Merge branch 'empatica_calculating_features'

.gitignore

@@ -93,6 +93,7 @@ packrat/*
 
 # exclude data from source control by default
 data/external/*
+!/data/external/empatica/empatica1/E4 Data.zip
 !/data/external/.gitkeep
 !/data/external/stachl_application_genre_catalogue.csv
 !/data/external/timesegments*.csv
@@ -113,4 +114,10 @@ sn_profile_*/
 settings.dcf
 tests/fakedata_generation/
 site/
-credentials.yaml
+!credentials.yaml
+
+# Docker container and other files
+.devcontainer
+
+# Calculating features module
+calculatingfeatures/

README.md

@@ -11,3 +11,22 @@
 For more information refer to our [documentation](http://www.rapids.science)
 
 By [MoSHI](https://www.moshi.pitt.edu/), [University of Pittsburgh](https://www.pitt.edu/)
+
+## Installation 
+
+For RAPIDS installation refer to to the [documentation](https://www.rapids.science/1.8/setup/installation/)
+
+## CalculatingFeatures
+
+This RAPIDS extension uses CalculatingFeatures library accessible [here](https://repo.ijs.si/matjazbostic/calculatingfeatures).
+
+To use CalculatingFeatures library:
+- Follow the installation instructions in the [README.md](https://repo.ijs.si/matjazbostic/calculatingfeatures/-/blob/master/README.md).
+
+- Copy built calculatingfeatures folder into the RAPIDS workspace.
+
+- Install the CalculatingFeatures package by:
+    ```
+    pip install "path/to/the/calculatingfeatures/folder"
+    CalculatingFeatures package has to be built and installed everytime to get the newest version.
+    ```

Snakefile

@@ -5,7 +5,6 @@ include: "rules/common.smk"
 include: "rules/renv.smk"
 include: "rules/preprocessing.smk"
 include: "rules/features.smk"
-include: "rules/models.smk"
 include: "rules/reports.smk"
 
 import itertools
@@ -328,6 +327,8 @@ 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"]:
@@ -347,6 +348,8 @@ 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"]:
@@ -356,6 +359,8 @@ 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"]:
@@ -365,6 +370,9 @@ 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")
+        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():
     if config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"][provider]["COMPUTE"]:
@@ -374,6 +382,8 @@ 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():
@@ -426,6 +436,9 @@ if config["PARAMS_FOR_ANALYSIS"]["TARGET"]["COMPUTE"]:
     files_to_compute.extend(expand("data/processed/models/population_model/input.csv"))
 
 #files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv", pid=config["PIDS"], cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"]))
+# 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:

config.yaml

@@ -3,36 +3,34 @@
 ########################################################################################################################
 
 # See https://www.rapids.science/latest/setup/configuration/#participant-files
-PIDS: ['p031', 'p032', 'p033', 'p034', 'p035', 'p036', 'p037', 'p038', 'p039', 'p040', 'p042', 'p043', 'p044', 'p045', 'p046', 'p049', 'p050', 'p052', 'p053', 'p054', 'p055', 'p057', 'p058', 'p059', 'p060', 'p061', 'p062', 'p064', 'p067', 'p068', 'p069', 'p070', 'p071', 'p072', 'p073', 'p074', 'p075', 'p076', 'p077', 'p078', 'p079', 'p080', 'p081', 'p082', 'p083', 'p084', 'p085', 'p086', 'p088', 'p089', 'p090', 'p091', 'p092', 'p093', 'p106', 'p107']
+PIDS: [p031] #p01, p02, p03]
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
-  USERNAMES_CSV: "data/external/main_study_usernames.csv"
+  CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
-  CSV_FILE_PATH: "data/external/main_study_participants.csv" # see docs for required format
   PHONE_SECTION:
     ADD: True
     IGNORED_DEVICE_IDS: []
   FITBIT_SECTION:
-    ADD: False
+    ADD: True
     IGNORED_DEVICE_IDS: []
   EMPATICA_SECTION:
-    ADD: False
+    ADD: True
     IGNORED_DEVICE_IDS: []
 
 # See https://www.rapids.science/latest/setup/configuration/#time-segments
 TIME_SEGMENTS: &time_segments
   TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
-  FILE: "data/external/timesegments_daily.csv"
+  FILE: "data/external/timesegments_periodic.csv"
-  INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs
+  INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
 
 # See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
 TIMEZONE: 
-    TYPE: MULTIPLE
+    TYPE: SINGLE
     SINGLE:
       TZCODE: Europe/Ljubljana
     MULTIPLE:
-      TZ_FILE: data/external/timezone.csv
+      TZCODES_FILE: data/external/multiple_timezones_example.csv
-      TZCODES_FILE: data/external/multiple_timezones.csv
       IF_MISSING_TZCODE: USE_DEFAULT
       DEFAULT_TZCODE: Europe/Ljubljana
       FITBIT: 
@@ -87,7 +85,7 @@ PHONE_ACTIVITY_RECOGNITION:
   EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same AR episode.
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
       ACTIVITY_CLASSES:
         STATIONARY: ["still", "tilting"]
@@ -116,7 +114,7 @@ PHONE_APPLICATIONS_FOREGROUND:
     SCRAPE_MISSING_CATEGORIES: False # whether or not to scrape missing genres, only effective if CATALOGUE_SOURCE is equal to FILE. If CATALOGUE_SOURCE is equal to GOOGLE, all genres are scraped anyway
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       INCLUDE_EPISODE_FEATURES: True
       SINGLE_CATEGORIES: ["all", "email"]
       MULTIPLE_CATEGORIES:
@@ -151,7 +149,7 @@ PHONE_BATTERY:
   EPISODE_THRESHOLD_BETWEEN_ROWS: 30 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
       SRC_SCRIPT: src/features/phone_battery/rapids/main.py
 
@@ -160,12 +158,12 @@ PHONE_BLUETOOTH:
   CONTAINER: bluetooth
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
       SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R
 
     DORYAB:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: 
         ALL: 
             DEVICES: ["countscans", "uniquedevices", "meanscans", "stdscans"]
@@ -186,7 +184,7 @@ PHONE_CALLS:
   CONTAINER: call
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES_TYPE: EPISODES # EVENTS or EPISODES
       CALL_TYPES: [missed, incoming, outgoing]
       FEATURES:
@@ -229,7 +227,7 @@ PHONE_DATA_YIELD:
             PHONE_WIFI_VISIBLE]
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: [ratiovalidyieldedminutes, ratiovalidyieldedhours]
       MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1, minimum percentage of valid minutes in an hour to be considered valid.
       SRC_SCRIPT: src/features/phone_data_yield/rapids/main.R
@@ -257,7 +255,7 @@ PHONE_LIGHT:
   CONTAINER: light_sensor
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
       SRC_SCRIPT: src/features/phone_light/rapids/main.py
 
@@ -271,7 +269,7 @@ PHONE_LOCATIONS:
 
   PROVIDERS:
     DORYAB:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["locationvariance","loglocationvariance","totaldistance","avgspeed","varspeed", "numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","avglengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy","timeathome", "homelabel"]
       DBSCAN_EPS: 100 # meters
       DBSCAN_MINSAMPLES: 5
@@ -286,7 +284,7 @@ PHONE_LOCATIONS:
       SRC_SCRIPT: src/features/phone_locations/doryab/main.py
 
     BARNETT:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"]
       IF_MULTIPLE_TIMEZONES: USE_MOST_COMMON
       MINUTES_DATA_USED: False # Use this for quality control purposes, how many minutes of data (location coordinates gruped by minute) were used to compute features
@@ -304,7 +302,7 @@ PHONE_MESSAGES:
   CONTAINER: sms
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       MESSAGES_TYPES : [received, sent]
       FEATURES: 
         received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
@@ -316,7 +314,7 @@ PHONE_SCREEN:
   CONTAINER: screen
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       REFERENCE_HOUR_FIRST_USE: 0
       IGNORE_EPISODES_SHORTER_THAN: 0 # in minutes, set to 0 to disable
       IGNORE_EPISODES_LONGER_THAN: 360 # in minutes, set to 0 to disable
@@ -338,12 +336,13 @@ PHONE_WIFI_VISIBLE:
   CONTAINER: wifi
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
       SRC_SCRIPT: src/features/phone_wifi_visible/rapids/main.R
 
