.gitignore

@@ -93,17 +93,10 @@ 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
 !/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
 data/interim/*
@@ -121,12 +114,3 @@ settings.dcf
 tests/fakedata_generation/
 site/
 credentials.yaml
-
-# Docker container and other files
-.devcontainer
-
-# Calculating features module
-calculatingfeatures/
-
-# Temp folder for rapids data/external
-rapids_temp_data/

README.md

@@ -11,191 +11,3 @@
 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/)
-
-### For the installation of the Docker version
-
-1. Follow the [instructions](https://www.rapids.science/1.8/setup/installation/) to setup RAPIDS via Docker (from scratch).
-
-2. Delete current contents in /rapids/ folder when in a container session.
-    ```
-    cd ..
-    rm -rf rapids/{*,.*}
-    cd rapids
-    ```
-
-3. Clone RAPIDS workspace from Git and checkout a specific branch.
-    ```
-    git clone "https://repo.ijs.si/junoslukan/rapids.git" .
-    git checkout <branch_name>
-    ```
-
-4. Install missing “libpq-dev” dependency with bash.
-    ```
-    apt-get update -y
-    apt-get install -y libpq-dev
-    ```
-
-5. Restore R venv.
-Type R to go to the interactive R session and then:
-    ```
-    renv::restore()
-    ```
-
-6. Install cr-features module 
-From: https://repo.ijs.si/matjazbostic/calculatingfeatures.git -> branch master. 
-Then follow the "cr-features module" section below.  
-
-7. Install all required packages from environment.yml, prune also deletes conda packages not present in environment file.
-    ```
-    conda env update --file environment.yml –prune
-    ```
-
-8. If you wish to update your R or Python venvs.
-    ```
-    R in interactive session:
-    renv::snapshot()
-    Python: 
-    conda env export --no-builds | sed 's/^.*libgfortran.*$/  - libgfortran/' | sed 's/^.*mkl=.*$/  - mkl/' >  environment.yml
-    ```
-
-### cr-features module 
-
-This RAPIDS extension uses cr-features library accessible [here](https://repo.ijs.si/matjazbostic/calculatingfeatures).
-
-To use cr-features 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 cr-features package by:
-    ```
-    pip install path/to/the/calculatingfeatures/folder
-    e.g. pip install ./calculatingfeatures if the folder is copied to main parent directory
-    cr-features package has to be built and installed everytime to get the newest version. 
-    Or an the newest version of the docker image must be used.   
-    ```
-
-## Updating RAPIDS
-
-To update RAPIDS, first pull and merge [origin]( https://github.com/carissalow/rapids), such as with:
-
-```commandline
-git fetch --progress "origin" refs/heads/master
-git merge --no-ff origin/master
-```
-
-Next, update the conda and R virtual environment.
-
-```bash
-R -e 'renv::restore(repos = c(CRAN = "https://packagemanager.rstudio.com/all/__linux__/focal/latest"))'
-```
-
-## Custom configuration
-### Credentials
-
-As mentioned under [Database in RAPIDS documentation](https://www.rapids.science/1.6/snippets/database/), a `credentials.yaml` file is needed to connect to a database.
-It should contain:
-
-```yaml
-PSQL_STRAW:
-  database: staw
-  host: 212.235.208.113
-  password: password
-  port: 5432
-  user: staw_db
-```
-
-where`password` needs to be specified as well.
-
-## Possible installation issues
-### Missing dependencies for RPostgres
-
-To install `RPostgres` R package (used to connect to the PostgreSQL database), an error might occur:
-
-```text
-------------------------- ANTICONF ERROR ---------------------------
-Configuration failed because libpq was not found. Try installing:
-   * deb: libpq-dev (Debian, Ubuntu, etc)
-   * rpm: postgresql-devel (Fedora, EPEL)
-   * rpm: postgreql8-devel, psstgresql92-devel, postgresql93-devel, or postgresql94-devel (Amazon Linux)
-   * csw: postgresql_dev (Solaris)
-   * brew: libpq (OSX)
-If libpq is already installed, check that either:
-  (i)  'pkg-config' is in your PATH AND PKG_CONFIG_PATH contains a libpq.pc file; or
-  (ii) 'pg_config' is in your PATH.
-If neither can detect , you can set INCLUDE_DIR
-and LIB_DIR manually via:
-  R CMD INSTALL --configure-vars='INCLUDE_DIR=... LIB_DIR=...'
---------------------------[ ERROR MESSAGE ]----------------------------
-  <stdin>:1:10: fatal error: libpq-fe.h: No such file or directory
-compilation terminated.
-```
-
-The library requires `libpq` for compiling from source, so install accordingly.
-
-### Timezone environment variable for tidyverse (relevant for WSL2)
-
-One of the R packages, `tidyverse` might need access to the `TZ` environment variable during the installation.
-On Ubuntu 20.04 on WSL2 this triggers the following error:
-
-```text
-> install.packages('tidyverse')
-
-ERROR: configuration failed for package ‘xml2’
-System has not been booted with systemd as init system (PID 1). Can't operate.
-Failed to create bus connection: Host is down
-Warning in system("timedatectl", intern = TRUE) :
-  running command 'timedatectl' had status 1
-Error in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]) :
-  namespace ‘xml2’ 1.3.1 is already loaded, but >= 1.3.2 is required
-Calls: <Anonymous> ... namespaceImportFrom -> asNamespace -> loadNamespace
-Execution halted
-ERROR: lazy loading failed for package ‘tidyverse’
-```
-
-This happens because WSL2 does not use the `timedatectl` service, which provides this variable.
-
-```bash
-~$ timedatectl
-System has not been booted with systemd as init system (PID 1). Can't operate.
-Failed to create bus connection: Host is down
-```
-
-and later 
-
-```bash 
-Warning message:
-In system("timedatectl", intern = TRUE) :
-  running command 'timedatectl' had status 1
-Execution halted
-```
-
-This can be amended by setting the environment variable manually before attempting to install `tidyverse`:
-
-```bash
-export TZ='Europe/Ljubljana'
-```
-
-Note: if this is needed to avoid runtime issues, you need to either define this environment variable in each new terminal window or (better) define it in your `~/.bashrc` or `~/.bash_profile`.
-
-## Possible runtime issues
-### Unix end of line characters
-
-Upon running rapids, an error might occur:
-
-```bash
-/usr/bin/env: ‘python3\r’: No such file or directory
-```
-
-This is due to Windows style end of line characters. 
-To amend this, I added a `.gitattributes` files to force `git` to checkout `rapids` using Unix EOL characters.
-If this still fails, `dos2unix` can be used to change them.
-
-### System has not been booted with systemd as init system (PID 1)
-
-See [the installation issue above](#Timezone-environment-variable-for-tidyverse-(relevant-for-WSL2)).

Snakefile

@@ -169,19 +169,9 @@ for provider in config["PHONE_ESM"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/raw/{pid}/phone_esm_raw.csv",pid=config["PIDS"]))
         files_to_compute.extend(expand("data/raw/{pid}/phone_esm_with_datetime.csv",pid=config["PIDS"]))
         files_to_compute.extend(expand("data/interim/{pid}/phone_esm_clean.csv",pid=config["PIDS"]))
-        files_to_compute.extend(expand("data/interim/{pid}/phone_esm_features/phone_esm_{language}_{provider_key}.csv",pid=config["PIDS"],language=get_script_language(config["PHONE_ESM"]["PROVIDERS"][provider]["SRC_SCRIPT"]),provider_key=provider.lower()))
+        files_to_compute.extend(expand("data/interim/{pid}/phone_esm_features/phone_esm_clean_{provider_key}.csv",pid=config["PIDS"],provider_key=provider.lower()))
-        files_to_compute.extend(expand("data/processed/features/{pid}/phone_esm.csv", pid=config["PIDS"]))
+        #files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv",pid=config["PIDS"]))
-        # files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv",pid=config["PIDS"]))
+        #files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
-        # files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
-
-for provider in config["PHONE_SPEECH"]["PROVIDERS"].keys():
-    if config["PHONE_SPEECH"]["PROVIDERS"][provider]["COMPUTE"]:
-        files_to_compute.extend(expand("data/raw/{pid}/phone_speech_raw.csv",pid=config["PIDS"]))
-        files_to_compute.extend(expand("data/raw/{pid}/phone_speech_with_datetime.csv",pid=config["PIDS"]))
-        files_to_compute.extend(expand("data/interim/{pid}/phone_speech_features/phone_speech_{language}_{provider_key}.csv",pid=config["PIDS"],language=get_script_language(config["PHONE_SPEECH"]["PROVIDERS"][provider]["SRC_SCRIPT"]),provider_key=provider.lower()))
-        files_to_compute.extend(expand("data/processed/features/{pid}/phone_speech.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")
 
 # We can delete these if's as soon as we add feature PROVIDERS to any of these sensors
 if isinstance(config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"], dict):
@@ -417,18 +407,10 @@ if config["HEATMAP_FEATURE_CORRELATION_MATRIX"]["PLOT"]:
 # Data Cleaning
 for provider in config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"].keys():
     if config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"][provider]["COMPUTE"]:
-        if provider == "STRAW":
+        files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned_" + provider.lower() +".csv", pid=config["PIDS"]))
-            files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned_" + provider.lower() + "_py.csv", pid=config["PIDS"]))
-        else:
-            files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned_" + provider.lower() + "_R.csv", pid=config["PIDS"]))
-
 for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
     if config["ALL_CLEANING_OVERALL"]["PROVIDERS"][provider]["COMPUTE"]:
-        if provider == "STRAW":
+        files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +".csv"))
-            for target in config["PARAMS_FOR_ANALYSIS"]["TARGET"]["ALL_LABELS"]:
-                files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_py_(" + target + ").csv"))
-        else:
-            files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_R.csv"))     
 
 # Baseline features
 if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
@@ -437,12 +419,6 @@ if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
     files_to_compute.extend(expand("data/interim/{pid}/baseline_questionnaires.csv", pid=config["PIDS"]))
     files_to_compute.extend(expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]))
 
-# Targets (labels)
-if config["PARAMS_FOR_ANALYSIS"]["TARGET"]["COMPUTE"]:
-    files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/input.csv", pid=config["PIDS"]))
-    for target in config["PARAMS_FOR_ANALYSIS"]["TARGET"]["ALL_LABELS"]:
-        files_to_compute.extend(expand("data/processed/models/population_model/input_" + target + ".csv"))
-
 rule all:
     input:
         files_to_compute

automl_test.py

@@ -1,57 +0,0 @@
-from pprint import pprint
-import sklearn.metrics
-import autosklearn.regression
-
-import datetime
-import importlib
-import os
-import sys
-
-import numpy as np
-import matplotlib.pyplot as plt
-import pandas as pd
-import seaborn as sns
-import yaml
-
-from sklearn import linear_model, svm, kernel_ridge, gaussian_process
-from sklearn.model_selection import LeaveOneGroupOut, cross_val_score, train_test_split
-from sklearn.metrics import mean_squared_error, r2_score
-from sklearn.impute import SimpleImputer
-
-model_input = pd.read_csv("data/processed/models/population_model/input_PANAS_negative_affect_mean.csv") # Standardizirani podatki
-
-model_input.dropna(axis=1, how="all", inplace=True)
-model_input.dropna(axis=0, how="any", subset=["target"], inplace=True)
-
-categorical_feature_colnames = ["gender", "startlanguage"]
-categorical_feature_colnames += [col for col in model_input.columns if "mostcommonactivity" in col or "homelabel" in col]
-categorical_features = model_input[categorical_feature_colnames].copy()
-mode_categorical_features = categorical_features.mode().iloc[0]
-categorical_features = categorical_features.fillna(mode_categorical_features)
-categorical_features = categorical_features.apply(lambda col: col.astype("category"))
-if not categorical_features.empty:
-    categorical_features = pd.get_dummies(categorical_features)
-numerical_features = model_input.drop(categorical_feature_colnames, axis=1)
-model_in = pd.concat([numerical_features, categorical_features], axis=1)
-
-index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
-model_in.set_index(index_columns, inplace=True)
-
-X_train, X_test, y_train, y_test = train_test_split(model_in.drop(["target", "pid"], axis=1), model_in["target"], test_size=0.30)
-
-automl = autosklearn.regression.AutoSklearnRegressor(
-    time_left_for_this_task=7200,
-    per_run_time_limit=120
-)
-automl.fit(X_train, y_train, dataset_name='straw')
-
-print(automl.leaderboard())
-pprint(automl.show_models(), indent=4)
-
-train_predictions = automl.predict(X_train)
-print("Train R2 score:", sklearn.metrics.r2_score(y_train, train_predictions))
-test_predictions = automl.predict(X_test)
-print("Test R2 score:", sklearn.metrics.r2_score(y_test, test_predictions))
-
-import sys
-sys.exit()

config.yaml

@@ -3,7 +3,7 @@
 ########################################################################################################################
 
