` must be `True` or `False`.")
+
+    if not vectorized:
+        statistic = _vectorize_statistic(statistic)
+
+    axis_int = int(axis)
+    if axis != axis_int:
+        raise ValueError("`axis` must be an integer.")
+
+    n_samples = 0
+    try:
+        n_samples = len(data)
+    except TypeError:
+        raise ValueError("`data` must be a sequence of samples.")
+
+    if n_samples == 0:
+        raise ValueError("`data` must contain at least one sample.")
+
+    data_iv = []
+    for sample in data:
+        sample = np.atleast_1d(sample)
+        if sample.shape[axis_int] <= 1:
+            raise ValueError("each sample in `data` must contain two or more "
+                             "observations along `axis`.")
+        sample = np.moveaxis(sample, axis_int, -1)
+        data_iv.append(sample)
+
+    if paired not in {True, False}:
+        raise ValueError("`paired` must be `True` or `False`.")
+
+    if paired:
+        n = data_iv[0].shape[-1]
+        for sample in data_iv[1:]:
+            if sample.shape[-1] != n:
+                message = ("When `paired is True`, all samples must have the "
+                           "same length along `axis`")
+                raise ValueError(message)
+
+        # to generate the bootstrap distribution for paired-sample statistics,
+        # resample the indices of the observations
+        def statistic(i, axis=-1, data=data_iv, unpaired_statistic=statistic):
+            data = [sample[..., i] for sample in data]
+            return unpaired_statistic(*data, axis=axis)
+
+        data_iv = [np.arange(n)]
+
+    confidence_level_float = float(confidence_level)
+
+    n_resamples_int = int(n_resamples)
+    if n_resamples != n_resamples_int or n_resamples_int <= 0:
+        raise ValueError("`n_resamples` must be a positive integer.")
+
+    if batch is None:
+        batch_iv = batch
+    else:
+        batch_iv = int(batch)
+        if batch != batch_iv or batch_iv <= 0:
+            raise ValueError("`batch` must be a positive integer or None.")
+
+    methods = {'percentile', 'basic', 'bca'}
+    method = method.lower()
+    if method not in methods:
+        raise ValueError(f"`method` must be in {methods}")
+
+    message = "`method = 'BCa' is only available for one-sample statistics"
+    if not paired and n_samples > 1 and method == 'bca':
+        raise ValueError(message)
+
+    random_state = check_random_state(random_state)
+
+    return (data_iv, statistic, vectorized, paired, axis_int,
+            confidence_level_float, n_resamples_int, batch_iv,
+            method, random_state)
+
+
+fields = ['confidence_interval', 'standard_error']
+BootstrapResult = make_dataclass("BootstrapResult", fields)
+
+
+def bootstrap(data, statistic, *, vectorized=True, paired=False, axis=0,
+              confidence_level=0.95, n_resamples=9999, batch=None,
+              method='BCa', random_state=None):
+    r"""
+    Compute a two-sided bootstrap confidence interval of a statistic.
+
+    When `method` is ``'percentile'``, a bootstrap confidence interval is
+    computed according to the following procedure.
+
+    1. Resample the data: for each sample in `data` and for each of
+       `n_resamples`, take a random sample of the original sample
+       (with replacement) of the same size as the original sample.
+
+    2. Compute the bootstrap distribution of the statistic: for each set of
+       resamples, compute the test statistic.
+
+    3. Determine the confidence interval: find the interval of the bootstrap
+       distribution that is
+
+       - symmetric about the median and
+       - contains `confidence_level` of the resampled statistic values.
+
+    While the ``'percentile'`` method is the most intuitive, it is rarely
+    used in practice. Two more common methods are available, ``'basic'``
+    ('reverse percentile') and ``'BCa'`` ('bias-corrected and accelerated');
+    they differ in how step 3 is performed.
+
+    If the samples in `data` are  taken at random from their respective
+    distributions :math:`n` times, the confidence interval returned by
+    `bootstrap` will contain the true value of the statistic for those
+    distributions approximately `confidence_level`:math:`\, \times \, n` times.
+
+    Parameters
+    ----------
+    data : sequence of array-like
+         Each element of data is a sample from an underlying distribution.
+    statistic : callable
+        Statistic for which the confidence interval is to be calculated.
+        `statistic` must be a callable that accepts ``len(data)`` samples
+        as separate arguments and returns the resulting statistic.
+        If `vectorized` is set ``True``,
+        `statistic` must also accept a keyword argument `axis` and be
+        vectorized to compute the statistic along the provided `axis`.
+    vectorized : bool, default: ``True``
+        If `vectorized` is set ``False``, `statistic` will not be passed
+        keyword argument `axis`, and is assumed to calculate the statistic
+        only for 1D samples.
+    paired : bool, default: ``False``
+        Whether the statistic treats corresponding elements of the samples
+        in `data` as paired.
+    axis : int, default: ``0``
+        The axis of the samples in `data` along which the `statistic` is
+        calculated.
+    confidence_level : float, default: ``0.95``
+        The confidence level of the confidence interval.
+    n_resamples : int, default: ``9999``
+        The number of resamples performed to form the bootstrap distribution
+        of the statistic.
+    batch : int, optional
+        The number of resamples to process in each vectorized call to
+        `statistic`. Memory usage is O(`batch`*``n``), where ``n`` is the
+        sample size. Default is ``None``, in which case ``batch = n_resamples``
+        (or ``batch = max(n_resamples, n)`` for ``method='BCa'``).
+    method : {'percentile', 'basic', 'bca'}, default: ``'BCa'``
+        Whether to return the 'percentile' bootstrap confidence interval
+        (``'percentile'``), the 'reverse' or the bias-corrected and accelerated
+        bootstrap confidence interval (``'BCa'``).
+        Note that only ``'percentile'`` and ``'basic'`` support multi-sample
+        statistics at this time.
+    random_state : {None, int, `numpy.random.Generator`,
+                    `numpy.random.RandomState`}, optional
+
+        Pseudorandom number generator state used to generate resamples.
+
+        If `random_state` is ``None`` (or `np.random`), the
+        `numpy.random.RandomState` singleton is used.
+        If `random_state` is an int, a new ``RandomState`` instance is used,
+        seeded with `random_state`.
+        If `random_state` is already a ``Generator`` or ``RandomState``
+        instance then that instance is used.
+
+    Returns
+    -------
+    res : BootstrapResult
+        An object with attributes:
+
+        confidence_interval : ConfidenceInterval
+            The bootstrap confidence interval as an instance of
+            `collections.namedtuple` with attributes `low` and `high`.
+        standard_error : float or ndarray
+            The bootstrap standard error, that is, the sample standard
+            deviation of the bootstrap distribution
+
+    Notes
+    -----
+    Elements of the confidence interval may be NaN for ``method='BCa'`` if
+    the bootstrap distribution is degenerate (e.g. all elements are identical).
+    In this case, consider using another `method` or inspecting `data` for
+    indications that other analysis may be more appropriate (e.g. all
+    observations are identical).
+
+    References
+    ----------
+    .. [1] B. Efron and R. J. Tibshirani, An Introduction to the Bootstrap,
+       Chapman & Hall/CRC, Boca Raton, FL, USA (1993)
+    .. [2] Nathaniel E. Helwig, "Bootstrap Confidence Intervals",
+       http://users.stat.umn.edu/~helwig/notes/bootci-Notes.pdf
+    .. [3] Bootstrapping (statistics), Wikipedia,
+       https://en.wikipedia.org/wiki/Bootstrapping_%28statistics%29
+
+    Examples
+    --------
+    Suppose we have sampled data from an unknown distribution.
+
+    >>> import numpy as np
+    >>> rng = np.random.default_rng()
+    >>> from scipy.stats import norm
+    >>> dist = norm(loc=2, scale=4)  # our "unknown" distribution
+    >>> data = dist.rvs(size=100, random_state=rng)
+
+    We are interested int the standard deviation of the distribution.
+
+    >>> std_true = dist.std()      # the true value of the statistic
+    >>> print(std_true)
+    4.0
+    >>> std_sample = np.std(data)  # the sample statistic
+    >>> print(std_sample)
+    3.9460644295563863
+
+    We can calculate a 90% confidence interval of the statistic using
+    `bootstrap`.
+
+    >>> from scipy.stats import bootstrap
+    >>> data = (data,)  # samples must be in a sequence
+    >>> res = bootstrap(data, np.std, confidence_level=0.9,
+    ...                 random_state=rng)
+    >>> print(res.confidence_interval)
+    ConfidenceInterval(low=3.57655333533867, high=4.382043696342881)
+
+    If we sample from the distribution 1000 times and form a bootstrap
+    confidence interval for each sample, the confidence interval
+    contains the true value of the statistic approximately 900 times.
+
+    >>> n_trials = 1000
+    >>> ci_contains_true_std = 0
+    >>> for i in range(n_trials):
+    ...    data = (dist.rvs(size=100, random_state=rng),)
+    ...    ci = bootstrap(data, np.std, confidence_level=0.9, n_resamples=1000,
+    ...                   random_state=rng).confidence_interval
+    ...    if ci[0] < std_true < ci[1]:
+    ...        ci_contains_true_std += 1
+    >>> print(ci_contains_true_std)
+    875
+
+    Rather than writing a loop, we can also determine the confidence intervals
+    for all 1000 samples at once.
+
+    >>> data = (dist.rvs(size=(n_trials, 100), random_state=rng),)
+    >>> res = bootstrap(data, np.std, axis=-1, confidence_level=0.9,
+    ...                 n_resamples=1000, random_state=rng)
+    >>> ci_l, ci_u = res.confidence_interval
+
+    Here, `ci_l` and `ci_u` contain the confidence interval for each of the
+    ``n_trials = 1000`` samples.
+
+    >>> print(ci_l[995:])
+    [3.77729695 3.75090233 3.45829131 3.34078217 3.48072829]
+    >>> print(ci_u[995:])
+    [4.88316666 4.86924034 4.32032996 4.2822427  4.59360598]
+
+    And again, approximately 90% contain the true value, ``std_true = 4``.
+
+    >>> print(np.sum((ci_l < std_true) & (std_true < ci_u)))
+    900
+
+    `bootstrap` can also be used to estimate confidence intervals of
+    multi-sample statistics, including those calculated by hypothesis
+    tests. `scipy.stats.mood` perform's Mood's test for equal scale parameters,
+    and it returns two outputs: a statistic, and a p-value. To get a
+    confidence interval for the test statistic, we first wrap
+    `scipy.stats.mood` in a function that accepts two sample arguments,
+    accepts an `axis` keyword argument, and returns only the statistic.
+
+    >>> from scipy.stats import mood
+    >>> def my_statistic(sample1, sample2, axis):
+    ...     statistic, _ = mood(sample1, sample2, axis=-1)
+    ...     return statistic
+
+    Here, we use the 'percentile' method with the default 95% confidence level.
+
+    >>> sample1 = norm.rvs(scale=1, size=100, random_state=rng)
+    >>> sample2 = norm.rvs(scale=2, size=100, random_state=rng)
+    >>> data = (sample1, sample2)
+    >>> res = bootstrap(data, my_statistic, method='basic', random_state=rng)
+    >>> print(mood(sample1, sample2)[0])  # element 0 is the statistic
+    -5.521109549096542
+    >>> print(res.confidence_interval)
+    ConfidenceInterval(low=-7.255994487314675, high=-4.016202624747605)
+
+    The bootstrap estimate of the standard error is also available.
+
+    >>> print(res.standard_error)
+    0.8344963846318795
+
+    Paired-sample statistics work, too. For example, consider the Pearson
+    correlation coefficient.
+
+    >>> from scipy.stats import pearsonr
+    >>> n = 100
+    >>> x = np.linspace(0, 10, n)
+    >>> y = x + rng.uniform(size=n)
+    >>> print(pearsonr(x, y)[0])  # element 0 is the statistic
+    0.9962357936065914
+
+    We wrap `pearsonr` so that it returns only the statistic.
+
+    >>> def my_statistic(x, y):
+    ...     return pearsonr(x, y)[0]
+
+    We call `bootstrap` using ``paired=True``.
+    Also, since ``my_statistic`` isn't vectorized to calculate the statistic
+    along a given axis, we pass in ``vectorized=False``.
+
+    >>> res = bootstrap((x, y), my_statistic, vectorized=False, paired=True,
+    ...                 random_state=rng)
+    >>> print(res.confidence_interval)
+    ConfidenceInterval(low=0.9950085825848624, high=0.9971212407917498)
+
+    """
+    # Input validation
+    args = _bootstrap_iv(data, statistic, vectorized, paired, axis,
+                         confidence_level, n_resamples, batch, method,
+                         random_state)
+    data, statistic, vectorized, paired, axis = args[:5]
+    confidence_level, n_resamples, batch, method, random_state = args[5:]
+
+    theta_hat_b = []
+
+    batch_nominal = batch or n_resamples
+
+    for k in range(0, n_resamples, batch_nominal):
+        batch_actual = min(batch_nominal, n_resamples-k)
+        # Generate resamples
+        resampled_data = []
+        for sample in data:
+            resample = _bootstrap_resample(sample, n_resamples=batch_actual,
+                                           random_state=random_state)
+            resampled_data.append(resample)
+
+        # Compute bootstrap distribution of statistic
+        theta_hat_b.append(statistic(*resampled_data, axis=-1))
+    theta_hat_b = np.concatenate(theta_hat_b, axis=-1)
+
+    # Calculate percentile interval
+    alpha = (1 - confidence_level)/2
+    if method == 'bca':
+        interval = _bca_interval(data, statistic, axis=-1, alpha=alpha,
+                                 theta_hat_b=theta_hat_b, batch=batch)
+        percentile_fun = _percentile_along_axis
+    else:
+        interval = alpha, 1-alpha
+
+        def percentile_fun(a, q):
+            return np.percentile(a=a, q=q, axis=-1)
+
+    # Calculate confidence interval of statistic
+    ci_l = percentile_fun(theta_hat_b, interval[0]*100)
+    ci_u = percentile_fun(theta_hat_b, interval[1]*100)
+    if method == 'basic':  # see [3]
+        theta_hat = statistic(*data, axis=-1)
+        ci_l, ci_u = 2*theta_hat - ci_u, 2*theta_hat - ci_l
+
+    return BootstrapResult(confidence_interval=ConfidenceInterval(ci_l, ci_u),
+                           standard_error=np.std(theta_hat_b, ddof=1, axis=-1))

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_common.py

@@ -0,0 +1,6 @@
+
+from collections import namedtuple
+
+
+ConfidenceInterval = namedtuple("ConfidenceInterval", ["low", "high"])
+ConfidenceInterval. __doc__ = "Class for confidence intervals."

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_constants.py

@@ -0,0 +1,31 @@
+"""
+Statistics-related constants.
+
+"""
+import numpy as np
+
+
+# The smallest representable positive number such that 1.0 + _EPS != 1.0.
+_EPS = np.finfo(float).eps
+
+# The largest [in magnitude] usable floating value.
+_XMAX = np.finfo(float).max
+
+# The log of the largest usable floating value; useful for knowing
+# when exp(something) will overflow
+_LOGXMAX = np.log(_XMAX)
+
+# The smallest [in magnitude] usable floating value.
+_XMIN = np.finfo(float).tiny
+
+# -special.psi(1)
+_EULER = 0.577215664901532860606512090082402431042
+
+# special.zeta(3, 1)  Apery's constant
+_ZETA3 = 1.202056903159594285399738161511449990765
+
+# sqrt(2/pi)
+_SQRT_2_OVER_PI = 0.7978845608028654
+
+# log(sqrt(2/pi))
+_LOG_SQRT_2_OVER_PI = -0.22579135264472744

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_crosstab.py

@@ -0,0 +1,194 @@
+import numpy as np
+from scipy.sparse import coo_matrix
+
+
+def crosstab(*args, levels=None, sparse=False):
+    """
+    Return table of counts for each possible unique combination in ``*args``.
+
+    When ``len(args) > 1``, the array computed by this function is
+    often referred to as a *contingency table* [1]_.
+
+    The arguments must be sequences with the same length.  The second return
+    value, `count`, is an integer array with ``len(args)`` dimensions.  If
+    `levels` is None, the shape of `count` is ``(n0, n1, ...)``, where ``nk``
+    is the number of unique elements in ``args[k]``.
+
+    Parameters
+    ----------
+    args : sequences
+        A sequence of sequences whose unique aligned elements are to be
+        counted.  The sequences in args must all be the same length.
+    levels : sequence, optional
+        If `levels` is given, it must be a sequence that is the same length as
+        `args`.  Each element in `levels` is either a sequence or None.  If it
+        is a sequence, it gives the values in the corresponding sequence in
+        `args` that are to be counted.  If any value in the sequences in `args`
+        does not occur in the corresponding sequence in `levels`, that value
+        is ignored and not counted in the returned array `count`.  The default
+        value of `levels` for ``args[i]`` is ``np.unique(args[i])``
+    sparse : bool, optional
+        If True, return a sparse matrix.  The matrix will be an instance of
+        the `scipy.sparse.coo_matrix` class.  Because SciPy's sparse matrices
+        must be 2-d, only two input sequences are allowed when `sparse` is
+        True.  Default is False.
+
+    Returns
+    -------
+    elements : tuple of numpy.ndarrays.
+        Tuple of length ``len(args)`` containing the arrays of elements that
+        are counted in `count`.  These can be interpreted as the labels of
+        the corresponding dimensions of `count`.
+        If `levels` was given, then if ``levels[i]`` is not None,
+        ``elements[i]`` will hold the values given in ``levels[i]``.
+    count : numpy.ndarray or scipy.sparse.coo_matrix
+        Counts of the unique elements in ``zip(*args)``, stored in an array.
+        Also known as a *contingency table* when ``len(args) > 1``.
+
+    See Also
+    --------
+    numpy.unique
+
+    Notes
+    -----
+    .. versionadded:: 1.7.0
+
+    References
+    ----------
+    .. [1] "Contingency table", http://en.wikipedia.org/wiki/Contingency_table
+
+    Examples
+    --------
+    >>> from scipy.stats.contingency import crosstab
+
+    Given the lists `a` and `x`, create a contingency table that counts the
+    frequencies of the corresponding pairs.
+
+    >>> a = ['A', 'B', 'A', 'A', 'B', 'B', 'A', 'A', 'B', 'B']
+    >>> x = ['X', 'X', 'X', 'Y', 'Z', 'Z', 'Y', 'Y', 'Z', 'Z']
+    >>> (avals, xvals), count = crosstab(a, x)
+    >>> avals
+    array(['A', 'B'], dtype='<U1')
+    >>> xvals
+    array(['X', 'Y', 'Z'], dtype='<U1')
+    >>> count
+    array([[2, 3, 0],
+           [1, 0, 4]])
+
+    So `('A', 'X')` occurs twice, `('A', 'Y')` occurs three times, etc.
+
+    Higher dimensional contingency tables can be created.
+
+    >>> p = [0, 0, 0, 0, 1, 1, 1, 0, 0, 1]
+    >>> (avals, xvals, pvals), count = crosstab(a, x, p)
+    >>> count
+    array([[[2, 0],
+            [2, 1],
+            [0, 0]],
+           [[1, 0],
+            [0, 0],
+            [1, 3]]])
+    >>> count.shape
+    (2, 3, 2)
+
+    The values to be counted can be set by using the `levels` argument.
+    It allows the elements of interest in each input sequence to be
+    given explicitly instead finding the unique elements of the sequence.
+
+    For example, suppose one of the arguments is an array containing the
+    answers to a survey question, with integer values 1 to 4.  Even if the
+    value 1 does not occur in the data, we want an entry for it in the table.
+
+    >>> q1 = [2, 3, 3, 2, 4, 4, 2, 3, 4, 4, 4, 3, 3, 3, 4]  # 1 does not occur.
+    >>> q2 = [4, 4, 2, 2, 2, 4, 1, 1, 2, 2, 4, 2, 2, 2, 4]  # 3 does not occur.
+    >>> options = [1, 2, 3, 4]
+    >>> vals, count = crosstab(q1, q2, levels=(options, options))
+    >>> count
+    array([[0, 0, 0, 0],
+           [1, 1, 0, 1],
+           [1, 4, 0, 1],
+           [0, 3, 0, 3]])
+
+    If `levels` is given, but an element of `levels` is None, the unique values
+    of the corresponding argument are used. For example,
+
+    >>> vals, count = crosstab(q1, q2, levels=(None, options))
+    >>> vals
+    [array([2, 3, 4]), [1, 2, 3, 4]]
+    >>> count
+    array([[1, 1, 0, 1],
+           [1, 4, 0, 1],
+           [0, 3, 0, 3]])
+
+    If we want to ignore the pairs where 4 occurs in ``q2``, we can
+    give just the values [1, 2] to `levels`, and the 4 will be ignored:
+
+    >>> vals, count = crosstab(q1, q2, levels=(None, [1, 2]))
+    >>> vals
+    [array([2, 3, 4]), [1, 2]]
+    >>> count
+    array([[1, 1],
+           [1, 4],
+           [0, 3]])
+
+    Finally, let's repeat the first example, but return a sparse matrix:
+
+    >>> (avals, xvals), count = crosstab(a, x, sparse=True)
+    >>> count
+    <2x3 sparse matrix of type '<class 'numpy.int64'>'
+            with 4 stored elements in COOrdinate format>
+    >>> count.A
+    array([[2, 3, 0],
+           [1, 0, 4]])
+
+    """
+    nargs = len(args)
+    if nargs == 0:
+        raise TypeError("At least one input sequence is required.")
+
+    len0 = len(args[0])
+    if not all(len(a) == len0 for a in args[1:]):
+        raise ValueError("All input sequences must have the same length.")
+
+    if sparse and nargs != 2:
+        raise ValueError("When `sparse` is True, only two input sequences "
+                         "are allowed.")
+
+    if levels is None:
+        # Call np.unique with return_inverse=True on each argument.
+        actual_levels, indices = zip(*[np.unique(a, return_inverse=True)
+                                       for a in args])
+    else:
+        # `levels` is not None...
+        if len(levels) != nargs:
+            raise ValueError('len(levels) must equal the number of input '
+                             'sequences')
+
+        args = [np.asarray(arg) for arg in args]
+        mask = np.zeros((nargs, len0), dtype=np.bool_)
+        inv = np.zeros((nargs, len0), dtype=np.intp)
+        actual_levels = []
+        for k, (levels_list, arg) in enumerate(zip(levels, args)):
+            if levels_list is None:
+                levels_list, inv[k, :] = np.unique(arg, return_inverse=True)
+                mask[k, :] = True
+            else:
+                q = arg == np.asarray(levels_list).reshape(-1, 1)
+                mask[k, :] = np.any(q, axis=0)
+                qnz = q.T.nonzero()
+                inv[k, qnz[0]] = qnz[1]
+            actual_levels.append(levels_list)
+
+        mask_all = mask.all(axis=0)
+        indices = tuple(inv[:, mask_all])
+
+    if sparse:
+        count = coo_matrix((np.ones(len(indices[0]), dtype=int),
+                            (indices[0], indices[1])))
+        count.sum_duplicates()
+    else:
+        shape = [len(u) for u in actual_levels]
+        count = np.zeros(shape, dtype=int)
+        np.add.at(count, indices, 1)
+
+    return actual_levels, count