 
 
+
 ########################################################################################################################
 #                                                 FITBIT                                                               #
 ########################################################################################################################
@@ -506,6 +505,16 @@ EMPATICA_ACCELEROMETER:
       COMPUTE: False
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
+    CR:
+      COMPUTE: False
+      FEATURES: ["totalMagnitudeBand", "absoluteMeanBand", "varianceBand"] # Acc features
+      WINDOWS:
+        COMPUTE: True
+        WINDOW_LENGTH: 15 # specify window length in seconds
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
+        STANDARDIZE_FEATURES: True
+      SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py
+
 
 # See https://www.rapids.science/latest/features/empatica-heartrate/
 EMPATICA_HEARTRATE:
@@ -524,6 +533,16 @@ EMPATICA_TEMPERATURE:
       COMPUTE: False
       FEATURES: ["maxtemp", "mintemp", "avgtemp", "mediantemp", "modetemp", "stdtemp", "diffmaxmodetemp", "diffminmodetemp", "entropytemp"]
       SRC_SCRIPT: src/features/empatica_temperature/dbdp/main.py
+    CR:
+      COMPUTE: False
+      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', 'nlargest', 'nsmallest', 'count_windows']
+        STANDARDIZE_FEATURES: True
+      SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-electrodermal-activity/
 EMPATICA_ELECTRODERMAL_ACTIVITY:
@@ -533,6 +552,20 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
       COMPUTE: False
       FEATURES: ["maxeda", "mineda", "avgeda", "medianeda", "modeeda", "stdeda", "diffmaxmodeeda", "diffminmodeeda", "entropyeda"]
       SRC_SCRIPT: src/features/empatica_electrodermal_activity/dbdp/main.py
+    CR:
+      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: True
+        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: True
+        IMPUTE_NANS: True
+      SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-blood-volume-pulse/
 EMPATICA_BLOOD_VOLUME_PULSE:
@@ -542,6 +575,16 @@ EMPATICA_BLOOD_VOLUME_PULSE:
       COMPUTE: False
       FEATURES: ["maxbvp", "minbvp", "avgbvp", "medianbvp", "modebvp", "stdbvp", "diffmaxmodebvp", "diffminmodebvp", "entropybvp"]
       SRC_SCRIPT: src/features/empatica_blood_volume_pulse/dbdp/main.py
+    CR:
+      COMPUTE: False
+      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
+      WINDOWS:
+        COMPUTE: True
+        WINDOW_LENGTH: 300 # specify window length in seconds
+        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
+        STANDARDIZE_FEATURES: True
+      SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-inter-beat-interval/
 EMPATICA_INTER_BEAT_INTERVAL:
@@ -551,6 +594,17 @@ EMPATICA_INTER_BEAT_INTERVAL:
       COMPUTE: False
       FEATURES: ["maxibi", "minibi", "avgibi", "medianibi", "modeibi", "stdibi", "diffmaxmodeibi", "diffminmodeibi", "entropyibi"]
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/dbdp/main.py
+    CR:
+      COMPUTE: False
+      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', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
+        STANDARDIZE_FEATURES: True
+      SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-tags/
 EMPATICA_TAGS:
@@ -558,6 +612,7 @@ EMPATICA_TAGS:
   PROVIDERS:  # None implemented yet
 
 
+
 ########################################################################################################################
 #                                                 PLOTS                                                                #
 ########################################################################################################################
@@ -566,7 +621,7 @@ EMPATICA_TAGS:
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#1-histograms-of-phone-data-yield
 HISTOGRAM_PHONE_DATA_YIELD:
-  PLOT: True
+  PLOT: False
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#2-heatmaps-of-overall-data-yield
 HEATMAP_PHONE_DATA_YIELD_PER_PARTICIPANT_PER_TIME_SEGMENT:
@@ -575,7 +630,7 @@ HEATMAP_PHONE_DATA_YIELD_PER_PARTICIPANT_PER_TIME_SEGMENT:
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#3-heatmap-of-recorded-phone-sensors
 HEATMAP_SENSORS_PER_MINUTE_PER_TIME_SEGMENT:
-  PLOT: True
+  PLOT: False
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#4-heatmap-of-sensor-row-count
 HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
@@ -586,7 +641,7 @@ HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
 
 # See https://www.rapids.science/latest/visualizations/feature-visualizations/#1-heatmap-correlation-matrix
 HEATMAP_FEATURE_CORRELATION_MATRIX:
-  PLOT: True
+  PLOT: False
   MIN_ROWS_RATIO: 0.5
   CORR_THRESHOLD: 0.1
   CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
@@ -599,17 +654,17 @@ HEATMAP_FEATURE_CORRELATION_MATRIX:
 ALL_CLEANING_INDIVIDUAL:
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       IMPUTE_SELECTED_EVENT_FEATURES:
         COMPUTE: True
         MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
       COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       COLS_VAR_THRESHOLD: True
-      ROWS_NAN_THRESHOLD: 1 # set to 1 to disable
+      ROWS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
-      DATA_YIELD_RATIO_THRESHOLD: 0.3 # set to 0 to disable
+      DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: False
+        COMPUTE: True
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R
@@ -617,23 +672,33 @@ ALL_CLEANING_INDIVIDUAL:
 ALL_CLEANING_OVERALL:
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       IMPUTE_SELECTED_EVENT_FEATURES:
         COMPUTE: True
         MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
       COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       COLS_VAR_THRESHOLD: True
-      ROWS_NAN_THRESHOLD: 1 # set to 1 to disable
+      ROWS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
-      DATA_YIELD_RATIO_THRESHOLD: 0.3 # set to 0 to disable
+      DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: False
+        COMPUTE: True
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
 
+
 ########################################################################################################################
-#                                              Analysis Workflow Example                                               #
+#                                                 Z-score standardization                                              #
+########################################################################################################################
+STANDARDIZATION:
+  PROVIDERS:
+    CR:
+      COMPUTE: True
+      SRC_SCRIPT: src/features/standardization/main.py
+
+########################################################################################################################
+#                                                      Baseline                                                        #
 ########################################################################################################################
 
 PARAMS_FOR_ANALYSIS:
@@ -651,3 +716,4 @@ PARAMS_FOR_ANALYSIS:
   TARGET:
     COMPUTE: True
     LABEL: PANAS_negative_affect_mean
+

credentials.yaml

@@ -0,0 +1,6 @@
+PSQL_STRAW:
+  database: staw
+  user: staw_db
+  password: kizi-x2yf-mate
+  host: 212.235.208.113
+  port: 5432

data/external/aware_csv/calls.csv

@@ -0,0 +1,9 @@
+"_id","timestamp","device_id","call_type","call_duration","trace"
+1,1587663260695,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",2,14,"d5e84f8af01b2728021d4f43f53a163c0c90000c"
+2,1587739118007,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",3,0,"47c125dc7bd163b8612cdea13724a814917b6e93"
+5,1587746544891,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",2,95,"9cc793ffd6e88b1d850ce540b5d7e000ef5650d4"
+6,1587911379859,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",2,63,"51fb9344e988049a3fec774c7ca622358bf80264"
+7,1587992647361,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",3,0,"2a862a7730cfdfaf103a9487afe3e02935fd6e02"
+8,1588020039448,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",1,11,"a2c53f6a086d98622c06107780980cf1bb4e37bd"
+11,1588176189024,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",2,65,"56589df8c830c70e330b644921ed38e08d8fd1f3"
+12,1588197745079,"a748ee1a-1d0b-4ae9-9074-279a2b6ba524",3,0,"cab458018a8ed3b626515e794c70b6f415318adc"

data/external/participant_files/p01.yaml

@@ -0,0 +1,11 @@
+PHONE:
+  DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524] # the participant's AWARE device id
+  PLATFORMS: [android] # or ios
+  LABEL: MyTestP01 # any string
+  START_DATE: 2020-01-01 # this can also be empty
+  END_DATE: 2021-01-01 # this can also be empty
+EMPATICA:
+  DEVICE_IDS: [empatica1]
+  LABEL: test01
+  START_DATE: 
+  END_DATE: 