 # 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']
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
@@ -16,19 +16,14 @@ CREATE_PARTICIPANT_FILES:
     ADD: False
     IGNORED_DEVICE_IDS: []
   EMPATICA_SECTION:
-    ADD: True
+    ADD: False
     IGNORED_DEVICE_IDS: []
 
 # See https://www.rapids.science/latest/setup/configuration/#time-segments
 TIME_SEGMENTS: &time_segments
-  TYPE: EVENT # FREQUENCY, PERIODIC, EVENT
+  TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
-  FILE: "data/external/straw_events.csv"
+  FILE: "data/external/timesegments_daily.csv"
   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
-    INTERVAL_OF_INTEREST: 10 # duration of event of interest [minutes]
-    IOI_ERROR_TOLERANCE: 5 # interval of interest erorr tolerance (before and after IOI) [minutes]
 
 # See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
 TIMEZONE: 
@@ -75,6 +70,7 @@ PHONE_ACCELEROMETER:
       COMPUTE: False
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/phone_accelerometer/rapids/main.py
+    
     PANDA:
       COMPUTE: False
       VALID_SENSED_MINUTES: False
@@ -104,9 +100,9 @@ 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 +110,24 @@ 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
       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"]
@@ -172,7 +160,7 @@ PHONE_BLUETOOTH:
   CONTAINER: bluetooth
   PROVIDERS:
     RAPIDS:
-      COMPUTE: False
+      COMPUTE: True
       FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
       SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R
 
@@ -251,8 +239,7 @@ 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: ["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"]
       FEATURES: [mean]
       SRC_SCRIPT: src/features/phone_esm/straw/main.py
 
@@ -337,15 +324,6 @@ PHONE_SCREEN:
       EPISODE_TYPES: ["unlock"]
       SRC_SCRIPT: src/features/phone_screen/rapids/main.py
 
-# Custom added sensor
-PHONE_SPEECH:
-  CONTAINER: speech
-  PROVIDERS:
-    STRAW:
-      COMPUTE: True
-      FEATURES: ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
-      SRC_SCRIPT: src/features/phone_speech/straw/main.py
-
 # See https://www.rapids.science/latest/features/phone-wifi-connected/
 PHONE_WIFI_CONNECTED:
   CONTAINER: sensor_wifi
@@ -463,6 +441,7 @@ FITBIT_SLEEP_INTRADAY:
         UNIFIED: [awake, asleep]
       SLEEP_TYPES: [main, nap, all]
       SRC_SCRIPT: src/features/fitbit_sleep_intraday/rapids/main.py
+  
     PRICE:
       COMPUTE: False
       FEATURES: [avgduration, avgratioduration, avgstarttimeofepisodemain, avgendtimeofepisodemain, avgmidpointofepisodemain, stdstarttimeofepisodemain, stdendtimeofepisodemain, stdmidpointofepisodemain, socialjetlag, rmssdmeanstarttimeofepisodemain, rmssdmeanendtimeofepisodemain, rmssdmeanmidpointofepisodemain, rmssdmedianstarttimeofepisodemain, rmssdmedianendtimeofepisodemain, rmssdmedianmidpointofepisodemain]
@@ -506,7 +485,6 @@ FITBIT_STEPS_INTRADAY:
       INCLUDE_ZERO_STEP_ROWS: False
       SRC_SCRIPT: src/features/fitbit_steps_intraday/rapids/main.py
 
-
 ########################################################################################################################
 #                                                 EMPATICA                                                             #
 ########################################################################################################################
@@ -528,15 +506,6 @@ EMPATICA_ACCELEROMETER:
       COMPUTE: False
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
-    CR:
-      COMPUTE: True
-      FEATURES: ["totalMagnitudeBand", "absoluteMeanBand", "varianceBand"] # Acc features
-      WINDOWS:
-        COMPUTE: True
-        WINDOW_LENGTH: 15 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
-      SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py
-
 
 # See https://www.rapids.science/latest/features/empatica-heartrate/
 EMPATICA_HEARTRATE:
@@ -555,15 +524,6 @@ 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: True
-      FEATURES: ["maximum", "minimum", "meanAbsChange", "longestStrikeAboveMean", "longestStrikeBelowMean", 
-                  "stdDev", "median", "meanChange", "sumSquared", "squareSumOfComponent", "sumOfSquareComponents"]
-      WINDOWS:
-        COMPUTE: True
-        WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
-      SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-electrodermal-activity/
 EMPATICA_ELECTRODERMAL_ACTIVITY:
@@ -573,19 +533,6 @@ 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]
-        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:
@@ -595,15 +542,6 @@ 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']
-      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:
@@ -613,16 +551,6 @@ 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: True
-      FEATURES: ['meanHr', 'ibi', 'sdnn', 'sdsd', 'rmssd', 'pnn20', 'pnn50', 'sd', 'sd2', 'sd1/sd2', 'numRR', # Time features
-                  'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features            
-      PATCH_WITH_BVP: True
-      WINDOWS:
-        COMPUTE: True
-        WINDOW_LENGTH: 300 # specify window length in seconds
-        SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
-      SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
 
 # See https://www.rapids.science/latest/features/empatica-tags/
 EMPATICA_TAGS:
@@ -638,7 +566,7 @@ EMPATICA_TAGS:
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#1-histograms-of-phone-data-yield
 HISTOGRAM_PHONE_DATA_YIELD:
-  PLOT: False
+  PLOT: True
 
 # 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:
@@ -647,7 +575,7 @@ 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: False
+  PLOT: True
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#4-heatmap-of-sensor-row-count
 HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
@@ -658,7 +586,7 @@ 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: False
+  PLOT: True
   MIN_ROWS_RATIO: 0.5
   CORR_THRESHOLD: 0.1
   CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
@@ -671,88 +599,55 @@ HEATMAP_FEATURE_CORRELATION_MATRIX:
 ALL_CLEANING_INDIVIDUAL:
   PROVIDERS:
     RAPIDS:
-      COMPUTE: False
+      COMPUTE: True
       IMPUTE_SELECTED_EVENT_FEATURES:
-        COMPUTE: False
+        COMPUTE: True
         MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
-      COLS_NAN_THRESHOLD: 1 # set to 1 to disable
+      COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       COLS_VAR_THRESHOLD: True
       ROWS_NAN_THRESHOLD: 1 # 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 # set to 0 to disable
+      DATA_YIELD_RATIO_THRESHOLD: 0.3 # 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
-      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
-      ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable
-      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
-        MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
-        CORR_THRESHOLD: 0.95
-      STANDARDIZATION: True
-      SRC_SCRIPT: src/features/all_cleaning_individual/straw/main.py
 
 ALL_CLEANING_OVERALL:
   PROVIDERS:
     RAPIDS:
-      COMPUTE: False
+      COMPUTE: True
       IMPUTE_SELECTED_EVENT_FEATURES:
-        COMPUTE: False
+        COMPUTE: True
         MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
-      COLS_NAN_THRESHOLD: 1 # set to 1 to disable
+      COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable
       COLS_VAR_THRESHOLD: True
       ROWS_NAN_THRESHOLD: 1 # 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 # set to 0 to disable
+      DATA_YIELD_RATIO_THRESHOLD: 0.3 # 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
-      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
-      ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable
-      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
-        MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
-        CORR_THRESHOLD: 0.95
-      STANDARDIZATION: True
-      TARGET_STANDARDIZATION: False
-      SRC_SCRIPT: src/features/all_cleaning_overall/straw/main.py
-
 
 ########################################################################################################################
-#                                                      Baseline                                                        #
+#                                              Analysis Workflow Example                                               #
 ########################################################################################################################
 
 PARAMS_FOR_ANALYSIS:
   BASELINE:
-    COMPUTE: True
+    COMPUTE: False
     FOLDER: data/external/baseline
     CONTAINER: [results-survey637813_final.csv,  # Slovenia
                 results-survey358134_final.csv,  # Belgium 1
                 results-survey413767_final.csv  # Belgium 2
     ]
     QUESTION_LIST: survey637813+question_text.csv
-    FEATURES: [age, gender, startlanguage, limesurvey_demand, limesurvey_control, limesurvey_demand_control_ratio, limesurvey_demand_control_ratio_quartile]
+    FEATURES: [age, gender, startlanguage, demand, control, demand_control_ratio]
     CATEGORICAL_FEATURES: [gender]
 
   TARGET:
-    COMPUTE: True
+    SCALE: [positive_affect, negative_affect]
-    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]
-                # 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/aware_csv/calls.csv

@@ -1,9 +0,0 @@
-"_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/main_study_usernames.csv

@@ -1,57 +0,0 @@
-label,empatica_id
-uploader_79170,A0245B
-uploader_89788,A02731
-uploader_68294,A02705
-uploader_92856,A024AF
-uploader_23726,A0231C
-uploader_66620,A02305
-uploader_58435,A026B5
-uploader_87801,A022A8
-uploader_96055,A027BA
-uploader_69549,A0226C
-uploader_26363,A0263D
-uploader_72010,A023FA
-uploader_13997,A024AF
-uploader_31156,A02305
-uploader_63187,A027BA
-uploader_94821,A022A8
-uploader_65413,A023F1;A023FA
-uploader_36488,A02713
-uploader_91087,A0231C
-uploader_35174,A025D1
-uploader_73880,A02705
-uploader_78650,A02731
-uploader_70578,A0245B
-uploader_88313,A02736
-uploader_58482,A0261A
-uploader_80601,A027BA
-uploader_93729,A0226C
-uploader_61663,A0245B
-uploader_80848,A025D1
-uploader_57312,A023F9;A02361;A027A0
-uploader_52087,A02666
-uploader_98770,A02953
-uploader_51327,A0245F
-uploader_11737,A02732
-uploader_77440,A0264E
-uploader_57277,A02422
-uploader_13098,A026E5
-uploader_80719,A023C8
-uploader_54698,A02953
-uploader_95571,A02853
-uploader_21880,A024DC
-uploader_92905,A02920
-uploader_12108,A023F4
-uploader_17436,A026E5
-uploader_58440,A0273F
-uploader_22172,A0245F
-uploader_39250,A02422
-uploader_15311,A023F9
-uploader_45766,A02920
-uploader_23096,A02361
-uploader_78243,A02422
-uploader_58777,A0245F
-uploader_82941,A02666
-uploader_89606,A023F4
-uploader_82969,A023C8
-uploader_53573,A024DC;A02361

data/external/participant_files/p01.yaml

@@ -1,11 +0,0 @@
-PHONE:
-  DEVICE_IDS: [4b62a655-cbf0-4ac0-a448-06726f45b56a]
-  PLATFORMS: [android]
-  LABEL: uploader_53573
-  START_DATE: 2021-05-21 09:21:24
-  END_DATE: 2021-07-12 17:32:07
-EMPATICA:
-  DEVICE_IDS: [uploader_53573]
-  LABEL: uploader_53573
-  START_DATE: 2021-05-21 09:21:24
-  END_DATE: 2021-07-12 17:32:07

