Extraction of additional SO features. Min/max has been changed to nsmallest/nlargest means.

config.yaml

@@ -484,13 +484,13 @@ EMPATICA_ACCELEROMETER:
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
     CR:
-      COMPUTE: False
+      COMPUTE: True
       FEATURES: ["totalMagnitudeBand", "absoluteMeanBand", "varianceBand"] # Acc features
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 15 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows']
-        STANDARDIZE_SO_FEATURES: True
+        STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py
 
 
@@ -512,14 +512,14 @@ EMPATICA_TEMPERATURE:
       FEATURES: ["maxtemp", "mintemp", "avgtemp", "mediantemp", "modetemp", "stdtemp", "diffmaxmodetemp", "diffminmodetemp", "entropytemp"]
       SRC_SCRIPT: src/features/empatica_temperature/dbdp/main.py
     CR:
-      COMPUTE: False
+      COMPUTE: True
       FEATURES: ["maximum", "minimum", "meanAbsChange", "longestStrikeAboveMean", "longestStrikeBelowMean", 
                   "stdDev", "median", "meanChange", "sumSquared", "squareSumOfComponent", "sumOfSquareComponents"]
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows']
-        STANDARDIZE_SO_FEATURES: True
+        STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-electrodermal-activity/
@@ -531,17 +531,17 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
       FEATURES: ["maxeda", "mineda", "avgeda", "medianeda", "modeeda", "stdeda", "diffmaxmodeeda", "diffminmodeeda", "entropyeda"]
       SRC_SCRIPT: src/features/empatica_electrodermal_activity/dbdp/main.py
     CR:
-      COMPUTE: False
+      COMPUTE: True
       FEATURES: ['mean', 'std', 'q25', 'q75', 'qd', 'deriv', 'power', 'numPeaks', 'ratePeaks', 'powerPeaks', 'sumPosDeriv', 'propPosDeriv', 'derivTonic', 
                   'sigTonicDifference', 'freqFeats','maxPeakAmplitudeChangeBefore', 'maxPeakAmplitudeChangeAfter', 'avgPeakAmplitudeChangeBefore', 
                   'avgPeakAmplitudeChangeAfter', 'avgPeakChangeRatio', 'maxPeakIncreaseTime', 'maxPeakDecreaseTime', 'maxPeakDuration', 'maxPeakChangeRatio',
                   'avgPeakIncreaseTime', 'avgPeakDecreaseTime', 'avgPeakDuration', 'signalOverallChange', 'changeDuration', 'changeRate', 'significantIncrease', 
                   'significantDecrease']
       WINDOWS:
-        COMPUTE: False
+        COMPUTE: True
         WINDOW_LENGTH: 60 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', count_windows, eda_num_peaks_non_zero]
-        STANDARDIZE_SO_FEATURES: True
+        STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-blood-volume-pulse/
@@ -559,8 +559,8 @@ EMPATICA_BLOOD_VOLUME_PULSE:
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows']
-        STANDARDIZE_SO_FEATURES: True
+        STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-inter-beat-interval/
@@ -579,8 +579,8 @@ EMPATICA_INTER_BEAT_INTERVAL:
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows']
-        STANDARDIZE_SO_FEATURES: True
+        STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-tags/
@@ -663,3 +663,17 @@ ALL_CLEANING_OVERALL:
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
+
+
+########################################################################################################################
+#                                                 Z-score standardization                                              #
+########################################################################################################################
+STANDARDIZATION:
+  COMPUTE: True
+  EXCECUTE_FULL_PIPELINE: False # Standardization to be calculated from feature extraction step including merging all sensors and participants steps (in seperate standardization file)
+EMPATICA_STANDARDIZATION:
+  PROVIDERS:
+    CR:
+      COMPUTE: False
+      TYPE: FROM_FIRST_ORDER # FROM_FIRST_ORDER or FROM_SECOND_ORDER(not implemented)
+      SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R