data/external/timesegments_frequency.csv

@@ -1,2 +1,2 @@
 label,length
-thirtyminutes,30
+fiveminutes,5

data/external/timesegments_periodic.csv

@@ -1,9 +1,2 @@
 label,start_time,length,repeats_on,repeats_value
-threeday,00:00:00,2D 23H 59M 59S,every_day,0
 daily,00:00:00,23H 59M 59S,every_day,0
-morning,06:00:00,5H 59M 59S,every_day,0
-afternoon,12:00:00,5H 59M 59S,every_day,0
-evening,18:00:00,5H 59M 59S,every_day,0
-night,00:00:00,5H 59M 59S,every_day,0
-two_weeks_overlapping,00:00:00,13D 23H 59M 59S,every_day,0
-weekends,00:00:00,2D 23H 59M 59S,wday,5

environment.yml

@@ -3,114 +3,138 @@ channels:
   - conda-forge
   - defaults
 dependencies:
+  - _libgcc_mutex=0.1
+  - _openmp_mutex=4.5
   - _py-xgboost-mutex=2.0
-  - appdirs=1.4.*
+  - appdirs=1.4.4
   - arrow=0.16.0
-  - asn1crypto=1.4.*
+  - asn1crypto=1.4.0
-  - astropy=4.2.*
+  - astropy=4.2.1
-  - attrs=20.3.*
+  - attrs=20.3.0
-  - binaryornot=0.4.*
+  - binaryornot=0.4.4
   - blas=1.0
-  - brotlipy=0.7.*
+  - brotlipy=0.7.0
-  - bzip2=1.0.*
+  - bzip2=1.0.8
-  - ca-certificates
+  - ca-certificates=2021.7.5
-  - certifi
+  - certifi=2021.5.30
   - cffi=1.14.4
-  - chardet=3.0.*
+  - chardet=3.0.4
-  - click=7.1.*
+  - click=7.1.2
-  - cookiecutter=1.6.*
+  - colorama=0.4.4
-  - cryptography=3.3.*
+  - cookiecutter=1.6.0
-  - datrie=0.8.*
+  - cryptography=3.3.1
+  - datrie=0.8.2
   - docutils=0.16
   - future=0.18.2
-  - gitdb=4.0.*
+  - gitdb=4.0.5
-  - gitdb2=4.0.*
+  - gitdb2=4.0.2
-  - gitpython=3.1.*
+  - gitpython=3.1.11
   - idna=2.10
-  - imbalanced-learn=0.6.*
+  - imbalanced-learn=0.6.2
-  - importlib-metadata=2.0.*
+  - importlib-metadata=2.0.0
-  - importlib_metadata=2.0.*
+  - importlib_metadata=2.0.0
   - intel-openmp=2019.4
   - jinja2=2.11.2
-  - jinja2-time=0.2.*
+  - jinja2-time=0.2.0
-  - joblib=1.0.*
+  - joblib=1.0.0
-  - jsonschema=3.2.*
+  - jsonschema=3.2.0
-  - libblas=3.8.*
+  - ld_impl_linux-64=2.36.1
-  - libcblas=3.8.*
+  - libblas=3.8.0
-  - libcxx=10.0.*
+  - libcblas=3.8.0
-  - libedit=3.1.*
+  - libcxx=10.0.0
+  - libcxxabi=10.0.0
+  - libedit=3.1.20191231
   - libffi=3.3
+  - libgcc-ng=11.2.0
   - libgfortran
-  - liblapack=3.8.*
+  - libgfortran
-  - libopenblas=0.3.*
+  - libgfortran
+  - liblapack=3.8.0
+  - libopenblas=0.3.10
+  - libstdcxx-ng=11.2.0
   - libxgboost=0.90
-  - lightgbm=3.1.*
+  - libzlib=1.2.11
-  - llvm-openmp=10.0.*
+  - lightgbm=3.1.1
-  - markupsafe=1.1.*
+  - llvm-openmp=10.0.0
+  - markupsafe=1.1.1
   - mkl
-  - mkl-service=2.3.*
+  - mkl-service=2.3.0
-  - mkl_fft=1.2.*
+  - mkl_fft=1.2.0
-  - mkl_random=1.1.*
+  - mkl_random=1.1.1
-  - more-itertools=8.6.*
+  - more-itertools=8.6.0
   - ncurses=6.2
   - numpy=1.19.2
   - numpy-base=1.19.2
-  - openblas=0.3.*
+  - openblas=0.3.4
-  - openssl
+  - openssl=1.1.1k
-  - pandas=1.1.*
+  - pandas=1.1.5
-  - pbr=5.5.*
+  - pbr=5.5.1
-  - pip=20.3.*
+  - pip=20.3.3
   - plotly=4.14.1
-  - poyo=0.5.*
+  - poyo=0.5.0
-  - psutil=5.7.*
+  - psutil=5.7.2
-  - psycopg2
   - py-xgboost=0.90
   - pycparser=2.20
-  - pyerfa=1.7.*
+  - pyerfa=1.7.1.1
-  - pyopenssl=20.0.*
+  - pyopenssl=20.0.1
-  - pyprojroot
+  - pysocks=1.7.1
-  - pysocks=1.7.*
+  - python=3.7.9
-  - python=3.7.*
+  - python-dateutil=2.8.1
-  - python-dateutil=2.8.*
-  - python-dotenv
   - python_abi=3.7
   - pytz=2020.4
-  - pyyaml=5.3.*
+  - pyyaml=5.3.1
   - readline=8.0
   - requests=2.25.0
-  - retrying=1.3.*
+  - retrying=1.3.3
   - scikit-learn=0.23.2
-  - scipy=1.5.*
+  - scipy=1.5.2
-  - setuptools=51.0.*
+  - setuptools=51.0.0
   - six=1.15.0
-  - smmap=3.0.*
+  - smmap=3.0.4
-  - smmap2=3.0.*
+  - smmap2=3.0.1
-  - sqlalchemy
   - sqlite=3.33.0
-  - threadpoolctl=2.1.*
+  - threadpoolctl=2.1.0
-  - tk=8.6.*
+  - tk=8.6.10
   - tqdm=4.62.0
   - urllib3=1.25.11
   - wheel=0.36.2
-  - whichcraft=0.6.*
+  - whichcraft=0.6.1
   - wrapt=1.12.1
   - xgboost=0.90
-  - xz=5.2.*
+  - xz=5.2.5
-  - yaml=0.2.*
+  - yaml=0.2.5
-  - zipp=3.4.*
+  - zipp=3.4.0
-  - zlib=1.2.*
+  - zlib=1.2.11
   - pip:
-    - amply==0.1.*
+    - amply==0.1.4
+    - bidict==0.22.0
+    - biosppy==0.8.0
+    - cached-property==1.5.2
     - configargparse==0.15.1
-    - decorator==4.4.*
+    - cr-features==0.1.15
-    - ipython-genutils==0.2.*
+    - cycler==0.11.0
-    - jupyter-core==4.6.*
+    - decorator==4.4.2
-    - nbformat==5.0.*
+    - fonttools==4.33.2
+    - h5py==3.6.0
+    - hmmlearn==0.2.7
+    - ipython-genutils==0.2.0
+    - jupyter-core==4.6.3
+    - kiwisolver==1.4.2
+    - matplotlib==3.5.1
+    - nbformat==5.0.7
+    - opencv-python==4.5.5.64
+    - packaging==21.3
+    - peakutils==1.3.3
+    - pillow==9.1.0
     - pulp==2.4
-    - pyparsing==2.4.*
+    - pyparsing==2.4.7
     - pyrsistent==0.15.5
-    - ratelimiter==1.2.*
+    - pywavelets==1.3.0
+    - ratelimiter==1.2.0.post0
+    - seaborn==0.11.2
+    - shortuuid==1.0.8
     - snakemake==5.30.2
     - toposort==1.5
-    - traitlets==4.3.*
+    - traitlets==4.3.3
-prefix: /usr/local/Caskroom/miniconda/base/envs/rapids202108
+    - typing-extensions==4.2.0
+prefix: /opt/conda/envs/rapids

renv/activate.R

@@ -14,9 +14,6 @@ local({
   # signal that we're loading renv during R startup
   Sys.setenv("RENV_R_INITIALIZING" = "true")
   on.exit(Sys.unsetenv("RENV_R_INITIALIZING"), add = TRUE)
-  
-  if(grepl("Darwin", Sys.info()["sysname"], fixed = TRUE) & grepl("ARM64", Sys.info()["version"], fixed = TRUE)) # M1 Macs
-    Sys.setenv("TZDIR" = file.path(R.home(), "share", "zoneinfo"))
 