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_distr_params.py

@@ -0,0 +1,274 @@
+"""
+Sane parameters for stats.distributions.
+"""
+import numpy as np
+
+distcont = [
+    ['alpha', (3.5704770516650459,)],
+    ['anglit', ()],
+    ['arcsine', ()],
+    ['argus', (1.0,)],
+    ['beta', (2.3098496451481823, 0.62687954300963677)],
+    ['betaprime', (5, 6)],
+    ['bradford', (0.29891359763170633,)],
+    ['burr', (10.5, 4.3)],
+    ['burr12', (10, 4)],
+    ['cauchy', ()],
+    ['chi', (78,)],
+    ['chi2', (55,)],
+    ['cosine', ()],
+    ['crystalball', (2.0, 3.0)],
+    ['dgamma', (1.1023326088288166,)],
+    ['dweibull', (2.0685080649914673,)],
+    ['erlang', (10,)],
+    ['expon', ()],
+    ['exponnorm', (1.5,)],
+    ['exponpow', (2.697119160358469,)],
+    ['exponweib', (2.8923945291034436, 1.9505288745913174)],
+    ['f', (29, 18)],
+    ['fatiguelife', (29,)],   # correction numargs = 1
+    ['fisk', (3.0857548622253179,)],
+    ['foldcauchy', (4.7164673455831894,)],
+    ['foldnorm', (1.9521253373555869,)],
+    ['gamma', (1.9932305483800778,)],
+    ['gausshyper', (13.763771604130699, 3.1189636648681431,
+                    2.5145980350183019, 5.1811649903971615)],  # veryslow
+    ['genexpon', (9.1325976465418908, 16.231956600590632, 3.2819552690843983)],
+    ['genextreme', (-0.1,)],
+    ['gengamma', (4.4162385429431925, 3.1193091679242761)],
+    ['gengamma', (4.4162385429431925, -3.1193091679242761)],
+    ['genhalflogistic', (0.77274727809929322,)],
+    ['genhyperbolic', (0.5, 1.5, -0.5,)],
+    ['geninvgauss', (2.3, 1.5)],
+    ['genlogistic', (0.41192440799679475,)],
+    ['gennorm', (1.2988442399460265,)],
+    ['halfgennorm', (0.6748054997000371,)],
+    ['genpareto', (0.1,)],   # use case with finite moments
+    ['gilbrat', ()],
+    ['gompertz', (0.94743713075105251,)],
+    ['gumbel_l', ()],
+    ['gumbel_r', ()],
+    ['halfcauchy', ()],
+    ['halflogistic', ()],
+    ['halfnorm', ()],
+    ['hypsecant', ()],
+    ['invgamma', (4.0668996136993067,)],
+    ['invgauss', (0.14546264555347513,)],
+    ['invweibull', (10.58,)],
+    ['johnsonsb', (4.3172675099141058, 3.1837781130785063)],
+    ['johnsonsu', (2.554395574161155, 2.2482281679651965)],
+    ['kappa4', (0.0, 0.0)],
+    ['kappa4', (-0.1, 0.1)],
+    ['kappa4', (0.0, 0.1)],
+    ['kappa4', (0.1, 0.0)],
+    ['kappa3', (1.0,)],
+    ['ksone', (1000,)],  # replace 22 by 100 to avoid failing range, ticket 956
+    ['kstwo', (10,)],
+    ['kstwobign', ()],
+    ['laplace', ()],
+    ['laplace_asymmetric', (2,)],
+    ['levy', ()],
+    ['levy_l', ()],
+    ['levy_stable', (1.8, -0.5)],
+    ['loggamma', (0.41411931826052117,)],
+    ['logistic', ()],
+    ['loglaplace', (3.2505926592051435,)],
+    ['lognorm', (0.95368226960575331,)],
+    ['loguniform', (0.01, 1.25)],
+    ['lomax', (1.8771398388773268,)],
+    ['maxwell', ()],
+    ['mielke', (10.4, 4.6)],
+    ['moyal', ()],
+    ['nakagami', (4.9673794866666237,)],
+    ['ncf', (27, 27, 0.41578441799226107)],
+    ['nct', (14, 0.24045031331198066)],
+    ['ncx2', (21, 1.0560465975116415)],
+    ['norm', ()],
+    ['norminvgauss', (1.25, 0.5)],
+    ['pareto', (2.621716532144454,)],
+    ['pearson3', (0.1,)],
+    ['powerlaw', (1.6591133289905851,)],
+    ['powerlognorm', (2.1413923530064087, 0.44639540782048337)],
+    ['powernorm', (4.4453652254590779,)],
+    ['rayleigh', ()],
+    ['rdist', (1.6,)],
+    ['recipinvgauss', (0.63004267809369119,)],
+    ['reciprocal', (0.01, 1.25)],
+    ['rice', (0.7749725210111873,)],
+    ['semicircular', ()],
+    ['skewcauchy', (0.5,)],
+    ['skewnorm', (4.0,)],
+    ['studentized_range', (3.0, 10.0)],
+    ['t', (2.7433514990818093,)],
+    ['trapezoid', (0.2, 0.8)],
+    ['triang', (0.15785029824528218,)],
+    ['truncexpon', (4.6907725456810478,)],
+    ['truncnorm', (-1.0978730080013919, 2.7306754109031979)],
+    ['truncnorm', (0.1, 2.)],
+    ['tukeylambda', (3.1321477856738267,)],
+    ['uniform', ()],
+    ['vonmises', (3.9939042581071398,)],
+    ['vonmises_line', (3.9939042581071398,)],
+    ['wald', ()],
+    ['weibull_max', (2.8687961709100187,)],
+    ['weibull_min', (1.7866166930421596,)],
+    ['wrapcauchy', (0.031071279018614728,)]]
+
+
+distdiscrete = [
+    ['bernoulli',(0.3,)],
+    ['betabinom', (5, 2.3, 0.63)],
+    ['binom', (5, 0.4)],
+    ['boltzmann',(1.4, 19)],
+    ['dlaplace', (0.8,)],  # 0.5
+    ['geom', (0.5,)],
+    ['hypergeom',(30, 12, 6)],
+    ['hypergeom',(21,3,12)],  # numpy.random (3,18,12) numpy ticket:921
+    ['hypergeom',(21,18,11)],  # numpy.random (18,3,11) numpy ticket:921
+    ['nchypergeom_fisher', (140, 80, 60, 0.5)],
+    ['nchypergeom_wallenius', (140, 80, 60, 0.5)],
+    ['logser', (0.6,)],  # re-enabled, numpy ticket:921
+    ['nbinom', (0.4, 0.4)],  # from tickets: 583
+    ['nbinom', (5, 0.5)],
+    ['planck', (0.51,)],   # 4.1
+    ['poisson', (0.6,)],
+    ['randint', (7, 31)],
+    ['skellam', (15, 8)],
+    ['zipf', (6.5,)],
+    ['zipfian', (0.75, 15)],
+    ['zipfian', (1.25, 10)],
+    ['yulesimon', (11.0,)],
+    ['nhypergeom', (20, 7, 1)]
+]
+
+
+invdistdiscrete = [
+    # In each of the following, at least one shape parameter is invalid
+    ['hypergeom', (3, 3, 4)],
+    ['nhypergeom', (5, 2, 8)],
+    ['nchypergeom_fisher', (3, 3, 4, 1)],
+    ['nchypergeom_wallenius', (3, 3, 4, 1)],
+    ['bernoulli', (1.5, )],
+    ['binom', (10, 1.5)],
+    ['betabinom', (10, -0.4, -0.5)],
+    ['boltzmann', (-1, 4)],
+    ['dlaplace', (-0.5, )],
+    ['geom', (1.5, )],
+    ['logser', (1.5, )],
+    ['nbinom', (10, 1.5)],
+    ['planck', (-0.5, )],
+    ['poisson', (-0.5, )],
+    ['randint', (5, 2)],
+    ['skellam', (-5, -2)],
+    ['zipf', (-2, )],
+    ['yulesimon', (-2, )],
+    ['zipfian', (-0.75, 15)]
+]
+
+
+invdistcont = [
+    # In each of the following, at least one shape parameter is invalid
+    ['alpha', (-1, )],
+    ['anglit', ()],
+    ['arcsine', ()],
+    ['argus', (-1, )],
+    ['beta', (-2, 2)],
+    ['betaprime', (-2, 2)],
+    ['bradford', (-1, )],
+    ['burr', (-1, 1)],
+    ['burr12', (-1, 1)],
+    ['cauchy', ()],
+    ['chi', (-1, )],
+    ['chi2', (-1, )],
+    ['cosine', ()],
+    ['crystalball', (-1, 2)],
+    ['dgamma', (-1, )],
+    ['dweibull', (-1, )],
+    ['erlang', (-1, )],
+    ['expon', ()],
+    ['exponnorm', (-1, )],
+    ['exponweib', (1, -1)],
+    ['exponpow', (-1, )],
+    ['f', (10, -10)],
+    ['fatiguelife', (-1, )],
+    ['fisk', (-1, )],
+    ['foldcauchy', (-1, )],
+    ['foldnorm', (-1, )],
+    ['genlogistic', (-1, )],
+    ['gennorm', (-1, )],
+    ['genpareto', (np.inf, )],
+    ['genexpon', (1, 2, -3)],
+    ['genextreme', (np.inf, )],
+    ['genhyperbolic', (0.5, -0.5, -1.5,)],
+    ['gausshyper', (1, 2, 3, -4)],
+    ['gamma', (-1, )],
+    ['gengamma', (-1, 0)],
+    ['genhalflogistic', (-1, )],
+    ['geninvgauss', (1, 0)],
+    ['gilbrat', ()],
+    ['gompertz', (-1, )],
+    ['gumbel_r', ()],
+    ['gumbel_l', ()],
+    ['halfcauchy', ()],
+    ['halflogistic', ()],
+    ['halfnorm', ()],
+    ['halfgennorm', (-1, )],
+    ['hypsecant', ()],
+    ['invgamma', (-1, )],
+    ['invgauss', (-1, )],
+    ['invweibull', (-1, )],
+    ['johnsonsb', (1, -2)],
+    ['johnsonsu', (1, -2)],
+    ['kappa4', (np.nan, 0)],
+    ['kappa3', (-1, )],
+    ['ksone', (-1, )],
+    ['kstwo', (-1, )],
+    ['kstwobign', ()],
+    ['laplace', ()],
+    ['laplace_asymmetric', (-1, )],
+    ['levy', ()],
+    ['levy_l', ()],
+    ['levy_stable', (-1, 1)],
+    ['logistic', ()],
+    ['loggamma', (-1, )],
+    ['loglaplace', (-1, )],
+    ['lognorm', (-1, )],
+    ['loguniform', (10, 5)],
+    ['lomax', (-1, )],
+    ['maxwell', ()],
+    ['mielke', (1, -2)],
+    ['moyal', ()],
+    ['nakagami', (-1, )],
+    ['ncx2', (-1, 2)],
+    ['ncf', (10, 20, -1)],
+    ['nct', (-1, 2)],
+    ['norm', ()],
+    ['norminvgauss', (5, -10)],
+    ['pareto', (-1, )],
+    ['pearson3', (np.nan, )],
+    ['powerlaw', (-1, )],
+    ['powerlognorm', (1, -2)],
+    ['powernorm', (-1, )],
+    ['rdist', (-1, )],
+    ['rayleigh', ()],
+    ['rice', (-1, )],
+    ['recipinvgauss', (-1, )],
+    ['semicircular', ()],
+    ['skewnorm', (np.inf, )],
+    ['studentized_range', (-1, 1)],
+    ['t', (-1, )],
+    ['trapezoid', (0, 2)],
+    ['triang', (2, )],
+    ['truncexpon', (-1, )],
+    ['truncnorm', (10, 5)],
+    ['tukeylambda', (np.nan, )],
+    ['uniform', ()],
+    ['vonmises', (-1, )],
+    ['vonmises_line', (-1, )],
+    ['wald', ()],
+    ['weibull_min', (-1, )],
+    ['weibull_max', (-1, )],
+    ['wrapcauchy', (2, )],
+    ['reciprocal', (15, 10)],
+    ['skewcauchy', (2, )]
+]

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_entropy.py

@@ -0,0 +1,340 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Apr  2 09:06:05 2021
+
+@author: matth
+"""
+
+from __future__ import annotations
+import math
+import numpy as np
+from scipy import special
+from typing import Optional, Union
+
+__all__ = ['entropy', 'differential_entropy']
+
+
+def entropy(pk: np.typing.ArrayLike,
+            qk: Optional[np.typing.ArrayLike] = None,
+            base: Optional[float] = None,
+            axis: int = 0
+            ) -> Union[np.number, np.ndarray]:
+    """Calculate the entropy of a distribution for given probability values.
+
+    If only probabilities `pk` are given, the entropy is calculated as
+    ``S = -sum(pk * log(pk), axis=axis)``.
+
+    If `qk` is not None, then compute the Kullback-Leibler divergence
+    ``S = sum(pk * log(pk / qk), axis=axis)``.
+
+    This routine will normalize `pk` and `qk` if they don't sum to 1.
+
+    Parameters
+    ----------
+    pk : array_like
+        Defines the (discrete) distribution. Along each axis-slice of ``pk``,
+        element ``i`` is the  (possibly unnormalized) probability of event
+        ``i``.
+    qk : array_like, optional
+        Sequence against which the relative entropy is computed. Should be in
+        the same format as `pk`.
+    base : float, optional
+        The logarithmic base to use, defaults to ``e`` (natural logarithm).
+    axis: int, optional
+        The axis along which the entropy is calculated. Default is 0.
+
+    Returns
+    -------
+    S : {float, array_like}
+        The calculated entropy.
+
+    Examples
+    --------
+
+    >>> from scipy.stats import entropy
+
+    Bernoulli trial with different p.
+    The outcome of a fair coin is the most uncertain:
+
+    >>> entropy([1/2, 1/2], base=2)
+    1.0
+
+    The outcome of a biased coin is less uncertain:
+
+    >>> entropy([9/10, 1/10], base=2)
+    0.46899559358928117
+
+    Relative entropy:
+
+    >>> entropy([1/2, 1/2], qk=[9/10, 1/10])
+    0.5108256237659907
+
+    """
+    if base is not None and base <= 0:
+        raise ValueError("`base` must be a positive number or `None`.")
+
+    pk = np.asarray(pk)
+    pk = 1.0*pk / np.sum(pk, axis=axis, keepdims=True)
+    if qk is None:
+        vec = special.entr(pk)
+    else:
+        qk = np.asarray(qk)
+        pk, qk = np.broadcast_arrays(pk, qk)
+        qk = 1.0*qk / np.sum(qk, axis=axis, keepdims=True)
+        vec = special.rel_entr(pk, qk)
+    S = np.sum(vec, axis=axis)
+    if base is not None:
+        S /= np.log(base)
+    return S
+
+
+def differential_entropy(
+    values: np.typing.ArrayLike,
+    *,
+    window_length: Optional[int] = None,
+    base: Optional[float] = None,
+    axis: int = 0,
+    method: str = "auto",
+) -> Union[np.number, np.ndarray]:
+    r"""Given a sample of a distribution, estimate the differential entropy.
+
+    Several estimation methods are available using the `method` parameter. By
+    default, a method is selected based the size of the sample.
+
+    Parameters
+    ----------
+    values : sequence
+        Sample from a continuous distribution.
+    window_length : int, optional
+        Window length for computing Vasicek estimate. Must be an integer
+        between 1 and half of the sample size. If ``None`` (the default), it
+        uses the heuristic value
+
+        .. math::
+            \left \lfloor \sqrt{n} + 0.5 \right \rfloor
+
+        where :math:`n` is the sample size. This heuristic was originally
+        proposed in [2]_ and has become common in the literature.
+    base : float, optional
+        The logarithmic base to use, defaults to ``e`` (natural logarithm).
+    axis : int, optional
+        The axis along which the differential entropy is calculated.
+        Default is 0.
+    method : {'vasicek', 'van es', 'ebrahimi', 'correa', 'auto'}, optional
+        The method used to estimate the differential entropy from the sample.
+        Default is ``'auto'``.  See Notes for more information.
+
+    Returns
+    -------
+    entropy : float
+        The calculated differential entropy.
+
+    Notes
+    -----
+    This function will converge to the true differential entropy in the limit
+
+    .. math::
+        n \to \infty, \quad m \to \infty, \quad \frac{m}{n} \to 0
+
+    The optimal choice of ``window_length`` for a given sample size depends on
+    the (unknown) distribution. Typically, the smoother the density of the
+    distribution, the larger the optimal value of ``window_length`` [1]_.
+
+    The following options are available for the `method` parameter.
+
+    * ``'vasicek'`` uses the estimator presented in [1]_. This is
+      one of the first and most influential estimators of differential entropy.
+    * ``'van es'`` uses the bias-corrected estimator presented in [3]_, which
+      is not only consistent but, under some conditions, asymptotically normal.
+    * ``'ebrahimi'`` uses an estimator presented in [4]_, which was shown
+      in simulation to have smaller bias and mean squared error than
+      the Vasicek estimator.
+    * ``'correa'`` uses the estimator presented in [5]_ based on local linear
+      regression. In a simulation study, it had consistently smaller mean
+      square error than the Vasiceck estimator, but it is more expensive to
+      compute.
+    * ``'auto'`` selects the method automatically (default). Currently,
+      this selects ``'van es'`` for very small samples (<10), ``'ebrahimi'``
+      for moderate sample sizes (11-1000), and ``'vasicek'`` for larger
+      samples, but this behavior is subject to change in future versions.
+
+    All estimators are implemented as described in [6]_.
+
+    References
+    ----------
+    .. [1] Vasicek, O. (1976). A test for normality based on sample entropy.
+           Journal of the Royal Statistical Society:
+           Series B (Methodological), 38(1), 54-59.
+    .. [2] Crzcgorzewski, P., & Wirczorkowski, R. (1999). Entropy-based
+           goodness-of-fit test for exponentiality. Communications in
+           Statistics-Theory and Methods, 28(5), 1183-1202.
+    .. [3] Van Es, B. (1992). Estimating functionals related to a density by a
+           class of statistics based on spacings. Scandinavian Journal of
+           Statistics, 61-72.
+    .. [4] Ebrahimi, N., Pflughoeft, K., & Soofi, E. S. (1994). Two measures
+           of sample entropy. Statistics & Probability Letters, 20(3), 225-234.
+    .. [5] Correa, J. C. (1995). A new estimator of entropy. Communications
+           in Statistics-Theory and Methods, 24(10), 2439-2449.
+    .. [6] Noughabi, H. A. (2015). Entropy Estimation Using Numerical Methods.
+           Annals of Data Science, 2(2), 231-241.
+           https://link.springer.com/article/10.1007/s40745-015-0045-9
+
+    Examples
+    --------
+    >>> from scipy.stats import differential_entropy, norm
+
+    Entropy of a standard normal distribution:
+
+    >>> rng = np.random.default_rng()
+    >>> values = rng.standard_normal(100)
+    >>> differential_entropy(values)
+    1.3407817436640392
+
+    Compare with the true entropy:
+
+    >>> float(norm.entropy())
+    1.4189385332046727
+
+    For several sample sizes between 5 and 1000, compare the accuracy of
+    the ``'vasicek'``, ``'van es'``, and ``'ebrahimi'`` methods. Specifically,
+    compare the root mean squared error (over 1000 trials) between the estimate
+    and the true differential entropy of the distribution.
+
+    >>> from scipy import stats
+    >>> import matplotlib.pyplot as plt
+    >>>
+    >>>
+    >>> def rmse(res, expected):
+    ...     '''Root mean squared error'''
+    ...     return np.sqrt(np.mean((res - expected)**2))
+    >>>
+    >>>
+    >>> a, b = np.log10(5), np.log10(1000)
+    >>> ns = np.round(np.logspace(a, b, 10)).astype(int)
+    >>> reps = 1000  # number of repetitions for each sample size
+    >>> expected = stats.expon.entropy()
+    >>>
+    >>> method_errors = {'vasicek': [], 'van es': [], 'ebrahimi': []}
+    >>> for method in method_errors:
+    ...     for n in ns:
+    ...        rvs = stats.expon.rvs(size=(reps, n), random_state=rng)
+    ...        res = stats.differential_entropy(rvs, method=method, axis=-1)
+    ...        error = rmse(res, expected)
+    ...        method_errors[method].append(error)
+    >>>
+    >>> for method, errors in method_errors.items():
+    ...     plt.loglog(ns, errors, label=method)
+    >>>
+    >>> plt.legend()
+    >>> plt.xlabel('sample size')
+    >>> plt.ylabel('RMSE (1000 trials)')
+    >>> plt.title('Entropy Estimator Error (Exponential Distribution)')
+
+    """
+    values = np.asarray(values)
+    values = np.moveaxis(values, axis, -1)
+    n = values.shape[-1]  # number of observations
+
+    if window_length is None:
+        window_length = math.floor(math.sqrt(n) + 0.5)
+
+    if not 2 <= 2 * window_length < n:
+        raise ValueError(
+            f"Window length ({window_length}) must be positive and less "
+            f"than half the sample size ({n}).",
+        )
+
+    if base is not None and base <= 0:
+        raise ValueError("`base` must be a positive number or `None`.")
+
+    sorted_data = np.sort(values, axis=-1)
+
+    methods = {"vasicek": _vasicek_entropy,
+               "van es": _van_es_entropy,
+               "correa": _correa_entropy,
+               "ebrahimi": _ebrahimi_entropy,
+               "auto": _vasicek_entropy}
+    method = method.lower()
+    if method not in methods:
+        message = f"`method` must be one of {set(methods)}"
+        raise ValueError(message)
+
+    if method == "auto":
+        if n <= 10:
+            method = 'van es'
+        elif n <= 1000:
+            method = 'ebrahimi'
+        else:
+            method = 'vasicek'
+
+    res = methods[method](sorted_data, window_length)
+
+    if base is not None:
+        res /= np.log(base)
+
+    return res
+
+
+def _pad_along_last_axis(X, m):
+    """Pad the data for computing the rolling window difference."""
+    # scales a  bit better than method in _vasicek_like_entropy
+    shape = np.array(X.shape)
+    shape[-1] = m
+    Xl = np.broadcast_to(X[..., [0]], shape)  # [0] vs 0 to maintain shape
+    Xr = np.broadcast_to(X[..., [-1]], shape)
+    return np.concatenate((Xl, X, Xr), axis=-1)
+
+
+def _vasicek_entropy(X, m):
+    """Compute the Vasicek estimator as described in [6] Eq. 1.3."""
+    n = X.shape[-1]
+    X = _pad_along_last_axis(X, m)
+    differences = X[..., 2 * m:] - X[..., : -2 * m:]
+    logs = np.log(n/(2*m) * differences)
+    return np.mean(logs, axis=-1)
+
+
+def _van_es_entropy(X, m):
+    """Compute the van Es estimator as described in [6]."""
+    # No equation number, but referred to as HVE_mn.
+    # Typo: there should be a log within the summation.
+    n = X.shape[-1]
+    difference = X[..., m:] - X[..., :-m]
+    term1 = 1/(n-m) * np.sum(np.log((n+1)/m * difference), axis=-1)
+    k = np.arange(m, n+1)
+    return term1 + np.sum(1/k) + np.log(m) - np.log(n+1)
+
+
+def _ebrahimi_entropy(X, m):
+    """Compute the Ebrahimi estimator as described in [6]."""
+    # No equation number, but referred to as HE_mn
+    n = X.shape[-1]
+    X = _pad_along_last_axis(X, m)
+
+    differences = X[..., 2 * m:] - X[..., : -2 * m:]
+
+    i = np.arange(1, n+1).astype(float)
+    ci = np.ones_like(i)*2
+    ci[i <= m] = 1 + (i[i <= m] - 1)/m
+    ci[i >= n - m + 1] = 1 + (n - i[i >= n-m+1])/m
+
+    logs = np.log(n * differences / (ci * m))
+    return np.mean(logs, axis=-1)
+
+
+def _correa_entropy(X, m):
+    """Compute the Correa estimator as described in [6]."""
+    # No equation number, but referred to as HC_mn
+    n = X.shape[-1]
+    X = _pad_along_last_axis(X, m)
+
+    i = np.arange(1, n+1)
+    dj = np.arange(-m, m+1)[:, None]
+    j = i + dj
+    j0 = j + m - 1  # 0-indexed version of j
+
+    Xibar = np.mean(X[..., j0], axis=-2, keepdims=True)
+    difference = X[..., j0] - Xibar
+    num = np.sum(difference*dj, axis=-2)  # dj is d-i
+    den = n*np.sum(difference**2, axis=-2)
+    return -np.mean(np.log(num/den), axis=-1)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_generate_pyx.py

@@ -0,0 +1,48 @@
+import pathlib
+import subprocess
+import sys
+
+
+def isNPY_OLD():
+    '''
+    A new random C API was added in 1.18 and became stable in 1.19.
+    Prefer the new random C API when building with recent numpy.
+    '''
+    import numpy as np
+    ver = tuple(int(num) for num in np.__version__.split('.')[:2])
+    return ver < (1, 19)
+
+
+def make_biasedurn():
+    '''Substitute True/False values for NPY_OLD Cython build variable.'''
+    biasedurn_base = (pathlib.Path(__file__).parent / '_biasedurn').absolute()
+    with open(biasedurn_base.with_suffix('.pyx.templ'), 'r') as src:
+        contents = src.read()
+    with open(biasedurn_base.with_suffix('.pyx'), 'w') as dest:
+        dest.write(contents.format(NPY_OLD=str(bool(isNPY_OLD()))))
+
+
+def make_unuran():
+    """Substitute True/False values for NPY_OLD Cython build variable."""
+    import re
+    unuran_base = (
+        pathlib.Path(__file__).parent / "_unuran" / "unuran_wrapper"
+    ).absolute()
+    with open(unuran_base.with_suffix(".pyx.templ"), "r") as src:
+        contents = src.read()
+    with open(unuran_base.with_suffix(".pyx"), "w") as dest:
+        dest.write(re.sub("DEF NPY_OLD = isNPY_OLD",
+                          f"DEF NPY_OLD = {isNPY_OLD()}",
+                          contents))
+
+
+def make_boost():
+    # Call code generator inside _boost directory
+    code_gen = pathlib.Path(__file__).parent / '_boost/include/code_gen.py'
+    subprocess.run([sys.executable, str(code_gen)], check=True)
+
+
+if __name__ == '__main__':
+    make_biasedurn()
+    make_unuran()
+    make_boost()