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

data/external/timesegments_daily.csv

@@ -1,3 +1,2 @@
 label,start_time,length,repeats_on,repeats_value
 daily,04:00:00,23H 59M 59S,every_day,0
-working_day,04:00:00,18H 00M 00S,every_day,0

data/external/timesegments_frequency.csv

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

data/external/timesegments_periodic.csv

@@ -1,2 +1,9 @@
 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

docs/change-log.md

@@ -1,9 +1,4 @@
 # Change Log
-## v1.8.0
-- Add data stream for AWARE Micro server
-- Fix the NA bug in PHONE_LOCATIONS BARNETT provider
-- Fix the bug of data type for call_duration field
-- Fix the index bug of heatmap_sensors_per_minute_per_time_segment
 ## v1.7.1
 - Update docs for Git Flow section
 - Update RAPIDS paper information

docs/datastreams/aware-micro-mysql.md

@@ -1,15 +0,0 @@
-# `aware_micro_mysql`
-
-This [data stream](../../datastreams/data-streams-introduction) handles iOS and Android sensor data collected with the [AWARE Framework's](https://awareframework.com/) [AWARE Micro](https://github.com/denzilferreira/aware-micro) server and stored in a MySQL database.
-
-## Container
-A MySQL database with a table per sensor, each containing the data for all participants. Sensor data is stored in a JSON field within each table called `data`
-
-The script to connect and download data from this container is at:
-```bash
-src/data/streams/aware_micro_mysql/container.R
-```
-
-## Format
-
---8<---- "docs/snippets/aware_format.md"

docs/datastreams/data-streams-introduction.md

@@ -16,7 +16,6 @@ For reference, these are the data streams we currently support:
 | Data Stream | Device | Format | Container | Docs
 |--|--|--|--|--|
 | `aware_mysql`| Phone | AWARE app | MySQL | [link](../aware-mysql)
-| `aware_micro_mysql`| Phone | AWARE Micro server | MySQL | [link](../aware-micro-mysql)
 | `aware_csv`| Phone | AWARE app | CSV files | [link](../aware-csv)
 | `aware_influxdb` (beta)| Phone | AWARE app | InfluxDB | [link](../aware-influxdb)
 | `fitbitjson_mysql`| Fitbit | JSON (per [Fitbit's API](https://dev.fitbit.com/build/reference/web-api/)) | MySQL | [link](../fitbitjson-mysql)

donotmakechanges.py

@@ -1,39 +0,0 @@
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !
-# !
-"""
-Please do not make any changes, as RAPIDS is running on tmux server ...
-"""
-# !

environment.yml

@@ -1,30 +1,116 @@
 name: rapids
 channels:
   - conda-forge
+  - defaults
 dependencies:
-    - auto-sklearn
+  - _py-xgboost-mutex=2.0
-    - hmmlearn
+  - appdirs=1.4.*
-    - imbalanced-learn
+  - arrow=0.16.0
-    - jsonschema
+  - asn1crypto=1.4.*
-    - lightgbm
+  - astropy=4.2.*
-    - matplotlib
+  - attrs=20.3.*
-    - numpy
+  - binaryornot=0.4.*
-    - pandas
+  - blas=1.0
-    - peakutils
+  - brotlipy=0.7.*
-    - pip
+  - bzip2=1.0.*
-    - plotly
+  - ca-certificates
-    - python-dateutil
+  - certifi
-    - pytz
+  - cffi=1.14.4
-    - pywavelets
+  - chardet=3.0.*
-    - pyyaml
+  - click=7.1.*
-    - scikit-learn
+  - cookiecutter=1.6.*
-    - scipy
+  - cryptography=3.3.*
-    - seaborn
+  - datrie=0.8.*
-    - setuptools
+  - docutils=0.16
-    - bioconda::snakemake 
+  - future=0.18.2
-    - bioconda::snakemake-minimal
+  - gitdb=4.0.*
-    - tqdm
+  - gitdb2=4.0.*
-    - xgboost
+  - gitpython=3.1.*
-    - pip:
+  - idna=2.10
-        - biosppy
+  - imbalanced-learn=0.6.*
-        - cr_features>=0.2
+  - importlib-metadata=2.0.*
+  - importlib_metadata=2.0.*
+  - intel-openmp=2019.4
+  - jinja2=2.11.2
+  - jinja2-time=0.2.*
+  - joblib=1.0.*
+  - jsonschema=3.2.*
+  - libblas=3.8.*
+  - libcblas=3.8.*
+  - libcxx=10.0.*
+  - libedit=3.1.*
+  - libffi=3.3
+  - libgfortran
+  - liblapack=3.8.*
+  - libopenblas=0.3.*
+  - libxgboost=0.90
+  - lightgbm=3.1.*
+  - llvm-openmp=10.0.*
+  - markupsafe=1.1.*
+  - mkl
+  - mkl-service=2.3.*
+  - mkl_fft=1.2.*
+  - mkl_random=1.1.*
+  - more-itertools=8.6.*
+  - ncurses=6.2
+  - numpy=1.19.2
+  - numpy-base=1.19.2
+  - openblas=0.3.*
+  - openssl
+  - pandas=1.1.*
+  - pbr=5.5.*
+  - pip=20.3.*
+  - plotly=4.14.1
+  - poyo=0.5.*
+  - psutil=5.7.*
+  - psycopg2
+  - py-xgboost=0.90
+  - pycparser=2.20
+  - pyerfa=1.7.*
+  - pyopenssl=20.0.*
+  - pyprojroot
+  - pysocks=1.7.*
+  - python=3.7.*
+  - python-dateutil=2.8.*
+  - python-dotenv
+  - python_abi=3.7
+  - pytz=2020.4
+  - pyyaml=5.3.*
+  - readline=8.0
+  - requests=2.25.0
+  - retrying=1.3.*
+  - scikit-learn=0.23.2
+  - scipy=1.5.*
+  - setuptools=51.0.*
+  - six=1.15.0
+  - smmap=3.0.*
+  - smmap2=3.0.*
+  - sqlalchemy
+  - sqlite=3.33.0
+  - threadpoolctl=2.1.*
+  - tk=8.6.*
+  - tqdm=4.62.0
+  - urllib3=1.25.11
+  - wheel=0.36.2
+  - whichcraft=0.6.*
+  - wrapt=1.12.1
+  - xgboost=0.90
+  - xz=5.2.*
+  - yaml=0.2.*
+  - zipp=3.4.*
+  - zlib=1.2.*
+  - pip:
+    - amply==0.1.*
+    - configargparse==0.15.1
+    - decorator==4.4.*
+    - ipython-genutils==0.2.*
+    - jupyter-core==4.6.*
+    - nbformat==5.0.*
+    - pulp==2.4
+    - pyparsing==2.4.*
+    - pyrsistent==0.15.5
+    - ratelimiter==1.2.*
+    - snakemake==5.30.2
+    - toposort==1.5
+    - traitlets==4.3.*
+prefix: /usr/local/Caskroom/miniconda/base/envs/rapids202108

mkdocs.yml

@@ -85,7 +85,6 @@ nav:
       - Introduction: datastreams/data-streams-introduction.md
       - Phone:
         - aware_mysql: datastreams/aware-mysql.md
-        - aware_micro_mysql: datastreams/aware-micro-mysql.md
         - aware_csv: datastreams/aware-csv.md
         - aware_influxdb (beta): datastreams/aware-influxdb.md
         - Mandatory Phone Format: datastreams/mandatory-phone-format.md

renv/activate.R

@@ -15,6 +15,9 @@ local({
   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/common.smk

@@ -40,17 +40,6 @@ def find_features_files(wildcards):
             feature_files.extend(expand("data/interim/{{pid}}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", sensor_key=wildcards.sensor_key.lower(), language=get_script_language(provider["SRC_SCRIPT"]), provider_key=provider_key.lower()))
     return(feature_files)
 
-def find_joint_non_empatica_sensor_files(wildcards):
-    joined_files = []
-    for config_key in config.keys():
-        if config_key.startswith(("PHONE", "FITBIT")) and "PROVIDERS" in config[config_key] and isinstance(config[config_key]["PROVIDERS"], dict):
-            for provider_key, provider in config[config_key]["PROVIDERS"].items():
-                if "COMPUTE" in provider.keys() and provider["COMPUTE"]:
-                    joined_files.append("data/processed/features/{pid}/" + config_key.lower() + ".csv")
-                    break
-    return joined_files
-
-
 def optional_steps_sleep_input(wildcards):
     if config["FITBIT_STEPS_INTRADAY"]["EXCLUDE_SLEEP"]["FITBIT_BASED"]["EXCLUDE"]:
         return "data/raw/{pid}/fitbit_sleep_summary_raw.csv"

rules/features.smk

@@ -341,20 +341,7 @@ rule esm_features:
         provider_key = "{provider_key}",
         sensor_key = "phone_esm",
         scales=lambda wildcards: config["PHONE_ESM"]["PROVIDERS"][wildcards.provider_key.upper()]["SCALES"]
-    output: "data/interim/{pid}/phone_esm_features/phone_esm_python_{provider_key}.csv"
+    output: "data/interim/{pid}/phone_esm_features/phone_esm_clean_{provider_key}.csv"
-    script:
-        "../src/features/entry.py"
-
-rule phone_speech_python_features:
-    input:
-        sensor_data = "data/raw/{pid}/phone_speech_with_datetime.csv",
-        time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
-    params:
-        provider = lambda wildcards: config["PHONE_SPEECH"]["PROVIDERS"][wildcards.provider_key.upper()],
-        provider_key = "{provider_key}",
-        sensor_key = "phone_speech"
-    output: 
-        "data/interim/{pid}/phone_speech_features/phone_speech_python_{provider_key}.csv"
     script:
         "../src/features/entry.py"
 
@@ -804,8 +791,7 @@ 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"
 
@@ -831,8 +817,7 @@ 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"
 
@@ -858,8 +843,7 @@ 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"
 
@@ -885,8 +869,7 @@ 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"
 
@@ -912,8 +895,7 @@ 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"
 
@@ -939,8 +921,7 @@ 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"
 
@@ -1007,12 +988,11 @@ rule clean_sensor_features_for_individual_participants:
     params:
         provider = lambda wildcards: config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"][wildcards.provider_key.upper()],
         provider_key = "{provider_key}",
-        script_extension = "{script_extension}",
         sensor_key = "all_cleaning_individual"
     output:
-        "data/processed/features/{pid}/all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" 
+        "data/processed/features/{pid}/all_sensor_features_cleaned_{provider_key}.csv"
     script:
-        "../src/features/entry.{params.script_extension}"
+        "../src/features/entry.R"
 
 rule clean_sensor_features_for_all_participants:
     input:
@@ -1020,10 +1000,9 @@ rule clean_sensor_features_for_all_participants:
     params:
         provider = lambda wildcards: config["ALL_CLEANING_OVERALL"]["PROVIDERS"][wildcards.provider_key.upper()],
         provider_key = "{provider_key}",
-        script_extension = "{script_extension}",
+        sensor_key = "all_cleaning_overall"
-        sensor_key = "all_cleaning_overall",
-        target = "{target}"
     output:
-        "data/processed/features/all_participants/all_sensor_features_cleaned_{provider_key}_{script_extension}_({target}).csv"
+        "data/processed/features/all_participants/all_sensor_features_cleaned_{provider_key}.csv"
     script:
-        "../src/features/entry.{params.script_extension}"
+        "../src/features/entry.R"
+

rules/models.smk

@@ -27,26 +27,3 @@ rule baseline_features:
         features="data/processed/features/{pid}/baseline_features.csv"
     script:
         "../src/data/baseline_features.py"
-
-rule select_target:
-    input:
-        cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned_straw_py.csv"
-    params:
-        target_variable = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"]
-    output:
-        "data/processed/models/individual_model/{pid}/input.csv"
-    script:
-        "../src/models/select_targets.py"
-
-rule merge_features_and_targets_for_population_model:
-    input:
-        cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned_straw_py_({target}).csv",
-        demographic_features = expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]),
-    params:
-        target_variable="{target}"
-    output:
-        "data/processed/models/population_model/input_{target}.csv"
-    script:
-        "../src/models/merge_features_and_targets_for_population_model.py"
-
-

