removed cleaning to make it run

.gitignore

@@ -100,9 +100,6 @@ data/external/*
 !/data/external/wiki_tz.csv
 !/data/external/main_study_usernames.csv
 !/data/external/timezone.csv
-!/data/external/play_store_application_genre_catalogue.csv
-!/data/external/play_store_categories_count.csv
-
 
 data/raw/*
 !/data/raw/.gitkeep

config.yaml

@@ -26,7 +26,7 @@ TIME_SEGMENTS: &time_segments
   INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs
   TAILORED_EVENTS: # Only relevant if TYPE=EVENT
     COMPUTE: True
-    SEGMENTING_METHOD: "30_before" # 30_before, 90_before, stress_event
+    SEGMENTING_METHOD: "10_before" # 30_before, 90_before, stress_event
     INTERVAL_OF_INTEREST: 10 # duration of event of interest [minutes]
     IOI_ERROR_TOLERANCE: 5 # interval of interest erorr tolerance (before and after IOI) [minutes]
 
@@ -91,7 +91,7 @@ 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"]
@@ -104,9 +104,9 @@ PHONE_APPLICATIONS_CRASHES:
   CONTAINER: applications_crashes
   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/play_store_application_genre_catalogue.csv"
+    CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
-    UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
+    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 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
+    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: # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
 
 # See https://www.rapids.science/latest/features/phone-applications-foreground/
@@ -114,32 +114,24 @@ PHONE_APPLICATIONS_FOREGROUND:
   CONTAINER: applications
   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/play_store_application_genre_catalogue.csv"
+    CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
-    # Refer to data/external/play_store_categories_count.csv for a list of categories (genres) and their frequency.
+    PACKAGE_NAMES_HASHED: True
-    UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
+    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 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
+    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: ["Productivity", "Tools", "Communication", "Education", "Social"]
+      SINGLE_CATEGORIES: ["all", "email"]
       MULTIPLE_CATEGORIES:
-        games: ["Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing"]
+        social: ["socialnetworks", "socialmediatools"]
-        social: ["Communication", "Social", "Dating"]
+        entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
-        productivity: ["Tools", "Productivity", "Finance", "Education", "News & Magazines", "Business", "Books & Reference"]
-        health: ["Health & Fitness", "Lifestyle", "Food & Drink", "Sports", "Medical", "Parenting"]
-        entertainment: ["Shopping", "Music & Audio", "Entertainment", "Travel & Local", "Photography", "Video Players & Editors", "Personalization", "House & Home", "Art & Design", "Auto & Vehicles", "Entertainment,Music & Video",
-                        "Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing" # Add all games.
-        ]
-        maps_weather: ["Maps & Navigation", "Weather"]
       CUSTOM_CATEGORIES:
-      SINGLE_APPS: []
+        social_media: ["com.google.android.youtube", "com.snapchat.android", "com.instagram.android", "com.zhiliaoapp.musically", "com.facebook.katana"]
-      EXCLUDED_CATEGORIES: ["System", "STRAW"]
+        dating: ["com.tinder", "com.relance.happycouple", "com.kiwi.joyride"]
-      # Note: A special option here is "is_system_app".
+      SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
-      # This excludes applications that have is_system_app = TRUE, which is a separate column in the table.
+      EXCLUDED_CATEGORIES: []
-      # However, all of these applications have been assigned System category.
+      EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"] # TODO list system apps?
-      # I will therefore filter by that category, which is a superset and is more complete. JL
-      EXCLUDED_APPS: []
       FEATURES: 
         APP_EVENTS: ["countevent", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
         APP_EPISODES: ["countepisode", "minduration", "maxduration", "meanduration", "sumduration"]
@@ -163,7 +155,7 @@ 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
 
@@ -177,7 +169,7 @@ PHONE_BLUETOOTH:
       SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R
 
     DORYAB:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: 
         ALL: 
             DEVICES: ["countscans", "uniquedevices", "meanscans", "stdscans"]
@@ -198,7 +190,7 @@ PHONE_CALLS:
   CONTAINER: call
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES_TYPE: EPISODES # EVENTS or EPISODES
       CALL_TYPES: [missed, incoming, outgoing]
       FEATURES:
@@ -227,18 +219,19 @@ PHONE_CONVERSATION: # TODO Adapt for speech
 
 # See https://www.rapids.science/latest/features/phone-data-yield/
 PHONE_DATA_YIELD:
-  SENSORS: [#PHONE_ACCELEROMETER,
+  SENSORS: [ #PHONE_ACCELEROMETER,
-            PHONE_ACTIVITY_RECOGNITION,
+            #PHONE_ACTIVITY_RECOGNITION,
-            PHONE_APPLICATIONS_FOREGROUND,
+            #PHONE_APPLICATIONS_FOREGROUND,
-            PHONE_APPLICATIONS_NOTIFICATIONS,
+            #PHONE_APPLICATIONS_NOTIFICATIONS,
-            PHONE_BATTERY,
+            #PHONE_BATTERY,
-            PHONE_BLUETOOTH,
+            PHONE_BLUETOOTH #,
-            PHONE_CALLS,
+            #PHONE_CALLS,
-            PHONE_LIGHT,
+            #PHONE_LIGHT,
-            PHONE_LOCATIONS,
+            #PHONE_LOCATIONS,
-            PHONE_MESSAGES,
+            #PHONE_MESSAGES,
-            PHONE_SCREEN,
+            #PHONE_SCREEN,
-            PHONE_WIFI_VISIBLE]
+            #PHONE_WIFI_VISIBLE
+            ]
   PROVIDERS:
     RAPIDS:
       COMPUTE: True
@@ -251,9 +244,8 @@ PHONE_ESM:
   PROVIDERS:
     STRAW:
       COMPUTE: True
-      SCALES: ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support", 
+      SCALES: ["activities"]
-              "appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]
+      FEATURES: [activities_n_others, activities_inperson, activities_formal]
-      FEATURES: [mean]
       SRC_SCRIPT: src/features/phone_esm/straw/main.py
 
 # See https://www.rapids.science/latest/features/phone-keyboard/
@@ -270,7 +262,7 @@ 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
 