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_hypotests_pythran.py

@@ -0,0 +1,151 @@
+import numpy as np
+
+#pythran export _Aij(float[:,:], int, int)
+#pythran export _Aij(int[:,:], int, int)
+def _Aij(A, i, j):
+    """Sum of upper-left and lower right blocks of contingency table."""
+    # See `somersd` References [2] bottom of page 309
+    return A[:i, :j].sum() + A[i+1:, j+1:].sum()
+
+#pythran export _Dij(float[:,:], int, int)
+#pythran export _Dij(int[:,:], int, int)
+def _Dij(A, i, j):
+    """Sum of lower-left and upper-right blocks of contingency table."""
+    # See `somersd` References [2] bottom of page 309
+    return A[i+1:, :j].sum() + A[:i, j+1:].sum()
+
+
+# pythran export _concordant_pairs(float[:,:])
+# pythran export _concordant_pairs(int[:,:])
+def _concordant_pairs(A):
+    """Twice the number of concordant pairs, excluding ties."""
+    # See `somersd` References [2] bottom of page 309
+    m, n = A.shape
+    count = 0
+    for i in range(m):
+        for j in range(n):
+            count += A[i, j]*_Aij(A, i, j)
+    return count
+
+
+# pythran export _discordant_pairs(float[:,:])
+# pythran export _discordant_pairs(int[:,:])
+def _discordant_pairs(A):
+    """Twice the number of discordant pairs, excluding ties."""
+    # See `somersd` References [2] bottom of page 309
+    m, n = A.shape
+    count = 0
+    for i in range(m):
+        for j in range(n):
+            count += A[i, j]*_Dij(A, i, j)
+    return count
+
+
+#pythran export _a_ij_Aij_Dij2(float[:,:])
+#pythran export _a_ij_Aij_Dij2(int[:,:])
+def _a_ij_Aij_Dij2(A):
+    """A term that appears in the ASE of Kendall's tau and Somers' D."""
+    # See `somersd` References [2] section 4: Modified ASEs to test the null hypothesis...
+    m, n = A.shape
+    count = 0
+    for i in range(m):
+        for j in range(n):
+            count += A[i, j]*(_Aij(A, i, j) - _Dij(A, i, j))**2
+    return count
+
+
+#pythran export _compute_outer_prob_inside_method(int64, int64, int64, int64)
+def _compute_outer_prob_inside_method(m, n, g, h):
+    """
+    Count the proportion of paths that do not stay strictly inside two
+    diagonal lines.
+
+    Parameters
+    ----------
+    m : integer
+        m > 0
+    n : integer
+        n > 0
+    g : integer
+        g is greatest common divisor of m and n
+    h : integer
+        0 <= h <= lcm(m,n)
+
+    Returns
+    -------
+    p : float
+        The proportion of paths that do not stay inside the two lines.
+
+    The classical algorithm counts the integer lattice paths from (0, 0)
+    to (m, n) which satisfy |x/m - y/n| < h / lcm(m, n).
+    The paths make steps of size +1 in either positive x or positive y
+    directions.
+    We are, however, interested in 1 - proportion to computes p-values,
+    so we change the recursion to compute 1 - p directly while staying
+    within the "inside method" a described by Hodges.
+
+    We generally follow Hodges' treatment of Drion/Gnedenko/Korolyuk.
+    Hodges, J.L. Jr.,
+    "The Significance Probability of the Smirnov Two-Sample Test,"
+    Arkiv fiur Matematik, 3, No. 43 (1958), 469-86.
+
+    For the recursion for 1-p see
+    Viehmann, T.: "Numerically more stable computation of the p-values
+    for the two-sample Kolmogorov-Smirnov test," arXiv: 2102.08037
+
+    """
+    # Probability is symmetrical in m, n.  Computation below uses m >= n.
+    if m < n:
+        m, n = n, m
+    mg = m // g
+    ng = n // g
+
+    # Count the integer lattice paths from (0, 0) to (m, n) which satisfy
+    # |nx/g - my/g| < h.
+    # Compute matrix A such that:
+    #  A(x, 0) = A(0, y) = 1
+    #  A(x, y) = A(x, y-1) + A(x-1, y), for x,y>=1, except that
+    #  A(x, y) = 0 if |x/m - y/n|>= h
+    # Probability is A(m, n)/binom(m+n, n)
+    # Optimizations exist for m==n, m==n*p.
+    # Only need to preserve a single column of A, and only a
+    # sliding window of it.
+    # minj keeps track of the slide.
+    minj, maxj = 0, min(int(np.ceil(h / mg)), n + 1)
+    curlen = maxj - minj
+    # Make a vector long enough to hold maximum window needed.
+    lenA = min(2 * maxj + 2, n + 1)
+    # This is an integer calculation, but the entries are essentially
+    # binomial coefficients, hence grow quickly.
+    # Scaling after each column is computed avoids dividing by a
+    # large binomial coefficient at the end, but is not sufficient to avoid
+    # the large dyanamic range which appears during the calculation.
+    # Instead we rescale based on the magnitude of the right most term in
+    # the column and keep track of an exponent separately and apply
+    # it at the end of the calculation.  Similarly when multiplying by
+    # the binomial coefficient
+    dtype = np.float64
+    A = np.ones(lenA, dtype=dtype)
+    # Initialize the first column
+    A[minj:maxj] = 0.0
+    for i in range(1, m + 1):
+        # Generate the next column.
+        # First calculate the sliding window
+        lastminj, lastlen = minj, curlen
+        minj = max(int(np.floor((ng * i - h) / mg)) + 1, 0)
+        minj = min(minj, n)
+        maxj = min(int(np.ceil((ng * i + h) / mg)), n + 1)
+        if maxj <= minj:
+            return 1.0
+        # Now fill in the values. We cannot use cumsum, unfortunately.
+        val = 0.0 if minj == 0 else 1.0
+        for jj in range(maxj - minj):
+            j = jj + minj
+            val = (A[jj + minj - lastminj] * i + val * j) / (i + j)
+            A[jj] = val
+        curlen = maxj - minj
+        if lastlen > curlen:
+            # Set some carried-over elements to 1
+            A[maxj - minj:maxj - minj + (lastlen - curlen)] = 1
+
+    return A[maxj - minj - 1]

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_kde.py

@@ -0,0 +1,638 @@
+#-------------------------------------------------------------------------------
+#
+#  Define classes for (uni/multi)-variate kernel density estimation.
+#
+#  Currently, only Gaussian kernels are implemented.
+#
+#  Written by: Robert Kern
+#
+#  Date: 2004-08-09
+#
+#  Modified: 2005-02-10 by Robert Kern.
+#              Contributed to SciPy
+#            2005-10-07 by Robert Kern.
+#              Some fixes to match the new scipy_core
+#
+#  Copyright 2004-2005 by Enthought, Inc.
+#
+#-------------------------------------------------------------------------------
+
+# Standard library imports.
+import warnings
+
+# SciPy imports.
+from scipy import linalg, special
+from scipy.special import logsumexp
+from scipy._lib._util import check_random_state
+
+from numpy import (asarray, atleast_2d, reshape, zeros, newaxis, dot, exp, pi,
+                   sqrt, ravel, power, atleast_1d, squeeze, sum, transpose,
+                   ones, cov)
+import numpy as np
+
+# Local imports.
+from . import _mvn
+from ._stats import gaussian_kernel_estimate
+
+
+__all__ = ['gaussian_kde']
+
+
+class gaussian_kde:
+    """Representation of a kernel-density estimate using Gaussian kernels.
+
+    Kernel density estimation is a way to estimate the probability density
+    function (PDF) of a random variable in a non-parametric way.
+    `gaussian_kde` works for both uni-variate and multi-variate data.   It
+    includes automatic bandwidth determination.  The estimation works best for
+    a unimodal distribution; bimodal or multi-modal distributions tend to be
+    oversmoothed.
+
+    Parameters
+    ----------
+    dataset : array_like
+        Datapoints to estimate from. In case of univariate data this is a 1-D
+        array, otherwise a 2-D array with shape (# of dims, # of data).
+    bw_method : str, scalar or callable, optional
+        The method used to calculate the estimator bandwidth.  This can be
+        'scott', 'silverman', a scalar constant or a callable.  If a scalar,
+        this will be used directly as `kde.factor`.  If a callable, it should
+        take a `gaussian_kde` instance as only parameter and return a scalar.
+        If None (default), 'scott' is used.  See Notes for more details.
+    weights : array_like, optional
+        weights of datapoints. This must be the same shape as dataset.
+        If None (default), the samples are assumed to be equally weighted
+
+    Attributes
+    ----------
+    dataset : ndarray
+        The dataset with which `gaussian_kde` was initialized.
+    d : int
+        Number of dimensions.
+    n : int
+        Number of datapoints.
+    neff : int
+        Effective number of datapoints.
+
+        .. versionadded:: 1.2.0
+    factor : float
+        The bandwidth factor, obtained from `kde.covariance_factor`. The square
+        of `kde.factor` multiplies the covariance matrix of the data in the kde
+        estimation.
+    covariance : ndarray
+        The covariance matrix of `dataset`, scaled by the calculated bandwidth
+        (`kde.factor`).
+    inv_cov : ndarray
+        The inverse of `covariance`.
+
+    Methods
+    -------
+    evaluate
+    __call__
+    integrate_gaussian
+    integrate_box_1d
+    integrate_box
+    integrate_kde
+    pdf
+    logpdf
+    resample
+    set_bandwidth
+    covariance_factor
+
+    Notes
+    -----
+    Bandwidth selection strongly influences the estimate obtained from the KDE
+    (much more so than the actual shape of the kernel).  Bandwidth selection
+    can be done by a "rule of thumb", by cross-validation, by "plug-in
+    methods" or by other means; see [3]_, [4]_ for reviews.  `gaussian_kde`
+    uses a rule of thumb, the default is Scott's Rule.
+
+    Scott's Rule [1]_, implemented as `scotts_factor`, is::
+
+        n**(-1./(d+4)),
+
+    with ``n`` the number of data points and ``d`` the number of dimensions.
+    In the case of unequally weighted points, `scotts_factor` becomes::
+
+        neff**(-1./(d+4)),
+
+    with ``neff`` the effective number of datapoints.
+    Silverman's Rule [2]_, implemented as `silverman_factor`, is::
+
+        (n * (d + 2) / 4.)**(-1. / (d + 4)).
+
+    or in the case of unequally weighted points::
+
+        (neff * (d + 2) / 4.)**(-1. / (d + 4)).
+
+    Good general descriptions of kernel density estimation can be found in [1]_
+    and [2]_, the mathematics for this multi-dimensional implementation can be
+    found in [1]_.
+
+    With a set of weighted samples, the effective number of datapoints ``neff``
+    is defined by::
+
+        neff = sum(weights)^2 / sum(weights^2)
+
+    as detailed in [5]_.
+
+    References
+    ----------
+    .. [1] D.W. Scott, "Multivariate Density Estimation: Theory, Practice, and
+           Visualization", John Wiley & Sons, New York, Chicester, 1992.
+    .. [2] B.W. Silverman, "Density Estimation for Statistics and Data
+           Analysis", Vol. 26, Monographs on Statistics and Applied Probability,
+           Chapman and Hall, London, 1986.
+    .. [3] B.A. Turlach, "Bandwidth Selection in Kernel Density Estimation: A
+           Review", CORE and Institut de Statistique, Vol. 19, pp. 1-33, 1993.
+    .. [4] D.M. Bashtannyk and R.J. Hyndman, "Bandwidth selection for kernel
+           conditional density estimation", Computational Statistics & Data
+           Analysis, Vol. 36, pp. 279-298, 2001.
+    .. [5] Gray P. G., 1969, Journal of the Royal Statistical Society.
+           Series A (General), 132, 272
+
+    Examples
+    --------
+    Generate some random two-dimensional data:
+
+    >>> from scipy import stats
+    >>> def measure(n):
+    ...     "Measurement model, return two coupled measurements."
+    ...     m1 = np.random.normal(size=n)
+    ...     m2 = np.random.normal(scale=0.5, size=n)
+    ...     return m1+m2, m1-m2
+
+    >>> m1, m2 = measure(2000)
+    >>> xmin = m1.min()
+    >>> xmax = m1.max()
+    >>> ymin = m2.min()
+    >>> ymax = m2.max()
+
+    Perform a kernel density estimate on the data:
+
+    >>> X, Y = np.mgrid[xmin:xmax:100j, ymin:ymax:100j]
+    >>> positions = np.vstack([X.ravel(), Y.ravel()])
+    >>> values = np.vstack([m1, m2])
+    >>> kernel = stats.gaussian_kde(values)
+    >>> Z = np.reshape(kernel(positions).T, X.shape)
+
+    Plot the results:
+
+    >>> import matplotlib.pyplot as plt
+    >>> fig, ax = plt.subplots()
+    >>> ax.imshow(np.rot90(Z), cmap=plt.cm.gist_earth_r,
+    ...           extent=[xmin, xmax, ymin, ymax])
+    >>> ax.plot(m1, m2, 'k.', markersize=2)
+    >>> ax.set_xlim([xmin, xmax])
+    >>> ax.set_ylim([ymin, ymax])
+    >>> plt.show()
+
+    """
+    def __init__(self, dataset, bw_method=None, weights=None):
+        self.dataset = atleast_2d(asarray(dataset))
+        if not self.dataset.size > 1:
+            raise ValueError("`dataset` input should have multiple elements.")
+
+        self.d, self.n = self.dataset.shape
+
+        if weights is not None:
+            self._weights = atleast_1d(weights).astype(float)
+            self._weights /= sum(self._weights)
+            if self.weights.ndim != 1:
+                raise ValueError("`weights` input should be one-dimensional.")
+            if len(self._weights) != self.n:
+                raise ValueError("`weights` input should be of length n")
+            self._neff = 1/sum(self._weights**2)
+
+        self.set_bandwidth(bw_method=bw_method)
+
+    def evaluate(self, points):
+        """Evaluate the estimated pdf on a set of points.
+
+        Parameters
+        ----------
+        points : (# of dimensions, # of points)-array
+            Alternatively, a (# of dimensions,) vector can be passed in and
+            treated as a single point.
+
+        Returns
+        -------
+        values : (# of points,)-array
+            The values at each point.
+
+        Raises
+        ------
+        ValueError : if the dimensionality of the input points is different than
+                     the dimensionality of the KDE.
+
+        """
+        points = atleast_2d(asarray(points))
+
+        d, m = points.shape
+        if d != self.d:
+            if d == 1 and m == self.d:
+                # points was passed in as a row vector
+                points = reshape(points, (self.d, 1))
+                m = 1
+            else:
+                msg = "points have dimension %s, dataset has dimension %s" % (d,
+                    self.d)
+                raise ValueError(msg)
+
+        output_dtype = np.common_type(self.covariance, points)
+        itemsize = np.dtype(output_dtype).itemsize
+        if itemsize == 4:
+            spec = 'float'
+        elif itemsize == 8:
+            spec = 'double'
+        elif itemsize in (12, 16):
+            spec = 'long double'
+        else:
+            raise TypeError('%s has unexpected item size %d' %
+                            (output_dtype, itemsize))
+        result = gaussian_kernel_estimate[spec](self.dataset.T, self.weights[:, None],
+                                                points.T, self.inv_cov, output_dtype)
+        return result[:, 0]
+
+    __call__ = evaluate
+
+    def integrate_gaussian(self, mean, cov):
+        """
+        Multiply estimated density by a multivariate Gaussian and integrate
+        over the whole space.
+
+        Parameters
+        ----------
+        mean : aray_like
+            A 1-D array, specifying the mean of the Gaussian.
+        cov : array_like
+            A 2-D array, specifying the covariance matrix of the Gaussian.
+
+        Returns
+        -------
+        result : scalar
+            The value of the integral.
+
+        Raises
+        ------
+        ValueError
+            If the mean or covariance of the input Gaussian differs from
+            the KDE's dimensionality.
+
+        """
+        mean = atleast_1d(squeeze(mean))
+        cov = atleast_2d(cov)
+
+        if mean.shape != (self.d,):
+            raise ValueError("mean does not have dimension %s" % self.d)
+        if cov.shape != (self.d, self.d):
+            raise ValueError("covariance does not have dimension %s" % self.d)
+
+        # make mean a column vector
+        mean = mean[:, newaxis]
+
+        sum_cov = self.covariance + cov
+
+        # This will raise LinAlgError if the new cov matrix is not s.p.d
+        # cho_factor returns (ndarray, bool) where bool is a flag for whether
+        # or not ndarray is upper or lower triangular
+        sum_cov_chol = linalg.cho_factor(sum_cov)
+
+        diff = self.dataset - mean
+        tdiff = linalg.cho_solve(sum_cov_chol, diff)
+
+        sqrt_det = np.prod(np.diagonal(sum_cov_chol[0]))
+        norm_const = power(2 * pi, sum_cov.shape[0] / 2.0) * sqrt_det
+
+        energies = sum(diff * tdiff, axis=0) / 2.0
+        result = sum(exp(-energies)*self.weights, axis=0) / norm_const
+
+        return result
+
+    def integrate_box_1d(self, low, high):
+        """
+        Computes the integral of a 1D pdf between two bounds.
+
+        Parameters
+        ----------
+        low : scalar
+            Lower bound of integration.
+        high : scalar
+            Upper bound of integration.
+
+        Returns
+        -------
+        value : scalar
+            The result of the integral.
+
+        Raises
+        ------
+        ValueError
+            If the KDE is over more than one dimension.
+
+        """
+        if self.d != 1:
+            raise ValueError("integrate_box_1d() only handles 1D pdfs")
+
+        stdev = ravel(sqrt(self.covariance))[0]
+
+        normalized_low = ravel((low - self.dataset) / stdev)
+        normalized_high = ravel((high - self.dataset) / stdev)
+
+        value = np.sum(self.weights*(
+                        special.ndtr(normalized_high) -
+                        special.ndtr(normalized_low)))
+        return value
+
+    def integrate_box(self, low_bounds, high_bounds, maxpts=None):
+        """Computes the integral of a pdf over a rectangular interval.
+
+        Parameters
+        ----------
+        low_bounds : array_like
+            A 1-D array containing the lower bounds of integration.
+        high_bounds : array_like
+            A 1-D array containing the upper bounds of integration.
+        maxpts : int, optional
+            The maximum number of points to use for integration.
+
+        Returns
+        -------
+        value : scalar
+            The result of the integral.
+
+        """
+        if maxpts is not None:
+            extra_kwds = {'maxpts': maxpts}
+        else:
+            extra_kwds = {}
+
+        value, inform = _mvn.mvnun_weighted(low_bounds, high_bounds,
+                                           self.dataset, self.weights,
+                                           self.covariance, **extra_kwds)
+        if inform:
+            msg = ('An integral in _mvn.mvnun requires more points than %s' %
+                   (self.d * 1000))
+            warnings.warn(msg)
+
+        return value
+
+    def integrate_kde(self, other):
+        """
+        Computes the integral of the product of this  kernel density estimate
+        with another.
+
+        Parameters
+        ----------
+        other : gaussian_kde instance
+            The other kde.
+
+        Returns
+        -------
+        value : scalar
+            The result of the integral.
+
+        Raises
+        ------
+        ValueError
+            If the KDEs have different dimensionality.
+
+        """
+        if other.d != self.d:
+            raise ValueError("KDEs are not the same dimensionality")
+
+        # we want to iterate over the smallest number of points
+        if other.n < self.n:
+            small = other
+            large = self
+        else:
+            small = self
+            large = other
+
+        sum_cov = small.covariance + large.covariance
+        sum_cov_chol = linalg.cho_factor(sum_cov)
+        result = 0.0
+        for i in range(small.n):
+            mean = small.dataset[:, i, newaxis]
+            diff = large.dataset - mean
+            tdiff = linalg.cho_solve(sum_cov_chol, diff)
+
+            energies = sum(diff * tdiff, axis=0) / 2.0
+            result += sum(exp(-energies)*large.weights, axis=0)*small.weights[i]
+
+        sqrt_det = np.prod(np.diagonal(sum_cov_chol[0]))
+        norm_const = power(2 * pi, sum_cov.shape[0] / 2.0) * sqrt_det
+
+        result /= norm_const
+
+        return result
+
+    def resample(self, size=None, seed=None):
+        """Randomly sample a dataset from the estimated pdf.
+
+        Parameters
+        ----------
+        size : int, optional
+            The number of samples to draw.  If not provided, then the size is
+            the same as the effective number of samples in the underlying
+            dataset.
+        seed : {None, int, `numpy.random.Generator`,
+                `numpy.random.RandomState`}, optional
+
+            If `seed` is None (or `np.random`), the `numpy.random.RandomState`
+            singleton is used.
+            If `seed` is an int, a new ``RandomState`` instance is used,
+            seeded with `seed`.
+            If `seed` is already a ``Generator`` or ``RandomState`` instance then
+            that instance is used.
+
+        Returns
+        -------
+        resample : (self.d, `size`) ndarray
+            The sampled dataset.
+
+        """
+        if size is None:
+            size = int(self.neff)
+
+        random_state = check_random_state(seed)
+        norm = transpose(random_state.multivariate_normal(
+            zeros((self.d,), float), self.covariance, size=size
+        ))
+        indices = random_state.choice(self.n, size=size, p=self.weights)
+        means = self.dataset[:, indices]
+
+        return means + norm
+
+    def scotts_factor(self):
+        """Compute Scott's factor.
+
+        Returns
+        -------
+        s : float
+            Scott's factor.
+        """
+        return power(self.neff, -1./(self.d+4))
+
+    def silverman_factor(self):
+        """Compute the Silverman factor.
+
+        Returns
+        -------
+        s : float
+            The silverman factor.
+        """
+        return power(self.neff*(self.d+2.0)/4.0, -1./(self.d+4))
+
+    #  Default method to calculate bandwidth, can be overwritten by subclass
+    covariance_factor = scotts_factor
+    covariance_factor.__doc__ = """Computes the coefficient (`kde.factor`) that
+        multiplies the data covariance matrix to obtain the kernel covariance
+        matrix. The default is `scotts_factor`.  A subclass can overwrite this
+        method to provide a different method, or set it through a call to
+        `kde.set_bandwidth`."""
+
+    def set_bandwidth(self, bw_method=None):
+        """Compute the estimator bandwidth with given method.
+
+        The new bandwidth calculated after a call to `set_bandwidth` is used
+        for subsequent evaluations of the estimated density.
+
+        Parameters
+        ----------
+        bw_method : str, scalar or callable, optional
+            The method used to calculate the estimator bandwidth.  This can be
+            'scott', 'silverman', a scalar constant or a callable.  If a
+            scalar, this will be used directly as `kde.factor`.  If a callable,
+            it should take a `gaussian_kde` instance as only parameter and
+            return a scalar.  If None (default), nothing happens; the current
+            `kde.covariance_factor` method is kept.
+
+        Notes
+        -----
+        .. versionadded:: 0.11
+
+        Examples
+        --------
+        >>> import scipy.stats as stats
+        >>> x1 = np.array([-7, -5, 1, 4, 5.])
+        >>> kde = stats.gaussian_kde(x1)
+        >>> xs = np.linspace(-10, 10, num=50)
+        >>> y1 = kde(xs)
+        >>> kde.set_bandwidth(bw_method='silverman')
+        >>> y2 = kde(xs)
+        >>> kde.set_bandwidth(bw_method=kde.factor / 3.)
+        >>> y3 = kde(xs)
+
+        >>> import matplotlib.pyplot as plt
+        >>> fig, ax = plt.subplots()
+        >>> ax.plot(x1, np.full(x1.shape, 1 / (4. * x1.size)), 'bo',
+        ...         label='Data points (rescaled)')
+        >>> ax.plot(xs, y1, label='Scott (default)')
+        >>> ax.plot(xs, y2, label='Silverman')
+        >>> ax.plot(xs, y3, label='Const (1/3 * Silverman)')
+        >>> ax.legend()
+        >>> plt.show()
+
+        """
+        if bw_method is None:
+            pass
+        elif bw_method == 'scott':
+            self.covariance_factor = self.scotts_factor
+        elif bw_method == 'silverman':
+            self.covariance_factor = self.silverman_factor
+        elif np.isscalar(bw_method) and not isinstance(bw_method, str):
+            self._bw_method = 'use constant'
+            self.covariance_factor = lambda: bw_method
+        elif callable(bw_method):
+            self._bw_method = bw_method
+            self.covariance_factor = lambda: self._bw_method(self)
+        else:
+            msg = "`bw_method` should be 'scott', 'silverman', a scalar " \
+                  "or a callable."
+            raise ValueError(msg)
+
+        self._compute_covariance()
+
+    def _compute_covariance(self):
+        """Computes the covariance matrix for each Gaussian kernel using
+        covariance_factor().
+        """
+        self.factor = self.covariance_factor()
+        # Cache covariance and inverse covariance of the data
+        if not hasattr(self, '_data_inv_cov'):
+            self._data_covariance = atleast_2d(cov(self.dataset, rowvar=1,
+                                               bias=False,
+                                               aweights=self.weights))
+            self._data_inv_cov = linalg.inv(self._data_covariance)
+
+        self.covariance = self._data_covariance * self.factor**2
+        self.inv_cov = self._data_inv_cov / self.factor**2
+        L = linalg.cholesky(self.covariance*2*pi)
+        self.log_det = 2*np.log(np.diag(L)).sum()
+
+    def pdf(self, x):
+        """
+        Evaluate the estimated pdf on a provided set of points.
+
+        Notes
+        -----
+        This is an alias for `gaussian_kde.evaluate`.  See the ``evaluate``
+        docstring for more details.
+
+        """
+        return self.evaluate(x)
+
+    def logpdf(self, x):
+        """
+        Evaluate the log of the estimated pdf on a provided set of points.
+        """
+        points = atleast_2d(x)
+
+        d, m = points.shape
+        if d != self.d:
+            if d == 1 and m == self.d:
+                # points was passed in as a row vector
+                points = reshape(points, (self.d, 1))
+                m = 1
+            else:
+                msg = "points have dimension %s, dataset has dimension %s" % (d,
+                    self.d)
+                raise ValueError(msg)
+
+        if m >= self.n:
+            # there are more points than data, so loop over data
+            energy = np.empty((self.n, m), dtype=float)
+            for i in range(self.n):
+                diff = self.dataset[:, i, newaxis] - points
+                tdiff = dot(self.inv_cov, diff)
+                energy[i] = sum(diff*tdiff, axis=0)
+            log_to_sum = 2.0 * np.log(self.weights) - self.log_det - energy.T
+            result = logsumexp(0.5 * log_to_sum, axis=1)
+        else:
+            # loop over points
+            result = np.empty((m,), dtype=float)
+            for i in range(m):
+                diff = self.dataset - points[:, i, newaxis]
+                tdiff = dot(self.inv_cov, diff)
+                energy = sum(diff * tdiff, axis=0)
+                log_to_sum = 2.0 * np.log(self.weights) - self.log_det - energy
+                result[i] = logsumexp(0.5 * log_to_sum)
+
+        return result
+
+    @property
+    def weights(self):
+        try:
+            return self._weights
+        except AttributeError:
+            self._weights = ones(self.n)/self.n
+            return self._weights
+
+    @property
+    def neff(self):
+        try:
+            return self._neff
+        except AttributeError:
+            self._neff = 1/sum(self.weights**2)
+            return self._neff

