Rename modeling.py to modelling.py & Update example_config.yaml

example_profile/example_config.yaml

@@ -31,8 +31,11 @@ DAY_SEGMENTS: &day_segments
   FILE: "example_profile/exampleworkflow_daysegments.csv"
   INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
 
-############## PHONE ###########################################################
+
-################################################################################
+
+########################################################################################################################
+#                                                 PHONE                                                                #
+########################################################################################################################
 
 # See https://www.rapids.science/setup/configuration/#device-data-source-configuration
 PHONE_DATA_CONFIGURATION:
@@ -46,30 +49,80 @@ PHONE_DATA_CONFIGURATION:
 
 # Sensors ------
 
-PHONE_DATA_YIELD:
+PHONE_ACCELEROMETER:
-  SENSORS: [PHONE_ACCELEROMETER, PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
+  TABLE: accelerometer
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
-      FEATURES: [ratiovalidyieldedminutes, ratiovalidyieldedhours]
+      FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
-      MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1 representing the number of minutes with at least
+      SRC_FOLDER: "rapids" # inside src/features/phone_accelerometer
-      SRC_LANGUAGE: "r"
+      SRC_LANGUAGE: "python"
-      SRC_FOLDER: "rapids" # inside src/features/phone_data_yield
     
-# Communication SMS features config, TYPES and FEATURES keys need to match
+    PANDA:
-PHONE_MESSAGES:
+      COMPUTE: False
-  TABLE: messages
+      VALID_SENSED_MINUTES: False
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: True
-      MESSAGES_TYPES : [received, sent]
       FEATURES:
-        received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
+        exertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
-        sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
+        nonexertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
-      SRC_LANGUAGE: "r"
+      SRC_FOLDER: "panda" # inside src/features/phone_accelerometer
-      SRC_FOLDER: "rapids" # inside src/features/phone_messages
+      SRC_LANGUAGE: "python"
+
+PHONE_ACTIVITY_RECOGNITION:
+  TABLE: 
+    ANDROID: plugin_google_activity_recognition
+    IOS: plugin_ios_activity_recognition
+  EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
+      ACTIVITY_CLASSES:
+        STATIONARY: ["still", "tilting"]
+        MOBILE: ["on_foot", "walking", "running", "on_bicycle"]
+        VEHICLE: ["in_vehicle"]
+      SRC_FOLDER: "rapids" # inside src/features/phone_activity_recognition
+      SRC_LANGUAGE: "python"
+
+PHONE_APPLICATIONS_FOREGROUND:
+  TABLE: applications_foreground
+  APPLICATION_CATEGORIES:
+    CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
+    CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
+    UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether or not to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
+    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
+      SINGLE_CATEGORIES: ["all", "email"]
+      MULTIPLE_CATEGORIES:
+        social: ["socialnetworks", "socialmediatools"]
+        entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
+      SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
+      EXCLUDED_CATEGORIES: ["system_apps"]
+      EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
+      FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
+      SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
+      SRC_LANGUAGE: "python"
+
+PHONE_BATTERY:
+  TABLE: 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
+      FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
+      SRC_FOLDER: "rapids" # inside src/features/phone_battery
+      SRC_LANGUAGE: "python"
+
+PHONE_BLUETOOTH:
+  TABLE: bluetooth
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
+      SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
+      SRC_LANGUAGE: "r"
 
-# Communication call features config, TYPES and FEATURES keys need to match
 PHONE_CALLS:
   TABLE: calls
   PROVIDERS:
@@ -83,6 +136,43 @@ PHONE_CALLS:
       SRC_LANGUAGE: "r"
       SRC_FOLDER: "rapids" # inside src/features/phone_calls
 