rules/preprocessing.smk

@@ -4,14 +4,14 @@ 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:
+rule query_usernames_device_empatica_ids:
-#     params:
+    params:
-#         baseline_folder = "/mnt/e/STRAWbaseline/"
+        baseline_folder = "/mnt/e/STRAWbaseline/"
-#     output:
+    output:
-#         usernames_file = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"],
+        usernames_file = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"],
-#         timezone_file = config["TIMEZONE"]["MULTIPLE"]["TZ_FILE"]
+        timezone_file = config["TIMEZONE"]["MULTIPLE"]["TZ_FILE"]
-#     script:
+    script:
-#         "../../participants/prepare_usernames_file.py"
+        "../../participants/prepare_usernames_file.py"
 
 rule prepare_tzcodes_file:
     input:
@@ -247,33 +247,5 @@ 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"
-
-
-rule extract_event_information_from_esm:
-    input:
-        esm_raw_input = "data/raw/{pid}/phone_esm_raw.csv",
-        pid_file = "data/external/participant_files/{pid}.yaml"
-    params:
-        stage = "extract",
-        pid = "{pid}"
-    output:
-        "data/raw/ers/{pid}_ers.csv",
-        "data/raw/ers/{pid}_stress_event_targets.csv"
-    script:
-        "../src/features/phone_esm/straw/process_user_event_related_segments.py"
-
-rule merge_event_related_segments_files:
-    input:
-        ers_files = expand("data/raw/ers/{pid}_ers.csv", pid=config["PIDS"]),
-        se_files = expand("data/raw/ers/{pid}_stress_event_targets.csv", pid=config["PIDS"])
-    params:
-        stage = "merge"
-    output:
-        "data/external/straw_events.csv",
-        "data/external/stress_event_targets.csv"
-    script:
-        "../src/features/phone_esm/straw/process_user_event_related_segments.py"

src/data/application_categories.R

@@ -29,16 +29,23 @@ 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"))
-    apps_with_genre <- left_join(apps, genre_catalogue, by = "package_name")
+    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)){

src/data/baseline_features.py

@@ -60,15 +60,15 @@ if not participant_info.empty:
             0, "startlanguage"
         ]
     if (
-        ("limesurvey_demand" in requested_features)
+        ("demand" in requested_features)
-        or ("limesurvey_control" in requested_features)
+        or ("control" in requested_features)
-        or ("limesurvey_demand_control_ratio" in requested_features)
+        or ("demand_control_ratio" in requested_features)
     ):
         participant_info_t = participant_info.T
         rows_baseline = participant_info_t.index
 
-        if ("limesurvey_demand" in requested_features) or (
+        if ("demand" in requested_features) or (
-            "limesurvey_demand_control_ratio" in requested_features
+            "demand_control_ratio" in requested_features
         ):
             # Find questions about demand, but disregard time (duration of filling in questionnaire)
             rows_demand = rows_baseline.str.startswith(
@@ -95,13 +95,13 @@ if not participant_info.empty:
                 - limesurvey_demand.loc[rows_demand_reverse, "score_original"]
             )
             baseline_interim = pd.concat([baseline_interim, limesurvey_demand], axis=0, ignore_index=True)
-            if "limesurvey_demand" in requested_features:
+            if "demand" in requested_features:
-                baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
+                baseline_features.loc[0, "demand"] = limesurvey_demand[
                     "score"
                 ].sum()
 
-        if ("limesurvey_control" in requested_features) or (
+        if ("control" in requested_features) or (
-            "limesurvey_demand_control_ratio" in requested_features
+            "demand_control_ratio" in requested_features
         ):
             # Find questions about control, but disregard time (duration of filling in questionnaire)
             rows_control = rows_baseline.str.startswith(
@@ -130,18 +130,15 @@ if not participant_info.empty:
 
             baseline_interim = pd.concat([baseline_interim, limesurvey_control], axis=0, ignore_index=True)
 
-            if "limesurvey_control" in requested_features:
+            if "control" in requested_features:
-                baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[
+                baseline_features.loc[0, "control"] = limesurvey_control[
                     "score"
                 ].sum()
 
-        if "limesurvey_demand_control_ratio" in requested_features:
+        if "demand_control_ratio" in requested_features:
-            if limesurvey_control["score"].sum():
+            limesurvey_demand_control_ratio = (
-                limesurvey_demand_control_ratio = (
+                limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
-                        limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
+            )
-                )
-            else:
-                limesurvey_demand_control_ratio = 0
             if (
                 JCQ_NORMS[participant_info.loc[0, "gender"]][0]
                 <= limesurvey_demand_control_ratio
@@ -170,10 +167,10 @@ if not participant_info.empty:
                 limesurvey_quartile = np.nan
 
             baseline_features.loc[
-                0, "limesurvey_demand_control_ratio"
+                0, "demand_control_ratio"
             ] = limesurvey_demand_control_ratio
             baseline_features.loc[
-                0, "limesurvey_demand_control_ratio_quartile"
+                0, "demand_control_ratio_quartile"
             ] = limesurvey_quartile
 
 if not baseline_interim.empty:

src/data/create_participants_files.R

@@ -58,7 +58,7 @@ participants %>%
       lines <- append(lines, empty_fitbit)
 
     if(add_empatica_section == TRUE && !is.na(row[empatica_device_id_column])){
-      lines <- append(lines, c("EMPATICA:", paste0("  DEVICE_IDS: [",row$label,"]"),
+      lines <- append(lines, c("EMPATICA:", paste0("  DEVICE_IDS: [",row[empatica_device_id_column],"]"),
                                paste("  LABEL:",row$label), paste("  START_DATE:", start_date), paste("  END_DATE:", end_date)))
     } else
       lines <- append(lines, empty_empatica)

src/data/datetime/assign_to_time_segment.R

@@ -5,16 +5,13 @@ options(scipen=999)
 
 assign_rows_to_segments <- function(data, segments){
   # This function is used by all segment types, we use data.tables because they are fast
-
   data <- data.table::as.data.table(data)
   data[, assigned_segments := ""]
   for(i in seq_len(nrow(segments))) {
     segment <- segments[i,]
-
     data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp,
          assigned_segments := stringi::stri_c(assigned_segments, segment$segment_id, sep = "|")]
   }
-  
   data[,assigned_segments:=substring(assigned_segments, 2)]
   data
 }

src/data/streams/aware_micro_mysql/container.R

@@ -1,85 +0,0 @@
-# if you need a new package, you should add it with renv::install(package) so your renv venv is updated
-library(RMariaDB)
-library(yaml)
-
-#' @description
-#' Auxiliary function to parse the connection credentials from a specifc group in ./credentials.yaml
-#' You can reause most of this function if you are connection to a DB or Web API.
-#' It's OK to delete this function if you don't need credentials, e.g., you are pulling data from a CSV for example.
-#' @param group the yaml key containing the credentials to connect to a database
-#' @preturn dbEngine a database engine (connection) ready to perform queries
-get_db_engine <- function(group){
-  # The working dir is aways RAPIDS root folder, so your credentials file is always /credentials.yaml
-  credentials <- read_yaml("./credentials.yaml")
-  if(!group %in% names(credentials))
-    stop(paste("The credentials group",group, "does not exist in ./credentials.yaml. The only groups that exist in that file are:", paste(names(credentials), collapse = ","), ". Did you forget to set the group in [PHONE_DATA_STREAMS][aware_mysql][DATABASE_GROUP] in config.yaml?"))
-  dbEngine <- dbConnect(MariaDB(), db = credentials[[group]][["database"]],
-                                    username = credentials[[group]][["user"]],
-                                    password = credentials[[group]][["password"]],
-                                    host = credentials[[group]][["host"]],
-                                    port = credentials[[group]][["port"]])
-  return(dbEngine)
-}
-
-# This file gets executed for each PHONE_SENSOR of each participant
-# If you are connecting to a database the env file containing its credentials is available at "./.env"
-# If you are reading a CSV file instead of a DB table, the @param sensor_container wil contain the file path as set in config.yaml
-# You are not bound to databases or files, you can query a web API or whatever data source you need.
-
-#' @description
-#' RAPIDS allows users to use the keyword "infer" (previously "multiple") to automatically infer the mobile Operative System a device was running.
-#' If you have a way to infer the OS of a device ID, implement this function. For example, for AWARE data we use the "aware_device" table.
-#'  
-#' If you don't have a way to infer the OS, call stop("Error Message") so other users know they can't use "infer" or the inference failed, 
-#' and they have to assign the OS manually in the participant file
-#' 
-#' @param stream_parameters The PHONE_STREAM_PARAMETERS key in config.yaml. If you need specific parameters add them there.
-#' @param device A device ID string
-#' @return The OS the device ran, "android" or "ios"
-
-infer_device_os <- function(stream_parameters, device){
-  dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
-  query <- paste0("SELECT device_id,brand FROM aware_device WHERE device_id = '", device, "'")
-  message(paste0("Executing the following query to infer phone OS: ", query)) 
-  os <- dbGetQuery(dbEngine, query)
-  dbDisconnect(dbEngine)
-  
-  if(nrow(os) > 0)
-    return(os %>% mutate(os = ifelse(brand == "iPhone", "ios", "android")) %>% pull(os))
-  else
-    stop(paste("We cannot infer the OS of the following device id because it does not exist in the aware_device table:", device))
-  
-  return(os)
-}
-
-#' @description
-#' Gets the sensor data for a specific device id from a database table, file or whatever source you want to query
-#' 
-#' @param stream_parameters The PHONE_STREAM_PARAMETERS key in config.yaml. If you need specific parameters add them there.
-#' @param device A device ID string
-#' @param sensor_container database table or file containing the sensor data for all participants. This is the PHONE_SENSOR[CONTAINER] key in config.yaml
-#' @param columns the columns needed from this sensor (we recommend to only return these columns instead of every column in sensor_container)
-#' @return A dataframe with the sensor data for device
-
-pull_data <- function(stream_parameters, device, sensor, sensor_container, columns){
-  dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
-
-  select_items <- c()
-  for (column in columns) {
-    select_items <- append(select_items, paste0("data->>'$.", column, "' ", column))
-  }
-
-  query <- paste0("SELECT ", paste(select_items, collapse = ",")," FROM ", sensor_container, " WHERE ", columns$DEVICE_ID ," = '", device,"'")
-
-  # Letting the user know what we are doing
-  message(paste0("Executing the following query to download data: ", query)) 
-  sensor_data <- dbGetQuery(dbEngine, query)
-  
-  dbDisconnect(dbEngine)
-  
-  if(nrow(sensor_data) == 0)
-    warning(paste("The device '", device,"' did not have data in ", sensor_container))
-
-  return(sensor_data)
-}
-