@@ -284,7 +276,7 @@ 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
@@ -299,7 +291,7 @@ 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
@@ -317,7 +309,7 @@ PHONE_MESSAGES:
   CONTAINER: sms
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       MESSAGES_TYPES : [received, sent]
       FEATURES: 
         received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
@@ -329,7 +321,7 @@ 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
@@ -342,7 +334,7 @@ PHONE_SPEECH:
   CONTAINER: speech
   PROVIDERS:
     STRAW:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
       SRC_SCRIPT: src/features/phone_speech/straw/main.py
 
@@ -360,7 +352,7 @@ 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
 
@@ -529,10 +521,10 @@ EMPATICA_ACCELEROMETER:
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
     CR:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["totalMagnitudeBand", "absoluteMeanBand", "varianceBand"] # Acc features
       WINDOWS:
-        COMPUTE: True
+        COMPUTE: False
         WINDOW_LENGTH: 15 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
       SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py
@@ -556,11 +548,11 @@ EMPATICA_TEMPERATURE:
       FEATURES: ["maxtemp", "mintemp", "avgtemp", "mediantemp", "modetemp", "stdtemp", "diffmaxmodetemp", "diffminmodetemp", "entropytemp"]
       SRC_SCRIPT: src/features/empatica_temperature/dbdp/main.py
     CR:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["maximum", "minimum", "meanAbsChange", "longestStrikeAboveMean", "longestStrikeBelowMean", 
                   "stdDev", "median", "meanChange", "sumSquared", "squareSumOfComponent", "sumOfSquareComponents"]
       WINDOWS:
-        COMPUTE: True
+        COMPUTE: False
         WINDOW_LENGTH: 300 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
       SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
@@ -574,14 +566,14 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
       FEATURES: ["maxeda", "mineda", "avgeda", "medianeda", "modeeda", "stdeda", "diffmaxmodeeda", "diffminmodeeda", "entropyeda"]
       SRC_SCRIPT: src/features/empatica_electrodermal_activity/dbdp/main.py
     CR:
-      COMPUTE: True
+      COMPUTE: False
       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
+        COMPUTE: False
         WINDOW_LENGTH: 60 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', count_windows, eda_num_peaks_non_zero]
         IMPUTE_NANS: True
@@ -600,7 +592,7 @@ EMPATICA_BLOOD_VOLUME_PULSE:
       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
+        COMPUTE: False
         WINDOW_LENGTH: 300 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
       SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
@@ -614,12 +606,12 @@ EMPATICA_INTER_BEAT_INTERVAL:
       FEATURES: ["maxibi", "minibi", "avgibi", "medianibi", "modeibi", "stdibi", "diffmaxmodeibi", "diffminmodeibi", "entropyibi"]
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/dbdp/main.py
     CR:
-      COMPUTE: True
+      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
+        COMPUTE: False
         WINDOW_LENGTH: 300 # specify window length in seconds
         SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
       SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
@@ -681,12 +673,12 @@ ALL_CLEANING_INDIVIDUAL:
       DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
       DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: True
+        COMPUTE: False
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R
     STRAW:
-      COMPUTE: True
+      COMPUTE: False
       PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
       PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
       EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
@@ -694,7 +686,7 @@ ALL_CLEANING_INDIVIDUAL:
       COLS_NAN_THRESHOLD: 0.9 # set to 1 to remove only columns that contains all (100% of) NaN
       COLS_VAR_THRESHOLD: True
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: True
+        COMPUTE: False
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       STANDARDIZATION: True
@@ -713,12 +705,12 @@ ALL_CLEANING_OVERALL:
       DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
       DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: True
+        COMPUTE: False
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
     STRAW:
-      COMPUTE: True
+      COMPUTE: False
       PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
       PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
       EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
@@ -726,7 +718,7 @@ ALL_CLEANING_OVERALL:
       COLS_NAN_THRESHOLD: 0.8 # set to 1 to remove only columns that contains all (100% of) NaN
       COLS_VAR_THRESHOLD: True
       DROP_HIGHLY_CORRELATED_FEATURES:
-        COMPUTE: True
+        COMPUTE: False
         MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
         CORR_THRESHOLD: 0.95
       STANDARDIZATION: True
@@ -740,7 +732,7 @@ ALL_CLEANING_OVERALL:
 
 PARAMS_FOR_ANALYSIS:
   BASELINE:
-    COMPUTE: True
+    COMPUTE: False
     FOLDER: data/external/baseline
     CONTAINER: [results-survey637813_final.csv,  # Slovenia
                 results-survey358134_final.csv,  # Belgium 1
@@ -751,8 +743,8 @@ PARAMS_FOR_ANALYSIS:
     CATEGORICAL_FEATURES: [gender]
 
   TARGET:
-    COMPUTE: True
+    COMPUTE: False
     LABEL: appraisal_stressfulness_event_mean
-    ALL_LABELS: [PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean, JCQ_coworker_support_mean, appraisal_stressfulness_period_mean]
+    ALL_LABELS: [appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean]
                 # PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean, 
                 # JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean

data/external/play_store_categories_count.csv

@@ -1,45 +0,0 @@
-genre,n
-System,261
-Tools,96
-Productivity,71
-Health & Fitness,60
-Finance,54
-Communication,39
-Music & Audio,39
-Shopping,38
-Lifestyle,33
-Education,28
-News & Magazines,24
-Maps & Navigation,23
-Entertainment,21
-Business,18
-Travel & Local,18
-Books & Reference,16
-Social,16
-Weather,16
-Food & Drink,14
-Sports,14
-Other,13
-Photography,13
-Puzzle,13
-Video Players & Editors,12
-Card,9
-Casual,9
-Personalization,8
-Medical,7
-Board,5
-Strategy,4
-House & Home,3
-Trivia,3
-Word,3
-Adventure,2
-Art & Design,2
-Auto & Vehicles,2
-Dating,2
-Role Playing,2
-STRAW,2
-Simulation,2
-"Board,Brain Games",1
-"Entertainment,Music & Video",1
-Parenting,1
-Racing,1