   # signal that we've consented to use renv
   options(renv.consent = TRUE)

rules/features.smk

@@ -791,10 +791,25 @@ rule empatica_accelerometer_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_accelerometer"
     output:
-        "data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_python_{provider_key}_windows.csv"
     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",
@@ -817,7 +832,8 @@ rule empatica_heartrate_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_heartrate"
     output:
-        "data/interim/{pid}/empatica_heartrate_features/empatica_heartrate_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_heartrate_features/empatica_heartrate_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_heartrate_features/empatica_heartrate_python_{provider_key}_windows.csv"
     script:
         "../src/features/entry.py"
 
@@ -843,10 +859,25 @@ rule empatica_temperature_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_temperature"
     output:
-        "data/interim/{pid}/empatica_temperature_features/empatica_temperature_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_temperature_features/empatica_temperature_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_temperature_features/empatica_temperature_python_{provider_key}_windows.csv"
     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",
@@ -869,10 +900,25 @@ rule empatica_electrodermal_activity_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_electrodermal_activity"
     output:
-        "data/interim/{pid}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_{provider_key}_windows.csv"
     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",
@@ -895,10 +941,25 @@ rule empatica_blood_volume_pulse_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_blood_volume_pulse"
     output:
-        "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}_windows.csv"
     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",
@@ -921,10 +982,25 @@ rule empatica_inter_beat_interval_python_features:
         provider_key = "{provider_key}",
         sensor_key = "empatica_inter_beat_interval"
     output:
-        "data/interim/{pid}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_{provider_key}.csv"
+        "data/interim/{pid}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_{provider_key}.csv",
+        "data/interim/{pid}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_{provider_key}_windows.csv"
     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",

rules/preprocessing.smk

@@ -4,36 +4,6 @@ rule create_example_participant_files:
     shell:
         "echo 'PHONE:\n  DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n  PLATFORMS: [android]\n  LABEL: test-01\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\nFITBIT:\n  DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n  LABEL: test-01\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example01.yaml && echo 'PHONE:\n  DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n  PLATFORMS: [ios]\n  LABEL: test-02\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\nFITBIT:\n  DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n  LABEL: test-02\n  START_DATE: 2020-04-23 00:00:00\n  END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example02.yaml"
 
-rule query_usernames_device_empatica_ids:
-    params:
-        baseline_folder = "/mnt/e/STRAWbaseline/"
-    output:
-        usernames_file = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"],
-        timezone_file = config["TIMEZONE"]["MULTIPLE"]["TZ_FILE"]
-    script:
-        "../../participants/prepare_usernames_file.py"
-
-rule prepare_tzcodes_file:
-    input:
-        timezone_file = config["TIMEZONE"]["MULTIPLE"]["TZ_FILE"]
-    output:
-        tzcodes_file = config["TIMEZONE"]["MULTIPLE"]["TZCODES_FILE"]
-    script:
-        "../tools/create_multi_timezones_file.py"
-
-rule prepare_participants_csv:
-    input:
-        username_list = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"]
-    params:
-        data_configuration = config["PHONE_DATA_STREAMS"][config["PHONE_DATA_STREAMS"]["USE"]],
-        participants_table = "participants",
-        device_id_table = "esm",
-        start_end_date_table = "esm"
-    output:
-        participants_file = config["CREATE_PARTICIPANT_FILES"]["CSV_FILE_PATH"]
-    script:
-        "../src/data/translate_usernames_into_participants_data.R"
-
 rule create_participants_files:
     input:
         participants_file = config["CREATE_PARTICIPANT_FILES"]["CSV_FILE_PATH"] 
@@ -248,4 +218,4 @@ rule empatica_readable_datetime:
     output:
         "data/raw/{pid}/empatica_{sensor}_with_datetime.csv"
     script:
-        "../src/data/datetime/readable_datetime.R"
+        "../src/data/datetime/readable_datetime.R"

src/data/streams/empatica_zip/container.py

@@ -2,11 +2,16 @@ from zipfile import ZipFile
 import warnings
 from pathlib import Path
 import pandas as pd
+import numpy as np
 from pandas.core import indexing
 import yaml
 import csv
 from collections import OrderedDict
 from io import BytesIO, StringIO
+import sys, os
+
+from cr_features.hrv import get_HRV_features, get_patched_ibi_with_bvp
+from cr_features.helper_functions import empatica1d_to_array, empatica2d_to_array
 
 def processAcceleration(x, y, z):
     x = float(x)
@@ -62,13 +67,18 @@ def extract_empatica_data(data,  sensor):
         df.index.name = 'timestamp'
 
     elif sensor == 'EMPATICA_INTER_BEAT_INTERVAL':
-        df = pd.read_csv(sensor_data_file, names=['timestamp', column], header=None)
+
+        df = pd.read_csv(sensor_data_file, names=['timings', column], header=None)
+        df['timestamp'] = df['timings']
+        if df.empty:
+            df = df.set_index('timestamp')
+            return df
         timestampstart = float(df['timestamp'][0])
-        df['timestamp'] = (df['timestamp'][1:len(df)]).astype(float) + timestampstart
+        df['timestamp'] = (df['timestamp'][1:len(df)]).astype(float) + timestampstart        
         df = df.drop([0])
         df[column] = df[column].astype(float)
         df = df.set_index('timestamp')
-
+        
     else:
         raise ValueError(
             "sensor has an invalid name: {}".format(sensor))
@@ -84,6 +94,10 @@ def pull_data(data_configuration, device, sensor, container, columns_to_download
     participant_data = pd.DataFrame(columns=columns_to_download.values())
     participant_data.set_index('timestamp', inplace=True)
 
+    with open('config.yaml', 'r') as stream:
+        config = yaml.load(stream, Loader=yaml.FullLoader)
+    cr_ibi_provider = config['EMPATICA_INTER_BEAT_INTERVAL']['PROVIDERS']['CR']
+
     available_zipfiles = list((Path(data_configuration["FOLDER"]) / Path(device)).rglob("*.zip"))
     if len(available_zipfiles) == 0:
         warnings.warn("There were no zip files in: {}. If you were expecting data for this participant the [EMPATICA][DEVICE_IDS] key in their participant file is missing the pid".format((Path(data_configuration["FOLDER"]) / Path(device))))
@@ -94,7 +108,13 @@ def pull_data(data_configuration, device, sensor, container, columns_to_download
             listOfFileNames = zipFile.namelist()
             for fileName in listOfFileNames:
                 if fileName == sensor_csv:
-                    participant_data = pd.concat([participant_data, extract_empatica_data(zipFile.read(fileName),  sensor)], axis=0)
+                    if sensor == "EMPATICA_INTER_BEAT_INTERVAL" and cr_ibi_provider.get('PATCH_WITH_BVP', False):
+                        participant_data = \
+                            pd.concat([participant_data, patch_ibi_with_bvp(zipFile.read('IBI.csv'), zipFile.read('BVP.csv'))], axis=0)
+                        #print("patch with ibi")
+                    else:
+                        participant_data = pd.concat([participant_data, extract_empatica_data(zipFile.read(fileName), sensor)], axis=0)
+                        #print("no patching")
                     warning = False
             if warning:
                 warnings.warn("We could not find a zipped file for {} in {} (we tried to find {})".format(sensor, zipFile, sensor_csv))
@@ -105,4 +125,53 @@ def pull_data(data_configuration, device, sensor, container, columns_to_download
     participant_data["device_id"] = device
     return(participant_data)
 