src/data/streams/aware_micro_mysql/format.yaml

@@ -1,337 +0,0 @@
-PHONE_ACCELEROMETER:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_VALUES_0: double_values_0
-      DOUBLE_VALUES_1: double_values_1
-      DOUBLE_VALUES_2: double_values_2
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_VALUES_0: double_values_0
-      DOUBLE_VALUES_1: double_values_1
-      DOUBLE_VALUES_2: double_values_2
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_ACTIVITY_RECOGNITION:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      ACTIVITY_NAME: activity_name
-      ACTIVITY_TYPE: activity_type
-      CONFIDENCE: confidence
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      ACTIVITY_NAME: FLAG_TO_MUTATE
-      ACTIVITY_TYPE: FLAG_TO_MUTATE
-      CONFIDENCE: FLAG_TO_MUTATE
-    MUTATION:
-      COLUMN_MAPPINGS:
-        ACTIVITIES: activities
-        CONFIDENCE: confidence
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-        - "src/data/streams/mutations/phone/aware/activity_recogniton_ios_unification.R"
-
-PHONE_APPLICATIONS_CRASHES:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      PACKAGE_NAME: package_name
-      APPLICATION_NAME: application_name
-      APPLICATION_VERSION: application_version
-      ERROR_SHORT: error_short
-      ERROR_LONG: error_long
-      ERROR_CONDITION: error_condition
-      IS_SYSTEM_APP: is_system_app
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_APPLICATIONS_FOREGROUND:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      PACKAGE_NAME: package_name
-      APPLICATION_NAME: application_name
-      IS_SYSTEM_APP: is_system_app
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_APPLICATIONS_NOTIFICATIONS:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      PACKAGE_NAME: package_name
-      APPLICATION_NAME: application_name
-      TEXT: text
-      SOUND: sound
-      VIBRATE: vibrate
-      DEFAULTS: defaults
-      FLAGS: flags
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_BATTERY:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      BATTERY_STATUS: battery_status
-      BATTERY_LEVEL: battery_level
-      BATTERY_SCALE: battery_scale
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      BATTERY_STATUS: FLAG_TO_MUTATE
-      BATTERY_LEVEL: battery_level
-      BATTERY_SCALE: battery_scale
-    MUTATION:
-      COLUMN_MAPPINGS:
-        BATTERY_STATUS: battery_status
-      SCRIPTS:
-        - "src/data/streams/mutations/phone/aware/battery_ios_unification.R"
-
-PHONE_BLUETOOTH:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      BT_ADDRESS: bt_address
-      BT_NAME: bt_name
-      BT_RSSI: bt_rssi
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      BT_ADDRESS: bt_address
-      BT_NAME: bt_name
-      BT_RSSI: bt_rssi
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_CALLS:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      CALL_TYPE: call_type
-      CALL_DURATION: call_duration
-      TRACE: trace
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      CALL_TYPE: FLAG_TO_MUTATE
-      CALL_DURATION: call_duration
-      TRACE: trace
-    MUTATION:
-      COLUMN_MAPPINGS:
-        CALL_TYPE: call_type
-      SCRIPTS:
-        - "src/data/streams/mutations/phone/aware/calls_ios_unification.R"
-
-PHONE_CONVERSATION:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_ENERGY: double_energy
-      INFERENCE: inference
-      DOUBLE_CONVO_START: double_convo_start
-      DOUBLE_CONVO_END: double_convo_end
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_ENERGY: double_energy
-      INFERENCE: inference
-      DOUBLE_CONVO_START: double_convo_start
-      DOUBLE_CONVO_END: double_convo_end
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-        - "src/data/streams/mutations/phone/aware/conversation_ios_timestamp.R"
-
-PHONE_KEYBOARD:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      PACKAGE_NAME: package_name
-      BEFORE_TEXT: before_text
-      CURRENT_TEXT: current_text
-      IS_PASSWORD: is_password
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_LIGHT:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_LIGHT_LUX: double_light_lux
-      ACCURACY: accuracy
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_LOCATIONS:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_LATITUDE: double_latitude
-      DOUBLE_LONGITUDE: double_longitude
-      DOUBLE_BEARING: double_bearing
-      DOUBLE_SPEED: double_speed
-      DOUBLE_ALTITUDE: double_altitude
-      PROVIDER: provider
-      ACCURACY: accuracy
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      DOUBLE_LATITUDE: double_latitude
-      DOUBLE_LONGITUDE: double_longitude
-      DOUBLE_BEARING: double_bearing
-      DOUBLE_SPEED: double_speed
-      DOUBLE_ALTITUDE: double_altitude
-      PROVIDER: provider
-      ACCURACY: accuracy
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_LOG:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      LOG_MESSAGE: log_message
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      LOG_MESSAGE: log_message
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_MESSAGES:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      MESSAGE_TYPE: message_type
-      TRACE: trace
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_SCREEN:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SCREEN_STATUS: screen_status
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SCREEN_STATUS: FLAG_TO_MUTATE
-    MUTATION:
-      COLUMN_MAPPINGS:
-        SCREEN_STATUS: screen_status
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-        - "src/data/streams/mutations/phone/aware/screen_ios_unification.R"
-
-PHONE_WIFI_CONNECTED:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      MAC_ADDRESS: mac_address
-      SSID: ssid
-      BSSID: bssid
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      MAC_ADDRESS: mac_address
-      SSID: ssid
-      BSSID: bssid
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-PHONE_WIFI_VISIBLE:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SSID: ssid
-      BSSID: bssid
-      SECURITY: security
-      FREQUENCY: frequency
-      RSSI: rssi
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SSID: ssid
-      BSSID: bssid
-      SECURITY: security
-      FREQUENCY: frequency
-      RSSI: rssi
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-

src/data/streams/aware_postgresql/format.yaml

@@ -349,24 +349,3 @@ PHONE_WIFI_VISIBLE:
       COLUMN_MAPPINGS:
       SCRIPTS: # List any python or r scripts that mutate your raw data
 
-PHONE_SPEECH:
-  ANDROID:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SPEECH_PROPORTION: speech_proportion
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-  IOS:
-    RAPIDS_COLUMN_MAPPINGS:
-      TIMESTAMP: timestamp
-      DEVICE_ID: device_id
-      SPEECH_PROPORTION: speech_proportion
-    MUTATION:
-      COLUMN_MAPPINGS:
-      SCRIPTS: # List any python or r scripts that mutate your raw data
-
-
-      
-

src/data/streams/empatica_zip/container.py

@@ -2,16 +2,11 @@ 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)
@@ -57,8 +52,6 @@ def extract_empatica_data(data,  sensor):
         df = pd.DataFrame.from_dict(ddict, orient='index', columns=[column])
         df[column] = df[column].astype(float)
         df.index.name = 'timestamp'
-        if df.empty:
-            return df
 
     elif sensor == 'EMPATICA_ACCELEROMETER':
         ddict = readFile(sensor_data_file, sensor)
@@ -67,16 +60,9 @@ def extract_empatica_data(data,  sensor):
         df['y'] = df['y'].astype(float)
         df['z'] = df['z'].astype(float)
         df.index.name = 'timestamp'
-        if df.empty:
-            return df
 
     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 = df.drop([0])
@@ -98,10 +84,6 @@ 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))))
@@ -112,13 +94,7 @@ def pull_data(data_configuration, device, sensor, container, columns_to_download
             listOfFileNames = zipFile.namelist()
             for fileName in listOfFileNames:
                 if fileName == sensor_csv:
-                    if sensor == "EMPATICA_INTER_BEAT_INTERVAL" and cr_ibi_provider.get('PATCH_WITH_BVP', False):
+                    participant_data = pd.concat([participant_data, extract_empatica_data(zipFile.read(fileName),  sensor)], axis=0)
-                        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))
@@ -129,54 +105,4 @@ 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, KeyError) 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']
-            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

@@ -50,7 +50,6 @@ 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/mutations/phone/aware/calls_ios_unification.R

@@ -39,7 +39,7 @@ unify_ios_calls <- function(ios_calls){
                         assigned_segments = first(assigned_segments))
         }
         else {
-            ios_calls <- ios_calls %>% summarise(call_type_sequence = paste(call_type, collapse = ","), call_duration = sum(as.numeric(call_duration)),  timestamp = first(timestamp), device_id = first(device_id))
+            ios_calls <- ios_calls %>% summarise(call_type_sequence = paste(call_type, collapse = ","), call_duration = sum(call_duration),  timestamp = first(timestamp), device_id = first(device_id))
         }
         ios_calls <- ios_calls %>% mutate(call_type = case_when(
             call_type_sequence == "1,2,4" | call_type_sequence == "2,1,4" ~ 1, # incoming

src/data/streams/rapids_columns.yaml

@@ -118,11 +118,6 @@ PHONE_SCREEN:
   - DEVICE_ID
   - SCREEN_STATUS
 
-PHONE_SPEECH:
-  - TIMESTAMP
-  - DEVICE_ID
-  - SPEECH_PROPORTION
-
 PHONE_WIFI_CONNECTED:
   - TIMESTAMP
   - DEVICE_ID
@@ -232,7 +227,6 @@ EMPATICA_INTER_BEAT_INTERVAL:
   - TIMESTAMP
   - DEVICE_ID
   - INTER_BEAT_INTERVAL
-  - TIMINGS
 
 EMPATICA_TAGS:
   - TIMESTAMP

src/features/all_cleaning_individual/rapids/main.R

@@ -39,18 +39,16 @@ rapids_cleaning <- function(sensor_data_files, provider){
     if(!data_yield_column %in% colnames(clean_features)){
         stop(paste0("Error: RAPIDS provider needs to clean data based on ", data_yield_column, " column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded", data_yield_unit, "' in [FEATURES]."))
     }
-    if (data_yield_ratio_threshold > 0) {
+    clean_features <- clean_features %>% 
-        clean_features <- clean_features %>% 
         filter(.[[data_yield_column]] >= data_yield_ratio_threshold)
-    }
 
     # Drop columns with a percentage of NA values above cols_nan_threshold
     if(nrow(clean_features))
-        clean_features <- clean_features %>% select(where(~ sum(is.na(.)) / length(.) <= cols_nan_threshold ), starts_with("phone_esm"))
+        clean_features <- clean_features %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
 
     # Drop columns with zero variance
     if(drop_zero_variance_columns)
-    clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime|phone_esm",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
+    clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
 
     # Drop highly correlated features
     if(as.logical(drop_highly_correlated_features$COMPUTE)){

src/features/all_cleaning_individual/straw/main.py

@@ -1,180 +0,0 @@
-import pandas as pd
-import numpy as np
-import math, sys, random
-import yaml
-
-from sklearn.impute import KNNImputer
-from sklearn.preprocessing import StandardScaler
-import matplotlib.pyplot as plt
-import seaborn as sns
-
-sys.path.append('/rapids/')
-from src.features import empatica_data_yield as edy
-
-pd.set_option('display.max_columns', 20)
-
-def straw_cleaning(sensor_data_files, provider):
-    
-    features = pd.read_csv(sensor_data_files["sensor_data"][0])
-    
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns
-
-    with open('config.yaml', 'r') as stream:
-        config = yaml.load(stream, Loader=yaml.FullLoader)
-
-    excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
-
-    # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE
-    if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']:
-        target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config
-        if 'phone_esm_straw_' + target in features:
-            features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
-        else:
-            return features
-
-    # (2.1) QUALITY CHECK (DATA YIELD COLUMN) deletes the rows where E4 or phone data is low quality
-    phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower()
-    phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit
-
-    if features.empty:
-        return features
-
-    features = edy.calculate_empatica_data_yield(features)
-
-    if not phone_data_yield_column in features.columns and not "empatica_data_yield" in features.columns:
-        raise KeyError(f"RAPIDS provider needs to clean the selected event features based on {phone_data_yield_column} and empatica_data_yield columns. For phone data yield, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].")
-        
-    # Drop rows where phone data yield is less then given threshold
-    if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]:
-        features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True)
-    
-    # Drop rows where empatica data yield is less then given threshold
-    if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]:
-        features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True)
-
-    if features.empty:
-        return features
-    
-    # (2.2) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES?
-    min_count =  math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row
-    features.dropna(axis=0, thresh=min_count, inplace=True) # Thresh => at least this many not-nans
-
-    # (3) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows)
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns
-
-    features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]]
-
-    # Preserve esm cols if deleted (has to come after drop cols operations)
-    for esm in esm_cols:
-        if esm not in features:
-            features[esm] = esm_cols[esm]
-
-    # (4) CONTEXTUAL IMPUTATION
-
-    # Impute selected phone features with a high number
-    impute_w_hn = [col for col in features.columns if \
-        "timeoffirstuse" in col or
-        "timeoflastuse" in col or
-        "timefirstcall" in col or
-        "timelastcall" in col or
-        "firstuseafter" in col or
-        "timefirstmessages" in col or
-        "timelastmessages" in col]
-    features[impute_w_hn] = features[impute_w_hn].fillna(1500)
-
-
-    # Impute special case (mostcommonactivity) and (homelabel)
-    impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col]
-    features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value
-
-    impute_w_sn2 = [col for col in features.columns if "homelabel" in col]
-    features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value
-
-    impute_w_sn3 = [col for col in features.columns if "loglocationvariance" in col]
-    features[impute_w_sn2] = features[impute_w_sn2].fillna(-1000000) # Special case of imputation - nominal/ordinal value
-
-
-    # Impute selected phone features with 0
-    impute_zero = [col for col in features if \
-        col.startswith('phone_applications_foreground_rapids_') or
-        col.startswith('phone_battery_rapids_') or
-        col.startswith('phone_bluetooth_rapids_') or
-        col.startswith('phone_light_rapids_') or
-        col.startswith('phone_calls_rapids_') or
-        col.startswith('phone_messages_rapids_') or
-        col.startswith('phone_screen_rapids_') or
-        col.startswith('phone_wifi_visible')]
-
-    features[impute_zero+list(esm_cols.columns)] = features[impute_zero+list(esm_cols.columns)].fillna(0)
-
-    ## (5) STANDARDIZATION 
-    if provider["STANDARDIZATION"]:
-        features.loc[:, ~features.columns.isin(excluded_columns)] = StandardScaler().fit_transform(features.loc[:, ~features.columns.isin(excluded_columns)])
-
-    # (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD
-    impute_cols = [col for col in features.columns if col not in excluded_columns]
-    features.reset_index(drop=True, inplace=True)
-    features[impute_cols] = impute(features[impute_cols], method="knn")
-
-    # (7) REMOVE COLS WHERE VARIANCE IS 0
-    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)
-
-    fe5 = features.copy()
-
-    # (8) DROP HIGHLY CORRELATED FEATURES
-    drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"]
-    if drop_corr_features["COMPUTE"] and features.shape[0]: # If small amount of segments (rows) is present, do not execute correlation check
-        
-        numerical_cols = features.select_dtypes(include=np.number).columns.tolist()
-
-        # Remove columns where NaN count threshold is passed
-        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))
-        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)
-
-    # Preserve esm cols if deleted (has to come after drop cols operations)
-    for esm in esm_cols:
-        if esm not in features:
-            features[esm] = esm_cols[esm]
-
-    # (9) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME
-    if features.isna().any().any():
-        raise ValueError("There are still some NaNs present in the dataframe. Please check for implementation errors.")
-
-    return features
-
-
-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),
-        'mean': df.fillna(df.mean()),
-        'median': df.fillna(df.median()),
-        '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)})
-        sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number)
-        plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight')
-
-    print(f"\n-------------{phase_name}-------------")
-    print("Rows number:", features.shape[0])
-    print("Columns number:", len(features.columns))
-    print("---------------------------------------------\n")