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_ksstats.py

@@ -0,0 +1,596 @@
+# Compute the two-sided one-sample Kolmogorov-Smirnov Prob(Dn <= d) where:
+#    D_n = sup_x{|F_n(x) - F(x)|},
+#    F_n(x) is the empirical CDF for a sample of size n {x_i: i=1,...,n},
+#    F(x) is the CDF of a probability distribution.
+#
+# Exact methods:
+# Prob(D_n >= d) can be computed via a matrix algorithm of Durbin[1]
+#   or a recursion algorithm due to Pomeranz[2].
+# Marsaglia, Tsang & Wang[3] gave a computation-efficient way to perform
+#   the Durbin algorithm.
+#   D_n >= d <==>  D_n+ >= d or D_n- >= d (the one-sided K-S statistics), hence
+#   Prob(D_n >= d) = 2*Prob(D_n+ >= d) - Prob(D_n+ >= d and D_n- >= d).
+#   For d > 0.5, the latter intersection probability is 0.
+#
+# Approximate methods:
+# For d close to 0.5, ignoring that intersection term may still give a
+#   reasonable approximation.
+# Li-Chien[4] and Korolyuk[5] gave an asymptotic formula extending
+# Kolmogorov's initial asymptotic, suitable for large d. (See
+#   scipy.special.kolmogorov for that asymptotic)
+# Pelz-Good[6] used the functional equation for Jacobi theta functions to
+#   transform the Li-Chien/Korolyuk formula produce a computational formula
+#   suitable for small d.
+#
+# Simard and L'Ecuyer[7] provided an algorithm to decide when to use each of
+#   the above approaches and it is that which is used here.
+#
+# Other approaches:
+# Carvalho[8] optimizes Durbin's matrix algorithm for large values of d.
+# Moscovich and Nadler[9] use FFTs to compute the convolutions.
+
+# References:
+# [1] Durbin J (1968).
+#     "The Probability that the Sample Distribution Function Lies Between Two
+#     Parallel Straight Lines."
+#     Annals of Mathematical Statistics, 39, 398-411.
+# [2] Pomeranz J (1974).
+#     "Exact Cumulative Distribution of the Kolmogorov-Smirnov Statistic for
+#     Small Samples (Algorithm 487)."
+#     Communications of the ACM, 17(12), 703-704.
+# [3] Marsaglia G, Tsang WW, Wang J (2003).
+#     "Evaluating Kolmogorov's Distribution."
+#     Journal of Statistical Software, 8(18), 1-4.
+# [4] LI-CHIEN, C. (1956).
+#     "On the exact distribution of the statistics of A. N. Kolmogorov and
+#     their asymptotic expansion."
+#     Acta Matematica Sinica, 6, 55-81.
+# [5] KOROLYUK, V. S. (1960).
+#     "Asymptotic analysis of the distribution of the maximum deviation in
+#     the Bernoulli scheme."
+#     Theor. Probability Appl., 4, 339-366.
+# [6] Pelz W, Good IJ (1976).
+#     "Approximating the Lower Tail-areas of the Kolmogorov-Smirnov One-sample
+#     Statistic."
+#     Journal of the Royal Statistical Society, Series B, 38(2), 152-156.
+#  [7] Simard, R., L'Ecuyer, P. (2011)
+# 	  "Computing the Two-Sided Kolmogorov-Smirnov Distribution",
+# 	  Journal of Statistical Software, Vol 39, 11, 1-18.
+#  [8] Carvalho, Luis (2015)
+#     "An Improved Evaluation of Kolmogorov's Distribution"
+#     Journal of Statistical Software, Code Snippets; Vol 65(3), 1-8.
+#  [9] Amit Moscovich, Boaz Nadler (2017)
+#     "Fast calculation of boundary crossing probabilities for Poisson
+#     processes",
+#     Statistics & Probability Letters, Vol 123, 177-182.
+
+
+import numpy as np
+import scipy.special
+import scipy.special._ufuncs as scu
+import scipy.misc
+
+_E128 = 128
+_EP128 = np.ldexp(np.longdouble(1), _E128)
+_EM128 = np.ldexp(np.longdouble(1), -_E128)
+
+_SQRT2PI = np.sqrt(2 * np.pi)
+_LOG_2PI = np.log(2 * np.pi)
+_MIN_LOG = -708
+_SQRT3 = np.sqrt(3)
+_PI_SQUARED = np.pi ** 2
+_PI_FOUR = np.pi ** 4
+_PI_SIX = np.pi ** 6
+
+# [Lifted from _loggamma.pxd.] If B_m are the Bernoulli numbers,
+# then Stirling coeffs are B_{2j}/(2j)/(2j-1) for j=8,...1.
+_STIRLING_COEFFS = [-2.955065359477124183e-2, 6.4102564102564102564e-3,
+                    -1.9175269175269175269e-3, 8.4175084175084175084e-4,
+                    -5.952380952380952381e-4, 7.9365079365079365079e-4,
+                    -2.7777777777777777778e-3, 8.3333333333333333333e-2]
+
+def _log_nfactorial_div_n_pow_n(n):
+    # Computes n! / n**n
+    #    = (n-1)! / n**(n-1)
+    # Uses Stirling's approximation, but removes n*log(n) up-front to
+    # avoid subtractive cancellation.
+    #    = log(n)/2 - n + log(sqrt(2pi)) + sum B_{2j}/(2j)/(2j-1)/n**(2j-1)
+    rn = 1.0/n
+    return np.log(n)/2 - n + _LOG_2PI/2 + rn * np.polyval(_STIRLING_COEFFS, rn/n)
+
+
+def _clip_prob(p):
+    """clips a probability to range 0<=p<=1."""
+    return np.clip(p, 0.0, 1.0)
+
+
+def _select_and_clip_prob(cdfprob, sfprob, cdf=True):
+    """Selects either the CDF or SF, and then clips to range 0<=p<=1."""
+    p = np.where(cdf, cdfprob, sfprob)
+    return _clip_prob(p)
+
+
+def _kolmogn_DMTW(n, d, cdf=True):
+    r"""Computes the Kolmogorov CDF:  Pr(D_n <= d) using the MTW approach to
+    the Durbin matrix algorithm.
+
+    Durbin (1968); Marsaglia, Tsang, Wang (2003). [1], [3].
+    """
+    # Write d = (k-h)/n, where k is positive integer and 0 <= h < 1
+    # Generate initial matrix H of size m*m where m=(2k-1)
+    # Compute k-th row of (n!/n^n) * H^n, scaling intermediate results.
+    # Requires memory O(m^2) and computation O(m^2 log(n)).
+    # Most suitable for small m.
+
+    if d >= 1.0:
+        return _select_and_clip_prob(1.0, 0.0, cdf)
+    nd = n * d
+    if nd <= 0.5:
+        return _select_and_clip_prob(0.0, 1.0, cdf)
+    k = int(np.ceil(nd))
+    h = k - nd
+    m = 2 * k - 1
+
+    H = np.zeros([m, m])
+
+    # Initialize: v is first column (and last row) of H
+    #  v[j] = (1-h^(j+1)/(j+1)!  (except for v[-1])
+    #  w[j] = 1/(j)!
+    # q = k-th row of H (actually i!/n^i*H^i)
+    intm = np.arange(1, m + 1)
+    v = 1.0 - h ** intm
+    w = np.empty(m)
+    fac = 1.0
+    for j in intm:
+        w[j - 1] = fac
+        fac /= j  # This might underflow.  Isn't a problem.
+        v[j - 1] *= fac
+    tt = max(2 * h - 1.0, 0)**m - 2*h**m
+    v[-1] = (1.0 + tt) * fac
+
+    for i in range(1, m):
+        H[i - 1:, i] = w[:m - i + 1]
+    H[:, 0] = v
+    H[-1, :] = np.flip(v, axis=0)
+
+    Hpwr = np.eye(np.shape(H)[0])  # Holds intermediate powers of H
+    nn = n
+    expnt = 0  # Scaling of Hpwr
+    Hexpnt = 0  # Scaling of H
+    while nn > 0:
+        if nn % 2:
+            Hpwr = np.matmul(Hpwr, H)
+            expnt += Hexpnt
+        H = np.matmul(H, H)
+        Hexpnt *= 2
+        # Scale as needed.
+        if np.abs(H[k - 1, k - 1]) > _EP128:
+            H /= _EP128
+            Hexpnt += _E128
+        nn = nn // 2
+
+    p = Hpwr[k - 1, k - 1]
+
+    # Multiply by n!/n^n
+    for i in range(1, n + 1):
+        p = i * p / n
+        if np.abs(p) < _EM128:
+            p *= _EP128
+            expnt -= _E128
+
+    # unscale
+    if expnt != 0:
+        p = np.ldexp(p, expnt)
+
+    return _select_and_clip_prob(p, 1.0-p, cdf)
+
+
+def _pomeranz_compute_j1j2(i, n, ll, ceilf, roundf):
+    """Compute the endpoints of the interval for row i."""
+    if i == 0:
+        j1, j2 = -ll - ceilf - 1, ll + ceilf - 1
+    else:
+        # i + 1 = 2*ip1div2 + ip1mod2
+        ip1div2, ip1mod2 = divmod(i + 1, 2)
+        if ip1mod2 == 0:  # i is odd
+            if ip1div2 == n + 1:
+                j1, j2 = n - ll - ceilf - 1, n + ll + ceilf - 1
+            else:
+                j1, j2 = ip1div2 - 1 - ll - roundf - 1, ip1div2 + ll - 1 + ceilf - 1
+        else:
+            j1, j2 = ip1div2 - 1 - ll - 1, ip1div2 + ll + roundf - 1
+
+    return max(j1 + 2, 0), min(j2, n)
+
+
+def _kolmogn_Pomeranz(n, x, cdf=True):
+    r"""Computes Pr(D_n <= d) using the Pomeranz recursion algorithm.
+
+    Pomeranz (1974) [2]
+    """
+
+    # V is n*(2n+2) matrix.
+    # Each row is convolution of the previous row and probabilities from a
+    #  Poisson distribution.
+    # Desired CDF probability is n! V[n-1, 2n+1]  (final entry in final row).
+    # Only two rows are needed at any given stage:
+    #  - Call them V0 and V1.
+    #  - Swap each iteration
+    # Only a few (contiguous) entries in each row can be non-zero.
+    #  - Keep track of start and end (j1 and j2 below)
+    #  - V0s and V1s track the start in the two rows
+    # Scale intermediate results as needed.
+    # Only a few different Poisson distributions can occur
+    t = n * x
+    ll = int(np.floor(t))
+    f = 1.0 * (t - ll)  # fractional part of t
+    g = min(f, 1.0 - f)
+    ceilf = (1 if f > 0 else 0)
+    roundf = (1 if f > 0.5 else 0)
+    npwrs = 2 * (ll + 1)    # Maximum number of powers needed in convolutions
+    gpower = np.empty(npwrs)  # gpower = (g/n)^m/m!
+    twogpower = np.empty(npwrs)  # twogpower = (2g/n)^m/m!
+    onem2gpower = np.empty(npwrs)  # onem2gpower = ((1-2g)/n)^m/m!
+    # gpower etc are *almost* Poisson probs, just missing normalizing factor.
+
+    gpower[0] = 1.0
+    twogpower[0] = 1.0
+    onem2gpower[0] = 1.0
+    expnt = 0
+    g_over_n, two_g_over_n, one_minus_two_g_over_n = g/n, 2*g/n, (1 - 2*g)/n
+    for m in range(1, npwrs):
+        gpower[m] = gpower[m - 1] * g_over_n / m
+        twogpower[m] = twogpower[m - 1] * two_g_over_n / m
+        onem2gpower[m] = onem2gpower[m - 1] * one_minus_two_g_over_n / m
+
+    V0 = np.zeros([npwrs])
+    V1 = np.zeros([npwrs])
+    V1[0] = 1  # first row
+    V0s, V1s = 0, 0  # start indices of the two rows
+
+    j1, j2 = _pomeranz_compute_j1j2(0, n, ll, ceilf, roundf)
+    for i in range(1, 2 * n + 2):
+        # Preserve j1, V1, V1s, V0s from last iteration
+        k1 = j1
+        V0, V1 = V1, V0
+        V0s, V1s = V1s, V0s
+        V1.fill(0.0)
+        j1, j2 = _pomeranz_compute_j1j2(i, n, ll, ceilf, roundf)
+        if i == 1 or i == 2 * n + 1:
+            pwrs = gpower
+        else:
+            pwrs = (twogpower if i % 2 else onem2gpower)
+        ln2 = j2 - k1 + 1
+        if ln2 > 0:
+            conv = np.convolve(V0[k1 - V0s:k1 - V0s + ln2], pwrs[:ln2])
+            conv_start = j1 - k1  # First index to use from conv
+            conv_len = j2 - j1 + 1  # Number of entries to use from conv
+            V1[:conv_len] = conv[conv_start:conv_start + conv_len]
+            # Scale to avoid underflow.
+            if 0 < np.max(V1) < _EM128:
+                V1 *= _EP128
+                expnt -= _E128
+            V1s = V0s + j1 - k1
+
+    # multiply by n!
+    ans = V1[n - V1s]
+    for m in range(1, n + 1):
+        if np.abs(ans) > _EP128:
+            ans *= _EM128
+            expnt += _E128
+        ans *= m
+
+    # Undo any intermediate scaling
+    if expnt != 0:
+        ans = np.ldexp(ans, expnt)
+    ans = _select_and_clip_prob(ans, 1.0 - ans, cdf)
+    return ans
+
+
+def _kolmogn_PelzGood(n, x, cdf=True):
+    """Computes the Pelz-Good approximation to Prob(Dn <= x) with 0<=x<=1.
+
+    Start with Li-Chien, Korolyuk approximation:
+        Prob(Dn <= x) ~ K0(z) + K1(z)/sqrt(n) + K2(z)/n + K3(z)/n**1.5
+    where z = x*sqrt(n).
+    Transform each K_(z) using Jacobi theta functions into a form suitable
+    for small z.
+    Pelz-Good (1976). [6]
+    """
+    if x <= 0.0:
+        return _select_and_clip_prob(0.0, 1.0, cdf=cdf)
+    if x >= 1.0:
+        return _select_and_clip_prob(1.0, 0.0, cdf=cdf)
+
+    z = np.sqrt(n) * x
+    zsquared, zthree, zfour, zsix = z**2, z**3, z**4, z**6
+
+    qlog = -_PI_SQUARED / 8 / zsquared
+    if qlog < _MIN_LOG:  # z ~ 0.041743441416853426
+        return _select_and_clip_prob(0.0, 1.0, cdf=cdf)
+
+    q = np.exp(qlog)
+
+    # Coefficients of terms in the sums for K1, K2 and K3
+    k1a = -zsquared
+    k1b = _PI_SQUARED / 4
+
+    k2a = 6 * zsix + 2 * zfour
+    k2b = (2 * zfour - 5 * zsquared) * _PI_SQUARED / 4
+    k2c = _PI_FOUR * (1 - 2 * zsquared) / 16
+
+    k3d = _PI_SIX * (5 - 30 * zsquared) / 64
+    k3c = _PI_FOUR * (-60 * zsquared + 212 * zfour) / 16
+    k3b = _PI_SQUARED * (135 * zfour - 96 * zsix) / 4
+    k3a = -30 * zsix - 90 * z**8
+
+    K0to3 = np.zeros(4)
+    # Use a Horner scheme to evaluate sum c_i q^(i^2)
+    # Reduces to a sum over odd integers.
+    maxk = int(np.ceil(16 * z / np.pi))
+    for k in range(maxk, 0, -1):
+        m = 2 * k - 1
+        msquared, mfour, msix = m**2, m**4, m**6
+        qpower = np.power(q, 8 * k)
+        coeffs = np.array([1.0,
+                           k1a + k1b*msquared,
+                           k2a + k2b*msquared + k2c*mfour,
+                           k3a + k3b*msquared + k3c*mfour + k3d*msix])
+        K0to3 *= qpower
+        K0to3 += coeffs
+    K0to3 *= q
+    K0to3 *= _SQRT2PI
+    # z**10 > 0 as z > 0.04
+    K0to3 /= np.array([z, 6 * zfour, 72 * z**7, 6480 * z**10])
+
+    # Now do the other sum over the other terms, all integers k
+    # K_2:  (pi^2 k^2) q^(k^2),
+    # K_3:  (3pi^2 k^2 z^2 - pi^4 k^4)*q^(k^2)
+    # Don't expect much subtractive cancellation so use direct calculation
+    q = np.exp(-_PI_SQUARED / 2 / zsquared)
+    ks = np.arange(maxk, 0, -1)
+    ksquared = ks ** 2
+    sqrt3z = _SQRT3 * z
+    kspi = np.pi * ks
+    qpwers = q ** ksquared
+    k2extra = np.sum(ksquared * qpwers)
+    k2extra *= _PI_SQUARED * _SQRT2PI/(-36 * zthree)
+    K0to3[2] += k2extra
+    k3extra = np.sum((sqrt3z + kspi) * (sqrt3z - kspi) * ksquared * qpwers)
+    k3extra *= _PI_SQUARED * _SQRT2PI/(216 * zsix)
+    K0to3[3] += k3extra
+    powers_of_n = np.power(n * 1.0, np.arange(len(K0to3)) / 2.0)
+    K0to3 /= powers_of_n
+
+    if not cdf:
+        K0to3 *= -1
+        K0to3[0] += 1
+
+    Ksum = sum(K0to3)
+    return Ksum
+
+
+def _kolmogn(n, x, cdf=True):
+    """Computes the CDF(or SF) for the two-sided Kolmogorov-Smirnov statistic.
+
+    x must be of type float, n of type integer.
+
+    Simard & L'Ecuyer (2011) [7].
+    """
+    if np.isnan(n):
+        return n  # Keep the same type of nan
+    if int(n) != n or n <= 0:
+        return np.nan
+    if x >= 1.0:
+        return _select_and_clip_prob(1.0, 0.0, cdf=cdf)
+    if x <= 0.0:
+        return _select_and_clip_prob(0.0, 1.0, cdf=cdf)
+    t = n * x
+    if t <= 1.0:  # Ruben-Gambino: 1/2n <= x <= 1/n
+        if t <= 0.5:
+            return _select_and_clip_prob(0.0, 1.0, cdf=cdf)
+        if n <= 140:
+            prob = np.prod(np.arange(1, n+1) * (1.0/n) * (2*t - 1))
+        else:
+            prob = np.exp(_log_nfactorial_div_n_pow_n(n) + n * np.log(2*t-1))
+        return _select_and_clip_prob(prob, 1.0 - prob, cdf=cdf)
+    if t >= n - 1:  # Ruben-Gambino
+        prob = 2 * (1.0 - x)**n
+        return _select_and_clip_prob(1 - prob, prob, cdf=cdf)
+    if x >= 0.5:  # Exact: 2 * smirnov
+        prob = 2 * scipy.special.smirnov(n, x)
+        return _select_and_clip_prob(1.0 - prob, prob, cdf=cdf)
+
+    nxsquared = t * x
+    if n <= 140:
+        if nxsquared <= 0.754693:
+            prob = _kolmogn_DMTW(n, x, cdf=True)
+            return _select_and_clip_prob(prob, 1.0 - prob, cdf=cdf)
+        if nxsquared <= 4:
+            prob = _kolmogn_Pomeranz(n, x, cdf=True)
+            return _select_and_clip_prob(prob, 1.0 - prob, cdf=cdf)
+        # Now use Miller approximation of 2*smirnov
+        prob = 2 * scipy.special.smirnov(n, x)
+        return _select_and_clip_prob(1.0 - prob, prob, cdf=cdf)
+
+    # Split CDF and SF as they have different cutoffs on nxsquared.
+    if not cdf:
+        if nxsquared >= 370.0:
+            return 0.0
+        if nxsquared >= 2.2:
+            prob = 2 * scipy.special.smirnov(n, x)
+            return _clip_prob(prob)
+        # Fall through and compute the SF as 1.0-CDF
+    if nxsquared >= 18.0:
+        cdfprob = 1.0
+    elif n <= 100000 and n * x**1.5 <= 1.4:
+        cdfprob = _kolmogn_DMTW(n, x, cdf=True)
+    else:
+        cdfprob = _kolmogn_PelzGood(n, x, cdf=True)
+    return _select_and_clip_prob(cdfprob, 1.0 - cdfprob, cdf=cdf)
+
+
+def _kolmogn_p(n, x):
+    """Computes the PDF for the two-sided Kolmogorov-Smirnov statistic.
+
+    x must be of type float, n of type integer.
+    """
+    if np.isnan(n):
+        return n  # Keep the same type of nan
+    if int(n) != n or n <= 0:
+        return np.nan
+    if x >= 1.0 or x <= 0:
+        return 0
+    t = n * x
+    if t <= 1.0:
+        # Ruben-Gambino: n!/n^n * (2t-1)^n -> 2 n!/n^n * n^2 * (2t-1)^(n-1)
+        if t <= 0.5:
+            return 0.0
+        if n <= 140:
+            prd = np.prod(np.arange(1, n) * (1.0 / n) * (2 * t - 1))
+        else:
+            prd = np.exp(_log_nfactorial_div_n_pow_n(n) + (n-1) * np.log(2 * t - 1))
+        return prd * 2 * n**2
+    if t >= n - 1:
+        # Ruben-Gambino : 1-2(1-x)**n -> 2n*(1-x)**(n-1)
+        return 2 * (1.0 - x) ** (n-1) * n
+    if x >= 0.5:
+        return 2 * scipy.stats.ksone.pdf(x, n)
+
+    # Just take a small delta.
+    # Ideally x +/- delta would stay within [i/n, (i+1)/n] for some integer a.
+    # as the CDF is a piecewise degree n polynomial.
+    # It has knots at 1/n, 2/n, ... (n-1)/n
+    # and is not a C-infinity function at the knots
+    delta = x / 2.0**16
+    delta = min(delta, x - 1.0/n)
+    delta = min(delta, 0.5 - x)
+
+    def _kk(_x):
+        return kolmogn(n, _x)
+
+    return scipy.misc.derivative(_kk, x, dx=delta, order=5)
+
+
+def _kolmogni(n, p, q):
+    """Computes the PPF/ISF of kolmogn.
+
+    n of type integer, n>= 1
+    p is the CDF, q the SF, p+q=1
+    """
+    if np.isnan(n):
+        return n  # Keep the same type of nan
+    if int(n) != n or n <= 0:
+        return np.nan
+    if p <= 0:
+        return 1.0/n
+    if q <= 0:
+        return 1.0
+    delta = np.exp((np.log(p) - scipy.special.loggamma(n+1))/n)
+    if delta <= 1.0/n:
+        return (delta + 1.0 / n) / 2
+    x = -np.expm1(np.log(q/2.0)/n)
+    if x >= 1 - 1.0/n:
+        return x
+    x1 = scu._kolmogci(p)/np.sqrt(n)
+    x1 = min(x1, 1.0 - 1.0/n)
+    _f = lambda x: _kolmogn(n, x) - p
+    return scipy.optimize.brentq(_f, 1.0/n, x1, xtol=1e-14)
+
+
+def kolmogn(n, x, cdf=True):
+    """Computes the CDF for the two-sided Kolmogorov-Smirnov distribution.
+
+    The two-sided Kolmogorov-Smirnov distribution has as its CDF Pr(D_n <= x),
+    for a sample of size n drawn from a distribution with CDF F(t), where
+    D_n &= sup_t |F_n(t) - F(t)|, and
+    F_n(t) is the Empirical Cumulative Distribution Function of the sample.
+
+    Parameters
+    ----------
+    n : integer, array_like
+        the number of samples
+    x : float, array_like
+        The K-S statistic, float between 0 and 1
+    cdf : bool, optional
+        whether to compute the CDF(default=true) or the SF.
+
+    Returns
+    -------
+    cdf : ndarray
+        CDF (or SF it cdf is False) at the specified locations.
+
+    The return value has shape the result of numpy broadcasting n and x.
+    """
+    it = np.nditer([n, x, cdf, None],
+                   op_dtypes=[None, np.float64, np.bool_, np.float64])
+    for _n, _x, _cdf, z in it:
+        if np.isnan(_n):
+            z[...] = _n
+            continue
+        if int(_n) != _n:
+            raise ValueError(f'n is not integral: {_n}')
+        z[...] = _kolmogn(int(_n), _x, cdf=_cdf)
+    result = it.operands[-1]
+    return result
+
+
+def kolmognp(n, x):
+    """Computes the PDF for the two-sided Kolmogorov-Smirnov distribution.
+
+    Parameters
+    ----------
+    n : integer, array_like
+        the number of samples
+    x : float, array_like
+        The K-S statistic, float between 0 and 1
+
+    Returns
+    -------
+    pdf : ndarray
+        The PDF at the specified locations
+
+    The return value has shape the result of numpy broadcasting n and x.
+    """
+    it = np.nditer([n, x, None])
+    for _n, _x, z in it:
+        if np.isnan(_n):
+            z[...] = _n
+            continue
+        if int(_n) != _n:
+            raise ValueError(f'n is not integral: {_n}')
+        z[...] = _kolmogn_p(int(_n), _x)
+    result = it.operands[-1]
+    return result
+
+
+def kolmogni(n, q, cdf=True):
+    """Computes the PPF(or ISF) for the two-sided Kolmogorov-Smirnov distribution.
+
+    Parameters
+    ----------
+    n : integer, array_like
+        the number of samples
+    q : float, array_like
+        Probabilities, float between 0 and 1
+    cdf : bool, optional
+        whether to compute the PPF(default=true) or the ISF.
+
+    Returns
+    -------
+    ppf : ndarray
+        PPF (or ISF if cdf is False) at the specified locations
+
+    The return value has shape the result of numpy broadcasting n and x.
+    """
+    it = np.nditer([n, q, cdf, None])
+    for _n, _q, _cdf, z in it:
+        if np.isnan(_n):
+            z[...] = _n
+            continue
+        if int(_n) != _n:
+            raise ValueError(f'n is not integral: {_n}')
+        _pcdf, _psf = (_q, 1-_q) if _cdf else (1-_q, _q)
+        z[...] = _kolmogni(int(_n), _pcdf, _psf)
+    result = it.operands[-1]
+    return result

