Debugging of the empatica data yield integration.

src/features/all_cleaning_individual/straw/main.py

@@ -8,6 +8,7 @@ from sklearn.preprocessing import StandardScaler
 import matplotlib.pyplot as plt
 import seaborn as sns
 
+sys.path.append('/rapids/')
 from src.features import empatica_data_yield as edy
 
 def straw_cleaning(sensor_data_files, provider):
@@ -22,14 +23,14 @@ def straw_cleaning(sensor_data_files, provider):
     excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
 
     # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE
-    if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']:
-        target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config
-        features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
+    # if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']:
+    #     target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config
+    #     features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
 
     # (2) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows)
     features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]]
 
-    # (3.1) QUALITY CHECK (DATA YIELD COLUMN) which determines if the row stays or not (if either E4 or phone is low quality the row is useless - TODO: determine threshold)
+    # (3.1) QUALITY CHECK (DATA YIELD COLUMN) deletes the rows where E4 or phone data is low quality
     phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower()
     phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit
 
@@ -111,12 +112,11 @@ def straw_cleaning(sensor_data_files, provider):
     if features.isna().any().any():
         raise ValueError
 
-    sys.exit()
-
     return features
 
 def graph_bf_af(features, phase_name):
     sns.set(rc={"figure.figsize":(16, 8)})
+    print(features)
     sns.heatmap(features.isna(), cbar=False)
     plt.savefig(f'features_nans_{phase_name}.png', bbox_inches='tight')
 

src/features/empatica_data_yield.py

@@ -6,8 +6,8 @@ import sys
 
 def calculate_empatica_data_yield(features):
     # Get time segment duration in seconds from dataframe
-    datetime_start = datetime.strptime(df.loc[0, 'local_segment_start_datetime'], '%y-%m-%d %H:%M:%S')
-    datetime_end = datetime.strptime(df.loc[0, 'local_segment_end_datetime'], '%y-%m-%d %H:%M:%S')
+    datetime_start = datetime.strptime(features.loc[0, 'local_segment_start_datetime'], '%Y-%m-%d %H:%M:%S')
+    datetime_end = datetime.strptime(features.loc[0, 'local_segment_end_datetime'], '%Y-%m-%d %H:%M:%S')
     tseg_duration = (datetime_end - datetime_start).total_seconds()
 
     features["acc_data_yield"] = (features['empatica_accelerometer_cr_SO_windowsCount'] * 15) / tseg_duration
@@ -15,12 +15,10 @@ def calculate_empatica_data_yield(features):
     features["eda_data_yield"] = (features['empatica_electrodermal_activity_cr_SO_windowsCount'] * 60) / tseg_duration
     features["ibi_data_yield"] = (features['empatica_inter_beat_interval_cr_SO_windowsCount'] * 300) / tseg_duration
 
-    features["empatica_data_yield"] = features[['acc_data_yield', 'temp_data_yield', 'eda_data_yield', 'ibi_data_yield']].mean(axis=1)
-
-    # TODO: morda smisleno obdelovati različne senzorje ločeno -> lahko da ibi ne bo dobre kvalitete, ostali pa bodo okej. Zakaj bi samo zaradi IBI zavrgli celotno vrstico ...
-    # lahko se tudi naredi overall kvaliteta empatice npr. povprečje vseh data_yield rezultatov? Oz. povprečje z utežmi glede na število stolpcev, ki jih senzor vsebuje
-    # ... čeprav št. stolpcev ni najboljše, saj je pomembnost nekaterih (npr. EDA) značilk zelo vprašljiva.  
-    # TODO: boljša nastavitev delovnih ur sedaj je od 4 do 4... to povzroči veliko manjkajočih podatkov in posledično nizek (telefonski in E4) data_yield ... 
+    # TODO: boljša nastavitev delovnih ur sedaj je od 4:00 do 4:00... to povzroči veliko manjkajočih podatkov in posledično nizek (telefonski in E4) data_yield ... 
+    empatica_data_yield_cols = ['acc_data_yield', 'temp_data_yield', 'eda_data_yield', 'ibi_data_yield']
+    features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1)
+    features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average)
 
     return features