src/features/cr_features_helper_methods.py

@@ -6,16 +6,25 @@ import sys
 def extract_second_order_features(intraday_features, so_features_names):
     if not intraday_features.empty:
         so_features = pd.DataFrame()
+        #print(intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).nsmallest())
         if "mean" in so_features_names:
             so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).mean().add_suffix("_SO_mean")], axis=1)
         if "median" in so_features_names:
             so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).median().add_suffix("_SO_median")], axis=1)
         if "sd" in so_features_names:
             so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).std().add_suffix("_SO_sd")], axis=1)
-        if "max" in so_features_names:
+        if "nlargest_mean" in so_features_names: # largest 5 -- maybe there is a faster groupby solution?
-            so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).max().add_suffix("_SO_max")], axis=1)
+            for column in intraday_features.columns[2:]:
-        if "min" in so_features_names:
+                so_features[column+"_SO_nlargest_mean"] = intraday_features.drop("level_1", axis=1).groupby("local_segment")[column].apply(lambda x: x.nlargest(5).mean())
-            so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).min().add_suffix("_SO_min")], axis=1)
+        if "nsmallest_mean" in so_features_names: # smallest 5 -- maybe there is a faster groupby solution?
+            for column in intraday_features.columns[2:]:
+                so_features[column+"_SO_nsmallest_mean"] = intraday_features.drop("level_1", axis=1).groupby("local_segment")[column].apply(lambda x: x.nsmallest(5).mean())
+        if "count_windows" in so_features_names:
+            so_features["SO_windowsCount"] = intraday_features.groupby(["local_segment"]).count()["level_1"]
+
+        # numPeaksNonZero specialized for EDA sensor
+        if "eda_num_peaks_non_zero" in so_features_names and "numPeaks" in intraday_features.columns:
+                so_features["SO_numPeaksNonZero"] = intraday_features.groupby("local_segment")["numPeaks"].apply(lambda x: (x!=0).sum())
         
         so_features.reset_index(inplace=True)
 

src/features/empatica_blood_volume_pulse/cr/main.py

@@ -66,7 +66,7 @@ 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"].get("STANDARDIZE_SO_FEATURES", False):
+        if provider["WINDOWS"].get("STANDARDIZE_FEATURES", False):
             fo_columns = bvp_intraday_features.columns.values[2:]
             fo_columns_z_score = [col + "_zscore" for col in fo_columns]
             bvp_intraday_features[fo_columns_z_score] = StandardScaler().fit_transform(bvp_intraday_features[fo_columns])

src/features/empatica_inter_beat_interval/cr/main.py

@@ -70,7 +70,7 @@ def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segmen
     ibi_intraday_features = extract_ibi_features_from_intraday_data(ibi_intraday_data, intraday_features_to_compute, 
                                                                 requested_window_length, time_segment, filter_data_by_segment)
     if calc_windows:
-        if provider["WINDOWS"].get("STANDARDIZE_SO_FEATURES", False):
+        if provider["WINDOWS"].get("STANDARDIZE_FEATURES", False):
             fo_columns = ibi_intraday_features.columns.values[2:]
             fo_columns_z_score = [col + "_zscore" for col in fo_columns]
             ibi_intraday_features[fo_columns_z_score] = StandardScaler().fit_transform(ibi_intraday_features[fo_columns])

src/features/entry.py

@@ -23,22 +23,6 @@ else:
     if calc_windows:
         window_features, second_order_features = fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file, calc_windows=True)        
 
-        # # Get basic stats from all participant's windows
-        # fo_means_stds = pd.DataFrame({"mean": window_features.mean(), "median": window_features.median(), "sd": window_features.std(), 
-        #                                 "min": window_features.min(), "max": window_features.max()})
-        
-        # fo_columns = window_features.columns.values[5:]
-        # fo_columns_z_score = [col + "_zscore" for col in fo_columns]
-        # window_features[fo_columns_z_score] = StandardScaler().fit_transform(window_features[fo_columns])
-        
-        # print(fo_means_stds)
-
-        # Z-score SO features by columns
-        # if provider["WINDOWS"].get("STANDARDIZE_SO_FEATURES", False):
-        #     for indx, fo_mean_std in fo_means_stds.iterrows():
-        #         print(indx, fo_mean_std)
-        
-        # sys.exit()
         window_features.to_csv(snakemake.output[1], index=False)
         second_order_features.to_csv(snakemake.output[0], index=False)
 

tests/scripts/zero_vals.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import seaborn as sns
+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/p031/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" 
+
+df = pd.read_csv(path)
+print(df)
+is_NaN = df.isnull()
+df = df[df["empatica_electrodermal_activity_cr_numPeaks"]]
+print(df)
+
+
+# row_has_NaN = is_NaN. any(axis=1)
+# rows_with_NaN = df[row_has_NaN]
+# print(rows_with_NaN.size)
+
+# sns.heatmap(df.isna(), cbar=False)
+plt.savefig('eda_windows_p03_window_60_thresh_default.png', bbox_inches='tight')
+
+