+PHONE_CONVERSATION:
+  TABLE: 
+    ANDROID: plugin_studentlife_audio_android
+    IOS: plugin_studentlife_audio
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
+    "sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","noisesumenergy",
+    "noiseavgenergy","noisesdenergy","noiseminenergy","noisemaxenergy","voicesumenergy",
+    "voiceavgenergy","voicesdenergy","voiceminenergy","voicemaxenergy","silencesensedfraction","noisesensedfraction",
+    "voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
+    "unknownexpectedfraction","countconversation"]
+      RECORDING_MINUTES: 1
+      PAUSED_MINUTES : 3
+      SRC_FOLDER: "rapids" # inside src/features/phone_conversation
+      SRC_LANGUAGE: "python"
+
+PHONE_DATA_YIELD:
+  SENSORS: [PHONE_ACCELEROMETER, PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: [ratiovalidyieldedminutes, ratiovalidyieldedhours]
+      MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1 representing the number of minutes with at least
+      SRC_LANGUAGE: "r"
+      SRC_FOLDER: "rapids" # inside src/features/phone_data_yield
+
+PHONE_LIGHT:
+  TABLE: light
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
+      SRC_FOLDER: "rapids" # inside src/features/phone_light
+      SRC_LANGUAGE: "python"
+
 PHONE_LOCATIONS:
   TABLE: locations
   LOCATIONS_TO_USE: FUSED_RESAMPLED # ALL, GPS OR FUSED_RESAMPLED  
@@ -110,41 +200,17 @@ PHONE_LOCATIONS:
       SRC_FOLDER: "barnett" # inside src/features/phone_locations
       SRC_LANGUAGE: "r"
 
-PHONE_BLUETOOTH:
+PHONE_MESSAGES:
-  TABLE: bluetooth
+  TABLE: messages
   PROVIDERS:
     RAPIDS:
       COMPUTE: True
-      FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
+      MESSAGES_TYPES : [received, sent]
-      SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
+      FEATURES: 
+        received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
+        sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
       SRC_LANGUAGE: "r"
-
+      SRC_FOLDER: "rapids" # inside src/features/phone_messages
-
-PHONE_ACTIVITY_RECOGNITION:
-  TABLE: 
-    ANDROID: plugin_google_activity_recognition
-    IOS: plugin_ios_activity_recognition
-  EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: True
-      FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
-      ACTIVITY_CLASSES:
-        STATIONARY: ["still", "tilting"]
-        MOBILE: ["on_foot", "walking", "running", "on_bicycle"]
-        VEHICLE: ["in_vehicle"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_activity_recognition
-      SRC_LANGUAGE: "python"
-
-PHONE_BATTERY:
-  TABLE: 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
-      FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_battery
-      SRC_LANGUAGE: "python"
 
 PHONE_SCREEN:
   TABLE: screen
@@ -159,53 +225,14 @@ PHONE_SCREEN:
       SRC_FOLDER: "rapids" # inside src/features/phone_screen
       SRC_LANGUAGE: "python"
 
-PHONE_LIGHT:
+PHONE_WIFI_CONNECTED:
-  TABLE: light
+  TABLE: "sensor_wifi"
   PROVIDERS:
     RAPIDS:
       COMPUTE: True
-      FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
+      FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_light
+      SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
-      SRC_LANGUAGE: "python"
+      SRC_LANGUAGE: "r"
-
-PHONE_ACCELEROMETER:
-  TABLE: accelerometer
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: False
-      FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_accelerometer
-      SRC_LANGUAGE: "python"
-    
-    PANDA:
-      COMPUTE: False
-      VALID_SENSED_MINUTES: False
-      FEATURES:
-        exertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
-        nonexertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
-      SRC_FOLDER: "panda" # inside src/features/phone_accelerometer
-      SRC_LANGUAGE: "python"
-
-PHONE_APPLICATIONS_FOREGROUND:
-  TABLE: applications_foreground
-  APPLICATION_CATEGORIES:
-    CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
-    CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
-    UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether or not to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
-    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
-      SINGLE_CATEGORIES: ["all", "email"]
-      MULTIPLE_CATEGORIES:
-        social: ["socialnetworks", "socialmediatools"]
-        entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
-      SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
-      EXCLUDED_CATEGORIES: ["system_apps"]
-      EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
-      FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
-      SRC_LANGUAGE: "python"
 
 PHONE_WIFI_VISIBLE:
   TABLE: "wifi"
@@ -216,36 +243,13 @@ PHONE_WIFI_VISIBLE:
       SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
       SRC_LANGUAGE: "r"
 
-PHONE_WIFI_CONNECTED:
-  TABLE: "sensor_wifi"
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: True
-      FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
-      SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
-      SRC_LANGUAGE: "r"
 
-PHONE_CONVERSATION:
-  TABLE: 
-    ANDROID: plugin_studentlife_audio_android
-    IOS: plugin_studentlife_audio
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: True
-      FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
-    "sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","noisesumenergy",
-    "noiseavgenergy","noisesdenergy","noiseminenergy","noisemaxenergy","voicesumenergy",
-    "voiceavgenergy","voicesdenergy","voiceminenergy","voicemaxenergy","silencesensedfraction","noisesensedfraction",
-    "voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
-    "unknownexpectedfraction","countconversation"]
-      RECORDING_MINUTES: 1
-      PAUSED_MINUTES : 3
-      SRC_FOLDER: "rapids" # inside src/features/phone_conversation
-      SRC_LANGUAGE: "python"
 