src/features/all_cleaning_overall/rapids/main.R

@@ -39,18 +39,16 @@ rapids_cleaning <- function(sensor_data_files, provider){
     if(!data_yield_column %in% colnames(clean_features)){
         stop(paste0("Error: RAPIDS provider needs to clean data based on ", data_yield_column, " column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded", data_yield_unit, "' in [FEATURES]."))
     }
-    if (data_yield_ratio_threshold > 0) {
+    clean_features <- clean_features %>% 
-        clean_features <- clean_features %>% 
         filter(.[[data_yield_column]] >= data_yield_ratio_threshold)
-    }
 
     # Drop columns with a percentage of NA values above cols_nan_threshold
     if(nrow(clean_features))
-        clean_features <- clean_features %>% select(where(~ sum(is.na(.)) / length(.) <= cols_nan_threshold ), starts_with("phone_esm"))
+        clean_features <- clean_features %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
 
     # Drop columns with zero variance
     if(drop_zero_variance_columns)
-        clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime|phone_esm",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
+    clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
 
     # Drop highly correlated features
     if(as.logical(drop_highly_correlated_features$COMPUTE)){

src/features/all_cleaning_overall/straw/main.py

@@ -1,275 +0,0 @@
-import pandas as pd
-import numpy as np
-import math, sys, random, warnings, yaml
-
-from sklearn.impute import KNNImputer
-from sklearn.preprocessing import StandardScaler, minmax_scale 
-import matplotlib.pyplot as plt
-import seaborn as sns
-
-sys.path.append('/rapids/')
-from src.features import empatica_data_yield as edy
-
-def straw_cleaning(sensor_data_files, provider, target):
-
-    features = pd.read_csv(sensor_data_files["sensor_data"][0])
-
-    with open('config.yaml', 'r') as stream:
-        config = yaml.load(stream, Loader=yaml.FullLoader)
-
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns
-
-    excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
-
-    graph_bf_af(features, "1target_rows_before")
-
-    # (1.0) OVERRIDE STRESSFULNESS EVENT TARGETS IF ERS SEGMENTING_METHOD IS "STRESS_EVENT"
-    if config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["SEGMENTING_METHOD"] == "stress_event": 
-    
-        stress_events_targets = pd.read_csv("data/external/stress_event_targets.csv")   
-
-        if "appraisal_stressfulness_event_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']:
-            features.drop(columns=['phone_esm_straw_appraisal_stressfulness_event_mean'], inplace=True)
-            features = features.merge(stress_events_targets[["label", "appraisal_stressfulness_event"]] \
-                        .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \
-                        .rename(columns={'appraisal_stressfulness_event': 'phone_esm_straw_appraisal_stressfulness_event_mean'})
-
-        if "appraisal_threat_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']:
-            features.drop(columns=['phone_esm_straw_appraisal_threat_mean'], inplace=True)
-            features = features.merge(stress_events_targets[["label", "appraisal_threat"]] \
-                        .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \
-                        .rename(columns={'appraisal_threat': 'phone_esm_straw_appraisal_threat_mean'})
-
-        if "appraisal_challenge_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']:
-            features.drop(columns=['phone_esm_straw_appraisal_challenge_mean'], inplace=True)
-            features = features.merge(stress_events_targets[["label", "appraisal_challenge"]] \
-                        .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \
-                        .rename(columns={'appraisal_challenge': 'phone_esm_straw_appraisal_challenge_mean'})
-
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns
-
-    # (1.1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE
-    if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']:
-        features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
-    
-    if features.empty:
-        return pd.DataFrame(columns=excluded_columns)
-
-    graph_bf_af(features, "2target_rows_after")
-
-    # (2) QUALITY CHECK (DATA YIELD COLUMN) drops the rows where E4 or phone data is low quality
-    phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower()
-    phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit
-
-    features = edy.calculate_empatica_data_yield(features)
-
-    if not phone_data_yield_column in features.columns and not "empatica_data_yield" in features.columns:
-        raise KeyError(f"RAPIDS provider needs to clean the selected event features based on {phone_data_yield_column} and empatica_data_yield columns. For phone data yield, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].")
-
-    hist = features[["empatica_data_yield", phone_data_yield_column]].hist()
-    plt.savefig(f'phone_E4_histogram.png', bbox_inches='tight')
-
-    # Drop rows where phone data yield is less then given threshold
-    if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]:
-        hist = features[phone_data_yield_column].hist(bins=5)
-        plt.close()
-        features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True)
-
-    # Drop rows where empatica data yield is less then given threshold
-    if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]:
-        features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True)
-
-    if features.empty:
-        return pd.DataFrame(columns=excluded_columns)
-
-    graph_bf_af(features, "3data_yield_drop_rows")
-
-    if features.empty:
-        return pd.DataFrame(columns=excluded_columns)
-
-
-    # (3) CONTEXTUAL IMPUTATION
-
-    # Impute selected phone features with a high number
-    impute_w_hn = [col for col in features.columns if \
-        "timeoffirstuse" in col or
-        "timeoflastuse" in col or
-        "timefirstcall" in col or
-        "timelastcall" in col or
-        "firstuseafter" in col or
-        "timefirstmessages" in col or
-        "timelastmessages" in col]
-    features[impute_w_hn] = features[impute_w_hn].fillna(1500)
-
-    # Impute special case (mostcommonactivity) and (homelabel)
-    impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col]
-    features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value
-
-    impute_w_sn2 = [col for col in features.columns if "homelabel" in col]
-    features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value
-
-    impute_w_sn3 = [col for col in features.columns if "loglocationvariance" in col]
-    features[impute_w_sn3] = features[impute_w_sn3].fillna(-1000000) # Special case of imputation - loglocation
-
-    # Impute location features
-    impute_locations = [col for col in features \
-        if col.startswith('phone_locations_doryab_') and
-        'radiusgyration' not in col    
-    ]
-
-    # Impute selected phone, location, and esm features with 0
-    impute_zero = [col for col in features if \
-        col.startswith('phone_applications_foreground_rapids_') or
-        col.startswith('phone_activity_recognition_') or
-        col.startswith('phone_battery_rapids_') or
-        col.startswith('phone_bluetooth_rapids_') or
-        col.startswith('phone_light_rapids_') or
-        col.startswith('phone_calls_rapids_') or
-        col.startswith('phone_messages_rapids_') or
-        col.startswith('phone_screen_rapids_') or
-        col.startswith('phone_bluetooth_doryab_') or
-        col.startswith('phone_wifi_visible')
-        ]
-
-    features[impute_zero+impute_locations+list(esm_cols.columns)] = features[impute_zero+impute_locations+list(esm_cols.columns)].fillna(0)
-
-    pd.set_option('display.max_rows', None)
-
-    graph_bf_af(features, "4context_imp")
- 
-    # (4) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows)
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns
-
-    features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]]
-
-    graph_bf_af(features, "5too_much_nans_cols")
-    # (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)
-
-    graph_bf_af(features, "6variance_drop")
-
-    # Preserve esm cols if deleted (has to come after drop cols operations)
-    for esm in esm_cols:
-        if esm not in features:
-            features[esm] = esm_cols[esm]
-    
-    # (6) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES?
-    min_count =  math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row
-    features.dropna(axis=0, thresh=min_count, inplace=True) # Thresh => at least this many not-nans
-
-    graph_bf_af(features, "7too_much_nans_rows")
-
-    if features.empty:
-        return pd.DataFrame(columns=excluded_columns)
-
-    # (7) STANDARDIZATION
-    if provider["STANDARDIZATION"]:
-        nominal_cols = [col for col in features.columns if "mostcommonactivity" in col or "homelabel" in col] # Excluded nominal features
-        # Expected warning within this code block
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore", category=RuntimeWarning)
-            if provider["TARGET_STANDARDIZATION"]:
-                features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols)] = \
-                    features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols)].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel())
-            else:
-                features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols + ['phone_esm_straw_' + target])] = \
-                    features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols + ['phone_esm_straw_' + target])].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel())
-
-    graph_bf_af(features, "8standardization")
-
-    # (8) IMPUTATION: IMPUTE DATA WITH KNN METHOD
-    features.reset_index(drop=True, inplace=True)
-    impute_cols = [col for col in features.columns if col not in excluded_columns and col != "pid"]
-
-    features[impute_cols] = impute(features[impute_cols], method="knn")
-
-    graph_bf_af(features, "9knn_after")
-
-
-    # (9) DROP HIGHLY CORRELATED FEATURES
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')]
-
-    drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"]
-    if drop_corr_features["COMPUTE"] and features.shape[0] > 5: # If small amount of segments (rows) is present, do not execute correlation check
-        
-        numerical_cols = features.select_dtypes(include=np.number).columns.tolist()
-
-        # Remove columns where NaN count threshold is passed
-        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))
-        to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])]
-
-        # sns.heatmap(corr_matrix, cmap="YlGnBu")
-        # plt.savefig(f'correlation_matrix.png', bbox_inches='tight')
-        # plt.close()
-
-        # s = corr_matrix.unstack()
-        # so = s.sort_values(ascending=False)
-
-        # pd.set_option('display.max_rows', None)
-        # sorted_upper = upper.unstack().sort_values(ascending=False)
-        # print(sorted_upper[sorted_upper > drop_corr_features["CORR_THRESHOLD"]])
-
-        features.drop(to_drop, axis=1, inplace=True)
-
-    # Preserve esm cols if deleted (has to come after drop cols operations)
-    for esm in esm_cols:
-        if esm not in features:
-            features[esm] = esm_cols[esm]
-
-    graph_bf_af(features, "10correlation_drop")
-
-    # Transform categorical columns to category dtype
-
-    cat1 = [col for col in features.columns if "mostcommonactivity" in col]
-    if cat1: # Transform columns to category dtype (mostcommonactivity)
-        features[cat1] = features[cat1].astype(int).astype('category')
-
-    cat2 = [col for col in features.columns if "homelabel" in col]
-    if cat2: # Transform columns to category dtype (homelabel)
-        features[cat2] = features[cat2].astype(int).astype('category')
-
-    # (10) DROP ALL WINDOW RELATED COLUMNS
-    win_count_cols = [col for col in features if "SO_windowsCount" in col]
-    if win_count_cols:
-        features.drop(columns=win_count_cols, inplace=True)
-
-    # (11) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME
-    if features.isna().any().any():
-        raise ValueError("There are still some NaNs present in the dataframe. Please check for implementation errors.")
-
-
-    return features
-
-
-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),
-        'mean': df.fillna(df.mean()),
-        'median': df.fillna(df.median()),
-        '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)})
-        sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number)
-        plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight')
-
-    print(f"\n-------------{phase_name}-------------")
-    print("Rows number:", features.shape[0])
-    print("Columns number:", len(features.columns))
-    print("NaN values:", features.isna().sum().sum())
-    print("---------------------------------------------\n")

src/features/cr_features_helper_methods.py

@@ -1,59 +0,0 @@
-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(numeric_only=True).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)
-        
-        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)
-        
-        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