environment.yml

@@ -1,30 +1,165 @@
 name: rapids
 channels:
   - conda-forge
+  - defaults
 dependencies:
-    - auto-sklearn
+  - _libgcc_mutex=0.1
-    - hmmlearn
+  - _openmp_mutex=4.5
-    - imbalanced-learn
+  - _py-xgboost-mutex=2.0
-    - jsonschema
+  - appdirs=1.4.4
-    - lightgbm
+  - arrow=0.16.0
-    - matplotlib
+  - asn1crypto=1.4.0
-    - numpy
+  - astropy=4.2.1
-    - pandas
+  - attrs=20.3.0
-    - peakutils
+  - binaryornot=0.4.4
-    - pip
+  - blas=1.0
-    - plotly
+  - brotlipy=0.7.0
-    - python-dateutil
+  - bzip2=1.0.8
-    - pytz
+  - ca-certificates=2021.7.5
-    - pywavelets
+  - certifi=2021.5.30
-    - pyyaml
+  - cffi=1.14.4
-    - scikit-learn
+  - chardet=3.0.4
-    - scipy
+  - click=7.1.2
-    - seaborn
+  - colorama=0.4.4
-    - setuptools
+  - cookiecutter=1.6.0
-    - bioconda::snakemake 
+  - cryptography=3.3.1
-    - bioconda::snakemake-minimal
+  - datrie=0.8.2
-    - tqdm
+  - docutils=0.16
-    - xgboost
+  - future=0.18.2
+  - gitdb=4.0.5
+  - gitdb2=4.0.2
+  - gitpython=3.1.11
+  - idna=2.10
+  - imbalanced-learn=0.6.2
+  - importlib-metadata=2.0.0
+  - importlib_metadata=2.0.0
+  - intel-openmp=2019.4
+  - jinja2=2.11.2
+  - jinja2-time=0.2.0
+  - joblib=1.0.0
+  - jsonschema=3.2.0
+  - ld_impl_linux-64=2.36.1
+  - libblas=3.8.0
+  - libcblas=3.8.0
+  - libcxx=10.0.0
+  - libcxxabi=10.0.0
+  - libedit=3.1.20191231
+  - libffi=3.3
+  - libgcc-ng=11.2.0
+  - libgfortran
+  - libgfortran
+  - libgfortran
+  - liblapack=3.8.0
+  - libopenblas=0.3.10
+  - libstdcxx-ng=11.2.0
+  - libxgboost=0.90
+  - libzlib=1.2.11
+  - lightgbm=3.1.1
+  - llvm-openmp=10.0.0
+  - markupsafe=1.1.1
+  - mkl
+  - mkl-service=2.3.0
+  - mkl_fft=1.2.0
+  - mkl_random=1.1.1
+  - more-itertools=8.6.0
+  - ncurses=6.2
+  - numpy=1.19.2
+  - numpy-base=1.19.2
+  - openblas=0.3.4
+  - openssl=1.1.1k
+  - pandas=1.1.5
+  - pbr=5.5.1
+  - pip=20.3.3
+  - plotly=4.14.1
+  - poyo=0.5.0
+  - psutil=5.7.2
+  - py-xgboost=0.90
+  - pycparser=2.20
+  - pyerfa=1.7.1.1
+  - pyopenssl=20.0.1
+  - pysocks=1.7.1
+  - python=3.7.9
+  - python-dateutil=2.8.1
+  - python_abi=3.7
+  - pytz=2020.4
+  - pyyaml=5.3.1
+  - readline=8.0
+  - requests=2.25.0
+  - retrying=1.3.3
+  - setuptools=51.0.0
+  - six=1.15.0
+  - smmap=3.0.4
+  - smmap2=3.0.1
+  - sqlite=3.33.0
+  - threadpoolctl=2.1.0
+  - tk=8.6.10
+  - tqdm=4.62.0
+  - urllib3=1.25.11
+  - wheel=0.36.2
+  - whichcraft=0.6.1
+  - wrapt=1.12.1
+  - xgboost=0.90
+  - xz=5.2.5
+  - yaml=0.2.5
+  - zipp=3.4.0
+  - zlib=1.2.11
   - pip:
-        - biosppy
+    - amply==0.1.4
-        - cr_features>=0.2
+    - auto-sklearn==0.14.7
+    - bidict==0.22.0
+    - biosppy==0.8.0
+    - build==0.8.0
+    - cached-property==1.5.2
+    - cloudpickle==2.2.0
+    - configargparse==0.15.1
+    - configspace==0.4.21
+    - cr-features==0.2.1
+    - cycler==0.11.0
+    - cython==0.29.32
+    - dask==2022.2.0
+    - decorator==4.4.2
+    - distributed==2022.2.0
+    - distro==1.7.0
+    - emcee==3.1.2
+    - fonttools==4.33.2
+    - fsspec==2022.8.2
+    - h5py==3.6.0
+    - heapdict==1.0.1
+    - hmmlearn==0.2.7
+    - ipython-genutils==0.2.0
+    - jupyter-core==4.6.3
+    - kiwisolver==1.4.2
+    - liac-arff==2.5.0
+    - locket==1.0.0
+    - matplotlib==3.5.1
+    - msgpack==1.0.4
+    - nbformat==5.0.7
+    - opencv-python==4.5.5.64
+    - packaging==21.3
+    - partd==1.3.0
+    - peakutils==1.3.3
+    - pep517==0.13.0
+    - pillow==9.1.0
+    - pulp==2.4
+    - pynisher==0.6.4
+    - pyparsing==2.4.7
+    - pyrfr==0.8.3
+    - pyrsistent==0.15.5
+    - pywavelets==1.3.0
+    - ratelimiter==1.2.0.post0
+    - scikit-learn==0.24.2
+    - scipy==1.7.3
+    - seaborn==0.11.2
+    - shortuuid==1.0.8
+    - smac==1.2
+    - snakemake==5.30.2
+    - sortedcontainers==2.4.0
+    - tblib==1.7.0
+    - tomli==2.0.1
+    - toolz==0.12.0
+    - toposort==1.5
+    - tornado==6.2
+    - traitlets==4.3.3
+    - typing-extensions==4.2.0
+    - zict==2.2.0
+prefix: /opt/conda/envs/rapids

rules/preprocessing.smk

@@ -247,8 +247,6 @@ rule empatica_readable_datetime:
         include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
     output:
         "data/raw/{pid}/empatica_{sensor}_with_datetime.csv"
-    resources:
-        mem_mb=50000
     script:
         "../src/data/datetime/readable_datetime.R"
 

src/data/application_categories.R

@@ -29,17 +29,24 @@ get_genre <- function(apps){
 apps <- read.csv(snakemake@input[[1]], stringsAsFactors = F)
 genre_catalogue <- data.frame()
 catalogue_source <- snakemake@params[["catalogue_source"]]
+package_names_hashed <- snakemake@params[["package_names_hashed"]]
 update_catalogue_file <- snakemake@params[["update_catalogue_file"]]
 scrape_missing_genres <- snakemake@params[["scrape_missing_genres"]]
 apps_with_genre <- data.frame(matrix(ncol=length(colnames(apps)) + 1,nrow=0, dimnames=list(NULL, c(colnames(apps), "genre"))))
 