-############## FITBIT ##########################################################
+########################################################################################################################
-################################################################################
+#                                                 FITBIT                                                               #
+########################################################################################################################
 
+# See https://www.rapids.science/latest/setup/configuration/#device-data-source-configuration
 FITBIT_DATA_CONFIGURATION:
   SOURCE: 
     TYPE: DATABASE # DATABASE or FILES (set each [FITBIT_SENSOR][TABLE] attribute with a table name or a file path accordingly)
@@ -276,6 +280,17 @@ FITBIT_HEARTRATE_INTRADAY:
       SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate_intraday
       SRC_LANGUAGE: "python"
 
+FITBIT_SLEEP_SUMMARY:
+  TABLE: fitbit_data
+  SLEEP_EPISODE_TIMESTAMP: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["countepisode", "avgefficiency", "sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgdurationafterwakeup", "avgdurationasleep", "avgdurationawake", "avgdurationtofallasleep", "avgdurationinbed"]
+      SLEEP_TYPES: ["main", "nap", "all"]
+      SRC_FOLDER: "rapids" # inside src/features/fitbit_sleep_summary
+      SRC_LANGUAGE: "python"
+
 FITBIT_STEPS_SUMMARY:
   TABLE: fitbit_data
   PROVIDERS:
@@ -299,19 +314,11 @@ FITBIT_STEPS_INTRADAY:
       SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_intraday
       SRC_LANGUAGE: "python"
 
-FITBIT_SLEEP_SUMMARY:
-  TABLE: fitbit_data
-  SLEEP_EPISODE_TIMESTAMP: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
-  PROVIDERS:
-    RAPIDS:
-      COMPUTE: True
-      FEATURES: ["countepisode", "avgefficiency", "sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgdurationafterwakeup", "avgdurationasleep", "avgdurationawake", "avgdurationtofallasleep", "avgdurationinbed"]
-      SLEEP_TYPES: ["main", "nap", "all"]
-      SRC_FOLDER: "rapids" # inside src/features/fitbit_sleep_summary
-      SRC_LANGUAGE: "python"
 
-### Analysis Workflow Example ##################################################
+
-################################################################################
+########################################################################################################################
+#                                              Analysis Workflow Example                                               #
+########################################################################################################################
 
 PARAMS_FOR_ANALYSIS:
   CATEGORICAL_OPERATORS: [mostcommon]

rules/models.smk

@@ -79,15 +79,6 @@ rule clean_sensor_features_for_all_participants:
     script:
         "../src/models/workflow_example/clean_sensor_features.R"
 
-
-
-
-
-
-
-
-
-
 rule merge_features_and_targets_for_individual_model:
     input:
         cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned.csv",
@@ -133,7 +124,7 @@ rule baselines_for_population_model:
     script:
         "../src/models/workflow_example/baselines.py"
 
-rule modeling_for_individual_participants:
+rule modelling_for_individual_participants:
     input:
         data = "data/processed/models/individual_model/{pid}/input.csv"
     params:
@@ -151,9 +142,9 @@ rule modeling_for_individual_participants:
     log:
         "data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/notes.log"
     script:
-        "../src/models/workflow_example/modeling.py"
+        "../src/models/workflow_example/modelling.py"
 
-rule modeling_for_all_participants:
+rule modelling_for_all_participants:
     input:
         data = "data/processed/models/population_model/input.csv"
     params:
@@ -171,4 +162,4 @@ rule modeling_for_all_participants:
     log:
         "data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/notes.log"
     script:
-        "../src/models/workflow_example/modeling.py"
+        "../src/models/workflow_example/modelling.py"

src/models/workflow_example/baselines.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pandas as pd
 from statistics import mean
-from modeling_utils import getMetrics, createPipeline
+from modelling_utils import getMetrics, createPipeline
 from sklearn.model_selection import LeaveOneOut
 
 

src/models/workflow_example/modelling.py

@@ -1,6 +1,6 @@
 import pandas as pd
 import numpy as np
-from modeling_utils import getMatchingColNames, getNormAllParticipantsScaler, getMetrics, getFeatureImportances, createPipeline
+from modelling_utils import getMatchingColNames, getNormAllParticipantsScaler, getMetrics, getFeatureImportances, createPipeline
 from sklearn.model_selection import LeaveOneOut, GridSearchCV