+def patch_ibi_with_bvp(ibi_data, bvp_data):
+    ibi_data_file = BytesIO(ibi_data).getvalue().decode('utf-8')
+    ibi_data_file = StringIO(ibi_data_file)
+
+    # Begin with the cr-features part
+    try:
+        ibi_data, ibi_start_timestamp = empatica2d_to_array(ibi_data_file)
+    except IndexError as e:
+        # Checks whether IBI.csv is empty
+        df_test = pd.read_csv(ibi_data_file, names=['timings', 'inter_beat_interval'], header=None)
+        if df_test.empty:
+            df_test['timestamp'] = df_test['timings']
+            df_test = df_test.set_index('timestamp')
+            return df_test
+        else:
+            raise IndexError("Something went wrong with indices. Error that was previously caught:\n", repr(e))
+
+    bvp_data_file = BytesIO(bvp_data).getvalue().decode('utf-8')
+    bvp_data_file = StringIO(bvp_data_file)
+
+    bvp_data, bvp_start_timestamp, sample_rate = empatica1d_to_array(bvp_data_file)
+
+    hrv_time_and_freq_features, sample, bvp_rr, bvp_timings, peak_indx = \
+        get_HRV_features(bvp_data, ma=False, 
+                        detrend=False, m_deternd=False, low_pass=False, winsorize=True, 
+                        winsorize_value=25, hampel_fiter=False, median_filter=False, 
+                        mod_z_score_filter=True, sampling=64, feature_names=['meanHr'])
+    
+    ibi_timings, ibi_rr = get_patched_ibi_with_bvp(ibi_data[0], ibi_data[1], bvp_timings, bvp_rr)
+
+    df = \
+        pd.DataFrame(np.array([ibi_timings, ibi_rr]).transpose(), columns=['timestamp', 'inter_beat_interval'])
+    df.loc[-1] = [ibi_start_timestamp, 'IBI']  # adding a row
+    df.index = df.index + 1  # shifting index
+    df = df.sort_index()  # sorting by index
+
+    # Repeated as in extract_empatica_data for IBI
+    df['timings'] = df['timestamp']
+    timestampstart = float(df['timestamp'][0])
+    df['timestamp'] = (df['timestamp'][1:len(df)]).astype(float) + timestampstart        
+    df = df.drop([0])
+    df['inter_beat_interval'] = df['inter_beat_interval'].astype(float)
+    df = df.set_index('timestamp')
+
+    # format timestamps
+    df.index *= 1000
+    df.index = df.index.astype(int)
+    return(df)
+
 # print(pull_data({'FOLDER': 'data/external/empatica'}, "e01", "EMPATICA_accelerometer", {'TIMESTAMP': 'timestamp', 'DEVICE_ID': 'device_id', 'DOUBLE_VALUES_0': 'x', 'DOUBLE_VALUES_1': 'y', 'DOUBLE_VALUES_2': 'z'}))

src/data/streams/empatica_zip/format.yaml

@@ -50,6 +50,7 @@ EMPATICA_INTER_BEAT_INTERVAL:
     TIMESTAMP: timestamp
     DEVICE_ID: device_id
     INTER_BEAT_INTERVAL: inter_beat_interval
+    TIMINGS: timings
   MUTATION:
     COLUMN_MAPPINGS:
     SCRIPTS: # List any python or r scripts that mutate your raw data

src/data/streams/rapids_columns.yaml

@@ -227,6 +227,7 @@ EMPATICA_INTER_BEAT_INTERVAL:
   - TIMESTAMP
   - DEVICE_ID
   - INTER_BEAT_INTERVAL
+  - TIMINGS
 
 EMPATICA_TAGS:
   - TIMESTAMP

src/features/cr_features_helper_methods.py

@@ -0,0 +1,59 @@
+import pandas as pd
+import numpy as np
+import math as m
+
+import sys
+
+def extract_second_order_features(intraday_features, so_features_names, prefix=""):
+    
+    if prefix:
+        groupby_cols = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
+    else:
+        groupby_cols = ['local_segment']
+
+    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(prefix+"level_1", axis=1).groupby(groupby_cols).mean().add_suffix("_SO_mean")], axis=1)
+        
+        if "median" in so_features_names:
+            so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).median().add_suffix("_SO_median")], axis=1)
+        
+        if "sd" in so_features_names:
+            so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std().add_suffix("_SO_sd")], axis=1)
+        
+        if "nlargest" in so_features_names: # largest 5 -- maybe there is a faster groupby solution?
+            for column in intraday_features.loc[:, ~intraday_features.columns.isin(groupby_cols+[prefix+"level_1"])]:
+                so_features[column+"_SO_nlargest"] = intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols)[column].apply(lambda x: x.nlargest(5).mean())
+        
+        if "nsmallest" in so_features_names: # smallest 5 -- maybe there is a faster groupby solution?
+            for column in intraday_features.loc[:, ~intraday_features.columns.isin(groupby_cols+[prefix+"level_1"])]:
+                so_features[column+"_SO_nsmallest"] = intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols)[column].apply(lambda x: x.nsmallest(5).mean())
+        
+        if "count_windows" in so_features_names:
+            so_features["SO_windowsCount"] = intraday_features.groupby(groupby_cols).count()[prefix+"level_1"]
+
+        # numPeaksNonZero specialized for EDA sensor
+        if "eda_num_peaks_non_zero" in so_features_names and prefix+"numPeaks" in intraday_features.columns:
+            so_features[prefix+"SO_numPeaksNonZero"] = intraday_features.groupby(groupby_cols)[prefix+"numPeaks"].apply(lambda x: (x!=0).sum())
+
+        # numWindowsNonZero specialized for BVP and IBI sensors
+        if "hrv_num_windows_non_nan" in so_features_names and prefix+"meanHr" in intraday_features.columns:
+            so_features[prefix+"SO_numWindowsNonNaN"] = intraday_features.groupby(groupby_cols)[prefix+"meanHr"].apply(lambda x: (~np.isnan(x)).sum())
+            
+        so_features.reset_index(inplace=True)
+
+    else:
+        so_features = pd.DataFrame(columns=groupby_cols)
+
+    return so_features
+
+def get_sample_rate(data): # To-Do get the sample rate information from the file's metadata
+    try:
+        timestamps_diff = data['timestamp'].diff().dropna().mean()
+        print("Timestamp diff:", timestamps_diff)
+    except:
+        raise Exception("Error occured while trying to get the mean sample rate from the data.")
+
+    return m.ceil(1000/timestamps_diff)