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_mannwhitneyu.py

@@ -0,0 +1,425 @@
+import numpy as np
+from collections import namedtuple
+from scipy import special
+from scipy import stats
+from ._axis_nan_policy import _axis_nan_policy_factory
+
+
+def _broadcast_concatenate(x, y, axis):
+    '''Broadcast then concatenate arrays, leaving concatenation axis last'''
+    x = np.moveaxis(x, axis, -1)
+    y = np.moveaxis(y, axis, -1)
+    z = np.broadcast(x[..., 0], y[..., 0])
+    x = np.broadcast_to(x, z.shape + (x.shape[-1],))
+    y = np.broadcast_to(y, z.shape + (y.shape[-1],))
+    z = np.concatenate((x, y), axis=-1)
+    return x, y, z
+
+
+class _MWU:
+    '''Distribution of MWU statistic under the null hypothesis'''
+    # Possible improvement: if m and n are small enough, use integer arithmetic
+
+    def __init__(self):
+        '''Minimal initializer'''
+        self._fmnks = -np.ones((1, 1, 1))
+
+    def pmf(self, k, m, n):
+        '''Probability mass function'''
+        self._resize_fmnks(m, n, np.max(k))
+        # could loop over just the unique elements, but probably not worth
+        # the time to find them
+        for i in np.ravel(k):
+            self._f(m, n, i)
+        return self._fmnks[m, n, k] / special.binom(m + n, m)
+
+    def cdf(self, k, m, n):
+        '''Cumulative distribution function'''
+        # We could use the fact that the distribution is symmetric to avoid
+        # summing more than m*n/2 terms, but it might not be worth the
+        # overhead. Let's leave that to an improvement.
+        pmfs = self.pmf(np.arange(0, np.max(k) + 1), m, n)
+        cdfs = np.cumsum(pmfs)
+        return cdfs[k]
+
+    def sf(self, k, m, n):
+        '''Survival function'''
+        # Use the fact that the distribution is symmetric; i.e.
+        # _f(m, n, m*n-k) = _f(m, n, k), and sum from the left
+        k = m*n - k
+        # Note that both CDF and SF include the PMF at k. The p-value is
+        # calculated from the SF and should include the mass at k, so this
+        # is desirable
+        return self.cdf(k, m, n)
+
+    def _resize_fmnks(self, m, n, k):
+        '''If necessary, expand the array that remembers PMF values'''
+        # could probably use `np.pad` but I'm not sure it would save code
+        shape_old = np.array(self._fmnks.shape)
+        shape_new = np.array((m+1, n+1, k+1))
+        if np.any(shape_new > shape_old):
+            shape = np.maximum(shape_old, shape_new)
+            fmnks = -np.ones(shape)             # create the new array
+            m0, n0, k0 = shape_old
+            fmnks[:m0, :n0, :k0] = self._fmnks  # copy remembered values
+            self._fmnks = fmnks
+
+    def _f(self, m, n, k):
+        '''Recursive implementation of function of [3] Theorem 2.5'''
+
+        # [3] Theorem 2.5 Line 1
+        if k < 0 or m < 0 or n < 0 or k > m*n:
+            return 0
+
+        # if already calculated, return the value
+        if self._fmnks[m, n, k] >= 0:
+            return self._fmnks[m, n, k]
+
+        if k == 0 and m >= 0 and n >= 0:  # [3] Theorem 2.5 Line 2
+            fmnk = 1
+        else:   # [3] Theorem 2.5 Line 3 / Equation 3
+            fmnk = self._f(m-1, n, k-n) + self._f(m, n-1, k)
+
+        self._fmnks[m, n, k] = fmnk  # remember result
+
+        return fmnk
+
+
+# Maintain state for faster repeat calls to mannwhitneyu w/ method='exact'
+_mwu_state = _MWU()
+
+
+def _tie_term(ranks):
+    """Tie correction term"""
+    # element i of t is the number of elements sharing rank i
+    _, t = np.unique(ranks, return_counts=True, axis=-1)
+    return (t**3 - t).sum(axis=-1)
+
+
+def _get_mwu_z(U, n1, n2, ranks, axis=0, continuity=True):
+    '''Standardized MWU statistic'''
+    # Follows mannwhitneyu [2]
+    mu = n1 * n2 / 2
+    n = n1 + n2
+
+    # Tie correction according to [2]
+    tie_term = np.apply_along_axis(_tie_term, -1, ranks)
+    s = np.sqrt(n1*n2/12 * ((n + 1) - tie_term/(n*(n-1))))
+
+    # equivalent to using scipy.stats.tiecorrect
+    # T = np.apply_along_axis(stats.tiecorrect, -1, ranks)
+    # s = np.sqrt(T * n1 * n2 * (n1+n2+1) / 12.0)
+
+    numerator = U - mu
+
+    # Continuity correction.
+    # Because SF is always used to calculate the p-value, we can always
+    # _subtract_ 0.5 for the continuity correction. This always increases the
+    # p-value to account for the rest of the probability mass _at_ q = U.
+    if continuity:
+        numerator -= 0.5
+
+    # no problem evaluating the norm SF at an infinity
+    with np.errstate(divide='ignore', invalid='ignore'):
+        z = numerator / s
+    return z
+
+
+def _mwu_input_validation(x, y, use_continuity, alternative, axis, method):
+    ''' Input validation and standardization for mannwhitneyu '''
+    # Would use np.asarray_chkfinite, but infs are OK
+    x, y = np.atleast_1d(x), np.atleast_1d(y)
+    if np.isnan(x).any() or np.isnan(y).any():
+        raise ValueError('`x` and `y` must not contain NaNs.')
+    if np.size(x) == 0 or np.size(y) == 0:
+        raise ValueError('`x` and `y` must be of nonzero size.')
+
+    bools = {True, False}
+    if use_continuity not in bools:
+        raise ValueError(f'`use_continuity` must be one of {bools}.')
+
+    alternatives = {"two-sided", "less", "greater"}
+    alternative = alternative.lower()
+    if alternative not in alternatives:
+        raise ValueError(f'`alternative` must be one of {alternatives}.')
+
+    axis_int = int(axis)
+    if axis != axis_int:
+        raise ValueError('`axis` must be an integer.')
+
+    methods = {"asymptotic", "exact", "auto"}
+    method = method.lower()
+    if method not in methods:
+        raise ValueError(f'`method` must be one of {methods}.')
+
+    return x, y, use_continuity, alternative, axis_int, method
+
+
+def _tie_check(xy):
+    """Find any ties in data"""
+    _, t = np.unique(xy, return_counts=True, axis=-1)
+    return np.any(t != 1)
+
+
+def _mwu_choose_method(n1, n2, xy, method):
+    """Choose method 'asymptotic' or 'exact' depending on input size, ties"""
+
+    # if both inputs are large, asymptotic is OK
+    if n1 > 8 and n2 > 8:
+        return "asymptotic"
+
+    # if there are any ties, asymptotic is preferred
+    if np.apply_along_axis(_tie_check, -1, xy).any():
+        return "asymptotic"
+
+    return "exact"
+
+
+MannwhitneyuResult = namedtuple('MannwhitneyuResult', ('statistic', 'pvalue'))
+
+
+@_axis_nan_policy_factory(MannwhitneyuResult, n_samples=2)
+def mannwhitneyu(x, y, use_continuity=True, alternative="two-sided",
+                 axis=0, method="auto"):
+    r'''Perform the Mann-Whitney U rank test on two independent samples.
+
+    The Mann-Whitney U test is a nonparametric test of the null hypothesis
+    that the distribution underlying sample `x` is the same as the
+    distribution underlying sample `y`. It is often used as a test of
+    difference in location between distributions.
+
+    Parameters
+    ----------
+    x, y : array-like
+        N-d arrays of samples. The arrays must be broadcastable except along
+        the dimension given by `axis`.
+    use_continuity : bool, optional
+            Whether a continuity correction (1/2) should be applied.
+            Default is True when `method` is ``'asymptotic'``; has no effect
+            otherwise.
+    alternative : {'two-sided', 'less', 'greater'}, optional
+        Defines the alternative hypothesis. Default is 'two-sided'.
+        Let *F(u)* and *G(u)* be the cumulative distribution functions of the
+        distributions underlying `x` and `y`, respectively. Then the following
+        alternative hypotheses are available:
+
+        * 'two-sided': the distributions are not equal, i.e. *F(u) ≠ G(u)* for
+          at least one *u*.
+        * 'less': the distribution underlying `x` is stochastically less
+          than the distribution underlying `y`, i.e. *F(u) > G(u)* for all *u*.
+        * 'greater': the distribution underlying `x` is stochastically greater
+          than the distribution underlying `y`, i.e. *F(u) < G(u)* for all *u*.
+
+        Under a more restrictive set of assumptions, the alternative hypotheses
+        can be expressed in terms of the locations of the distributions;
+        see [5] section 5.1.
+    axis : int, optional
+        Axis along which to perform the test. Default is 0.
+    method : {'auto', 'asymptotic', 'exact'}, optional
+        Selects the method used to calculate the *p*-value.
+        Default is 'auto'. The following options are available.
+
+        * ``'asymptotic'``: compares the standardized test statistic
+          against the normal distribution, correcting for ties.
+        * ``'exact'``: computes the exact *p*-value by comparing the observed
+          :math:`U` statistic against the exact distribution of the :math:`U`
+          statistic under the null hypothesis. No correction is made for ties.
+        * ``'auto'``: chooses ``'exact'`` when the size of one of the samples
+          is less than 8 and there are no ties; chooses ``'asymptotic'``
+          otherwise.
+
+    Returns
+    -------
+    res : MannwhitneyuResult
+        An object containing attributes:
+
+        statistic : float
+            The Mann-Whitney U statistic corresponding with sample `x`. See
+            Notes for the test statistic corresponding with sample `y`.
+        pvalue : float
+            The associated *p*-value for the chosen `alternative`.
+
+    Notes
+    -----
+    If ``U1`` is the statistic corresponding with sample `x`, then the
+    statistic corresponding with sample `y` is
+    `U2 = `x.shape[axis] * y.shape[axis] - U1``.
+
+    `mannwhitneyu` is for independent samples. For related / paired samples,
+    consider `scipy.stats.wilcoxon`.
+
+    `method` ``'exact'`` is recommended when there are no ties and when either
+    sample size is less than 8 [1]_. The implementation follows the recurrence
+    relation originally proposed in [1]_ as it is described in [3]_.
+    Note that the exact method is *not* corrected for ties, but
+    `mannwhitneyu` will not raise errors or warnings if there are ties in the
+    data.
+
+    The Mann-Whitney U test is a non-parametric version of the t-test for
+    independent samples. When the the means of samples from the populations
+    are normally distributed, consider `scipy.stats.ttest_ind`.
+
+    See Also
+    --------
+    scipy.stats.wilcoxon, scipy.stats.ranksums, scipy.stats.ttest_ind
+
+    References
+    ----------
+    .. [1] H.B. Mann and D.R. Whitney, "On a test of whether one of two random
+           variables is stochastically larger than the other", The Annals of
+           Mathematical Statistics, Vol. 18, pp. 50-60, 1947.
+    .. [2] Mann-Whitney U Test, Wikipedia,
+           http://en.wikipedia.org/wiki/Mann-Whitney_U_test
+    .. [3] A. Di Bucchianico, "Combinatorics, computer algebra, and the
+           Wilcoxon-Mann-Whitney test", Journal of Statistical Planning and
+           Inference, Vol. 79, pp. 349-364, 1999.
+    .. [4] Rosie Shier, "Statistics: 2.3 The Mann-Whitney U Test", Mathematics
+           Learning Support Centre, 2004.
+    .. [5] Michael P. Fay and Michael A. Proschan. "Wilcoxon-Mann-Whitney
+           or t-test? On assumptions for hypothesis tests and multiple \
+           interpretations of decision rules." Statistics surveys, Vol. 4, pp.
+           1-39, 2010. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2857732/
+
+    Examples
+    --------
+    We follow the example from [4]_: nine randomly sampled young adults were
+    diagnosed with type II diabetes at the ages below.
+
+    >>> males = [19, 22, 16, 29, 24]
+    >>> females = [20, 11, 17, 12]
+
+    We use the Mann-Whitney U test to assess whether there is a statistically
+    significant difference in the diagnosis age of males and females.
+    The null hypothesis is that the distribution of male diagnosis ages is
+    the same as the distribution of female diagnosis ages. We decide
+    that a confidence level of 95% is required to reject the null hypothesis
+    in favor of the alternative that the distributions are different.
+    Since the number of samples is very small and there are no ties in the
+    data, we can compare the observed test statistic against the *exact*
+    distribution of the test statistic under the null hypothesis.
+
+    >>> from scipy.stats import mannwhitneyu
+    >>> U1, p = mannwhitneyu(males, females, method="exact")
+    >>> print(U1)
+    17.0
+
+    `mannwhitneyu` always reports the statistic associated with the first
+    sample, which, in this case, is males. This agrees with :math:`U_M = 17`
+    reported in [4]_. The statistic associated with the second statistic
+    can be calculated:
+
+    >>> nx, ny = len(males), len(females)
+    >>> U2 = nx*ny - U1
+    >>> print(U2)
+    3.0
+
+    This agrees with :math:`U_F = 3` reported in [4]_. The two-sided
+    *p*-value can be calculated from either statistic, and the value produced
+    by `mannwhitneyu` agrees with :math:`p = 0.11` reported in [4]_.
+
+    >>> print(p)
+    0.1111111111111111
+
+    The exact distribution of the test statistic is asymptotically normal, so
+    the example continues by comparing the exact *p*-value against the
+    *p*-value produced using the normal approximation.
+
+    >>> _, pnorm = mannwhitneyu(males, females, method="asymptotic")
+    >>> print(pnorm)
+    0.11134688653314041
+
+    Here `mannwhitneyu`'s reported *p*-value appears to conflict with the
+    value :math:`p = 0.09` given in [4]_. The reason is that [4]_
+    does not apply the continuity correction performed by `mannwhitneyu`;
+    `mannwhitneyu` reduces the distance between the test statistic and the
+    mean :math:`\mu = n_x n_y / 2` by 0.5 to correct for the fact that the
+    discrete statistic is being compared against a continuous distribution.
+    Here, the :math:`U` statistic used is less than the mean, so we reduce
+    the distance by adding 0.5 in the numerator.
+
+    >>> import numpy as np
+    >>> from scipy.stats import norm
+    >>> U = min(U1, U2)
+    >>> N = nx + ny
+    >>> z = (U - nx*ny/2 + 0.5) / np.sqrt(nx*ny * (N + 1)/ 12)
+    >>> p = 2 * norm.cdf(z)  # use CDF to get p-value from smaller statistic
+    >>> print(p)
+    0.11134688653314041
+
+    If desired, we can disable the continuity correction to get a result
+    that agrees with that reported in [4]_.
+
+    >>> _, pnorm = mannwhitneyu(males, females, use_continuity=False,
+    ...                         method="asymptotic")
+    >>> print(pnorm)
+    0.0864107329737
+
+    Regardless of whether we perform an exact or asymptotic test, the
+    probability of the test statistic being as extreme or more extreme by
+    chance exceeds 5%, so we do not consider the results statistically
+    significant.
+
+    Suppose that, before seeing the data, we had hypothesized that females
+    would tend to be diagnosed at a younger age than males.
+    In that case, it would be natural to provide the female ages as the
+    first input, and we would have performed a one-sided test using
+    ``alternative = 'less'``: females are diagnosed at an age that is
+    stochastically less than that of males.
+
+    >>> res = mannwhitneyu(females, males, alternative="less", method="exact")
+    >>> print(res)
+    MannwhitneyuResult(statistic=3.0, pvalue=0.05555555555555555)
+
+    Again, the probability of getting a sufficiently low value of the
+    test statistic by chance under the null hypothesis is greater than 5%,
+    so we do not reject the null hypothesis in favor of our alternative.
+
+    If it is reasonable to assume that the means of samples from the
+    populations are normally distributed, we could have used a t-test to
+    perform the analysis.
+
+    >>> from scipy.stats import ttest_ind
+    >>> res = ttest_ind(females, males, alternative="less")
+    >>> print(res)
+    Ttest_indResult(statistic=-2.239334696520584, pvalue=0.030068441095757924)
+
+    Under this assumption, the *p*-value would be low enough to reject the
+    null hypothesis in favor of the alternative.
+
+    '''
+
+    x, y, use_continuity, alternative, axis_int, method = (
+        _mwu_input_validation(x, y, use_continuity, alternative, axis, method))
+
+    x, y, xy = _broadcast_concatenate(x, y, axis)
+
+    n1, n2 = x.shape[-1], y.shape[-1]
+
+    if method == "auto":
+        method = _mwu_choose_method(n1, n2, xy, method)
+
+    # Follows [2]
+    ranks = stats.rankdata(xy, axis=-1)  # method 2, step 1
+    R1 = ranks[..., :n1].sum(axis=-1)    # method 2, step 2
+    U1 = R1 - n1*(n1+1)/2                # method 2, step 3
+    U2 = n1 * n2 - U1                    # as U1 + U2 = n1 * n2
+
+    if alternative == "greater":
+        U, f = U1, 1  # U is the statistic to use for p-value, f is a factor
+    elif alternative == "less":
+        U, f = U2, 1  # Due to symmetry, use SF of U2 rather than CDF of U1
+    else:
+        U, f = np.maximum(U1, U2), 2  # multiply SF by two for two-sided test
+
+    if method == "exact":
+        p = _mwu_state.sf(U.astype(int), n1, n2)
+    elif method == "asymptotic":
+        z = _get_mwu_z(U, n1, n2, ranks, continuity=use_continuity)
+        p = stats.norm.sf(z)
+    p *= f
+
+    # Ensure that test statistic is not greater than 1
+    # This could happen for exact test when U = m*n/2
+    p = np.clip(p, 0, 1)
+
+    return MannwhitneyuResult(U1, p)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_mstats_extras.py