+if (length(package_names_hashed) == 0) {package_names_hashed <- FALSE}
+
 if(nrow(apps) > 0){
   if(catalogue_source == "GOOGLE"){
     apps_with_genre <- apps %>% mutate(genre = NA_character_)
   } else if(catalogue_source == "FILE"){
     genre_catalogue <- read.csv(snakemake@params[["catalogue_file"]], colClasses = c("character", "character"))
+    if (package_names_hashed) {
+      apps_with_genre <- left_join(apps, genre_catalogue, by = "package_hash")
+    } else {
       apps_with_genre <- left_join(apps, genre_catalogue, by = "package_name")
     }
+  }
 
   if(catalogue_source == "GOOGLE" || (catalogue_source == "FILE" && scrape_missing_genres)){
     apps_without_genre <- (apps_with_genre %>% filter(is.na(genre)) %>% distinct(package_name))$package_name

src/data/streams/empatica_zip/container.py

@@ -136,9 +136,8 @@ def patch_ibi_with_bvp(ibi_data, bvp_data):
     # Begin with the cr-features part
     try:
         ibi_data, ibi_start_timestamp = empatica2d_to_array(ibi_data_file)
-    except (IndexError, KeyError) as e:
+    except IndexError as e:
         # Checks whether IBI.csv is empty
-        # It may raise a KeyError if df is empty here: startTimeStamp = df.time[0]
         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']

src/features/all_cleaning_individual/straw/main.py

@@ -120,7 +120,7 @@ def straw_cleaning(sensor_data_files, provider):
     esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')]
 
     if provider["COLS_VAR_THRESHOLD"]:
-        features.drop(features.std(numeric_only=True)[features.std(numeric_only=True) == 0].index.values, axis=1, inplace=True)
+        features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True)
 
     fe5 = features.copy()
 
@@ -134,7 +134,7 @@ def straw_cleaning(sensor_data_files, provider):
         valid_features = features[numerical_cols].loc[:, features[numerical_cols].isna().sum() < drop_corr_features['MIN_OVERLAP_FOR_CORR_THRESHOLD'] * features[numerical_cols].shape[0]]
 
         corr_matrix = valid_features.corr().abs()
-        upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
+        upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))
         to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])]
 
         features.drop(to_drop, axis=1, inplace=True)
@@ -150,15 +150,13 @@ def straw_cleaning(sensor_data_files, provider):
 
     return features
 
+def impute(df, method='zero'):
     
-def k_nearest(df):
+    def k_nearest(df):
         pd.set_option('display.max_columns', None)
         imputer = KNNImputer(n_neighbors=3)
         return pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
 
-
-def impute(df, method='zero'):
-
     return {
         'zero': df.fillna(0),
         'high_number': df.fillna(1500),
@@ -167,7 +165,6 @@ def impute(df, method='zero'):
         'knn': k_nearest(df) 
     }[method]
 
-
 def graph_bf_af(features, phase_name, plt_flag=False):
     if plt_flag:
         sns.set(rc={"figure.figsize":(16, 8)})

src/features/all_cleaning_overall/straw/main.py

@@ -146,7 +146,7 @@ def straw_cleaning(sensor_data_files, provider, target):
     # (5) REMOVE COLS WHERE VARIANCE IS 0
 
     if provider["COLS_VAR_THRESHOLD"]:
-        features.drop(features.std(numeric_only=True)[features.std(numeric_only=True) == 0].index.values, axis=1, inplace=True)
+        features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True)
 
     graph_bf_af(features, "6variance_drop")
 
@@ -200,7 +200,7 @@ def straw_cleaning(sensor_data_files, provider, target):
         valid_features = features[numerical_cols].loc[:, features[numerical_cols].isna().sum() < drop_corr_features['MIN_OVERLAP_FOR_CORR_THRESHOLD'] * features[numerical_cols].shape[0]]
 
         corr_matrix = valid_features.corr().abs()
-        upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
+        upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))
         to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])]
 
         # sns.heatmap(corr_matrix, cmap="YlGnBu")
@@ -245,14 +245,12 @@ def straw_cleaning(sensor_data_files, provider, target):
 
     return features
 
+def impute(df, method='zero'):
     
-def k_nearest(df):
+    def k_nearest(df):
         imputer = KNNImputer(n_neighbors=3)
         return pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
 
-
-def impute(df, method='zero'):
-
     return {
         'zero': df.fillna(0),
         'high_number': df.fillna(1500),
@@ -261,7 +259,6 @@ def impute(df, method='zero'):
         'knn': k_nearest(df) 
     }[method]
 
-
 def graph_bf_af(features, phase_name, plt_flag=False):
     if plt_flag:
         sns.set(rc={"figure.figsize":(16, 8)})

src/features/cr_features_helper_methods.py

@@ -15,13 +15,13 @@ def extract_second_order_features(intraday_features, so_features_names, prefix="
         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(numeric_only=True).add_suffix("_SO_mean")], axis=1)
+            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(numeric_only=True).add_suffix("_SO_median")], axis=1)
+            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(numeric_only=True).fillna(0).add_suffix("_SO_sd")], axis=1)
+            so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std().fillna(0).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"])]:

src/features/empatica_data_yield.py

@@ -26,7 +26,7 @@ def calculate_empatica_data_yield(features): # TODO
     # Assigns 1 to values that are over 1 (in case of windows not being filled fully)
     features[empatica_data_yield_cols] = features[empatica_data_yield_cols].apply(lambda x: [y if y <= 1 or np.isnan(y) else 1 for y in x])
     
