Standardization as a Snakefile's rule enabled for all E4 sensors.

Snakefile

@@ -317,6 +317,8 @@ for provider in config["EMPATICA_ACCELEROMETER"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/empatica_accelerometer.csv", pid=config["PIDS"]))
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
+        if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"]:
+            files_to_compute.extend(expand("data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
 
 for provider in config["EMPATICA_HEARTRATE"]["PROVIDERS"].keys():
     if config["EMPATICA_HEARTRATE"]["PROVIDERS"][provider]["COMPUTE"]:
@@ -336,6 +338,8 @@ for provider in config["EMPATICA_TEMPERATURE"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/empatica_temperature.csv", pid=config["PIDS"]))
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
+        if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"]:
+            files_to_compute.extend(expand("data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
 
 for provider in config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"].keys():
     if config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"][provider]["COMPUTE"]:
@@ -345,6 +349,8 @@ for provider in config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/empatica_electrodermal_activity.csv", pid=config["PIDS"]))
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
+        if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"]:
+            files_to_compute.extend(expand("data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
 
 for provider in config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"].keys():
     if config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"][provider]["COMPUTE"]:
@@ -354,7 +360,8 @@ for provider in config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/empatica_blood_volume_pulse.csv", pid=config["PIDS"]))
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
-        files_to_compute.extend(expand("data/interim/{pid}/empatica_blood_volume_pulse_features/standardization_empatica_blood_volume_pulse_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["EMPATICA_STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
+        if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"]:
+            files_to_compute.extend(expand("data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
         
 
 for provider in config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"].keys():
@@ -365,6 +372,8 @@ for provider in config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/empatica_inter_beat_interval.csv", pid=config["PIDS"]))
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
+        if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"]:
+            files_to_compute.extend(expand("data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower()))
 
 if isinstance(config["EMPATICA_TAGS"]["PROVIDERS"], dict):
     for provider in config["EMPATICA_TAGS"]["PROVIDERS"].keys():
@@ -404,6 +413,10 @@ for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
     if config["ALL_CLEANING_OVERALL"]["PROVIDERS"][provider]["COMPUTE"]:
         files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +".csv"))
 
+# Put the for loop over STANDARDIZATION providers if all are COMPUTE == True 
+# then merge all that are set to True in z_all_sensors for all and each participant
+# See the logic behind: in each sensor the "data/processed/features/all_participants/all_sensor_features.csv" is listed  
+
 rule all:
     input:
         files_to_compute

config.yaml

@@ -484,7 +484,7 @@ 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
@@ -512,7 +512,7 @@ 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:
@@ -531,7 +531,7 @@ 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',
@@ -559,7 +559,7 @@ EMPATICA_BLOOD_VOLUME_PULSE:
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows', 'hrv_num_windows_non_zero']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows', 'hrv_num_windows_non_nan']
         STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
 
@@ -572,14 +572,14 @@ EMPATICA_INTER_BEAT_INTERVAL:
       FEATURES: ["maxibi", "minibi", "avgibi", "medianibi", "modeibi", "stdibi", "diffmaxmodeibi", "diffminmodeibi", "entropyibi"]
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/dbdp/main.py
     CR:
-      COMPUTE: False
+      COMPUTE: True
       FEATURES: ['meanHr', 'ibi', 'sdnn', 'sdsd', 'rmssd', 'pnn20', 'pnn50', 'sd', 'sd2', 'sd1/sd2', 'numRR', # Time features
                   'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features            
       PATCH_WITH_BVP: True
       WINDOWS:
         COMPUTE: True
         WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows', 'hrv_num_windows_non_zero']
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest_mean', 'nsmallest_mean', 'count_windows', 'hrv_num_windows_non_nan']
         STANDARDIZE_FEATURES: False
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
 
@@ -669,11 +669,7 @@ ALL_CLEANING_OVERALL:
 #                                                 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:
-      STANDARDIZE: True
+      COMPUTE: True
-      TYPE: FROM_FIRST_ORDER # FROM_FIRST_ORDER or FROM_SECOND_ORDER(not implemented)
+      SRC_SCRIPT: src/features/standardization/main.py
-      SRC_SCRIPT: src/features/standardization/empatica_standardization/main.py

rules/features.smk

@@ -775,6 +775,20 @@ rule empatica_accelerometer_python_features:
     script:
         "../src/features/entry.py"
 
+rule empatica_accelerometer_python_features_standardization:
+    input:
+        windows_features_data = "data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_python_{provider_key}_windows.csv"
+    params:
+        provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"],
+        provider_key = "{provider_key}",
+        sensor_key = "empatica_accelerometer",
+        provider_main = config["EMPATICA_ACCELEROMETER"]["PROVIDERS"]["CR"]
+    output:
+        "data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_python_{provider_key}_windows.csv"
+    script:
+        "../src/features/standardization/main.py"
+
 rule empatica_accelerometer_r_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_accelerometer_with_datetime.csv",
@@ -829,6 +843,20 @@ rule empatica_temperature_python_features:
     script:
         "../src/features/entry.py"
 