@@ -0,0 +1,474 @@
+"""
+Additional statistics functions with support for masked arrays.
+
+"""
+
+# Original author (2007): Pierre GF Gerard-Marchant
+
+
+__all__ = ['compare_medians_ms',
+           'hdquantiles', 'hdmedian', 'hdquantiles_sd',
+           'idealfourths',
+           'median_cihs','mjci','mquantiles_cimj',
+           'rsh',
+           'trimmed_mean_ci',]
+
+
+import numpy as np
+from numpy import float_, int_, ndarray
+
+import numpy.ma as ma
+from numpy.ma import MaskedArray
+
+from . import _mstats_basic as mstats
+
+from scipy.stats.distributions import norm, beta, t, binom
+
+
+def hdquantiles(data, prob=list([.25,.5,.75]), axis=None, var=False,):
+    """
+    Computes quantile estimates with the Harrell-Davis method.
+
+    The quantile estimates are calculated as a weighted linear combination
+    of order statistics.
+
+    Parameters
+    ----------
+    data : array_like
+        Data array.
+    prob : sequence, optional
+        Sequence of quantiles to compute.
+    axis : int or None, optional
+        Axis along which to compute the quantiles. If None, use a flattened
+        array.
+    var : bool, optional
+        Whether to return the variance of the estimate.
+
+    Returns
+    -------
+    hdquantiles : MaskedArray
+        A (p,) array of quantiles (if `var` is False), or a (2,p) array of
+        quantiles and variances (if `var` is True), where ``p`` is the
+        number of quantiles.
+
+    See Also
+    --------
+    hdquantiles_sd
+
+    """
+    def _hd_1D(data,prob,var):
+        "Computes the HD quantiles for a 1D array. Returns nan for invalid data."
+        xsorted = np.squeeze(np.sort(data.compressed().view(ndarray)))
+        # Don't use length here, in case we have a numpy scalar
+        n = xsorted.size
+
+        hd = np.empty((2,len(prob)), float_)
+        if n < 2:
+            hd.flat = np.nan
+            if var:
+                return hd
+            return hd[0]
+
+        v = np.arange(n+1) / float(n)
+        betacdf = beta.cdf
+        for (i,p) in enumerate(prob):
+            _w = betacdf(v, (n+1)*p, (n+1)*(1-p))
+            w = _w[1:] - _w[:-1]
+            hd_mean = np.dot(w, xsorted)
+            hd[0,i] = hd_mean
+            #
+            hd[1,i] = np.dot(w, (xsorted-hd_mean)**2)
+            #
+        hd[0, prob == 0] = xsorted[0]
+        hd[0, prob == 1] = xsorted[-1]
+        if var:
+            hd[1, prob == 0] = hd[1, prob == 1] = np.nan
+            return hd
+        return hd[0]
+    # Initialization & checks
+    data = ma.array(data, copy=False, dtype=float_)
+    p = np.array(prob, copy=False, ndmin=1)
+    # Computes quantiles along axis (or globally)
+    if (axis is None) or (data.ndim == 1):
+        result = _hd_1D(data, p, var)
+    else:
+        if data.ndim > 2:
+            raise ValueError("Array 'data' must be at most two dimensional, "
+                             "but got data.ndim = %d" % data.ndim)
+        result = ma.apply_along_axis(_hd_1D, axis, data, p, var)
+
+    return ma.fix_invalid(result, copy=False)
+
+
+def hdmedian(data, axis=-1, var=False):
+    """
+    Returns the Harrell-Davis estimate of the median along the given axis.
+
+    Parameters
+    ----------
+    data : ndarray
+        Data array.
+    axis : int, optional
+        Axis along which to compute the quantiles. If None, use a flattened
+        array.
+    var : bool, optional
+        Whether to return the variance of the estimate.
+
+    Returns
+    -------
+    hdmedian : MaskedArray
+        The median values.  If ``var=True``, the variance is returned inside
+        the masked array.  E.g. for a 1-D array the shape change from (1,) to
+        (2,).
+
+    """
+    result = hdquantiles(data,[0.5], axis=axis, var=var)
+    return result.squeeze()
+
+
+def hdquantiles_sd(data, prob=list([.25,.5,.75]), axis=None):
+    """
+    The standard error of the Harrell-Davis quantile estimates by jackknife.
+
+    Parameters
+    ----------
+    data : array_like
+        Data array.
+    prob : sequence, optional
+        Sequence of quantiles to compute.
+    axis : int, optional
+        Axis along which to compute the quantiles. If None, use a flattened
+        array.
+
+    Returns
+    -------
+    hdquantiles_sd : MaskedArray
+        Standard error of the Harrell-Davis quantile estimates.
+
+    See Also
+    --------
+    hdquantiles
+
+    """
+    def _hdsd_1D(data, prob):
+        "Computes the std error for 1D arrays."
+        xsorted = np.sort(data.compressed())
+        n = len(xsorted)
+
+        hdsd = np.empty(len(prob), float_)
+        if n < 2:
+            hdsd.flat = np.nan
+
+        vv = np.arange(n) / float(n-1)
+        betacdf = beta.cdf
+
+        for (i,p) in enumerate(prob):
+            _w = betacdf(vv, (n+1)*p, (n+1)*(1-p))
+            w = _w[1:] - _w[:-1]
+            mx_ = np.fromiter([w[:k] @ xsorted[:k] + w[k:] @ xsorted[k+1:]
+                               for k in range(n)], dtype=float_)
+            # mx_var = np.array(mx_.var(), copy=False, ndmin=1) * n / (n - 1)
+            # hdsd[i] = (n - 1) * np.sqrt(mx_var / n)
+            hdsd[i] = np.sqrt(mx_.var() * (n - 1))
+        return hdsd
+
+    # Initialization & checks
+    data = ma.array(data, copy=False, dtype=float_)
+    p = np.array(prob, copy=False, ndmin=1)
+    # Computes quantiles along axis (or globally)
+    if (axis is None):
+        result = _hdsd_1D(data, p)
+    else:
+        if data.ndim > 2:
+            raise ValueError("Array 'data' must be at most two dimensional, "
+                             "but got data.ndim = %d" % data.ndim)
+        result = ma.apply_along_axis(_hdsd_1D, axis, data, p)
+
+    return ma.fix_invalid(result, copy=False).ravel()
+
+
+def trimmed_mean_ci(data, limits=(0.2,0.2), inclusive=(True,True),
+                    alpha=0.05, axis=None):
+    """
+    Selected confidence interval of the trimmed mean along the given axis.
+
+    Parameters
+    ----------
+    data : array_like
+        Input data.
+    limits : {None, tuple}, optional
+        None or a two item tuple.
+        Tuple of the percentages to cut on each side of the array, with respect
+        to the number of unmasked data, as floats between 0. and 1. If ``n``
+        is the number of unmasked data before trimming, then
+        (``n * limits[0]``)th smallest data and (``n * limits[1]``)th
+        largest data are masked.  The total number of unmasked data after
+        trimming is ``n * (1. - sum(limits))``.
+        The value of one limit can be set to None to indicate an open interval.
+
+        Defaults to (0.2, 0.2).
+    inclusive : (2,) tuple of boolean, optional
+        If relative==False, tuple indicating whether values exactly equal to
+        the absolute limits are allowed.
+        If relative==True, tuple indicating whether the number of data being
+        masked on each side should be rounded (True) or truncated (False).
+
+        Defaults to (True, True).
+    alpha : float, optional
+        Confidence level of the intervals.
+
+        Defaults to 0.05.
+    axis : int, optional
+        Axis along which to cut. If None, uses a flattened version of `data`.
+
+        Defaults to None.
+
+    Returns
+    -------
+    trimmed_mean_ci : (2,) ndarray
+        The lower and upper confidence intervals of the trimmed data.
+
+    """
+    data = ma.array(data, copy=False)
+    trimmed = mstats.trimr(data, limits=limits, inclusive=inclusive, axis=axis)
+    tmean = trimmed.mean(axis)
+    tstde = mstats.trimmed_stde(data,limits=limits,inclusive=inclusive,axis=axis)
+    df = trimmed.count(axis) - 1
+    tppf = t.ppf(1-alpha/2.,df)
+    return np.array((tmean - tppf*tstde, tmean+tppf*tstde))
+
+
+def mjci(data, prob=[0.25,0.5,0.75], axis=None):
+    """
+    Returns the Maritz-Jarrett estimators of the standard error of selected
+    experimental quantiles of the data.
+
+    Parameters
+    ----------
+    data : ndarray
+        Data array.
+    prob : sequence, optional
+        Sequence of quantiles to compute.
+    axis : int or None, optional
+        Axis along which to compute the quantiles. If None, use a flattened
+        array.
+
+    """
+    def _mjci_1D(data, p):
+        data = np.sort(data.compressed())
+        n = data.size
+        prob = (np.array(p) * n + 0.5).astype(int_)
+        betacdf = beta.cdf
+
+        mj = np.empty(len(prob), float_)
+        x = np.arange(1,n+1, dtype=float_) / n
+        y = x - 1./n
+        for (i,m) in enumerate(prob):
+            W = betacdf(x,m-1,n-m) - betacdf(y,m-1,n-m)
+            C1 = np.dot(W,data)
+            C2 = np.dot(W,data**2)
+            mj[i] = np.sqrt(C2 - C1**2)
+        return mj
+
+    data = ma.array(data, copy=False)
+    if data.ndim > 2:
+        raise ValueError("Array 'data' must be at most two dimensional, "
+                         "but got data.ndim = %d" % data.ndim)
+
+    p = np.array(prob, copy=False, ndmin=1)
+    # Computes quantiles along axis (or globally)
+    if (axis is None):
+        return _mjci_1D(data, p)
+    else:
+        return ma.apply_along_axis(_mjci_1D, axis, data, p)
+
+
+def mquantiles_cimj(data, prob=[0.25,0.50,0.75], alpha=0.05, axis=None):
+    """
+    Computes the alpha confidence interval for the selected quantiles of the
+    data, with Maritz-Jarrett estimators.
+
+    Parameters
+    ----------
+    data : ndarray
+        Data array.
+    prob : sequence, optional
+        Sequence of quantiles to compute.
+    alpha : float, optional
+        Confidence level of the intervals.
+    axis : int or None, optional
+        Axis along which to compute the quantiles.
+        If None, use a flattened array.
+
+    Returns
+    -------
+    ci_lower : ndarray
+        The lower boundaries of the confidence interval.  Of the same length as
+        `prob`.
+    ci_upper : ndarray
+        The upper boundaries of the confidence interval.  Of the same length as
+        `prob`.
+
+    """
+    alpha = min(alpha, 1 - alpha)
+    z = norm.ppf(1 - alpha/2.)
+    xq = mstats.mquantiles(data, prob, alphap=0, betap=0, axis=axis)
+    smj = mjci(data, prob, axis=axis)
+    return (xq - z * smj, xq + z * smj)
+
+
+def median_cihs(data, alpha=0.05, axis=None):
+    """
+    Computes the alpha-level confidence interval for the median of the data.
+
+    Uses the Hettmasperger-Sheather method.
+
+    Parameters
+    ----------
+    data : array_like
+        Input data. Masked values are discarded. The input should be 1D only,
+        or `axis` should be set to None.
+    alpha : float, optional
+        Confidence level of the intervals.
+    axis : int or None, optional
+        Axis along which to compute the quantiles. If None, use a flattened
+        array.
+
+    Returns
+    -------
+    median_cihs
+        Alpha level confidence interval.
+
+    """
+    def _cihs_1D(data, alpha):
+        data = np.sort(data.compressed())
+        n = len(data)
+        alpha = min(alpha, 1-alpha)
+        k = int(binom._ppf(alpha/2., n, 0.5))
+        gk = binom.cdf(n-k,n,0.5) - binom.cdf(k-1,n,0.5)
+        if gk < 1-alpha:
+            k -= 1
+            gk = binom.cdf(n-k,n,0.5) - binom.cdf(k-1,n,0.5)
+        gkk = binom.cdf(n-k-1,n,0.5) - binom.cdf(k,n,0.5)
+        I = (gk - 1 + alpha)/(gk - gkk)
+        lambd = (n-k) * I / float(k + (n-2*k)*I)
+        lims = (lambd*data[k] + (1-lambd)*data[k-1],
+                lambd*data[n-k-1] + (1-lambd)*data[n-k])
+        return lims
+    data = ma.array(data, copy=False)
+    # Computes quantiles along axis (or globally)
+    if (axis is None):
+        result = _cihs_1D(data, alpha)
+    else:
+        if data.ndim > 2:
+            raise ValueError("Array 'data' must be at most two dimensional, "
+                             "but got data.ndim = %d" % data.ndim)
+        result = ma.apply_along_axis(_cihs_1D, axis, data, alpha)
+
+    return result
+
+
+def compare_medians_ms(group_1, group_2, axis=None):
+    """
+    Compares the medians from two independent groups along the given axis.
+
+    The comparison is performed using the McKean-Schrader estimate of the
+    standard error of the medians.
+
+    Parameters
+    ----------
+    group_1 : array_like
+        First dataset.  Has to be of size >=7.
+    group_2 : array_like
+        Second dataset.  Has to be of size >=7.
+    axis : int, optional
+        Axis along which the medians are estimated. If None, the arrays are
+        flattened.  If `axis` is not None, then `group_1` and `group_2`
+        should have the same shape.
+
+    Returns
+    -------
+    compare_medians_ms : {float, ndarray}
+        If `axis` is None, then returns a float, otherwise returns a 1-D
+        ndarray of floats with a length equal to the length of `group_1`
+        along `axis`.
+
+    """
+    (med_1, med_2) = (ma.median(group_1,axis=axis), ma.median(group_2,axis=axis))
+    (std_1, std_2) = (mstats.stde_median(group_1, axis=axis),
+                      mstats.stde_median(group_2, axis=axis))
+    W = np.abs(med_1 - med_2) / ma.sqrt(std_1**2 + std_2**2)
+    return 1 - norm.cdf(W)
+
+
+def idealfourths(data, axis=None):
+    """
+    Returns an estimate of the lower and upper quartiles.
+
+    Uses the ideal fourths algorithm.
+
+    Parameters
+    ----------
+    data : array_like
+        Input array.
+    axis : int, optional
+        Axis along which the quartiles are estimated. If None, the arrays are
+        flattened.
+
+    Returns
+    -------
+    idealfourths : {list of floats, masked array}
+        Returns the two internal values that divide `data` into four parts
+        using the ideal fourths algorithm either along the flattened array
+        (if `axis` is None) or along `axis` of `data`.
+
+    """
+    def _idf(data):
+        x = data.compressed()
+        n = len(x)
+        if n < 3:
+            return [np.nan,np.nan]
+        (j,h) = divmod(n/4. + 5/12.,1)
+        j = int(j)
+        qlo = (1-h)*x[j-1] + h*x[j]
+        k = n - j
+        qup = (1-h)*x[k] + h*x[k-1]
+        return [qlo, qup]
+    data = ma.sort(data, axis=axis).view(MaskedArray)
+    if (axis is None):
+        return _idf(data)
+    else:
+        return ma.apply_along_axis(_idf, axis, data)
+
+
+def rsh(data, points=None):
+    """
+    Evaluates Rosenblatt's shifted histogram estimators for each data point.
+
+    Rosenblatt's estimator is a centered finite-difference approximation to the
+    derivative of the empirical cumulative distribution function.
+
+    Parameters
+    ----------
+    data : sequence
+        Input data, should be 1-D. Masked values are ignored.
+    points : sequence or None, optional
+        Sequence of points where to evaluate Rosenblatt shifted histogram.
+        If None, use the data.
+
+    """
+    data = ma.array(data, copy=False)
+    if points is None:
+        points = data
+    else:
+        points = np.array(points, copy=False, ndmin=1)
+
+    if data.ndim != 1:
+        raise AttributeError("The input array should be 1D only !")
+
+    n = data.count()
+    r = idealfourths(data, axis=None)
+    h = 1.2 * (r[-1]-r[0]) / n**(1./5)
+    nhi = (data[:,None] <= points[None,:] + h).sum(0)
+    nlo = (data[:,None] < points[None,:] - h).sum(0)
+    return (nhi-nlo) / (2.*n*h)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_page_trend_test.py

@@ -0,0 +1,476 @@
+from itertools import permutations
+import numpy as np
+import math
+from ._continuous_distns import norm
+import scipy.stats
+from dataclasses import make_dataclass
+
+
+PageTrendTestResult = make_dataclass("PageTrendTestResult",
+                                     ("statistic", "pvalue", "method"))
+
+
+def page_trend_test(data, ranked=False, predicted_ranks=None, method='auto'):
+    r"""
+    Perform Page's Test, a measure of trend in observations between treatments.
+
+    Page's Test (also known as Page's :math:`L` test) is useful when:
+
+    * there are :math:`n \geq 3` treatments,
+    * :math:`m \geq 2` subjects are observed for each treatment, and
+    * the observations are hypothesized to have a particular order.
+
+    Specifically, the test considers the null hypothesis that
+
+    .. math::
+
+        m_1 = m_2 = m_3 \cdots = m_n,
+
+    where :math:`m_j` is the mean of the observed quantity under treatment
+    :math:`j`, against the alternative hypothesis that
+
+    .. math::
+
+        m_1 \leq m_2 \leq m_3 \leq \cdots \leq m_n,
+
+    where at least one inequality is strict.
+
+    As noted by [4]_, Page's :math:`L` test has greater statistical power than
+    the Friedman test against the alternative that there is a difference in
+    trend, as Friedman's test only considers a difference in the means of the
+    observations without considering their order. Whereas Spearman :math:`\rho`
+    considers the correlation between the ranked observations of two variables
+    (e.g. the airspeed velocity of a swallow vs. the weight of the coconut it
+    carries), Page's :math:`L` is concerned with a trend in an observation
+    (e.g. the airspeed velocity of a swallow) across several distinct
+    treatments (e.g. carrying each of five coconuts of different weight) even
+    as the observation is repeated with multiple subjects (e.g. one European
+    swallow and one African swallow).
+
+    Parameters
+    ----------
+    data : array-like
+        A :math:`m \times n` array; the element in row :math:`i` and
+        column :math:`j` is the observation corresponding with subject
+        :math:`i` and treatment :math:`j`. By default, the columns are
+        assumed to be arranged in order of increasing predicted mean.
+
+    ranked : boolean, optional
+        By default, `data` is assumed to be observations rather than ranks;
+        it will be ranked with `scipy.stats.rankdata` along ``axis=1``. If
+        `data` is provided in the form of ranks, pass argument ``True``.
+
+    predicted_ranks : array-like, optional
+        The predicted ranks of the column means. If not specified,
+        the columns are assumed to be arranged in order of increasing
+        predicted mean, so the default `predicted_ranks` are
+        :math:`[1, 2, \dots, n-1, n]`.
+
+    method : {'auto', 'asymptotic', 'exact'}, optional
+        Selects the method used to calculate the *p*-value. The following
+        options are available.
+
+        * 'auto': selects between 'exact' and 'asymptotic' to
+          achieve reasonably accurate results in reasonable time (default)
+        * 'asymptotic': compares the standardized test statistic against
+          the normal distribution
+        * 'exact': computes the exact *p*-value by comparing the observed
+          :math:`L` statistic against those realized by all possible
+          permutations of ranks (under the null hypothesis that each
+          permutation is equally likely)
+
+    Returns
+    -------
+    res : PageTrendTestResult
+        An object containing attributes:
+
+        statistic : float
+            Page's :math:`L` test statistic.
+        pvalue : float
+            The associated *p*-value
+        method : {'asymptotic', 'exact'}
+            The method used to compute the *p*-value
+
+    See Also
+    --------
+    rankdata, friedmanchisquare, spearmanr
+
+    Notes
+    -----
+    As noted in [1]_, "the :math:`n` 'treatments' could just as well represent
+    :math:`n` objects or events or performances or persons or trials ranked."
+    Similarly, the :math:`m` 'subjects' could equally stand for :math:`m`
+    "groupings by ability or some other control variable, or judges doing
+    the ranking, or random replications of some other sort."
+
+    The procedure for calculating the :math:`L` statistic, adapted from
+    [1]_, is:
+
+    1. "Predetermine with careful logic the appropriate hypotheses
+       concerning the predicted ording of the experimental results.
+       If no reasonable basis for ordering any treatments is known, the
+       :math:`L` test is not appropriate."
+    2. "As in other experiments, determine at what level of confidence
+       you will reject the null hypothesis that there is no agreement of
+       experimental results with the monotonic hypothesis."
+    3. "Cast the experimental material into a two-way table of :math:`n`
+       columns (treatments, objects ranked, conditions) and :math:`m`
+       rows (subjects, replication groups, levels of control variables)."
+    4. "When experimental observations are recorded, rank them across each
+       row", e.g. ``ranks = scipy.stats.rankdata(data, axis=1)``.
+    5. "Add the ranks in each column", e.g.
+       ``colsums = np.sum(ranks, axis=0)``.
+    6. "Multiply each sum of ranks by the predicted rank for that same
+       column", e.g. ``products = predicted_ranks * colsums``.
+    7. "Sum all such products", e.g. ``L = products.sum()``.
+
+    [1]_ continues by suggesting use of the standardized statistic
+
+    .. math::
+
+        \chi_L^2 = \frac{\left[12L-3mn(n+1)^2\right]^2}{mn^2(n^2-1)(n+1)}
+
+    "which is distributed approximately as chi-square with 1 degree of
+    freedom. The ordinary use of :math:`\chi^2` tables would be
+    equivalent to a two-sided test of agreement. If a one-sided test
+    is desired, *as will almost always be the case*, the probability
+    discovered in the chi-square table should be *halved*."
+
+    However, this standardized statistic does not distinguish between the
+    observed values being well correlated with the predicted ranks and being
+    _anti_-correlated with the predicted ranks. Instead, we follow [2]_
+    and calculate the standardized statistic
+
+    .. math::
+
+        \Lambda = \frac{L - E_0}{\sqrt{V_0}},
+
+    where :math:`E_0 = \frac{1}{4} mn(n+1)^2` and
+    :math:`V_0 = \frac{1}{144} mn^2(n+1)(n^2-1)`, "which is asymptotically
+    normal under the null hypothesis".
+
+    The *p*-value for ``method='exact'`` is generated by comparing the observed
+    value of :math:`L` against the :math:`L` values generated for all
+    :math:`(n!)^m` possible permutations of ranks. The calculation is performed
+    using the recursive method of [5].
+
+    The *p*-values are not adjusted for the possibility of ties. When
+    ties are present, the reported  ``'exact'`` *p*-values may be somewhat
+    larger (i.e. more conservative) than the true *p*-value [2]_. The
+    ``'asymptotic'``` *p*-values, however, tend to be smaller (i.e. less
+    conservative) than the ``'exact'`` *p*-values.
+
+    References
+    ----------
+    .. [1] Ellis Batten Page, "Ordered hypotheses for multiple treatments:
+       a significant test for linear ranks", *Journal of the American
+       Statistical Association* 58(301), p. 216--230, 1963.
+
+    .. [2] Markus Neuhauser, *Nonparametric Statistical Test: A computational
+       approach*, CRC Press, p. 150--152, 2012.
+
+    .. [3] Statext LLC, "Page's L Trend Test - Easy Statistics", *Statext -
+       Statistics Study*, https://www.statext.com/practice/PageTrendTest03.php,
+       Accessed July 12, 2020.
+
+    .. [4] "Page's Trend Test", *Wikipedia*, WikimediaFoundation,
+       https://en.wikipedia.org/wiki/Page%27s_trend_test,
+       Accessed July 12, 2020.
+
+    .. [5] Robert E. Odeh, "The exact distribution of Page's L-statistic in
+       the two-way layout", *Communications in Statistics - Simulation and
+       Computation*,  6(1), p. 49--61, 1977.
+
+    Examples
+    --------
+    We use the example from [3]_: 10 students are asked to rate three
+    teaching methods - tutorial, lecture, and seminar - on a scale of 1-5,
+    with 1 being the lowest and 5 being the highest. We have decided that
+    a confidence level of 99% is required to reject the null hypothesis in
+    favor of our alternative: that the seminar will have the highest ratings
+    and the tutorial will have the lowest. Initially, the data have been
+    tabulated with each row representing an individual student's ratings of
+    the three methods in the following order: tutorial, lecture, seminar.
+
+    >>> table = [[3, 4, 3],
+    ...          [2, 2, 4],
+    ...          [3, 3, 5],
+    ...          [1, 3, 2],
+    ...          [2, 3, 2],
+    ...          [2, 4, 5],
+    ...          [1, 2, 4],
+    ...          [3, 4, 4],
+    ...          [2, 4, 5],
+    ...          [1, 3, 4]]
+
+    Because the tutorial is hypothesized to have the lowest ratings, the
+    column corresponding with tutorial rankings should be first; the seminar
+    is hypothesized to have the highest ratings, so its column should be last.
+    Since the columns are already arranged in this order of increasing
+    predicted mean, we can pass the table directly into `page_trend_test`.
+
+    >>> from scipy.stats import page_trend_test
+    >>> res = page_trend_test(table)
+    >>> res
+    PageTrendTestResult(statistic=133.5, pvalue=0.0018191161948127822,
+                        method='exact')
+
+    This *p*-value indicates that there is a 0.1819% chance that
+    the :math:`L` statistic would reach such an extreme value under the null
+    hypothesis. Because 0.1819% is less than 1%, we have evidence to reject
+    the null hypothesis in favor of our alternative at a 99% confidence level.
+
+    The value of the :math:`L` statistic is 133.5. To check this manually,
+    we rank the data such that high scores correspond with high ranks, settling
+    ties with an average rank:
+
+    >>> from scipy.stats import rankdata
+    >>> ranks = rankdata(table, axis=1)
+    >>> ranks
+    array([[1.5, 3. , 1.5],
+           [1.5, 1.5, 3. ],
+           [1.5, 1.5, 3. ],
+           [1. , 3. , 2. ],
+           [1.5, 3. , 1.5],
+           [1. , 2. , 3. ],
+           [1. , 2. , 3. ],
+           [1. , 2.5, 2.5],
+           [1. , 2. , 3. ],
+           [1. , 2. , 3. ]])
+
+    We add the ranks within each column, multiply the sums by the
+    predicted ranks, and sum the products.
+
+    >>> import numpy as np
+    >>> m, n = ranks.shape
+    >>> predicted_ranks = np.arange(1, n+1)
+    >>> L = (predicted_ranks * np.sum(ranks, axis=0)).sum()
+    >>> res.statistic == L
+    True
+
+    As presented in [3]_, the asymptotic approximation of the *p*-value is the
+    survival function of the normal distribution evaluated at the standardized
+    test statistic:
+
+    >>> from scipy.stats import norm
+    >>> E0 = (m*n*(n+1)**2)/4
+    >>> V0 = (m*n**2*(n+1)*(n**2-1))/144
+    >>> Lambda = (L-E0)/np.sqrt(V0)
+    >>> p = norm.sf(Lambda)
+    >>> p
+    0.0012693433690751756
+
+    This does not precisely match the *p*-value reported by `page_trend_test`
+    above. The asymptotic distribution is not very accurate, nor conservative,
+    for :math:`m \leq 12` and :math:`n \leq 8`, so `page_trend_test` chose to
+    use ``method='exact'`` based on the dimensions of the table and the
+    recommendations in Page's original paper [1]_. To override
+    `page_trend_test`'s choice, provide the `method` argument.
+
+    >>> res = page_trend_test(table, method="asymptotic")
+    >>> res
+    PageTrendTestResult(statistic=133.5, pvalue=0.0012693433690751756,
+                        method='asymptotic')
+
+    If the data are already ranked, we can pass in the ``ranks`` instead of
+    the ``table`` to save computation time.
+
+    >>> res = page_trend_test(ranks,             # ranks of data
+    ...                       ranked=True,       # data is already ranked
+    ...                       )
+    >>> res
+    PageTrendTestResult(statistic=133.5, pvalue=0.0018191161948127822,
+                        method='exact')
+
+    Suppose the raw data had been tabulated in an order different from the
+    order of predicted means, say lecture, seminar, tutorial.
+
+    >>> table = np.asarray(table)[:, [1, 2, 0]]
+
+    Since the arrangement of this table is not consistent with the assumed
+    ordering, we can either rearrange the table or provide the
+    `predicted_ranks`. Remembering that the lecture is predicted
+    to have the middle rank, the seminar the highest, and tutorial the lowest,
+    we pass:
+
+    >>> res = page_trend_test(table,             # data as originally tabulated
+    ...                       predicted_ranks=[2, 3, 1],  # our predicted order
+    ...                       )
+    >>> res
+    PageTrendTestResult(statistic=133.5, pvalue=0.0018191161948127822,
+                        method='exact')
+
+    """
+
+    # Possible values of the method parameter and the corresponding function
+    # used to evaluate the p value
+    methods = {"asymptotic": _l_p_asymptotic,
+               "exact": _l_p_exact,
+               "auto": None}
+    if method not in methods:
+        raise ValueError(f"`method` must be in {set(methods)}")
+
+    ranks = np.array(data, copy=False)
+    if ranks.ndim != 2:  # TODO: relax this to accept 3d arrays?
+        raise ValueError("`data` must be a 2d array.")
+
+    m, n = ranks.shape
+    if m < 2 or n < 3:
+        raise ValueError("Page's L is only appropriate for data with two "
+                         "or more rows and three or more columns.")
+
+    if np.any(np.isnan(data)):
+        raise ValueError("`data` contains NaNs, which cannot be ranked "
+                         "meaningfully")
+
+    # ensure NumPy array and rank the data if it's not already ranked
+    if ranked:
+        # Only a basic check on whether data is ranked. Checking that the data
+        # is properly ranked could take as much time as ranking it.
+        if not (ranks.min() >= 1 and ranks.max() <= ranks.shape[1]):
+            raise ValueError("`data` is not properly ranked. Rank the data or "
+                             "pass `ranked=False`.")
+    else:
+        ranks = scipy.stats.rankdata(data, axis=-1)
+
+    # generate predicted ranks if not provided, ensure valid NumPy array
+    if predicted_ranks is None:
+        predicted_ranks = np.arange(1, n+1)
+    else:
+        predicted_ranks = np.array(predicted_ranks, copy=False)
+        if (predicted_ranks.ndim < 1 or
+                (set(predicted_ranks) != set(range(1, n+1)) or
+                 len(predicted_ranks) != n)):
+            raise ValueError(f"`predicted_ranks` must include each integer "
+                             f"from 1 to {n} (the number of columns in "
+                             f"`data`) exactly once.")
+
+    if type(ranked) is not bool:
+        raise TypeError("`ranked` must be boolean.")
+
+    # Calculate the L statistic
+    L = _l_vectorized(ranks, predicted_ranks)
+
+    # Calculate the p-value
+    if method == "auto":
+        method = _choose_method(ranks)
+    p_fun = methods[method]  # get the function corresponding with the method
+    p = p_fun(L, m, n)
+
+    page_result = PageTrendTestResult(statistic=L, pvalue=p, method=method)
+    return page_result
+
+
+def _choose_method(ranks):
+    '''Choose method for computing p-value automatically'''
+    m, n = ranks.shape
+    if n > 8 or (m > 12 and n > 3) or m > 20:  # as in [1], [4]
+        method = "asymptotic"
+    else:
+        method = "exact"
+    return method
+
+
+def _l_vectorized(ranks, predicted_ranks):
+    '''Calculate's Page's L statistic for each page of a 3d array'''
+    colsums = ranks.sum(axis=-2, keepdims=True)
+    products = predicted_ranks * colsums
+    Ls = products.sum(axis=-1)
+    Ls = Ls[0] if Ls.size == 1 else Ls.ravel()
+    return Ls
+
+
+def _l_p_asymptotic(L, m, n):
+    '''Calculate the p-value of Page's L from the asymptotic distribution'''
+    # Using [1] as a reference, the asymptotic p-value would be calculated as:
+    # chi_L = (12*L - 3*m*n*(n+1)**2)**2/(m*n**2*(n**2-1)*(n+1))
+    # p = chi2.sf(chi_L, df=1, loc=0, scale=1)/2
+    # but this is insentive to the direction of the hypothesized ranking
+
+    # See [2] page 151
+    E0 = (m*n*(n+1)**2)/4
+    V0 = (m*n**2*(n+1)*(n**2-1))/144
+    Lambda = (L-E0)/np.sqrt(V0)
+    # This is a one-sided "greater" test - calculate the probability that the
+    # L statistic under H0 would be greater than the observed L statistic
+    p = norm.sf(Lambda)
+    return p
+
+
+def _l_p_exact(L, m, n):
+    '''Calculate the p-value of Page's L exactly'''
+    # [1] uses m, n; [5] uses n, k.
+    # Switch convention here because exact calculation code references [5].
+    L, n, k = int(L), int(m), int(n)
+    _pagel_state.set_k(k)
+    return _pagel_state.sf(L, n)
+
+
+class _PageL:
+    '''Maintains state between `page_trend_test` executions'''
+
+    def __init__(self):
+        '''Lightweight initialization'''
+        self.all_pmfs = {}
+
+    def set_k(self, k):
+        '''Calculate lower and upper limits of L for single row'''
+        self.k = k
+        # See [5] top of page 52
+        self.a, self.b = (k*(k+1)*(k+2))//6, (k*(k+1)*(2*k+1))//6
+
+    def sf(self, l, n):
+        '''Survival function of Page's L statistic'''
+        ps = [self.pmf(l, n) for l in range(l, n*self.b + 1)]
+        return np.sum(ps)
+
+    def p_l_k_1(self):
+        '''Relative frequency of each L value over all possible single rows'''
+
+        # See [5] Equation (6)
+        ranks = range(1, self.k+1)
+        # generate all possible rows of length k
+        rank_perms = np.array(list(permutations(ranks)))
+        # compute Page's L for all possible rows
+        Ls = (ranks*rank_perms).sum(axis=1)
+        # count occurences of each L value
+        counts = np.histogram(Ls, np.arange(self.a-0.5, self.b+1.5))[0]
+        # factorial(k) is number of possible permutations
+        return counts/math.factorial(self.k)
+
+    def pmf(self, l, n):
+        '''Recursive function to evaluate p(l, k, n); see [5] Equation 1'''
+
+        if n not in self.all_pmfs:
+            self.all_pmfs[n] = {}
+        if self.k not in self.all_pmfs[n]:
+            self.all_pmfs[n][self.k] = {}
+
+        # Cache results to avoid repeating calculation. Initially this was
+        # written with lru_cache, but this seems faster? Also, we could add
+        # an option to save this for future lookup.
+        if l in self.all_pmfs[n][self.k]:
+            return self.all_pmfs[n][self.k][l]
+
+        if n == 1:
+            ps = self.p_l_k_1()  # [5] Equation 6
+            ls = range(self.a, self.b+1)
+            # not fast, but we'll only be here once
+            self.all_pmfs[n][self.k] = {l: p for l, p in zip(ls, ps)}
+            return self.all_pmfs[n][self.k][l]
+
+        p = 0
+        low = max(l-(n-1)*self.b, self.a)  # [5] Equation 2
+        high = min(l-(n-1)*self.a, self.b)
+
+        # [5] Equation 1
+        for t in range(low, high+1):
+            p1 = self.pmf(l-t, n-1)
+            p2 = self.pmf(t, 1)
+            p += p1*p2
+        self.all_pmfs[n][self.k][l] = p
+        return p
+
+
+# Maintain state for faster repeat calls to page_trend_test w/ method='exact'
+_pagel_state = _PageL()