-    features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1, numeric_only=True).fillna(0)
+    features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1).fillna(0)
     features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average)
 
     return features

src/features/phone_esm/straw/esm_activities.py

@@ -0,0 +1,292 @@
+import pandas as pd
+import numpy as np
+
+id2qc = {  44:["What have you mainly been doing within the last 10 minutes?",
+                            "Waar ben je voornamelijk mee bezig geweest de laatste 10 minuten?",
+                            "Kaj ste v glavnem počeli v zadnjih 10 minutah?"],
+                        45:["What type of individual work?",
+                            "Wat voor soort individueel werk?",
+                            "Kakšno vrsto samostojnega dela ste opravljali?"],
+                        46:["How did you work with others?",
+                            "Hoe heb je met anderen gewerkt?",
+                            "Kako ste sodelovali z drugimi?"],
+                        47:["What type of break?",
+                            "Wat voor soort pauze?",
+                            "Kakšno vrsto odmora ste imeli?"],
+                        48:["Where did you travel between?",
+                            "Waar heb je tussen gereisd?",
+                            "Kam ste potovali?"],
+                        49:["Did you use a computer or phone for that?",
+                            "Heb je daarvoor een computer of telefoon gebruikt?",
+                            "Ste za to uporabljali računalnik ali telefon?"],
+                        50:["What kind of an interaction was that?",
+                            "Wat voor interactie was dat?",
+                            "Kakšne vrste sodelovanja je bilo to?"],
+                        51:["How many people were involved besides yourself?",
+                            "Hoeveel mensen waren er behalve jezelf betrokken?",
+                            "Koliko oseb je bilo poleg vas še vpletenih?"],
+                        # 52:["What have you mainly been doing within the last 10 minutes?",
+                        #     "Waar ben je voornamelijk mee bezig geweest de laatste 10 minuten?",
+                        #     "Kaj ste v glavnem počeli v zadnjih 10 minutah?"]
+}
+qc2id = {v:k for k,values in id2qc.items() for v in values}
+
+next_questions = {  44: [45,46,47,48],
+                    45:[49,49],
+                    46:[50,50],
+                    47:[],
+                    48:[],
+                    49:[],
+                    50:[51,51],
+                    51:[]
+                    #52:[45,46,47,48],
+                 }
+
+def esm_activities_LTM_features(
+    df_esm_activities_cleaned: pd.DataFrame,
+) -> pd.DataFrame:
+    """ Function for calculating LTM(Last 10 minutes) features of questionnaire answers. It first corrects the question ids according
+        to esm_instructions and the updated corpus of question_ids. It then processes each LTM question chain to 
+        find relevant social properties given by the answers such as the number of people interacted with, the formality and whether the socializing was done in person.
+
+    Parameters
+    ----------
+    df_esm_activities_cleaned: pd.DataFrame
+        A cleaned up dataframe, which must include esm_instructions, esm_user_answer_numeric.
+
+    Returns
+    -------
+    df_esm_activities_cleaned: pd.DataFrame
+        The same dataframe with columns which contain:
+            ["correct_ids"] - Corrected question_ids
+            ["ans_seq"] - For each LTM question, the sequence of numerical user answers pertaining to this chain of questions.
+            ["n_others","inperson","formal"]- Properties of known potential social encounters as given by process_answers().
+    """
+    #TODO: preprocess questionaires
+        #DONE: correct ids
+    correct_id_df = correct_activity_qids(df_esm_activities_cleaned)
+        #DONE: process subquestions 
+    ids = correct_id_df["correct_ids"]
+    main_q_indices = ids[ids==44].index
+    q_group = []
+    i=-1
+    for id in ids:
+        if(id==44):
+            i=i+1
+        q_group.append(i)
+    correct_id_df["q_group"] = q_group
+    ans_seq = correct_id_df.groupby("q_group").agg({"esm_user_answer_numeric":lambda group: list(group)}).rename(columns={"esm_user_answer_numeric":"ans_seq"})
+    ans_seq.set_index(main_q_indices,inplace=True)
+    # correct_id_df["ans_seq"] = [[] for i in range(len(correct_id_df))]
+    # correct_id_df["ans_seq"].loc[main_q_indices] = correct_id_df.groupby("q_group").agg({"esm_user_answer_numeric":lambda group: list(group)}).values.reshape(-1)
+    #DONE: find types of status for each main question: socializing:[none,irl,online,unknown], num_people:[0,1,2,>2,unknown]
+    processed_ans_df = process_answers(ans_seq)
+    # df_out = df_esm_activities_cleaned.join(test)
+    return df_esm_activities_cleaned.join(processed_ans_df)
+
+    
+""" 
+possible answer sequences for LTM question chains
+
+#alone
+0,0,0 not social
+0,0,1 not social
+0,1,0 not social
+0,1,1 not social
+0,2 not social
+0,3 not social
+0,4 not social
+0,5 not social
+0,6 not social
+#w/ others
+1,0,0,0 1 irl
+1,0,0,1 2 irl
+1,0,0,2 3+ irl
+1,0,1,0 1 irl
+1,0,1,1 2 irl
+1,0,1,2 3+ irl
+1,1,0,0 1 online 
+1,1,0,1 2 online 
+1,1,0,2 3+ online 
+1,1,1,0 1 online 
+1,1,1,1 2 online 
+1,1,1,2 3+ online 
+1,2 positive likely to be more than 2
+1,3 positive
+#break
+2,0 ambiguous
+2,1 positive irl
+2,2 ambiguous
+2,3 ambiguous
+#transit
+3,0 ambiguous
+3,1 ambiguous
+3,2 ambiguous
+"""
+
+
+
+
+#TODO: docstring
+def process_answers(df:pd.DataFrame)-> pd.DataFrame:
+    """ Function to process answer sequences for LTM question chains. It checks the chain of subquestion answers and extracts the following attributes:
+        > n_others: Number of other people interacted with in the last 10 minutes
+            - -1: Number is positive but unknown exactly
+            - 0: No people/alone
+            - 1: One extra person
+            - 2: Two extra people
+            - 3: More than two extra people
+            - NaN : Can't say anything with enough certainty.
+        > inperson: 
