Fill EDA NaN values where numPeak is zero. Other small changes.

calculatingfeatures

@@ -0,0 +1 @@
+Subproject commit 98e6207ecc23a23b1f621a11f28eb87cbfb7f9da

config.yaml

@@ -3,7 +3,7 @@
 ########################################################################################################################
 
 # See https://www.rapids.science/latest/setup/configuration/#participant-files
-PIDS: [p02] #p01, p02, p03]
+PIDS: [p01] #p01, p02, p03]
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
@@ -542,6 +542,7 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
         WINDOW_LENGTH: 60 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', count_windows, eda_num_peaks_non_zero]
         STANDARDIZE_FEATURES: False
+        IMPUTE_NANS: False
       SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-blood-volume-pulse/

src/features/empatica_electrodermal_activity/cr/main.py

@@ -63,6 +63,11 @@ def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segmen
                                                                 requested_window_length, time_segment, filter_data_by_segment)
 
     if calc_windows:
+        if provider["WINDOWS"]["IMPUTE_NANS"]:
+            eda_intraday_features[eda_intraday_features["numPeaks"] == 0] = \
+                eda_intraday_features[eda_intraday_features["numPeaks"] == 0].fillna(0)
+            pd.set_option('display.max_columns', None)
+            
         so_features_names = provider["WINDOWS"]["SECOND_ORDER_FEATURES"]
         eda_second_order_features = extract_second_order_features(eda_intraday_features, so_features_names)
     

src/features/entry.py

@@ -28,7 +28,8 @@ else:
     elif "empatica" in sensor_key: 
         pd.DataFrame().to_csv(snakemake.output[1], index=False)
 
-    sensor_features = fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file, calc_windows=False)
+    if not calc_windows:
+        sensor_features = fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file, calc_windows=False)
 
 if not calc_windows:
     sensor_features.to_csv(snakemake.output[0], index=False)

tests/scripts/missing_values_heatmap.py

@@ -5,7 +5,7 @@ import matplotlib.pyplot as plt
 
 # path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants
 # path = "/rapids/data/interim/p03/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv" 
-path = "/rapids/data/interim/p02/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv" 
+path = "/rapids/data/interim/p01/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv" 
 # path = "/rapids/data/interim/p02/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv" 
 # path = "/rapids/data/interim/p02/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv" 
 # path = "/rapids/data/interim/p02/empatica_temperature_features/empatica_temperature_python_cr_windows.csv"