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_qmc_cy.pyi

@@ -0,0 +1,54 @@
+import numpy as np
+from scipy._lib._util import DecimalNumber, IntNumber
+
+
+def _cy_wrapper_centered_discrepancy(
+        sample: np.ndarray, 
+        iterative: bool, 
+        workers: IntNumber,
+) -> float: ...
+
+
+def _cy_wrapper_wrap_around_discrepancy(
+        sample: np.ndarray,
+        iterative: bool, 
+        workers: IntNumber,
+) -> float: ...
+
+
+def _cy_wrapper_mixture_discrepancy(
+        sample: np.ndarray,
+        iterative: bool, 
+        workers: IntNumber,
+) -> float: ...
+
+
+def _cy_wrapper_l2_star_discrepancy(
+        sample: np.ndarray,
+        iterative: bool,
+        workers: IntNumber,
+) -> float: ...
+
+
+def _cy_wrapper_update_discrepancy(
+        x_new_view: np.ndarray,
+        sample_view: np.ndarray,
+        initial_disc: DecimalNumber,
+) -> float: ...
+
+
+def _cy_van_der_corput(
+        n: IntNumber,
+        base: IntNumber,
+        start_index: IntNumber,
+        workers: IntNumber,
+) -> np.ndarray: ...
+
+
+def _cy_van_der_corput_scrambled(
+        n: IntNumber,
+        base: IntNumber,
+        start_index: IntNumber,
+        permutations: np.ndarray,
+        workers: IntNumber,
+) -> np.ndarray: ...

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_relative_risk.py

@@ -0,0 +1,260 @@
+
+import operator
+from dataclasses import dataclass
+import numpy as np
+from scipy.special import ndtri
+from ._common import ConfidenceInterval
+
+
+def _validate_int(n, bound, name):
+    msg = f'{name} must be an integer not less than {bound}, but got {n!r}'
+    try:
+        n = operator.index(n)
+    except TypeError:
+        raise TypeError(msg) from None
+    if n < bound:
+        raise ValueError(msg)
+    return n
+
+
+@dataclass
+class RelativeRiskResult:
+    """
+    Result of `scipy.stats.contingency.relative_risk`.
+
+    Attributes
+    ----------
+    relative_risk : float
+        This is::
+
+            (exposed_cases/exposed_total) / (control_cases/control_total)
+
+    exposed_cases : int
+        The number of "cases" (i.e. occurrence of disease or other event
+        of interest) among the sample of "exposed" individuals.
+    exposed_total : int
+        The total number of "exposed" individuals in the sample.
+    control_cases : int
+        The number of "cases" among the sample of "control" or non-exposed
+        individuals.
+    control_total : int
+        The total number of "control" individuals in the sample.
+
+    Methods
+    -------
+    confidence_interval :
+        Compute the confidence interval for the relative risk estimate.
+    """
+
+    relative_risk: float
+    exposed_cases: int
+    exposed_total: int
+    control_cases: int
+    control_total: int
+
+    def confidence_interval(self, confidence_level=0.95):
+        """
+        Compute the confidence interval for the relative risk.
+
+        The confidence interval is computed using the Katz method
+        (i.e. "Method C" of [1]_; see also [2]_, section 3.1.2).
+
+        Parameters
+        ----------
+        confidence_level : float, optional
+            The confidence level to use for the confidence interval.
+            Default is 0.95.
+
+        Returns
+        -------
+        ci : ConfidenceInterval instance
+            The return value is an object with attributes ``low`` and
+            ``high`` that hold the confidence interval.
+
+        References
+        ----------
+        .. [1] D. Katz, J. Baptista, S. P. Azen and M. C. Pike, "Obtaining
+               confidence intervals for the risk ratio in cohort studies",
+               Biometrics, 34, 469-474 (1978).
+        .. [2] Hardeo Sahai and Anwer Khurshid, Statistics in Epidemiology,
+               CRC Press LLC, Boca Raton, FL, USA (1996).
+
+
+        Examples
+        --------
+        >>> from scipy.stats.contingency import relative_risk
+        >>> result = relative_risk(exposed_cases=10, exposed_total=75,
+        ...                        control_cases=12, control_total=225)
+        >>> result.relative_risk
+        2.5
+        >>> result.confidence_interval()
+        ConfidenceInterval(low=1.1261564003469628, high=5.549850800541033)
+        """
+        if not 0 <= confidence_level <= 1:
+            raise ValueError('confidence_level must be in the interval '
+                             '[0, 1].')
+
+        # Handle edge cases where either exposed_cases or control_cases
+        # is zero.  We follow the convention of the R function riskratio
+        # from the epitools library.
+        if self.exposed_cases == 0 and self.control_cases == 0:
+            # relative risk is nan.
+            return ConfidenceInterval(low=np.nan, high=np.nan)
+        elif self.exposed_cases == 0:
+            # relative risk is 0.
+            return ConfidenceInterval(low=0.0, high=np.nan)
+        elif self.control_cases == 0:
+            # relative risk is inf
+            return ConfidenceInterval(low=np.nan, high=np.inf)
+
+        alpha = 1 - confidence_level
+        z = ndtri(1 - alpha/2)
+        rr = self.relative_risk
+
+        # Estimate of the variance of log(rr) is
+        # var(log(rr)) = 1/exposed_cases - 1/exposed_total +
+        #                1/control_cases - 1/control_total
+        # and the standard error is the square root of that.
+        se = np.sqrt(1/self.exposed_cases - 1/self.exposed_total +
+                     1/self.control_cases - 1/self.control_total)
+        delta = z*se
+        katz_lo = rr*np.exp(-delta)
+        katz_hi = rr*np.exp(delta)
+        return ConfidenceInterval(low=katz_lo, high=katz_hi)
+
+
+def relative_risk(exposed_cases, exposed_total, control_cases, control_total):
+    """
+    Compute the relative risk (also known as the risk ratio).
+
+    This function computes the relative risk associated with a 2x2
+    contingency table ([1]_, section 2.2.3; [2]_, section 3.1.2). Instead
+    of accepting a table as an argument, the individual numbers that are
+    used to compute the relative risk are given as separate parameters.
+    This is to avoid the ambiguity of which row or column of the contingency
+    table corresponds to the "exposed" cases and which corresponds to the
+    "control" cases.  Unlike, say, the odds ratio, the relative risk is not
+    invariant under an interchange of the rows or columns.
+
+    Parameters
+    ----------
+    exposed_cases : nonnegative int
+        The number of "cases" (i.e. occurrence of disease or other event
+        of interest) among the sample of "exposed" individuals.
+    exposed_total : positive int
+        The total number of "exposed" individuals in the sample.
+    control_cases : nonnegative int
+        The number of "cases" among the sample of "control" or non-exposed
+        individuals.
+    control_total : positive int
+        The total number of "control" individuals in the sample.
+
+    Returns
+    -------
+    result : instance of `~scipy.stats._result_classes.RelativeRiskResult`
+        The object has the float attribute ``relative_risk``, which is::
+
+            rr = (exposed_cases/exposed_total) / (control_cases/control_total)
+
+        The object also has the method ``confidence_interval`` to compute
+        the confidence interval of the relative risk for a given confidence
+        level.
+
+    Notes
+    -----
+    The R package epitools has the function `riskratio`, which accepts
+    a table with the following layout::
+
+                        disease=0   disease=1
+        exposed=0 (ref)    n00         n01
+        exposed=1          n10         n11
+
+    With a 2x2 table in the above format, the estimate of the CI is
+    computed by `riskratio` when the argument method="wald" is given,
+    or with the function `riskratio.wald`.
+
+    For example, in a test of the incidence of lung cancer among a
+    sample of smokers and nonsmokers, the "exposed" category would
+    correspond to "is a smoker" and the "disease" category would
+    correspond to "has or had lung cancer".
+
+    To pass the same data to ``relative_risk``, use::
+
+        relative_risk(n11, n10 + n11, n01, n00 + n01)
+
+    .. versionadded:: 1.7.0
+
+    References
+    ----------
+    .. [1] Alan Agresti, An Introduction to Categorical Data Analysis
+           (second edition), Wiley, Hoboken, NJ, USA (2007).
+    .. [2] Hardeo Sahai and Anwer Khurshid, Statistics in Epidemiology,
+           CRC Press LLC, Boca Raton, FL, USA (1996).
+
+    Examples
+    --------
+    >>> from scipy.stats.contingency import relative_risk
+
+    This example is from Example 3.1 of [2]_.  The results of a heart
+    disease study are summarized in the following table::
+
+                 High CAT   Low CAT    Total
+                 --------   -------    -----
+        CHD         27         44        71
+        No CHD      95        443       538
+
+        Total      122        487       609
+
+    CHD is coronary heart disease, and CAT refers to the level of
+    circulating catecholamine.  CAT is the "exposure" variable, and
+    high CAT is the "exposed" category. So the data from the table
+    to be passed to ``relative_risk`` is::
+
+        exposed_cases = 27
+        exposed_total = 122
+        control_cases = 44
+        control_total = 487
+
+    >>> result = relative_risk(27, 122, 44, 487)
+    >>> result.relative_risk
+    2.4495156482861398
+
+    Find the confidence interval for the relative risk.
+
+    >>> result.confidence_interval(confidence_level=0.95)
+    ConfidenceInterval(low=1.5836990926700116, high=3.7886786315466354)
+
+    The interval does not contain 1, so the data supports the statement
+    that high CAT is associated with greater risk of CHD.
+    """
+    # Relative risk is a trivial calculation.  The nontrivial part is in the
+    # `confidence_interval` method of the RelativeRiskResult class.
+
+    exposed_cases = _validate_int(exposed_cases, 0, "exposed_cases")
+    exposed_total = _validate_int(exposed_total, 1, "exposed_total")
+    control_cases = _validate_int(control_cases, 0, "control_cases")
+    control_total = _validate_int(control_total, 1, "control_total")
+
+    if exposed_cases > exposed_total:
+        raise ValueError('exposed_cases must not exceed exposed_total.')
+    if control_cases > control_total:
+        raise ValueError('control_cases must not exceed control_total.')
+
+    if exposed_cases == 0 and control_cases == 0:
+        # relative risk is 0/0.
+        rr = np.nan
+    elif exposed_cases == 0:
+        # relative risk is 0/nonzero
+        rr = 0.0
+    elif control_cases == 0:
+        # relative risk is nonzero/0.
+        rr = np.inf
+    else:
+        p1 = exposed_cases / exposed_total
+        p2 = control_cases / control_total
+        rr = p1 / p2
+    return RelativeRiskResult(relative_risk=rr,
+                              exposed_cases=exposed_cases,
+                              exposed_total=exposed_total,
+                              control_cases=control_cases,
+                              control_total=control_total)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_result_classes.py

@@ -0,0 +1,24 @@
+# This module exists only to allow Sphinx to generate docs
+# for the result objects returned by some functions in stats.
+
+"""
+Result classes
+--------------
+
+.. currentmodule:: scipy.stats._result_classes
+
+.. autosummary::
+   :toctree: generated/
+
+   RelativeRiskResult
+   BinomTestResult
+   TukeyHSDResult
+
+"""
+
+__all__ = ['BinomTestResult', 'RelativeRiskResult', 'TukeyHSDResult']
+
+
+from ._binomtest import BinomTestResult
+from ._relative_risk import RelativeRiskResult
+from ._hypotests import TukeyHSDResult

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_rvs_sampling.py

@@ -0,0 +1,195 @@
+# -*- coding: utf-8 -*-
+import numpy as np
+from ._unuran import unuran_wrapper
+from scipy._lib.deprecation import _deprecated
+from scipy._lib._util import check_random_state
+
+
+def rvs_ratio_uniforms(pdf, umax, vmin, vmax, size=1, c=0, random_state=None):
+    """
+    Generate random samples from a probability density function using the
+    ratio-of-uniforms method.
+
+    Parameters
+    ----------
+    pdf : callable
+        A function with signature `pdf(x)` that is proportional to the
+        probability density function of the distribution.
+    umax : float
+        The upper bound of the bounding rectangle in the u-direction.
+    vmin : float
+        The lower bound of the bounding rectangle in the v-direction.
+    vmax : float
+        The upper bound of the bounding rectangle in the v-direction.
+    size : int or tuple of ints, optional
+        Defining number of random variates (default is 1).
+    c : float, optional.
+        Shift parameter of ratio-of-uniforms method, see Notes. Default is 0.
+    random_state : {None, int, `numpy.random.Generator`,
+                    `numpy.random.RandomState`}, optional
+
+        If `seed` is None (or `np.random`), the `numpy.random.RandomState`
+        singleton is used.
+        If `seed` is an int, a new ``RandomState`` instance is used,
+        seeded with `seed`.
+        If `seed` is already a ``Generator`` or ``RandomState`` instance then
+        that instance is used.
+
+    Returns
+    -------
+    rvs : ndarray
+        The random variates distributed according to the probability
+        distribution defined by the pdf.
+
+    Notes
+    -----
+    Given a univariate probability density function `pdf` and a constant `c`,
+    define the set ``A = {(u, v) : 0 < u <= sqrt(pdf(v/u + c))}``.
+    If `(U, V)` is a random vector uniformly distributed over `A`,
+    then `V/U + c` follows a distribution according to `pdf`.
+
+    The above result (see [1]_, [2]_) can be used to sample random variables
+    using only the pdf, i.e. no inversion of the cdf is required. Typical
+    choices of `c` are zero or the mode of `pdf`. The set `A` is a subset of
+    the rectangle ``R = [0, umax] x [vmin, vmax]`` where
+
+    - ``umax = sup sqrt(pdf(x))``
+    - ``vmin = inf (x - c) sqrt(pdf(x))``
+    - ``vmax = sup (x - c) sqrt(pdf(x))``
+
+    In particular, these values are finite if `pdf` is bounded and
+    ``x**2 * pdf(x)`` is bounded (i.e. subquadratic tails).
+    One can generate `(U, V)` uniformly on `R` and return
+    `V/U + c` if `(U, V)` are also in `A` which can be directly
+    verified.
+
+    The algorithm is not changed if one replaces `pdf` by k * `pdf` for any
+    constant k > 0. Thus, it is often convenient to work with a function
+    that is proportional to the probability density function by dropping
+    unneccessary normalization factors.
+
+    Intuitively, the method works well if `A` fills up most of the
+    enclosing rectangle such that the probability is high that `(U, V)`
+    lies in `A` whenever it lies in `R` as the number of required
+    iterations becomes too large otherwise. To be more precise, note that
+    the expected number of iterations to draw `(U, V)` uniformly
+    distributed on `R` such that `(U, V)` is also in `A` is given by
+    the ratio ``area(R) / area(A) = 2 * umax * (vmax - vmin) / area(pdf)``,
+    where `area(pdf)` is the integral of `pdf` (which is equal to one if the
+    probability density function is used but can take on other values if a
+    function proportional to the density is used). The equality holds since
+    the area of `A` is equal to 0.5 * area(pdf) (Theorem 7.1 in [1]_).
+    If the sampling fails to generate a single random variate after 50000
+    iterations (i.e. not a single draw is in `A`), an exception is raised.
+
+    If the bounding rectangle is not correctly specified (i.e. if it does not
+    contain `A`), the algorithm samples from a distribution different from
+    the one given by `pdf`. It is therefore recommended to perform a
+    test such as `~scipy.stats.kstest` as a check.
+
+    References
+    ----------
+    .. [1] L. Devroye, "Non-Uniform Random Variate Generation",
+       Springer-Verlag, 1986.
+
+    .. [2] W. Hoermann and J. Leydold, "Generating generalized inverse Gaussian
+       random variates", Statistics and Computing, 24(4), p. 547--557, 2014.
+
+    .. [3] A.J. Kinderman and J.F. Monahan, "Computer Generation of Random
+       Variables Using the Ratio of Uniform Deviates",
+       ACM Transactions on Mathematical Software, 3(3), p. 257--260, 1977.
+
+    Examples
+    --------
+    >>> from scipy import stats
+    >>> rng = np.random.default_rng()
+
+    Simulate normally distributed random variables. It is easy to compute the
+    bounding rectangle explicitly in that case. For simplicity, we drop the
+    normalization factor of the density.
+
+    >>> f = lambda x: np.exp(-x**2 / 2)
+    >>> v_bound = np.sqrt(f(np.sqrt(2))) * np.sqrt(2)
+    >>> umax, vmin, vmax = np.sqrt(f(0)), -v_bound, v_bound
+    >>> rvs = stats.rvs_ratio_uniforms(f, umax, vmin, vmax, size=2500,
+    ...                                random_state=rng)
+
+    The K-S test confirms that the random variates are indeed normally
+    distributed (normality is not rejected at 5% significance level):
+
+    >>> stats.kstest(rvs, 'norm')[1]
+    0.250634764150542
+
+    The exponential distribution provides another example where the bounding
+    rectangle can be determined explicitly.
+
+    >>> rvs = stats.rvs_ratio_uniforms(lambda x: np.exp(-x), umax=1,
+    ...                                vmin=0, vmax=2*np.exp(-1), size=1000,
+    ...                                random_state=rng)
+    >>> stats.kstest(rvs, 'expon')[1]
+    0.21121052054580314
+
+    """
+    if vmin >= vmax:
+        raise ValueError("vmin must be smaller than vmax.")
+
+    if umax <= 0:
+        raise ValueError("umax must be positive.")
+
+    size1d = tuple(np.atleast_1d(size))
+    N = np.prod(size1d)  # number of rvs needed, reshape upon return
+
+    # start sampling using ratio of uniforms method
+    rng = check_random_state(random_state)
+    x = np.zeros(N)
+    simulated, i = 0, 1
+
+    # loop until N rvs have been generated: expected runtime is finite.
+    # to avoid infinite loop, raise exception if not a single rv has been
+    # generated after 50000 tries. even if the expected numer of iterations
+    # is 1000, the probability of this event is (1-1/1000)**50000
+    # which is of order 10e-22
+    while simulated < N:
+        k = N - simulated
+        # simulate uniform rvs on [0, umax] and [vmin, vmax]
+        u1 = umax * rng.uniform(size=k)
+        v1 = rng.uniform(vmin, vmax, size=k)
+        # apply rejection method
+        rvs = v1 / u1 + c
+        accept = (u1**2 <= pdf(rvs))
+        num_accept = np.sum(accept)
+        if num_accept > 0:
+            x[simulated:(simulated + num_accept)] = rvs[accept]
+            simulated += num_accept
+
+        if (simulated == 0) and (i*N >= 50000):
+            msg = ("Not a single random variate could be generated in {} "
+                   "attempts. The ratio of uniforms method does not appear "
+                   "to work for the provided parameters. Please check the "
+                   "pdf and the bounds.".format(i*N))
+            raise RuntimeError(msg)
+        i += 1
+
+    return np.reshape(x, size1d)
+
+
+class NumericalInverseHermite:
+    @_deprecated(
+        "NumericalInverseHermite has been deprecated from `scipy.stats`. "
+        " To use `NumericalInverseHermite`, import/use it from "
+        "`scipy.stats.sampling` module instead. "
+        "i.e. `from scipy.stats.sampling import NumericalInverseHermite`"
+    )
+    def __init__(self, *args, **kwargs):
+        self.hinv = unuran_wrapper.NumericalInverseHermite(*args, **kwargs)
+        self.intervals = self.hinv.intervals
+        self.midpoint_error = self.hinv.midpoint_error
+
+    def rvs(self, *args, **kwargs):
+        return self.hinv.rvs(*args, **kwargs)
+
+    def ppf(self, *args, **kwargs):
+        return self.hinv.ppf(*args, **kwargs)
+
+    def qrvs(self, *args, **kwargs):
+        return self.hinv.qrvs(*args, **kwargs)

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_sobol.pyi

@@ -0,0 +1,54 @@
+import numpy as np
+from scipy._lib._util import IntNumber
+from typing_extensions import Literal
+
+def initialize_v(
+    v : np.ndarray, 
+    dim : IntNumber
+) -> None: ...
+
+def _cscramble (
+    dim : IntNumber,
+    ltm : np.ndarray,
+    sv: np.ndarray
+) -> None: ...
+
+def _fill_p_cumulative(
+    p: np.ndarray,
+    p_cumulative: np.ndarray
+) -> None: ...
+
+def _draw(
+    n : IntNumber,
+    num_gen: IntNumber,
+    dim: IntNumber,
+    sv: np.ndarray,
+    quasi: np.ndarray,
+    result: np.ndarray
+    ) -> None: ...
+
+def _fast_forward(
+    n: IntNumber,
+    num_gen: IntNumber,
+    dim: IntNumber,
+    sv: np.ndarray,
+    quasi: np.ndarray
+    ) -> None: ...
+
+def _categorize(
+    draws: np.ndarray,
+    p_cumulative: np.ndarray,
+    result: np.ndarray
+    ) -> None: ...
+
+def initialize_direction_numbers() -> None: ...
+
+_MAXDIM: Literal[21201]
+_MAXBIT: Literal[30]
+_MAXDEG: Literal[18]
+
+def _test_find_index(
+    p_cumulative: np.ndarray, 
+    size: int, 
+    value: float
+    ) -> int: ...