+            - True/False: The interaction in question was/wasn't in person.
+            - None: Can't say anything with enough certainty.
+        > formal: 
+            - True/False: The interaction in question was/wasn't formal.
+            - None: Can't say anything with enough certainty.
+    Args:
+        df (pd.DataFrame): _description_
+
+    Returns:
+        pd.DataFrame: _description_
+    """    
+    properties = {"n_others":[],
+                  "inperson":[],
+                  "formal":[]}
+    for ans_seq in df["ans_seq"]:
+        n_other = None
+        inperson = None
+        formal = None
+        if(ans_seq[0]==0):
+            n_other = 0
+        elif(ans_seq[0]==1):
+            if(ans_seq[1]==3):
+                n_other = -1    # anwsered "Other" but did work with other people        
+            elif(ans_seq[1]==2):
+                n_other = 3 #assuming more than 2 people participated in the lecture or presentation
+            elif(ans_seq[1] in [0,1]):
+                    inperson = ans_seq[1]==0 #ans[1]==0, means irl interaction, ==1 means online or phone
+                    formal = ans_seq[2]==0#0 means formal
+                    n_other = ans_seq[3]+1 #ans3 is on [0,2] so we add 1 to make it [1,3]
+        elif(ans_seq[0]==2):
+            formal = False#assuming one does not have a formal meeting during break time
+            if(ans_seq[1]==1):
+                n_other = -1
+                inperson = True
+            #if not 1 then we dont know anythong for sure
+        elif(ans_seq[0]==3):
+            #we cant say whether the persion was carpooling or driving alone.
+            pass
+        properties["n_others"].append(n_other)
+        properties["inperson"].append(inperson)
+        properties["formal"].append(formal)
+
+
+    #df = df.join(pd.DataFrame(properties,index=df.index))
+    return pd.DataFrame(properties,index=df.index)
+
+def correct_activity_qids(df:pd.DataFrame)->pd.DataFrame:
+    """_summary_
+
+    Args:
+        df (pd.DataFrame): _description_
+
+    Returns:
+        pd.DataFrame: Input dataframe with added column "correct_ids"
+    """
+    df["correct_ids"] = df["esm_instructions"].apply(lambda x: qc2id[x])
+    return df
+
+
+
+def process_answers_aggregation(df:pd.core.groupby.generic.DataFrameGroupBy)-> pd.core.groupby.generic.DataFrameGroupBy:
+    """ Function to process answer sequences for LTM question chains. It checks the chain of subquestion answers and extracts the following attributes:
+        > n_others: Number of other people interacted with in the last 10 minutes
+            - -1: Number is positive but unknown exactly
+            - 0: No people/alone
+            - 1: One extra person
+            - 2: Two extra people
+            - 3: More than two extra people
+            - NaN : Can't say anything with enough certainty.
+        > inperson: 
+            - True/False: The interaction in question was/wasn't in person.
+            - None: Can't say anything with enough certainty.
+        > formal: 
+            - True/False: The interaction in question was/wasn't formal.
+            - None: Can't say anything with enough certainty.
+    Args:
+        df (pd.DataFrame): _description_
+
+    Returns:
+        pd.DataFrame: _description_
+    """    
+
+    #print("=======================\nAPPLY START:\ndf=",df.columns,df.local_segment)
+    properties = {"n_others":[],
+                  "inperson":[],
+                  "formal":[]}
+    ans_seq = df["esm_user_answer_numeric"].values
+    n_other = None
+    inperson = None
+    formal = None
+    if(ans_seq[0]==0):
+        n_other = 0
+    elif(ans_seq[0]==1):
+        if(ans_seq[1]==3):
+            n_other = -1    # anwsered "Other" but did work with other people        
+        elif(ans_seq[1]==2):
+            n_other = 3 #assuming more than 2 people participated in the lecture or presentation
+        elif(ans_seq[1] in [0,1]):
+                inperson = ans_seq[1]==0 #ans[1]==0, means irl interaction, ==1 means online or phone
+                formal = ans_seq[2]==0#0 means formal
+                n_other = ans_seq[3]+1 #ans3 is on [0,2] so we add 1 to make it [1,3]
+    elif(ans_seq[0]==2):
+        formal = False#assuming one does not have a formal meeting during break time
+        if(ans_seq[1]==1):
+            n_other = -1
+            inperson = True
+        #if not 1 then we dont know anythong for sure
+    elif(ans_seq[0]==3):
+        #we cant say whether the persion was carpooling or driving alone.
+        pass
+    properties["n_others"].append(n_other)
+    properties["inperson"].append(inperson)
+    properties["formal"].append(formal)
+
+
+    df = df.join(pd.DataFrame(properties,index=df.index))
+    #print("APPLY END:\ndf=",df[["n_others","inperson","formal"]])
+
+    return df
+
+
+
+#test stuff
+def test():
+    from esm_preprocess import preprocess_esm,clean_up_esm
+    df = pd.read_csv("data/raw/p031/phone_esm_with_datetime.csv")
+    df = preprocess_esm(df)
+    df = clean_up_esm(df)
+    df = df[df["questionnaire_id"]==97]
+    original = esm_activities_LTM_features(df)
+    df["local_segment"] = [str(i)+":"+j for i,j in df[["esm_session","device_id"]].values]
+    temp = df.groupby("local_segment")
+    temp2 = temp.apply(process_answers_aggregation)
+
+    #compare with original function results
+    selection = original[original["correct_ids"]==44][["n_others",  "inperson", "formal"]]
+    temp_selection = temp2.loc[selection.index]
+    temp_selection.compare(selection,keep_shape=True,keep_equal =True)
+
+    #print out ans_seq processing results
+    # import json
+    # i = 0
+    # for j,ans in correct_id_df[["esm_json","esm_user_answer"]].values:
+    #     obj = json.loads(j)
+    #     text = obj["esm_instructions"]
+    #     if ("10 minut" in text):
+    #         print("---\n",test.ans_seq.iloc[i])
+    #         print(test[["n_others","inperson","formal"]].values[i])
+    #         i = i+1
+    #     print(text,ans)
+
+#test()

src/features/phone_esm/straw/main.py

@@ -1,4 +1,8 @@
 import pandas as pd
+import sys
+import warnings
+sys.path.append('src/features/phone_esm/straw')   
+from esm_activities import esm_activities_LTM_features,process_answers_aggregation
 