src/features/empatica_accelerometer/cr/main.py

@@ -0,0 +1,71 @@
+import pandas as pd
+from scipy.stats import entropy
+
+from cr_features.helper_functions import convert_to2d, accelerometer_features, frequency_features
+from cr_features.calculate_features_old import calculateFeatures
+from cr_features.calculate_features import calculate_features
+from cr_features_helper_methods import extract_second_order_features
+
+import sys
+
+def extract_acc_features_from_intraday_data(acc_intraday_data, features, window_length, time_segment, filter_data_by_segment):
+    acc_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
+
+    if not acc_intraday_data.empty:   
+        sample_rate = 32
+     
+        acc_intraday_data = filter_data_by_segment(acc_intraday_data, time_segment)
+
+        if not acc_intraday_data.empty:
+
+            acc_intraday_features = pd.DataFrame()
+
+            # apply methods from calculate features module
+            if window_length is None:
+                acc_intraday_features = \
+                    acc_intraday_data.groupby('local_segment').apply(lambda x: calculate_features( \
+                    convert_to2d(x['double_values_0'], x.shape[0]), \
+                    convert_to2d(x['double_values_1'], x.shape[0]), \
+                    convert_to2d(x['double_values_2'], x.shape[0]), \
+                    fs=sample_rate, feature_names=features, show_progress=False)) 
+            else:
+                acc_intraday_features = \
+                    acc_intraday_data.groupby('local_segment').apply(lambda x: calculate_features( \
+                    convert_to2d(x['double_values_0'], window_length*sample_rate), \
+                    convert_to2d(x['double_values_1'], window_length*sample_rate), \
+                    convert_to2d(x['double_values_2'], window_length*sample_rate), \
+                    fs=sample_rate, feature_names=features, show_progress=False)) 
+
+            acc_intraday_features.reset_index(inplace=True)
+
+    return acc_intraday_features
+
+
+
+def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    acc_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
+
+    requested_intraday_features = provider["FEATURES"]
+    
+    calc_windows = kwargs.get('calc_windows', False)
+
+    if provider["WINDOWS"]["COMPUTE"] and calc_windows:
+        requested_window_length = provider["WINDOWS"]["WINDOW_LENGTH"]
+    else:
+        requested_window_length = None
+
+    # name of the features this function can compute
+    base_intraday_features_names = accelerometer_features + frequency_features
+    # the subset of requested features this function can compute
+    intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
+
+    # extract features from intraday data
+    acc_intraday_features = extract_acc_features_from_intraday_data(acc_intraday_data, intraday_features_to_compute, 
+                                                                requested_window_length, time_segment, filter_data_by_segment)
+
+    if calc_windows:
+        so_features_names = provider["WINDOWS"]["SECOND_ORDER_FEATURES"]
+        acc_second_order_features = extract_second_order_features(acc_intraday_features, so_features_names)
+        return acc_intraday_features, acc_second_order_features
+
+    return acc_intraday_features

src/features/empatica_blood_volume_pulse/cr/main.py

@@ -0,0 +1,73 @@
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+
+from cr_features.helper_functions import convert_to2d, hrv_features
+from cr_features.hrv import extract_hrv_features_2d_wrapper
+from cr_features_helper_methods import extract_second_order_features
+
+import sys
+
+# pd.set_option('display.max_rows', 1000)
+pd.set_option('display.max_columns', None)
+
+def extract_bvp_features_from_intraday_data(bvp_intraday_data, features, window_length, time_segment, filter_data_by_segment):
+    bvp_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
+
+    if not bvp_intraday_data.empty:
+        sample_rate = 64
+     
+        bvp_intraday_data = filter_data_by_segment(bvp_intraday_data, time_segment)
+
+        if not bvp_intraday_data.empty:
+
+            bvp_intraday_features = pd.DataFrame()
+
+            # apply methods from calculate features module
+            if window_length is None:
+                bvp_intraday_features = \
+                    bvp_intraday_data.groupby('local_segment').apply(\
+                    lambda x: 
+                        extract_hrv_features_2d_wrapper(
+                            convert_to2d(x['blood_volume_pulse'], x.shape[0]), 
+                            sampling=sample_rate, hampel_fiter=False, median_filter=False, mod_z_score_filter=True, feature_names=features))
+
+            else:
+                bvp_intraday_features = \
+                    bvp_intraday_data.groupby('local_segment').apply(\
+                    lambda x: 
+                        extract_hrv_features_2d_wrapper(
+                            convert_to2d(x['blood_volume_pulse'], window_length*sample_rate), 
+                            sampling=sample_rate, hampel_fiter=False, median_filter=False, mod_z_score_filter=True, feature_names=features)) 
+
+            bvp_intraday_features.reset_index(inplace=True)
+
+    return bvp_intraday_features
+
+
+def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    bvp_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
+
+    requested_intraday_features = provider["FEATURES"]
+    
+    calc_windows = kwargs.get('calc_windows', False)
+
+    if provider["WINDOWS"]["COMPUTE"] and calc_windows:
+        requested_window_length = provider["WINDOWS"]["WINDOW_LENGTH"]
+    else:
+        requested_window_length = None
+
+    # name of the features this function can compute
+    base_intraday_features_names = hrv_features
+    # the subset of requested features this function can compute
+    intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
+
+    # extract features from intraday data
+    bvp_intraday_features = extract_bvp_features_from_intraday_data(bvp_intraday_data, intraday_features_to_compute, 
+                                                                requested_window_length, time_segment, filter_data_by_segment)
+                                                                
+    if calc_windows:
+        so_features_names = provider["WINDOWS"]["SECOND_ORDER_FEATURES"]
+        bvp_second_order_features = extract_second_order_features(bvp_intraday_features, so_features_names)
+        return bvp_intraday_features, bvp_second_order_features
+
+    return bvp_intraday_features

src/features/empatica_electrodermal_activity/cr/main.py

@@ -0,0 +1,78 @@
+import pandas as pd
+import numpy as np
+from scipy.stats import entropy
+
+from cr_features.helper_functions import convert_to2d, gsr_features
+from cr_features.calculate_features import calculate_features
+from cr_features.gsr import extractGsrFeatures2D
+from cr_features_helper_methods import extract_second_order_features
+
+import sys
+
+#pd.set_option('display.max_columns', None)
+#pd.set_option('display.max_rows', None)
+#np.seterr(invalid='ignore')
+
+
+def extract_eda_features_from_intraday_data(eda_intraday_data, features, window_length, time_segment, filter_data_by_segment):
+    eda_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
+
+    if not eda_intraday_data.empty:   
+        sample_rate = 4  
+     
+        eda_intraday_data = filter_data_by_segment(eda_intraday_data, time_segment)
+
+        if not eda_intraday_data.empty: 
+
+            eda_intraday_features = pd.DataFrame()
+
+            # apply methods from calculate features module 
+            if window_length is None:
+                eda_intraday_features = \
+                    eda_intraday_data.groupby('local_segment').apply(\
+                    lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], x.shape[0]), sampleRate=sample_rate, featureNames=features,
+                    threshold=.01, offset=1, riseTime=5, decayTime=15)) 
+            else:
+                eda_intraday_features = \
+                    eda_intraday_data.groupby('local_segment').apply(\
+                    lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], window_length*sample_rate), sampleRate=sample_rate, featureNames=features,
+                    threshold=.01, offset=1, riseTime=5, decayTime=15)) 
+
+            eda_intraday_features.reset_index(inplace=True)
+
+    return eda_intraday_features
+
+
+def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    eda_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
+
+    requested_intraday_features = provider["FEATURES"]
+    
+    calc_windows = kwargs.get('calc_windows', False)
+
+    if provider["WINDOWS"]["COMPUTE"] and calc_windows:
+        requested_window_length = provider["WINDOWS"]["WINDOW_LENGTH"]
+    else:
+        requested_window_length = None
+
+    # name of the features this function can compute
+    base_intraday_features_names = gsr_features
+    # the subset of requested features this function can compute
+    intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
+
+    # extract features from intraday data
+    eda_intraday_features = extract_eda_features_from_intraday_data(eda_intraday_data, intraday_features_to_compute, 
+                                                                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)
+    
+        return eda_intraday_features, eda_second_order_features
+
+    return eda_intraday_features