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_stats_mstats_common.py

@@ -0,0 +1,484 @@
+import numpy as np
+import scipy.stats._stats_py
+from . import distributions
+from .._lib._bunch import _make_tuple_bunch
+
+
+__all__ = ['_find_repeats', 'linregress', 'theilslopes', 'siegelslopes']
+
+# This is not a namedtuple for backwards compatibility. See PR #12983
+LinregressResult = _make_tuple_bunch('LinregressResult',
+                                     ['slope', 'intercept', 'rvalue',
+                                      'pvalue', 'stderr'],
+                                     extra_field_names=['intercept_stderr'])
+
+
+def linregress(x, y=None, alternative='two-sided'):
+    """
+    Calculate a linear least-squares regression for two sets of measurements.
+
+    Parameters
+    ----------
+    x, y : array_like
+        Two sets of measurements.  Both arrays should have the same length.  If
+        only `x` is given (and ``y=None``), then it must be a two-dimensional
+        array where one dimension has length 2.  The two sets of measurements
+        are then found by splitting the array along the length-2 dimension. In
+        the case where ``y=None`` and `x` is a 2x2 array, ``linregress(x)`` is
+        equivalent to ``linregress(x[0], x[1])``.
+    alternative : {'two-sided', 'less', 'greater'}, optional
+        Defines the alternative hypothesis. Default is 'two-sided'.
+        The following options are available:
+
+        * 'two-sided': the slope of the regression line is nonzero
+        * 'less': the slope of the regression line is less than zero
+        * 'greater':  the slope of the regression line is greater than zero
+
+        .. versionadded:: 1.7.0
+
+    Returns
+    -------
+    result : ``LinregressResult`` instance
+        The return value is an object with the following attributes:
+
+        slope : float
+            Slope of the regression line.
+        intercept : float
+            Intercept of the regression line.
+        rvalue : float
+            The Pearson correlation coefficient. The square of ``rvalue``
+            is equal to the coefficient of determination.
+        pvalue : float
+            The p-value for a hypothesis test whose null hypothesis is
+            that the slope is zero, using Wald Test with t-distribution of
+            the test statistic. See `alternative` above for alternative
+            hypotheses.
+        stderr : float
+            Standard error of the estimated slope (gradient), under the
+            assumption of residual normality.
+        intercept_stderr : float
+            Standard error of the estimated intercept, under the assumption
+            of residual normality.
+
+    See Also
+    --------
+    scipy.optimize.curve_fit :
+        Use non-linear least squares to fit a function to data.
+    scipy.optimize.leastsq :
+        Minimize the sum of squares of a set of equations.
+
+    Notes
+    -----
+    Missing values are considered pair-wise: if a value is missing in `x`,
+    the corresponding value in `y` is masked.
+
+    For compatibility with older versions of SciPy, the return value acts
+    like a ``namedtuple`` of length 5, with fields ``slope``, ``intercept``,
+    ``rvalue``, ``pvalue`` and ``stderr``, so one can continue to write::
+
+        slope, intercept, r, p, se = linregress(x, y)
+
+    With that style, however, the standard error of the intercept is not
+    available.  To have access to all the computed values, including the
+    standard error of the intercept, use the return value as an object
+    with attributes, e.g.::
+
+        result = linregress(x, y)
+        print(result.intercept, result.intercept_stderr)
+
+    Examples
+    --------
+    >>> import matplotlib.pyplot as plt
+    >>> from scipy import stats
+    >>> rng = np.random.default_rng()
+
+    Generate some data:
+
+    >>> x = rng.random(10)
+    >>> y = 1.6*x + rng.random(10)
+
+    Perform the linear regression:
+
+    >>> res = stats.linregress(x, y)
+
+    Coefficient of determination (R-squared):
+
+    >>> print(f"R-squared: {res.rvalue**2:.6f}")
+    R-squared: 0.717533
+
+    Plot the data along with the fitted line:
+
+    >>> plt.plot(x, y, 'o', label='original data')
+    >>> plt.plot(x, res.intercept + res.slope*x, 'r', label='fitted line')
+    >>> plt.legend()
+    >>> plt.show()
+
+    Calculate 95% confidence interval on slope and intercept:
+
+    >>> # Two-sided inverse Students t-distribution
+    >>> # p - probability, df - degrees of freedom
+    >>> from scipy.stats import t
+    >>> tinv = lambda p, df: abs(t.ppf(p/2, df))
+
+    >>> ts = tinv(0.05, len(x)-2)
+    >>> print(f"slope (95%): {res.slope:.6f} +/- {ts*res.stderr:.6f}")
+    slope (95%): 1.453392 +/- 0.743465
+    >>> print(f"intercept (95%): {res.intercept:.6f}"
+    ...       f" +/- {ts*res.intercept_stderr:.6f}")
+    intercept (95%): 0.616950 +/- 0.544475
+
+    """
+    TINY = 1.0e-20
+    if y is None:  # x is a (2, N) or (N, 2) shaped array_like
+        x = np.asarray(x)
+        if x.shape[0] == 2:
+            x, y = x
+        elif x.shape[1] == 2:
+            x, y = x.T
+        else:
+            raise ValueError("If only `x` is given as input, it has to "
+                             "be of shape (2, N) or (N, 2); provided shape "
+                             f"was {x.shape}.")
+    else:
+        x = np.asarray(x)
+        y = np.asarray(y)
+
+    if x.size == 0 or y.size == 0:
+        raise ValueError("Inputs must not be empty.")
+
+    if np.amax(x) == np.amin(x) and len(x) > 1:
+        raise ValueError("Cannot calculate a linear regression "
+                         "if all x values are identical")
+
+    n = len(x)
+    xmean = np.mean(x, None)
+    ymean = np.mean(y, None)
+
+    # Average sums of square differences from the mean
+    #   ssxm = mean( (x-mean(x))^2 )
+    #   ssxym = mean( (x-mean(x)) * (y-mean(y)) )
+    ssxm, ssxym, _, ssym = np.cov(x, y, bias=1).flat
+
+    # R-value
+    #   r = ssxym / sqrt( ssxm * ssym )
+    if ssxm == 0.0 or ssym == 0.0:
+        # If the denominator was going to be 0
+        r = 0.0
+    else:
+        r = ssxym / np.sqrt(ssxm * ssym)
+        # Test for numerical error propagation (make sure -1 < r < 1)
+        if r > 1.0:
+            r = 1.0
+        elif r < -1.0:
+            r = -1.0
+
+    slope = ssxym / ssxm
+    intercept = ymean - slope*xmean
+    if n == 2:
+        # handle case when only two points are passed in
+        if y[0] == y[1]:
+            prob = 1.0
+        else:
+            prob = 0.0
+        slope_stderr = 0.0
+        intercept_stderr = 0.0
+    else:
+        df = n - 2  # Number of degrees of freedom
+        # n-2 degrees of freedom because 2 has been used up
+        # to estimate the mean and standard deviation
+        t = r * np.sqrt(df / ((1.0 - r + TINY)*(1.0 + r + TINY)))
+        t, prob = scipy.stats._stats_py._ttest_finish(df, t, alternative)
+
+        slope_stderr = np.sqrt((1 - r**2) * ssym / ssxm / df)
+
+        # Also calculate the standard error of the intercept
+        # The following relationship is used:
+        #   ssxm = mean( (x-mean(x))^2 )
+        #        = ssx - sx*sx
+        #        = mean( x^2 ) - mean(x)^2
+        intercept_stderr = slope_stderr * np.sqrt(ssxm + xmean**2)
+
+    return LinregressResult(slope=slope, intercept=intercept, rvalue=r,
+                            pvalue=prob, stderr=slope_stderr,
+                            intercept_stderr=intercept_stderr)
+
+
+def theilslopes(y, x=None, alpha=0.95, method='separate'):
+    r"""
+    Computes the Theil-Sen estimator for a set of points (x, y).
+
+    `theilslopes` implements a method for robust linear regression.  It
+    computes the slope as the median of all slopes between paired values.
+
+    Parameters
+    ----------
+    y : array_like
+        Dependent variable.
+    x : array_like or None, optional
+        Independent variable. If None, use ``arange(len(y))`` instead.
+    alpha : float, optional
+        Confidence degree between 0 and 1. Default is 95% confidence.
+        Note that `alpha` is symmetric around 0.5, i.e. both 0.1 and 0.9 are
+        interpreted as "find the 90% confidence interval".
+    method : {'joint', 'separate'}, optional
+        Method to be used for computing estimate for intercept.
+        Following methods are supported,
+
+            * 'joint': Uses np.median(y - medslope * x) as intercept.
+            * 'separate': Uses np.median(y) - medslope * np.median(x)
+                          as intercept.
+
+        The default is 'separate'.
+
+        .. versionadded:: 1.8.0
+
+    Returns
+    -------
+    medslope : float
+        Theil slope.
+    medintercept : float
+        Intercept of the Theil line.
+    lo_slope : float
+        Lower bound of the confidence interval on `medslope`.
+    up_slope : float
+        Upper bound of the confidence interval on `medslope`.
+
+    See also
+    --------
+    siegelslopes : a similar technique using repeated medians
+
+    Notes
+    -----
+    The implementation of `theilslopes` follows [1]_. The intercept is
+    not defined in [1]_, and here it is defined as ``median(y) -
+    medslope*median(x)``, which is given in [3]_. Other definitions of
+    the intercept exist in the literature such as  ``median(y - medslope*x)``
+    in [4]_. The approach to compute the intercept can be determined by the
+    parameter ``method``. A confidence interval for the intercept is not
+    given as this question is not addressed in [1]_.
+
+    References
+    ----------
+    .. [1] P.K. Sen, "Estimates of the regression coefficient based on
+           Kendall's tau", J. Am. Stat. Assoc., Vol. 63, pp. 1379-1389, 1968.
+    .. [2] H. Theil, "A rank-invariant method of linear and polynomial
+           regression analysis I, II and III",  Nederl. Akad. Wetensch., Proc.
+           53:, pp. 386-392, pp. 521-525, pp. 1397-1412, 1950.
+    .. [3] W.L. Conover, "Practical nonparametric statistics", 2nd ed.,
+           John Wiley and Sons, New York, pp. 493.
+    .. [4] https://en.wikipedia.org/wiki/Theil%E2%80%93Sen_estimator
+
+    Examples
+    --------
+    >>> from scipy import stats
+    >>> import matplotlib.pyplot as plt
+
+    >>> x = np.linspace(-5, 5, num=150)
+    >>> y = x + np.random.normal(size=x.size)
+    >>> y[11:15] += 10  # add outliers
+    >>> y[-5:] -= 7
+
+    Compute the slope, intercept and 90% confidence interval.  For comparison,
+    also compute the least-squares fit with `linregress`:
+
+    >>> res = stats.theilslopes(y, x, 0.90, method='separate')
+    >>> lsq_res = stats.linregress(x, y)
+
+    Plot the results. The Theil-Sen regression line is shown in red, with the
+    dashed red lines illustrating the confidence interval of the slope (note
+    that the dashed red lines are not the confidence interval of the regression
+    as the confidence interval of the intercept is not included). The green
+    line shows the least-squares fit for comparison.
+
+    >>> fig = plt.figure()
+    >>> ax = fig.add_subplot(111)
+    >>> ax.plot(x, y, 'b.')
+    >>> ax.plot(x, res[1] + res[0] * x, 'r-')
+    >>> ax.plot(x, res[1] + res[2] * x, 'r--')
+    >>> ax.plot(x, res[1] + res[3] * x, 'r--')
+    >>> ax.plot(x, lsq_res[1] + lsq_res[0] * x, 'g-')
+    >>> plt.show()
+
+    """
+    if method not in ['joint', 'separate']:
+        raise ValueError(("method must be either 'joint' or 'separate'."
+                          "'{}' is invalid.".format(method)))
+    # We copy both x and y so we can use _find_repeats.
+    y = np.array(y).flatten()
+    if x is None:
+        x = np.arange(len(y), dtype=float)
+    else:
+        x = np.array(x, dtype=float).flatten()
+        if len(x) != len(y):
+            raise ValueError("Incompatible lengths ! (%s<>%s)" %
+                             (len(y), len(x)))
+
+    # Compute sorted slopes only when deltax > 0
+    deltax = x[:, np.newaxis] - x
+    deltay = y[:, np.newaxis] - y
+    slopes = deltay[deltax > 0] / deltax[deltax > 0]
+    slopes.sort()
+    medslope = np.median(slopes)
+    if method == 'joint':
+        medinter = np.median(y - medslope * x)
+    else:
+        medinter = np.median(y) - medslope * np.median(x)
+    # Now compute confidence intervals
+    if alpha > 0.5:
+        alpha = 1. - alpha
+
+    z = distributions.norm.ppf(alpha / 2.)
+    # This implements (2.6) from Sen (1968)
+    _, nxreps = _find_repeats(x)
+    _, nyreps = _find_repeats(y)
+    nt = len(slopes)       # N in Sen (1968)
+    ny = len(y)            # n in Sen (1968)
+    # Equation 2.6 in Sen (1968):
+    sigsq = 1/18. * (ny * (ny-1) * (2*ny+5) -
+                     sum(k * (k-1) * (2*k + 5) for k in nxreps) -
+                     sum(k * (k-1) * (2*k + 5) for k in nyreps))
+    # Find the confidence interval indices in `slopes`
+    sigma = np.sqrt(sigsq)
+    Ru = min(int(np.round((nt - z*sigma)/2.)), len(slopes)-1)
+    Rl = max(int(np.round((nt + z*sigma)/2.)) - 1, 0)
+    delta = slopes[[Rl, Ru]]
+    return medslope, medinter, delta[0], delta[1]
+
+
+def _find_repeats(arr):
+    # This function assumes it may clobber its input.
+    if len(arr) == 0:
+        return np.array(0, np.float64), np.array(0, np.intp)
+
+    # XXX This cast was previously needed for the Fortran implementation,
+    # should we ditch it?
+    arr = np.asarray(arr, np.float64).ravel()
+    arr.sort()
+
+    # Taken from NumPy 1.9's np.unique.
+    change = np.concatenate(([True], arr[1:] != arr[:-1]))
+    unique = arr[change]
+    change_idx = np.concatenate(np.nonzero(change) + ([arr.size],))
+    freq = np.diff(change_idx)
+    atleast2 = freq > 1
+    return unique[atleast2], freq[atleast2]
+
+
+def siegelslopes(y, x=None, method="hierarchical"):
+    r"""
+    Computes the Siegel estimator for a set of points (x, y).
+
+    `siegelslopes` implements a method for robust linear regression
+    using repeated medians (see [1]_) to fit a line to the points (x, y).
+    The method is robust to outliers with an asymptotic breakdown point
+    of 50%.
+
+    Parameters
+    ----------
+    y : array_like
+        Dependent variable.
+    x : array_like or None, optional
+        Independent variable. If None, use ``arange(len(y))`` instead.
+    method : {'hierarchical', 'separate'}
+        If 'hierarchical', estimate the intercept using the estimated
+        slope ``medslope`` (default option).
+        If 'separate', estimate the intercept independent of the estimated
+        slope. See Notes for details.
+
+    Returns
+    -------
+    medslope : float
+        Estimate of the slope of the regression line.
+    medintercept : float
+        Estimate of the intercept of the regression line.
+
+    See also
+    --------
+    theilslopes : a similar technique without repeated medians
+
+    Notes
+    -----
+    With ``n = len(y)``, compute ``m_j`` as the median of
+    the slopes from the point ``(x[j], y[j])`` to all other `n-1` points.
+    ``medslope`` is then the median of all slopes ``m_j``.
+    Two ways are given to estimate the intercept in [1]_ which can be chosen
+    via the parameter ``method``.
+    The hierarchical approach uses the estimated slope ``medslope``
+    and computes ``medintercept`` as the median of ``y - medslope*x``.
+    The other approach estimates the intercept separately as follows: for
+    each point ``(x[j], y[j])``, compute the intercepts of all the `n-1`
+    lines through the remaining points and take the median ``i_j``.
+    ``medintercept`` is the median of the ``i_j``.
+
+    The implementation computes `n` times the median of a vector of size `n`
+    which can be slow for large vectors. There are more efficient algorithms
+    (see [2]_) which are not implemented here.
+
+    References
+    ----------
+    .. [1] A. Siegel, "Robust Regression Using Repeated Medians",
+           Biometrika, Vol. 69, pp. 242-244, 1982.
+
+    .. [2] A. Stein and M. Werman, "Finding the repeated median regression
+           line", Proceedings of the Third Annual ACM-SIAM Symposium on
+           Discrete Algorithms, pp. 409-413, 1992.
+
+    Examples
+    --------
+    >>> from scipy import stats
+    >>> import matplotlib.pyplot as plt
+
+    >>> x = np.linspace(-5, 5, num=150)
+    >>> y = x + np.random.normal(size=x.size)
+    >>> y[11:15] += 10  # add outliers
+    >>> y[-5:] -= 7
+
+    Compute the slope and intercept.  For comparison, also compute the
+    least-squares fit with `linregress`:
+
+    >>> res = stats.siegelslopes(y, x)
+    >>> lsq_res = stats.linregress(x, y)
+
+    Plot the results. The Siegel regression line is shown in red. The green
+    line shows the least-squares fit for comparison.
+
+    >>> fig = plt.figure()
+    >>> ax = fig.add_subplot(111)
+    >>> ax.plot(x, y, 'b.')
+    >>> ax.plot(x, res[1] + res[0] * x, 'r-')
+    >>> ax.plot(x, lsq_res[1] + lsq_res[0] * x, 'g-')
+    >>> plt.show()
+
+    """
+    if method not in ['hierarchical', 'separate']:
+        raise ValueError("method can only be 'hierarchical' or 'separate'")
+    y = np.asarray(y).ravel()
+    if x is None:
+        x = np.arange(len(y), dtype=float)
+    else:
+        x = np.asarray(x, dtype=float).ravel()
+        if len(x) != len(y):
+            raise ValueError("Incompatible lengths ! (%s<>%s)" %
+                             (len(y), len(x)))
+
+    deltax = x[:, np.newaxis] - x
+    deltay = y[:, np.newaxis] - y
+    slopes, intercepts = [], []
+
+    for j in range(len(x)):
+        id_nonzero = deltax[j, :] != 0
+        slopes_j = deltay[j, id_nonzero] / deltax[j, id_nonzero]
+        medslope_j = np.median(slopes_j)
+        slopes.append(medslope_j)
+        if method == 'separate':
+            z = y*x[j] - y[j]*x
+            medintercept_j = np.median(z[id_nonzero] / deltax[j, id_nonzero])
+            intercepts.append(medintercept_j)
+
+    medslope = np.median(np.asarray(slopes))
+    if method == "separate":
+        medinter = np.median(np.asarray(intercepts))
+    else:
+        medinter = np.median(y - medslope*x)
+
+    return medslope, medinter

dashboard/flask-server/venv/Lib/site-packages/scipy/stats/_tukeylambda_stats.py

@@ -0,0 +1,199 @@
+import numpy as np
+from numpy import poly1d
+from scipy.special import beta
+
+
+# The following code was used to generate the Pade coefficients for the
+# Tukey Lambda variance function.  Version 0.17 of mpmath was used.
+#---------------------------------------------------------------------------
+# import mpmath as mp
+#
+# mp.mp.dps = 60
+#
+# one   = mp.mpf(1)
+# two   = mp.mpf(2)
+#
+# def mpvar(lam):
+#     if lam == 0:
+#         v = mp.pi**2 / three
+#     else:
+#         v = (two / lam**2) * (one / (one + two*lam) -
+#                               mp.beta(lam + one, lam + one))
+#     return v
+#
+# t = mp.taylor(mpvar, 0, 8)
+# p, q = mp.pade(t, 4, 4)
+# print("p =", [mp.fp.mpf(c) for c in p])
+# print("q =", [mp.fp.mpf(c) for c in q])
+#---------------------------------------------------------------------------
+
+# Pade coefficients for the Tukey Lambda variance function.
+_tukeylambda_var_pc = [3.289868133696453, 0.7306125098871127,
+                       -0.5370742306855439, 0.17292046290190008,
+                       -0.02371146284628187]
+_tukeylambda_var_qc = [1.0, 3.683605511659861, 4.184152498888124,
+                       1.7660926747377275, 0.2643989311168465]
+
+# numpy.poly1d instances for the numerator and denominator of the
+# Pade approximation to the Tukey Lambda variance.
+_tukeylambda_var_p = poly1d(_tukeylambda_var_pc[::-1])
+_tukeylambda_var_q = poly1d(_tukeylambda_var_qc[::-1])
+
+
+def tukeylambda_variance(lam):
+    """Variance of the Tukey Lambda distribution.
+
+    Parameters
+    ----------
+    lam : array_like
+        The lambda values at which to compute the variance.
+
+    Returns
+    -------
+    v : ndarray
+        The variance.  For lam < -0.5, the variance is not defined, so
+        np.nan is returned.  For lam = 0.5, np.inf is returned.
+
+    Notes
+    -----
+    In an interval around lambda=0, this function uses the [4,4] Pade
+    approximation to compute the variance.  Otherwise it uses the standard
+    formula (https://en.wikipedia.org/wiki/Tukey_lambda_distribution).  The
+    Pade approximation is used because the standard formula has a removable
+    discontinuity at lambda = 0, and does not produce accurate numerical
+    results near lambda = 0.
+    """
+    lam = np.asarray(lam)
+    shp = lam.shape
+    lam = np.atleast_1d(lam).astype(np.float64)
+
+    # For absolute values of lam less than threshold, use the Pade
+    # approximation.
+    threshold = 0.075
+
+    # Play games with masks to implement the conditional evaluation of
+    # the distribution.
+    # lambda < -0.5:  var = nan
+    low_mask = lam < -0.5
+    # lambda == -0.5: var = inf
+    neghalf_mask = lam == -0.5
+    # abs(lambda) < threshold:  use Pade approximation
+    small_mask = np.abs(lam) < threshold
+    # else the "regular" case:  use the explicit formula.
+    reg_mask = ~(low_mask | neghalf_mask | small_mask)
+
+    # Get the 'lam' values for the cases where they are needed.
+    small = lam[small_mask]
+    reg = lam[reg_mask]
+
+    # Compute the function for each case.
+    v = np.empty_like(lam)
+    v[low_mask] = np.nan
+    v[neghalf_mask] = np.inf
+    if small.size > 0:
+        # Use the Pade approximation near lambda = 0.
+        v[small_mask] = _tukeylambda_var_p(small) / _tukeylambda_var_q(small)
+    if reg.size > 0:
+        v[reg_mask] = (2.0 / reg**2) * (1.0 / (1.0 + 2 * reg) -
+                                      beta(reg + 1, reg + 1))
+    v.shape = shp
+    return v
+
+
+# The following code was used to generate the Pade coefficients for the
+# Tukey Lambda kurtosis function.  Version 0.17 of mpmath was used.
+#---------------------------------------------------------------------------
+# import mpmath as mp
+#
+# mp.mp.dps = 60
+#
+# one   = mp.mpf(1)
+# two   = mp.mpf(2)
+# three = mp.mpf(3)
+# four  = mp.mpf(4)
+#
+# def mpkurt(lam):
+#     if lam == 0:
+#         k = mp.mpf(6)/5
+#     else:
+#         numer = (one/(four*lam+one) - four*mp.beta(three*lam+one, lam+one) +
+#                  three*mp.beta(two*lam+one, two*lam+one))
+#         denom = two*(one/(two*lam+one) - mp.beta(lam+one,lam+one))**2
+#         k = numer / denom - three
+#     return k
+#
+# # There is a bug in mpmath 0.17: when we use the 'method' keyword of the
+# # taylor function and we request a degree 9 Taylor polynomial, we actually
+# # get degree 8.
+# t = mp.taylor(mpkurt, 0, 9, method='quad', radius=0.01)
+# t = [mp.chop(c, tol=1e-15) for c in t]
+# p, q = mp.pade(t, 4, 4)
+# print("p =", [mp.fp.mpf(c) for c in p])
+# print("q =", [mp.fp.mpf(c) for c in q])
+#---------------------------------------------------------------------------
+
+# Pade coefficients for the Tukey Lambda kurtosis function.
+_tukeylambda_kurt_pc = [1.2, -5.853465139719495, -22.653447381131077,
+                        0.20601184383406815, 4.59796302262789]
+_tukeylambda_kurt_qc = [1.0, 7.171149192233599, 12.96663094361842,
+                        0.43075235247853005, -2.789746758009912]
+
+# numpy.poly1d instances for the numerator and denominator of the
+# Pade approximation to the Tukey Lambda kurtosis.
+_tukeylambda_kurt_p = poly1d(_tukeylambda_kurt_pc[::-1])
+_tukeylambda_kurt_q = poly1d(_tukeylambda_kurt_qc[::-1])
+
+
+def tukeylambda_kurtosis(lam):
+    """Kurtosis of the Tukey Lambda distribution.
+
+    Parameters
+    ----------
+    lam : array_like
+        The lambda values at which to compute the variance.
+
+    Returns
+    -------
+    v : ndarray
+        The variance.  For lam < -0.25, the variance is not defined, so
+        np.nan is returned.  For lam = 0.25, np.inf is returned.
+
+    """
+    lam = np.asarray(lam)
+    shp = lam.shape
+    lam = np.atleast_1d(lam).astype(np.float64)
+
+    # For absolute values of lam less than threshold, use the Pade
+    # approximation.
+    threshold = 0.055
+
+    # Use masks to implement the conditional evaluation of the kurtosis.
+    # lambda < -0.25:  kurtosis = nan
+    low_mask = lam < -0.25
+    # lambda == -0.25: kurtosis = inf
+    negqrtr_mask = lam == -0.25
+    # lambda near 0:  use Pade approximation
+    small_mask = np.abs(lam) < threshold
+    # else the "regular" case:  use the explicit formula.
+    reg_mask = ~(low_mask | negqrtr_mask | small_mask)
+
+    # Get the 'lam' values for the cases where they are needed.
+    small = lam[small_mask]
+    reg = lam[reg_mask]
+
+    # Compute the function for each case.
+    k = np.empty_like(lam)
+    k[low_mask] = np.nan
+    k[negqrtr_mask] = np.inf
+    if small.size > 0:
+        k[small_mask] = _tukeylambda_kurt_p(small) / _tukeylambda_kurt_q(small)
+    if reg.size > 0:
+        numer = (1.0 / (4 * reg + 1) - 4 * beta(3 * reg + 1, reg + 1) +
+                 3 * beta(2 * reg + 1, 2 * reg + 1))
+        denom = 2 * (1.0/(2 * reg + 1) - beta(reg + 1, reg + 1))**2
+        k[reg_mask] = numer / denom - 3
+
+    # The return value will be a numpy array; resetting the shape ensures that
+    # if `lam` was a scalar, the return value is a 0-d array.
+    k.shape = shp
+    return k