nlp feature

dbm_lib/dbm_features/raw_features/nlp/speech_features.py

@@ -0,0 +1,47 @@
+"""
+file_name: speech_features
+project_name: DBM
+created: 2020-13-11
+"""
+
+import os
+import numpy as np
+import pandas as pd
+import glob
+from os.path import join
+import logging
+
+from dbm_lib.dbm_features.raw_features.util import util as ut
+from dbm_lib.dbm_features.raw_features.util import nlp_util as n_util
+
+logging.basicConfig(level=logging.INFO)
+logger=logging.getLogger()
+
+speech_dir = 'nlp/speech_feature'
+speech_ext = '_nlp.csv'
+transcribe_ext = 'nlp/transcribe/*_transcribe.csv'
+
+def run_speech_feature(video_uri, out_dir, r_config):
+    """
+    Processing all patient's for fetching nlp features
+    -------------------
+    -------------------
+    Args:
+        video_uri: video path; r_config: raw variable config object
+        out_dir: (str) Output directory for processed output
+    """
+    try:
+        
+        input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
+
+        transcribe_path = glob.glob(join(out_loc, transcribe_ext))
+        if len(transcribe_path)>0:
+
+            transcribe_df = pd.read_csv(transcribe_path[0])
+            df_speech= n_util.process_speech(transcribe_df, r_config)
+
+            logger.info('Saving Output file {} '.format(out_loc))
+            ut.save_output(df_speech, out_loc, fl_name, speech_dir, speech_ext)
+            
+    except Exception as e:
+        logger.error('Failed to process video file')

dbm_lib/dbm_features/raw_features/nlp/transcribe.py

@@ -21,7 +21,7 @@ formant_dir = 'nlp/transcribe'
 csv_ext = '_transcribe.csv'
 error_txt = 'error: length less than 0.1'
 
-def calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config, deep_path):
+def calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config, deep_path, aud_dur):
     """
     Preparing Formant freq matrix
     Args:
@@ -33,6 +33,7 @@ def calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config, deep_path
     df_formant = pd.DataFrame([text], columns=[r_config.nlp_transcribe])
     
     df_formant.replace('', np.nan, regex=True,inplace=True)
+    df_formant[r_config.nlp_totalTime] = aud_dur
     df_formant[r_config.err_reason] = 'Pass'# will replace with threshold in future release
     df_formant['dbm_master_url'] = video_uri
     
@@ -44,8 +45,8 @@ def empty_transcribe(video_uri, out_loc, fl_name, r_config):
     """
     Preparing empty formant frequency matrix if something fails
     """
-    cols = [r_config.nlp_transcribe, r_config.err_reason]
-    out_val = [[np.nan, error_txt]]
+    cols = [r_config.nlp_transcribe, r_config.nlp_totalTime, r_config.err_reason]
+    out_val = [[np.nan, np.nan, error_txt]]
     df_fm = pd.DataFrame(out_val, columns = cols)
     df_fm['dbm_master_url'] = video_uri
     
@@ -77,6 +78,7 @@ def run_transcribe(video_uri, out_dir, r_config, deep_path):
                 empty_transcribe(video_uri, out_loc, fl_name, r_config)
                 return
 
-            calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config, deep_path)
+            calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config, deep_path, aud_dur)
     except Exception as e:
-        logger.error('Failed to process audio file')
+        logger.error('Failed to process audio file')
+