 QUESTIONNAIRE_IDS = {
     "sleep_quality": 1,
@@ -39,23 +43,49 @@ QUESTIONNAIRE_IDS = {
 
 def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
     esm_data = pd.read_csv(sensor_data_files["sensor_data"])
+    
     requested_features = provider["FEATURES"]
     # name of the features this function can compute
     requested_scales = provider["SCALES"]
     base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support", 
-                            "appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]
+                            "appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge","activities_n_others","activities_inperson","activities_formal"]
     #TODO Check valid questionnaire and feature names.
     # the subset of requested features this function can compute
     features_to_compute = list(set(requested_features) & set(base_features_names))
     esm_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
     if not esm_data.empty:
         esm_data = filter_data_by_segment(esm_data, time_segment)
-
         if not esm_data.empty:
             esm_features = pd.DataFrame()
             for scale in requested_scales:
                 questionnaire_id = QUESTIONNAIRE_IDS[scale]
                 mask = esm_data["questionnaire_id"] == questionnaire_id
+                #print(esm_data.loc[mask].head())
+                #print(time_segment)
+                if not mask.any():
+                    temp = sensor_data_files["sensor_data"]
+                    warnings.warn(f"Warning........... No relevant questions for scale {scale} in {temp}-{time_segment}",RuntimeWarning) 
+                    continue
+                #TODO: calculation of LTM features
+                if scale=="activities":
+                    requested_subset = [req for req in requested_features if req.startswith("activities")]
+                    if not bool(requested_subset):
+                        continue
+                    # ltm_features = esm_activities_LTM_features(esm_data.loc[mask])
+                    # print(esm_data["esm_json"].values)
+                    # print(mask)
+                    # print(esm_data.loc[mask])
+                    # #ltm_features = ltm_features[ltm_features["correct_ids"==44]]
+                    #print(esm_data.loc[mask]["local_segment"])
+                    ltm_features = esm_data.loc[mask].groupby(["local_segment"]).apply(process_answers_aggregation)
+                    #print("PRINTING ltm_features:\n",ltm_features)
+                    ltm_features.rename(columns={"n_others":"activities_n_others","inperson":"activities_inperson","formal":"activities_formal"},inplace=True)
+                    esm_features[requested_subset] = ltm_features.groupby("local_segment").first()[requested_subset]
+                    #print(esm_features.columns)
+                    #print("PRINTING esm_features after rename:\n",ltm_features)
+                    #FIXME: it might be an issue that im calculating for whole time segment and not grouping by "local segment"
+                    #print("~~~~~~~~~~~~~~~~~~~~~~~~===============================~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n     LTM FEATURES STORED...     AFTER RETURN:\n",ltm_features,esm_features[["activities_"+req for req in requested_subset]])
+                if("mean" in features_to_compute):
                     esm_features[scale + "_mean"] = esm_data.loc[mask].groupby(["local_segment"])["esm_user_score"].mean()
                 #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
 
@@ -64,3 +94,15 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
                 esm_features.rename(columns={'index': 'local_segment'}, inplace=True)
 
     return esm_features
+
+def test_main():
+    import temp_help
+    provider = {
+        "FEATURES":["mean","activities_n_others","activities_inperson","activities_formal"],
+        "SCALES":['activities']
+    }
+    sensor_data_files = {"sensor_data":"data/interim/p069/phone_esm_clean.csv"}
+    s_feat = straw_features(sensor_data_files,"straw_event_stress_event_p069_110",provider,temp_help.filter_data_by_segment)
+    print(s_feat)
+
+#test_main()

src/features/phone_esm/straw/process_user_event_related_segments.py

@@ -67,7 +67,7 @@ def extract_ers(esm_df):
     
     segmenting_method = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["SEGMENTING_METHOD"]
     
-    if segmenting_method in ["30_before", "90_before"]: # takes 30-minute peroid before the questionnaire + the duration of the questionnaire
+    if segmenting_method in ["10_before", "30_before", "90_before"]: # takes 30-minute peroid before the questionnaire + the duration of the questionnaire
         """ '30-minutes and 90-minutes before' have the same fundamental logic with couple of deviations that will be explained below.
         Both take x-minute period before the questionnaire that is summed with the questionnaire duration.
         All questionnaire durations over 15 minutes are excluded from the querying.
@@ -79,7 +79,18 @@ def extract_ers(esm_df):
         extracted_ers = extracted_ers[extracted_ers["timestamp"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min 
         extracted_ers["shift_direction"] = -1 
 
-        if segmenting_method == "30_before":
+        if segmenting_method == "10_before":
+            """The method 10-minutes before simply takes 10 minutes before the questionnaire and sums it with the questionnaire duration.
+            The timestamps are formatted with the help of format_timestamp() method.
+            """
+            time_before_questionnaire = 10 * 60 # in seconds (10 minutes)
+            #TODO: split into small segments with manipulating lenght and shift
+            extracted_ers["length"] = (extracted_ers["timestamp"] + time_before_questionnaire).apply(lambda x: format_timestamp(x))
+            extracted_ers["shift"] = time_before_questionnaire
+            extracted_ers["shift"] = extracted_ers["shift"].apply(lambda x: format_timestamp(x))
+        
+
+        elif segmenting_method == "30_before":
             """The method 30-minutes before simply takes 30 minutes before the questionnaire and sums it with the questionnaire duration.
             The timestamps are formatted with the help of format_timestamp() method.
             """
@@ -140,8 +151,8 @@ def extract_ers(esm_df):
 
         # Extracted 3 targets that will be transfered in the csv file to the cleaning script. 
         se_stressfulness_event_tg = esm_df[esm_df.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_stressfulness_event'})
-        se_threat_tg = esm_df[esm_df.questionnaire_id == 88.].groupby(["device_id", "esm_session"]).mean(numeric_only=True)['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_threat'})
+        se_threat_tg = esm_df[esm_df.questionnaire_id == 88.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_threat'})
-        se_challenge_tg = esm_df[esm_df.questionnaire_id == 89.].groupby(["device_id", "esm_session"]).mean(numeric_only=True)['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_challenge'})
+        se_challenge_tg = esm_df[esm_df.questionnaire_id == 89.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_challenge'})
 