@@ -1,75 +0,0 @@
-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):
-    
-    data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'double_values_0': 'float64',
-                    'double_values_1': 'float64', 'double_values_2': 'float64', 'local_date_time': 'str', 'local_date': "str",
-                    'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"}
-    acc_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types)    
-
-    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

@@ -1,73 +0,0 @@
-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_data_yield.py

@@ -1,32 +0,0 @@
-import pandas as pd
-import numpy as np
-from datetime import datetime
-
-import sys, yaml
-
-def calculate_empatica_data_yield(features): # TODO
-
-    # Get time segment duration in seconds from all segments in features dataframe
-    datetime_start =  pd.to_datetime(features['local_segment_start_datetime'], format='%Y-%m-%d %H:%M:%S')
-    datetime_end = pd.to_datetime(features['local_segment_end_datetime'], format='%Y-%m-%d %H:%M:%S')
-    tseg_duration = (datetime_end - datetime_start).dt.total_seconds()
-
-    with open('config.yaml', 'r') as stream:
-        config = yaml.load(stream, Loader=yaml.FullLoader)
-        
-    sensors = ["EMPATICA_ACCELEROMETER", "EMPATICA_TEMPERATURE", "EMPATICA_ELECTRODERMAL_ACTIVITY", "EMPATICA_INTER_BEAT_INTERVAL"]
-    for sensor in sensors:
-        features[f"{sensor.lower()}_data_yield"] = \
-            (features[f"{sensor.lower()}_cr_SO_windowsCount"] * config[sensor]["PROVIDERS"]["CR"]["WINDOWS"]["WINDOW_LENGTH"]) / tseg_duration \
-            if f'{sensor.lower()}_cr_SO_windowsCount' in features else 0
-
-    empatica_data_yield_cols = [sensor.lower() + "_data_yield" for sensor in sensors]
-    pd.set_option('display.max_rows', None)
-
-    # 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.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/empatica_electrodermal_activity/cr/main.py

@@ -1,82 +0,0 @@
-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):
-
-    data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'electrodermal_activity': 'float64', 'local_date_time': 'str', 
-                  'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"}
-
-    eda_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types)
-
-    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

@@ -1,83 +0,0 @@
-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):
-
-    data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'inter_beat_interval': 'float64', 'timings': 'float64', 'local_date_time': 'str', 
-                  'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"}
-
-    ibi_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types)
-
-    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

@@ -1,68 +0,0 @@
-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):
-    data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'temperature': 'float64', 'local_date_time': 'str', 
-                'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"}
-
-    temperature_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types)
-
-    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

@@ -1,38 +1,19 @@
 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
-    if "overall" in sensor_key:
+    sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files)
-        sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files, snakemake.params["target"])
-    else:
-        sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files)
 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)
 
-    if calc_windows:
+sensor_features.to_csv(snakemake.output[0], index=False)
-        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/phone_activity_recognition/rapids/main.py

@@ -37,6 +37,6 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se
             ar_features.index.names = ["local_segment"]
             ar_features = ar_features.reset_index()
     
-    ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0, "mostcommonactivity": 4}, inplace=True)
+    ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0}, inplace=True)
 
     return ar_features

src/features/phone_applications_foreground/rapids/main.py

@@ -9,19 +9,19 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features
     if "timeoffirstuse" in requested_features:
         time_first_event = filtered_data.sort_values(by="timestamp", ascending=True).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment")
         if time_first_event.empty:
-            apps_features["timeoffirstuse" + apps_type] = 1500 # np.nan
+            apps_features["timeoffirstuse" + apps_type] = np.nan
         else:
             apps_features["timeoffirstuse" + apps_type] = time_first_event["local_hour"] * 60 + time_first_event["local_minute"]
     if "timeoflastuse" in requested_features:
         time_last_event = filtered_data.sort_values(by="timestamp", ascending=False).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment")
         if time_last_event.empty:
-            apps_features["timeoflastuse" + apps_type] = 1500 # np.nan
+            apps_features["timeoflastuse" + apps_type] = np.nan
         else:
             apps_features["timeoflastuse" + apps_type] = time_last_event["local_hour"] * 60 + time_last_event["local_minute"]
     if "frequencyentropy" in requested_features:
         apps_with_count = filtered_data.groupby(["local_segment","application_name"]).count().sort_values(by="timestamp", ascending=False).reset_index()
         if (len(apps_with_count.index) < 2 ):
-            apps_features["frequencyentropy" + apps_type] = 0 # np.nan
+            apps_features["frequencyentropy" + apps_type] = np.nan
         else:    
             apps_features["frequencyentropy" + apps_type] = apps_with_count.groupby("local_segment")["timestamp"].agg(entropy)
     if "countevent" in requested_features:
@@ -43,7 +43,6 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features
         apps_features["sumduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].sum()
     
     apps_features.index.names = ["local_segment"]
-    
     return apps_features
 
 def process_app_features(data, requested_features, time_segment, provider, filter_data_by_segment):

src/features/phone_bluetooth/doryab/main.py

@@ -15,7 +15,7 @@ def deviceFeatures(devices, ownership, common_devices, features_to_compute, feat
     if "meanscans" in features_to_compute:
         features = features.join(device_value_counts.groupby("local_segment")["scans"].mean().to_frame("meanscans" + ownership), how="outer")
     if "stdscans" in features_to_compute:
-        features = features.join(device_value_counts.groupby("local_segment")["scans"].std().to_frame("stdscans" + ownership).fillna(0), how="outer")
+        features = features.join(device_value_counts.groupby("local_segment")["scans"].std().to_frame("stdscans" + ownership), how="outer")
     # Most frequent device within segments, across segments, and across dataset
     if "countscansmostfrequentdevicewithinsegments" in features_to_compute:
         features = features.join(device_value_counts.groupby("local_segment")["scans"].max().to_frame("countscansmostfrequentdevicewithinsegments" + ownership), how="outer")

src/features/phone_calls/rapids/main.R

@@ -88,16 +88,6 @@ rapids_features <- function(sensor_data_files, time_segment, provider){
         features <- call_features_of_type(calls_of_type, features_type, call_type, time_segment, requested_features)
         call_features <- merge(call_features, features, all=TRUE)
     }
-
+    call_features <- call_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count") | contains("sumduration") | contains("minduration") | contains("maxduration") | contains("meanduration") | contains("modeduration")), list( ~ replace_na(., 0)))
-    # Fill seleted columns with a high number
-    time_cols <- select(call_features, contains("timefirstcall") |  contains("timelastcall")) %>% 
-        colnames(.)
-
-    call_features <- call_features %>% 
-        mutate_at(., time_cols, ~replace(., is.na(.), 1500))
-
-    # Fill NA values with 0
-    call_features <- call_features %>% mutate_all(~replace(., is.na(.), 0))
-
     return(call_features)
 }

src/features/phone_data_yield/rapids/main.R

@@ -3,11 +3,9 @@ library(tidyr)
 library(readr)
 
 compute_data_yield_features <- function(data, feature_name, time_segment, provider){
-  
   data <- data %>% filter_data_by_segment(time_segment)
-  if(nrow(data) == 0){
+  if(nrow(data) == 0)
     return(tibble(local_segment = character(), ratiovalidyieldedminutes = numeric(), ratiovalidyieldedhours = numeric()))
-  }
   features <- data %>%
     separate(timestamps_segment, into = c("start_timestamp", "end_timestamp"), convert = T, sep = ",") %>% 
     mutate(duration_minutes = (end_timestamp - start_timestamp) / 60000,