+rule empatica_temperature_python_features_standardization:
+    input:
+        windows_features_data = "data/interim/{pid}/empatica_temperature_features/empatica_temperature_python_{provider_key}_windows.csv"
+    params:
+        provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"],
+        provider_key = "{provider_key}",
+        sensor_key = "empatica_temperature",
+        provider_main = config["EMPATICA_TEMPERATURE"]["PROVIDERS"]["CR"]
+    output:
+        "data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_python_{provider_key}_windows.csv"
+    script:
+        "../src/features/standardization/main.py"
+
 rule empatica_temperature_r_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_temperature_with_datetime.csv",
@@ -856,6 +884,20 @@ rule empatica_electrodermal_activity_python_features:
     script:
         "../src/features/entry.py"
 
+rule empatica_electrodermal_activity_python_features_standardization:
+    input:
+        windows_features_data = "data/interim/{pid}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_{provider_key}_windows.csv"
+    params:
+        provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"],
+        provider_key = "{provider_key}",
+        sensor_key = "empatica_electrodermal_activity",
+        provider_main = config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"]["CR"]
+    output:
+        "data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_python_{provider_key}_windows.csv"
+    script:
+        "../src/features/standardization/main.py"
+
 rule empatica_electrodermal_activity_r_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_electrodermal_activity_with_datetime.csv",
@@ -883,6 +925,20 @@ rule empatica_blood_volume_pulse_python_features:
     script:
         "../src/features/entry.py"
 
+rule empatica_blood_volume_pulse_python_cr_features_standardization:
+    input:
+        windows_features_data = "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}_windows.csv"
+    params:
+        provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"],
+        provider_key = "{provider_key}",
+        sensor_key = "empatica_blood_volume_pulse",
+        provider_main = config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"]["CR"]
+    output:
+        "data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_python_{provider_key}_windows.csv"
+    script:
+        "../src/features/standardization/main.py"
+
 rule empatica_blood_volume_pulse_r_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_blood_volume_pulse_with_datetime.csv",
@@ -896,20 +952,6 @@ rule empatica_blood_volume_pulse_r_features:
     script:
         "../src/features/entry.R"
 
-rule empatica_blood_volume_pulse_python_cr_features_standardization:
-    input:
-        windows_features_data = "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}_windows.csv"
-    params:
-        provider = config["EMPATICA_STANDARDIZATION"]["PROVIDERS"]["CR"],
-        provider_key = "{provider_key}",
-        sensor_key = "empatica_blood_volume_pulse",
-        provider_main = config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"]["CR"]
-    output:
-        "data/interim/{pid}/empatica_blood_volume_pulse_features/standardization_empatica_blood_volume_pulse_python_{provider_key}.csv",
-        "data/interim/{pid}/empatica_blood_volume_pulse_features/standardization_empatica_blood_volume_pulse_python_{provider_key}_windows.csv"
-    script:
-        "../src/features/standardization/empatica_standardization/main.py"
-
 rule empatica_inter_beat_interval_python_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_inter_beat_interval_with_datetime.csv",
@@ -924,6 +966,20 @@ rule empatica_inter_beat_interval_python_features:
     script:
         "../src/features/entry.py"
 
+rule empatica_inter_beat_interval_python_features_standardization:
+    input:
+        windows_features_data = "data/interim/{pid}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_{provider_key}_windows.csv"
+    params:
+        provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"],
+        provider_key = "{provider_key}",
+        sensor_key = "empatica_inter_beat_interval",
+        provider_main = config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"]["CR"]
+    output:
+        "data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_python_{provider_key}_windows.csv"
+    script:
+        "../src/features/standardization/main.py"
+
 rule empatica_inter_beat_interval_r_features:
     input:
         sensor_data = "data/raw/{pid}/empatica_inter_beat_interval_with_datetime.csv",

src/features/standardization/main.py

@@ -4,9 +4,6 @@ from sklearn.preprocessing import StandardScaler
 
 import sys
 
-sys.path.append('/rapids/src/features/')
-from cr_features_helper_methods import extract_second_order_features
-
 sensor_data_files = dict(snakemake.input)
 
 provider = snakemake.params["provider"]
@@ -16,12 +13,14 @@ sensor_key = snakemake.params["sensor_key"]
 pd.set_option('display.max_columns', None)
 
 if provider_key == "cr":
+    sys.path.append('/rapids/src/features/')
+    from cr_features_helper_methods import extract_second_order_features
+
     provider_main = snakemake.params["provider_main"]
     prefix = sensor_key + "_" + provider_key + "_"
 
     windows_features_data = pd.read_csv(sensor_data_files["windows_features_data"])
-    excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', 
+    excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', prefix + "level_1"]
-                        prefix + "level_1"]
     windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)] = \
         StandardScaler().fit_transform(windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)])
 
@@ -31,3 +30,8 @@ if provider_key == "cr":
         so_features_names = provider_main["WINDOWS"]["SECOND_ORDER_FEATURES"]
         windows_so_features_data = extract_second_order_features(windows_features_data, so_features_names, prefix)
         windows_so_features_data.to_csv(snakemake.output[0], index=False)
+    else:
+        pd.DataFrame().to_csv(snakemake.output[0], index=False)
+
+else: 
+    pass #To-Do for the rest of the sensors.