         # All relevant features are joined by inner join to remove standalone columns (e.g., stressfulness event target has larger count)
         extracted_ers = extracted_ers.join(session_start_timestamp, on=['device_id', 'esm_session'], how='inner') \

src/features/phone_esm/straw/temp_help.py

@@ -0,0 +1,70 @@
+"""This file is TEMPORARY and intended for testing main.py
+"""
+
+def filter_data_by_segment(data, time_segment):
+    data.dropna(subset=["assigned_segments"], inplace=True)
+    if(data.shape[0] == 0): # data is empty
+        data["local_segment"] = data["timestamps_segment"] = None
+        return data
+
+    datetime_regex = "[0-9]{4}[\-|\/][0-9]{2}[\-|\/][0-9]{2} [0-9]{2}:[0-9]{2}:[0-9]{2}"
+    timestamps_regex = "[0-9]{13}"
+    segment_regex = "\[({}#{},{};{},{})\]".format(time_segment, datetime_regex, datetime_regex, timestamps_regex, timestamps_regex)
+    data["local_segment"] = data["assigned_segments"].str.extract(segment_regex, expand=True)
+    data = data.drop(columns=["assigned_segments"])
+    data = data.dropna(subset = ["local_segment"])
+    if(data.shape[0] == 0): # there are no rows belonging to time_segment after droping na
+        data["timestamps_segment"] = None
+    else:
+        data[["local_segment","timestamps_segment"]] = data["local_segment"].str.split(pat =";",n=1, expand=True)
+    
+    # chunk episodes
+    if (not data.empty) and ("start_timestamp" in data.columns) and ("end_timestamp" in data.columns):
+        data = chunk_episodes(data)
+    
+    return data
+
+def chunk_episodes(sensor_episodes):
+    import copy
+    import pandas as pd
+
+    # Deduplicate episodes
+    # Drop rows where segments of start_timestamp and end_timestamp are the same
+    sensor_episodes = sensor_episodes.drop_duplicates(subset=["start_timestamp", "end_timestamp", "local_segment"], keep="first")
+
+    # Delete useless columns
+    for drop_col in ["local_date_time", "local_date", "local_time", "local_hour", "local_minute"]:
+        del sensor_episodes[drop_col]
+    
+    # Avoid SettingWithCopyWarning
+    sensor_episodes = sensor_episodes.copy()
+
+    # Unix timestamp for current segment in milliseconds
+    sensor_episodes[["segment_start_timestamp", "segment_end_timestamp"]] = sensor_episodes["timestamps_segment"].str.split(",", expand=True).astype(int)
+
+    # Compute chunked timestamp
+    sensor_episodes["chunked_start_timestamp"] = sensor_episodes[["start_timestamp", "segment_start_timestamp"]].max(axis=1)
+    sensor_episodes["chunked_end_timestamp"] = sensor_episodes[["end_timestamp", "segment_end_timestamp"]].min(axis=1)
+
+    # Compute duration: intersection of current row and segment
+    sensor_episodes["duration"] = (sensor_episodes["chunked_end_timestamp"] - sensor_episodes["chunked_start_timestamp"]) / (1000 * 60)
+
+    # Merge episodes
+    cols_for_groupby = [col for col in sensor_episodes.columns if col not in ["timestamps_segment", "timestamp", "assigned_segments", "start_datetime", "end_datetime", "start_timestamp", "end_timestamp", "duration", "chunked_start_timestamp", "chunked_end_timestamp"]]
+
+    sensor_episodes_grouped = sensor_episodes.groupby(by=cols_for_groupby, sort=False, dropna=False)
+    merged_sensor_episodes = sensor_episodes_grouped[["duration"]].sum()
+
+    merged_sensor_episodes["start_timestamp"] = sensor_episodes_grouped["chunked_start_timestamp"].first()
+    merged_sensor_episodes["end_timestamp"] = sensor_episodes_grouped["chunked_end_timestamp"].last()
+
+    merged_sensor_episodes.reset_index(inplace=True)
+
+    # Compute datetime
+    merged_sensor_episodes["local_start_date_time"] = pd.to_datetime(merged_sensor_episodes["start_timestamp"], unit="ms", utc=True)
+    merged_sensor_episodes["local_start_date_time"] = pd.concat([data["local_start_date_time"].dt.tz_convert(tz) for tz, data in merged_sensor_episodes.groupby("local_timezone")]).apply(lambda x: x.tz_localize(None).replace(microsecond=0))
+
+    merged_sensor_episodes["local_end_date_time"] = pd.to_datetime(merged_sensor_episodes["end_timestamp"], unit="ms", utc=True)
+    merged_sensor_episodes["local_end_date_time"] = pd.concat([data["local_end_date_time"].dt.tz_convert(tz) for tz, data in merged_sensor_episodes.groupby("local_timezone")]).apply(lambda x: x.tz_localize(None).replace(microsecond=0))
+
+    return merged_sensor_episodes

src/features/phone_locations/doryab/add_doryab_extra_columns.py

@@ -115,7 +115,7 @@ cluster_on = provider["CLUSTER_ON"]
 strategy = provider["INFER_HOME_LOCATION_STRATEGY"]
 days_threshold = provider["MINIMUM_DAYS_TO_DETECT_HOME_CHANGES"]
 
-if not location_data.timestamp.is_monotonic_increasing:
+if not location_data.timestamp.is_monotonic:
     location_data.sort_values(by=["timestamp"], inplace=True)
 
 location_data["duration_in_seconds"] = -1 * location_data.timestamp.diff(-1) / 1000

src/features/utils/utils.py

@@ -14,6 +14,7 @@ def import_path(path):
     sys.modules[module_name] = module
     return module
 
+#TODO:check why segments change to int 
 def filter_data_by_segment(data, time_segment):
     data.dropna(subset=["assigned_segments"], inplace=True)
     if(data.shape[0] == 0): # data is empty
@@ -151,6 +152,7 @@ def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_file
 
     else: 
         segment_colums = pd.DataFrame()
+        print(sensor_features,sensor_features['local_segment'])
         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"])