src/features/empatica_inter_beat_interval/cr/main.py

@@ -0,0 +1,79 @@
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+import numpy as np
+
+from cr_features.helper_functions import convert_ibi_to2d_time, hrv_features
+from cr_features.hrv import extract_hrv_features_2d_wrapper, get_HRV_features
+from cr_features_helper_methods import extract_second_order_features
+
+import math
+import sys
+
+# pd.set_option('display.max_rows', 1000)
+pd.set_option('display.max_columns', None)
+
+
+def extract_ibi_features_from_intraday_data(ibi_intraday_data, features, window_length, time_segment, filter_data_by_segment):
+    ibi_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
+
+    if not ibi_intraday_data.empty:   
+
+        ibi_intraday_data = filter_data_by_segment(ibi_intraday_data, time_segment)
+
+        if not ibi_intraday_data.empty:
+
+            ibi_intraday_features = pd.DataFrame()
+
+            # apply methods from calculate features module
+            if window_length is None:
+                ibi_intraday_features = \
+                    ibi_intraday_data.groupby('local_segment').apply(\
+                    lambda x: 
+                        extract_hrv_features_2d_wrapper(
+                            signal_2D = \
+                                convert_ibi_to2d_time(x[['timings', 'inter_beat_interval']], math.ceil(x['timings'].iloc[-1]))[0], 
+                            ibi_timings = \
+                                convert_ibi_to2d_time(x[['timings', 'inter_beat_interval']], math.ceil(x['timings'].iloc[-1]))[1], 
+                            sampling=None, hampel_fiter=False, median_filter=False, mod_z_score_filter=True, feature_names=features)) 
+            else:
+                ibi_intraday_features = \
+                    ibi_intraday_data.groupby('local_segment').apply(\
+                    lambda x: 
+                        extract_hrv_features_2d_wrapper(
+                            signal_2D = convert_ibi_to2d_time(x[['timings', 'inter_beat_interval']], window_length)[0],
+                            ibi_timings = convert_ibi_to2d_time(x[['timings', 'inter_beat_interval']], window_length)[1],
+                            sampling=None, hampel_fiter=False, median_filter=False, mod_z_score_filter=True, feature_names=features)) 
+
+            ibi_intraday_features.reset_index(inplace=True)
+
+    return ibi_intraday_features
+
+
+def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    ibi_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
+
+    requested_intraday_features = provider["FEATURES"]
+    
+    calc_windows = kwargs.get('calc_windows', False)
+
+    if provider["WINDOWS"]["COMPUTE"] and calc_windows:
+        requested_window_length = provider["WINDOWS"]["WINDOW_LENGTH"]
+    else:
+        requested_window_length = None
+
+    # name of the features this function can compute
+    base_intraday_features_names = hrv_features
+    # the subset of requested features this function can compute
+    intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
+
+    # extract features from intraday data
+    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:        
+        so_features_names = provider["WINDOWS"]["SECOND_ORDER_FEATURES"]
+        ibi_second_order_features = extract_second_order_features(ibi_intraday_features, so_features_names)
+
+        return ibi_intraday_features, ibi_second_order_features
+
+    return ibi_intraday_features

src/features/empatica_temperature/cr/main.py

@@ -0,0 +1,65 @@
+import pandas as pd
+from scipy.stats import entropy
+
+from cr_features.helper_functions import convert_to2d, generic_features
+from cr_features.calculate_features_old import calculateFeatures
+from cr_features.calculate_features import calculate_features
+from cr_features_helper_methods import extract_second_order_features
+
+import sys
+
+def extract_temp_features_from_intraday_data(temperature_intraday_data, features, window_length, time_segment, filter_data_by_segment):
+    temperature_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
+
+    if not temperature_intraday_data.empty:
+        sample_rate = 4
+
+        temperature_intraday_data = filter_data_by_segment(temperature_intraday_data, time_segment)
+
+        if not temperature_intraday_data.empty:
+
+            temperature_intraday_features = pd.DataFrame()
+
+            # apply methods from calculate features module
+            if window_length is None:
+                temperature_intraday_features = \
+                    temperature_intraday_data.groupby('local_segment').apply(\
+                    lambda x: calculate_features(convert_to2d(x['temperature'], x.shape[0]), fs=sample_rate, feature_names=features, show_progress=False))
+            else:
+                temperature_intraday_features = \
+                    temperature_intraday_data.groupby('local_segment').apply(\
+                    lambda x: calculate_features(convert_to2d(x['temperature'], window_length*sample_rate), fs=sample_rate, feature_names=features, show_progress=False))
+
+
+            temperature_intraday_features.reset_index(inplace=True)
+
+    return temperature_intraday_features
+
+
+def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    temperature_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
+
+    requested_intraday_features = provider["FEATURES"]
+
+    calc_windows = kwargs.get('calc_windows', False)
+
+    if provider["WINDOWS"]["COMPUTE"] and calc_windows:
+        requested_window_length = provider["WINDOWS"]["WINDOW_LENGTH"]
+    else:
+        requested_window_length = None
+    
+    # name of the features this function can compute
+    base_intraday_features_names = generic_features
+    # the subset of requested features this function can compute
+    intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
+
+    # extract features from intraday data
+    temperature_intraday_features = extract_temp_features_from_intraday_data(temperature_intraday_data, intraday_features_to_compute, 
+                                                                        requested_window_length, time_segment, filter_data_by_segment)
+
+    if calc_windows:
+        so_features_names = provider["WINDOWS"]["SECOND_ORDER_FEATURES"]
+        temperature_second_order_features = extract_second_order_features(temperature_intraday_features, so_features_names)
+        return temperature_intraday_features, temperature_second_order_features
+
+    return temperature_intraday_features

src/features/entry.py

@@ -1,12 +1,16 @@
 import pandas as pd
 from utils.utils import fetch_provider_features, run_provider_cleaning_script
 
+import sys
+
 sensor_data_files = dict(snakemake.input)
 
 provider = snakemake.params["provider"]
 provider_key = snakemake.params["provider_key"]
 sensor_key = snakemake.params["sensor_key"]
 
+calc_windows = True if (provider.get("WINDOWS", False) and provider["WINDOWS"].get("COMPUTE", False)) else False
+
 if sensor_key == "all_cleaning_individual" or sensor_key == "all_cleaning_overall":
     # Data cleaning
     sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files)
@@ -14,6 +18,18 @@ else:
     # Extract sensor features
     del sensor_data_files["time_segments_labels"]
     time_segments_file = snakemake.input["time_segments_labels"]
-    sensor_features = fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file)
 
-sensor_features.to_csv(snakemake.output[0], index=False)
+    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)        
+
+        window_features.to_csv(snakemake.output[1], index=False)
+        second_order_features.to_csv(snakemake.output[0], index=False)
+
+    elif "empatica" in sensor_key: 
+        pd.DataFrame().to_csv(snakemake.output[1], index=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)

src/features/standardization/main.py

@@ -0,0 +1,37 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+
+import sys
+
+sensor_data_files = dict(snakemake.input)
+
+provider = snakemake.params["provider"]
+provider_key = snakemake.params["provider_key"]
+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', 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)])
+
+    windows_features_data.to_csv(snakemake.output[1], index=False)
+
+    if provider_main["WINDOWS"]["COMPUTE"] and "SECOND_ORDER_FEATURES" in provider_main["WINDOWS"]:
+        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.

src/features/utils/utils.py

@@ -88,11 +88,13 @@ def chunk_episodes(sensor_episodes):
 
     return merged_sensor_episodes
 
-def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file):
+def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file, calc_windows=False):
     import pandas as pd
     from importlib import import_module, util
 
     sensor_features = pd.DataFrame(columns=["local_segment"])
+    sensor_fo_features = pd.DataFrame(columns=["local_segment"])
+    sensor_so_features = pd.DataFrame(columns=["local_segment"])
     time_segments_labels = pd.read_csv(time_segments_file, header=0)
     if "FEATURES" not in provider:
         raise ValueError("Provider config[{}][PROVIDERS][{}] is missing a FEATURES attribute in config.yaml".format(sensor_key.upper(), provider_key.upper()))
@@ -106,23 +108,57 @@ def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_file
             time_segments_labels["label"] = [""]
         for time_segment in time_segments_labels["label"]:
             print("{} Processing {} {} {}".format(rapids_log_tag, sensor_key, provider_key, time_segment))
-            features = feature_function(sensor_data_files, time_segment, provider, filter_data_by_segment=filter_data_by_segment, chunk_episodes=chunk_episodes)
+
-            if not "local_segment" in features.columns:
+            features = feature_function(sensor_data_files, time_segment, provider, filter_data_by_segment=filter_data_by_segment, chunk_episodes=chunk_episodes, calc_windows=calc_windows)
-                raise ValueError("The dataframe returned by the " + sensor_key + " provider '" + provider_key + "' is missing the 'local_segment' column added by the 'filter_data_by_segment()' function. Check the provider script is using such function and is not removing 'local_segment' by accident (" + provider["SRC_SCRIPT"] + ")\n  The 'local_segment' column is used to index a provider's features (each row corresponds to a different time segment instance (e.g. 2020-01-01, 2020-01-02, 2020-01-03, etc.)")
+            
-            features.columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features.columns]
+            # In case of calc_window = True
-            sensor_features = pd.concat([sensor_features, features], axis=0, sort=False)
+            if isinstance(features, tuple):
+                if not "local_segment" in features[0].columns or not "local_segment" in features[1].columns:
+                        raise ValueError("The dataframe returned by the " + sensor_key + " provider '" + provider_key + "' is missing the 'local_segment' column added by the 'filter_data_by_segment()' function. Check the provider script is using such function and is not removing 'local_segment' by accident (" + provider["SRC_SCRIPT"] + ")\n  The 'local_segment' column is used to index a provider's features (each row corresponds to a different time segment instance (e.g. 2020-01-01, 2020-01-02, 2020-01-03, etc.)")
+                features[0].columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features[0].columns]
+                features[1].columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features[1].columns]
+                if not features[0].empty:
+                    sensor_fo_features = pd.concat([sensor_fo_features, features[0]], axis=0, sort=False)                
+                if not features[1].empty:
+                    sensor_so_features = pd.concat([sensor_so_features, features[1]], axis=0, sort=False)
+            else: 
+                if not "local_segment" in features.columns:
+                    raise ValueError("The dataframe returned by the " + sensor_key + " provider '" + provider_key + "' is missing the 'local_segment' column added by the 'filter_data_by_segment()' function. Check the provider script is using such function and is not removing 'local_segment' by accident (" + provider["SRC_SCRIPT"] + ")\n  The 'local_segment' column is used to index a provider's features (each row corresponds to a different time segment instance (e.g. 2020-01-01, 2020-01-02, 2020-01-03, etc.)")
+                features.columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features.columns]
+                sensor_features = pd.concat([sensor_features, features], axis=0, sort=False)
     else:
         for feature in provider["FEATURES"]:
             sensor_features[feature] = None
-    segment_colums = pd.DataFrame()
+    
-    sensor_features['local_segment'] = sensor_features['local_segment'].str.replace(r'_RR\d+SS', '')
+    if calc_windows:
-    split_segemnt_columns = sensor_features["local_segment"].str.split(pat="(.*)#(.*),(.*)", expand=True)
+        segment_colums = pd.DataFrame()
-    new_segment_columns = split_segemnt_columns.iloc[:,1:4] if split_segemnt_columns.shape[1] == 5 else pd.DataFrame(columns=["local_segment_label", "local_segment_start_datetime","local_segment_end_datetime"])
+        sensor_fo_features['local_segment'] = sensor_fo_features['local_segment'].str.replace(r'_RR\d+SS', '')
-    segment_colums[["local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]] = new_segment_columns
+        split_segemnt_columns = sensor_fo_features["local_segment"].str.split(pat="(.*)#(.*),(.*)", expand=True)
-    for i in range(segment_colums.shape[1]):
+        new_segment_columns = split_segemnt_columns.iloc[:,1:4] if split_segemnt_columns.shape[1] == 5 else pd.DataFrame(columns=["local_segment_label", "local_segment_start_datetime","local_segment_end_datetime"])
-            sensor_features.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
+        segment_colums[["local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]] = new_segment_columns
+        for i in range(segment_colums.shape[1]):
+                sensor_fo_features.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
+        
+        segment_colums = pd.DataFrame()
+        sensor_so_features['local_segment'] = sensor_so_features['local_segment'].str.replace(r'_RR\d+SS', '')
+        split_segemnt_columns = sensor_so_features["local_segment"].str.split(pat="(.*)#(.*),(.*)", expand=True)
+        new_segment_columns = split_segemnt_columns.iloc[:,1:4] if split_segemnt_columns.shape[1] == 5 else pd.DataFrame(columns=["local_segment_label", "local_segment_start_datetime","local_segment_end_datetime"])
+        segment_colums[["local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]] = new_segment_columns
+        for i in range(segment_colums.shape[1]):
+                sensor_so_features.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
 
-    return sensor_features
+        return sensor_fo_features, sensor_so_features
+
+    else: 
+        segment_colums = pd.DataFrame()
+        sensor_features['local_segment'] = sensor_features['local_segment'].str.replace(r'_RR\d+SS', '')
+        split_segemnt_columns = sensor_features["local_segment"].str.split(pat="(.*)#(.*),(.*)", expand=True)
+        new_segment_columns = split_segemnt_columns.iloc[:,1:4] if split_segemnt_columns.shape[1] == 5 else pd.DataFrame(columns=["local_segment_label", "local_segment_start_datetime","local_segment_end_datetime"])
+        segment_colums[["local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]] = new_segment_columns
+        for i in range(segment_colums.shape[1]):
+                sensor_features.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
+
+        return sensor_features
 
 def run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files):
     from importlib import import_module, util
@@ -132,4 +168,4 @@ def run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data
     cleaning_function = getattr(cleaning_module,  provider_key.lower() + "_cleaning")
     sensor_features = cleaning_function(sensor_data_files, provider)
 
-    return sensor_features
+    return sensor_features

tests/scripts/missing_vals.py

@@ -0,0 +1,39 @@
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+
+participant = "p031"
+all_sensors = ["eda", "bvp", "ibi", "temp", "acc"]
+
+for sensor in all_sensors:
+
+    if sensor == "eda":
+        path = f"/rapids/data/interim/{participant}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv"
+    elif sensor == "bvp":
+        path = f"/rapids/data/interim/{participant}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv"
+    elif sensor == "ibi":
+        path = f"/rapids/data/interim/{participant}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv" 
+    elif sensor == "acc":
+        path = f"/rapids/data/interim/{participant}/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv" 
+    elif sensor == "temp":
+        path = f"/rapids/data/interim/{participant}/empatica_temperature_features/empatica_temperature_python_cr_windows.csv" 
+    else:
+        path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants
+
+
+    df = pd.read_csv(path)
+    print(df)
+    is_NaN = df.isnull()
+    row_has_NaN = is_NaN.any(axis=1)
+    rows_with_NaN = df[row_has_NaN]
+
+    print("All rows:", len(df.index))
+    print("\nCount NaN vals:", rows_with_NaN.size)
+    print("\nDf mean:")
+    print(df.mean())
+
+    sns.heatmap(df.isna(), cbar=False)
+    plt.savefig(f'{sensor}_{participant}_windows_NaN.png', bbox_inches='tight')
+
+

tests/scripts/zero_vals.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from itertools import compress
+
+
+participant = "p031"
+sensor = "eda"
+
+if sensor == "eda":
+    path = f"/rapids/data/interim/{participant}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv"
+elif sensor == "bvp":
+    path = f"/rapids/data/interim/{participant}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv"
+elif sensor == "ibi":
+    path = f"/rapids/data/interim/{participant}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv" 
+elif sensor == "acc":
+    path = f"/rapids/data/interim/{participant}/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv" 
+elif sensor == "temp":
+    path = f"/rapids/data/interim/{participant}/empatica_temperature_features/empatica_temperature_python_cr_windows.csv" 
+else:
+    path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants" 
+
+
+df = pd.read_csv(path)
+df_num_peaks_zero = df[df["empatica_electrodermal_activity_cr_numPeaks"] == 0]
+columns_num_peaks_zero = df_num_peaks_zero.columns[df_num_peaks_zero.isna().any()].tolist()
+
+df_num_peaks_non_zero = df[df["empatica_electrodermal_activity_cr_numPeaks"] != 0]
+df_num_peaks_non_zero = df_num_peaks_non_zero[columns_num_peaks_zero]
+
+pd.set_option('display.max_columns', None)
+
+df_q = pd.DataFrame()
+for col in df_num_peaks_non_zero:
+    df_q[col] = pd.to_numeric(pd.cut(df_num_peaks_non_zero[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
+
+sns.heatmap(df_q)
+plt.savefig(f'eda_{participant}_window_non_zero_peak_other_vals.png', bbox_inches='tight')
+plt.close()
+
+# Filter columns that do not contain 0
+non_zero_cols = list(compress(columns_num_peaks_zero, df_num_peaks_non_zero.all().tolist()))
+zero_cols = list(set(columns_num_peaks_zero) - set(non_zero_cols))
+
+print(non_zero_cols, "\n")
+print(zero_cols)
+
+