src/features/phone_esm/straw/esm.py

@@ -1,274 +0,0 @@
-from collections.abc import Collection
-
-import numpy as np
-import pandas as pd
-from pytz import timezone
-import datetime, json
-
-# from config.models import ESM, Participant
-# from features import helper
-
-ESM_STATUS_ANSWERED = 2
-
-GROUP_SESSIONS_BY = ["device_id", "esm_session"] # 'participant_id
-
-SESSION_STATUS_UNANSWERED = "ema_unanswered"
-SESSION_STATUS_DAY_FINISHED = "day_finished"
-SESSION_STATUS_COMPLETE = "ema_completed"
-
-ANSWER_DAY_FINISHED = "DayFinished3421"
-ANSWER_DAY_OFF = "DayOff3421"
-ANSWER_SET_EVENING = "DayFinishedSetEvening"
-
-MAX_MORNING_LENGTH = 3
-# When the participants was not yet at work at the time of the first (morning) EMA,
-# only three items were answered.
-# Two sleep related items and one indicating NOT starting work yet.
-# Daytime EMAs are all longer, in fact they always consist of at least 6 items.
-
-
-TZ_LJ = timezone("Europe/Ljubljana")
-COLUMN_TIMESTAMP = "timestamp"
-COLUMN_TIMESTAMP_ESM = "double_esm_user_answer_timestamp"
-
-
-def get_date_from_timestamp(df_aware) -> pd.DataFrame:
-    """
-    Transform a UNIX timestamp into a datetime (with Ljubljana timezone).
-    Additionally, extract only the date part, where anything until 4 AM is considered the same day.
-
-    Parameters
-    ----------
-    df_aware: pd.DataFrame
-        Any AWARE-type data as defined in models.py.
-
-    Returns
-    -------
-    df_aware: pd.DataFrame
-        The same dataframe with datetime_lj and date_lj columns added.
-
-    """
-    if COLUMN_TIMESTAMP_ESM in df_aware:
-        column_timestamp = COLUMN_TIMESTAMP_ESM
-    else:
-        column_timestamp = COLUMN_TIMESTAMP
-
-    df_aware["datetime_lj"] = df_aware[column_timestamp].apply(
-        lambda x: datetime.datetime.fromtimestamp(x / 1000.0, tz=TZ_LJ)
-    )
-    df_aware = df_aware.assign(
-        date_lj=lambda x: (x.datetime_lj - datetime.timedelta(hours=4)).dt.date
-    )
-    # Since daytime EMAs could *theoretically* last beyond midnight, but never after 4 AM,
-    # the datetime is first translated to 4 h earlier.
-
-    return df_aware
-
-
-def preprocess_esm(df_esm: pd.DataFrame) -> pd.DataFrame:
-    """
-    Convert timestamps into human-readable datetimes and dates
-    and expand the JSON column into several Pandas DF columns.
-
-    Parameters
-    ----------
-    df_esm: pd.DataFrame
-        A dataframe of esm data.
-
-    Returns
-    -------
-    df_esm_preprocessed: pd.DataFrame
-        A dataframe with added columns: datetime in Ljubljana timezone and all fields from ESM_JSON column.
-    """
-    df_esm = get_date_from_timestamp(df_esm)
-
-    df_esm_json = df_esm["esm_json"].apply(json.loads)
-    df_esm_json = pd.json_normalize(df_esm_json).drop(
-        columns=["esm_trigger"]
-    )  # The esm_trigger column is already present in the main df.
-    return df_esm.join(df_esm_json)
-
-
-def classify_sessions_by_completion(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame:
-    """
-    For each distinct EMA session, determine how the participant responded to it.
-    Possible outcomes are: SESSION_STATUS_UNANSWERED, SESSION_STATUS_DAY_FINISHED, and SESSION_STATUS_COMPLETE
-
-    This is done in three steps.
-
-    First, the esm_status is considered.
-    If any of the ESMs in a session has a status *other than* "answered", then this session is taken as unfinished.
-
-    Second, the sessions which do not represent full questionnaires are identified.
-    These are sessions where participants only marked they are finished with the day or have not yet started working.
-
-    Third, the sessions with only one item are marked with their trigger.
-    We never offered questionnaires with single items, so we can be sure these are unfinished.
-
-    Finally, all sessions that remain are marked as completed.
-    By going through different possibilities in expl_esm_adherence.ipynb, this turned out to be a reasonable option.
-
-    Parameters
-    ----------
-    df_esm_preprocessed: pd.DataFrame
-        A preprocessed dataframe of esm data, which must include the session ID (esm_session).
-
-    Returns
-    -------
-    df_session_counts: pd.Dataframe
-        A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with their statuses and the number of items.
-    """
-    sessions_grouped = df_esm_preprocessed.groupby(GROUP_SESSIONS_BY)
-
-    # 0. First, assign all session statuses as NaN.
-    df_session_counts = pd.DataFrame(sessions_grouped.count()["timestamp"]).rename(
-        columns={"timestamp": "esm_session_count"}
-    )
-    df_session_counts["session_response"] = np.nan
-
-    # 1. Identify all ESMs with status other than answered.
-    esm_not_answered = sessions_grouped.apply(
-        lambda x: (x.esm_status != ESM_STATUS_ANSWERED).any()
-    )
-    df_session_counts.loc[
-        esm_not_answered, "session_response"
-    ] = SESSION_STATUS_UNANSWERED
-
-    # 2. Identify non-sessions, i.e. answers about the end of the day.
-    non_session = sessions_grouped.apply(
-        lambda x: (
-            (x.esm_user_answer == ANSWER_DAY_FINISHED)  # I finished working for today.
-            | (x.esm_user_answer == ANSWER_DAY_OFF)  # I am not going to work today.
-            | (
-                x.esm_user_answer == ANSWER_SET_EVENING
-            )  # When would you like to answer the evening EMA?
-        ).any()
-    )
-    df_session_counts.loc[non_session, "session_response"] = SESSION_STATUS_DAY_FINISHED
-
-    # 3. Identify sessions appearing only once, as those were not true EMAs for sure.
-    singleton_sessions = (df_session_counts.esm_session_count == 1) & (
-        df_session_counts.session_response.isna()
-    )
-    df_session_1 = df_session_counts[singleton_sessions]
-    df_esm_unique_session = df_session_1.join(
-        df_esm_preprocessed.set_index(GROUP_SESSIONS_BY), how="left"
-    )
-    df_esm_unique_session = df_esm_unique_session.assign(
-        session_response=lambda x: x.esm_trigger
-    )["session_response"]
-    df_session_counts.loc[
-        df_esm_unique_session.index, "session_response"
-    ] = df_esm_unique_session
-
-    # 4. Mark the remaining sessions as completed.
-    df_session_counts.loc[
-        df_session_counts.session_response.isna(), "session_response"
-    ] = SESSION_STATUS_COMPLETE
-
-    return df_session_counts
-
-
-def classify_sessions_by_time(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame:
-    """
-    For each EMA session, determine the time of the first user answer and its time type (morning, workday, or evening.)
-
-    Parameters
-    ----------
-    df_esm_preprocessed: pd.DataFrame
-        A preprocessed dataframe of esm data, which must include the session ID (esm_session).
-
-    Returns
-    -------
-    df_session_time: pd.DataFrame
-        A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with their time type and timestamp of first answer.
-    """
-    df_session_time = (
-        df_esm_preprocessed.sort_values(["datetime_lj"]) # "participant_id"
-        .groupby(GROUP_SESSIONS_BY)
-        .first()[["time", "datetime_lj"]]
-    )
-    return df_session_time
-
-
-def classify_sessions_by_completion_time(
-    df_esm_preprocessed: pd.DataFrame,
-) -> pd.DataFrame:
-    """
-    The point of this function is to not only classify sessions by using the previously defined functions.
-    It also serves to "correct" the time type of some EMA sessions.
-
-    A morning questionnaire could seamlessly transition into a daytime questionnaire,
-        if the participant was already at work.
-    In this case, the "time" label changed mid-session.
-    Because of the way classify_sessions_by_time works, this questionnaire was classified as "morning".
-    But for all intents and purposes, it can be treated as a "daytime" EMA.
-
-    The way this scenario is differentiated from a true "morning" questionnaire,
-        where the participants NOT yet at work, is by considering their length.
-
-    Parameters
-    ----------
-    df_esm_preprocessed: pd.DataFrame
-        A preprocessed dataframe of esm data, which must include the session ID (esm_session).
-
-    Returns
-    -------
-    df_session_counts_time: pd.DataFrame
-        A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with statuses, the number of items,
-            their time type (with some morning EMAs reclassified) and timestamp of first answer.
-
-    """
-    df_session_counts = classify_sessions_by_completion(df_esm_preprocessed)
-    df_session_time = classify_sessions_by_time(df_esm_preprocessed)
-
-    df_session_counts_time = df_session_time.join(df_session_counts)
-
-    morning_transition_to_daytime = (df_session_counts_time.time == "morning") & (
-        df_session_counts_time.esm_session_count > MAX_MORNING_LENGTH
-    )
-
-    df_session_counts_time.loc[morning_transition_to_daytime, "time"] = "daytime"
-
-    return df_session_counts_time
-
-
-# def clean_up_esm(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame:
-#     """
-#     This function eliminates invalid ESM responses.
-#     It removes unanswered ESMs and those that indicate end of work and similar.
-#     It also extracts a numeric answer from strings such as "4 - I strongly agree".
-
-#     Parameters
-#     ----------
-#     df_esm_preprocessed: pd.DataFrame
-#         A preprocessed dataframe of esm data.
-
-#     Returns
-#     -------
-#     df_esm_clean: pd.DataFrame
-#         A subset of the original dataframe.
-
-#     """
-#     df_esm_clean = df_esm_preprocessed[
-#         df_esm_preprocessed["esm_status"] == ESM_STATUS_ANSWERED
-#     ]
-#     df_esm_clean = df_esm_clean[
-#         ~df_esm_clean["esm_user_answer"].isin(
-#             [ANSWER_DAY_FINISHED, ANSWER_DAY_OFF, ANSWER_SET_EVENING]
-#         )
-#     ]
-#     df_esm_clean["esm_user_answer_numeric"] = np.nan
-#     esm_type_numeric = [
-#         ESM.ESM_TYPE.get("radio"),
-#         ESM.ESM_TYPE.get("scale"),
-#         ESM.ESM_TYPE.get("number"),
-#     ]
-#     df_esm_clean.loc[
-#         df_esm_clean["esm_type"].isin(esm_type_numeric)
-#     ] = df_esm_clean.loc[df_esm_clean["esm_type"].isin(esm_type_numeric)].assign(
-#         esm_user_answer_numeric=lambda x: x.esm_user_answer.str.slice(stop=1).astype(
-#             int
-#         )
-#     )
-#     return df_esm_clean

src/features/phone_esm/straw/main.py

@@ -42,8 +42,7 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
     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", 
+    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"]
     #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))
@@ -53,6 +52,7 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
 
         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
@@ -60,7 +60,4 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
                 #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
 
             esm_features = esm_features.reset_index()
-            if 'index' in esm_features: # In calse of empty esm_features df 
-                esm_features.rename(columns={'index': 'local_segment'}, inplace=True)
-
     return esm_features

src/features/phone_esm/straw/process_user_event_related_segments.py

@@ -1,260 +0,0 @@
-import pandas as pd
-import numpy as np
-import datetime
-
-import math, sys, yaml
-
-from esm_preprocess import clean_up_esm
-from esm import classify_sessions_by_completion_time, preprocess_esm
-
-input_data_files = dict(snakemake.input)
-
-def format_timestamp(x):
-    """This method formates inputed timestamp into format "HH MM SS". Including spaces. If there is no hours or minutes present
-    that part is ignored, e.g., "MM SS" or just "SS". 
-
-    Args:
-        x (int): unix timestamp in seconds
-
-    Returns:
-        str: formatted timestamp using "HH MM SS" sintax
-    """
-    tstring=""
-    space = False
-    if x//3600 > 0:
-        tstring += f"{x//3600}H"
-        space = True
-    if x % 3600 // 60 > 0:
-        tstring += f" {x % 3600 // 60}M" if "H" in tstring else f"{x % 3600 // 60}M"
-    if x % 60 > 0:  
-        tstring += f" {x % 60}S" if "M" in tstring or "H" in tstring else f"{x % 60}S"
-    
-    return tstring
-
-
-def extract_ers(esm_df):
-    """This method has two major functionalities: 
-        (1) It prepares STRAW event-related segments file with the use of esm file. The execution protocol is depended on 
-            the segmenting method specified in the config.yaml file.
-        (2) It prepares and writes csv with targets and corresponding time segments labels. This is later used 
-            in the overall cleaning script (straw).
-    
-    Details about each segmenting method are listed below by each corresponding condition. Refer to the RAPIDS documentation for the 
-    ERS file format: https://www.rapids.science/1.9/setup/configuration/#time-segments -> event segments
-
-    Args:
-        esm_df (DataFrame): read esm file that is dependend on the current participant.
-
-    Returns:
-        extracted_ers (DataFrame): dataframe with all necessary information to write event-related segments file 
-        in the correct format.
-    """
-
-    pd.set_option("display.max_rows", 100)
-    pd.set_option("display.max_columns", None)
-
-    with open('config.yaml', 'r') as stream:
-        config = yaml.load(stream, Loader=yaml.FullLoader)
-
-    pd.DataFrame(columns=["label"]).to_csv(snakemake.output[1]) # Create an empty stress_events_targets file 
-
-    esm_preprocessed = clean_up_esm(preprocess_esm(esm_df))
-
-    # Take only ema_completed sessions responses
-    classified = classify_sessions_by_completion_time(esm_preprocessed)
-    esm_filtered_sessions = classified[classified["session_response"] == 'ema_completed'].reset_index()[['device_id', 'esm_session']]
-    esm_df = esm_preprocessed.loc[(esm_preprocessed['device_id'].isin(esm_filtered_sessions['device_id'])) & (esm_preprocessed['esm_session'].isin(esm_filtered_sessions['esm_session']))]
-    
-    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
-        """ '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.
-        """
-        # Extract time-relevant information
-        extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # questionnaire length
-        extracted_ers["label"] = f"straw_event_{segmenting_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3) 
-        extracted_ers[['event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].min().reset_index()[['timestamp', 'device_id']]
-        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":
-            """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.
-            """
-            time_before_questionnaire = 30 * 60 # in seconds (30 minutes)
-
-            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 == "90_before":
-            """The method 90-minutes before has an important condition. If the time between the current and the previous questionnaire is
-            longer then 90 minutes it takes 90 minutes, otherwise it takes the original time difference between the questionnaires.
-            """
-            time_before_questionnaire = 90 * 60 # in seconds (90 minutes)
-
-            extracted_ers[['end_event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].max().reset_index()[['timestamp', 'device_id']]
-
-            extracted_ers['diffs'] = extracted_ers['event_timestamp'].astype('int64') - extracted_ers['end_event_timestamp'].shift(1, fill_value=0).astype('int64')
-            extracted_ers.loc[extracted_ers['diffs'] > time_before_questionnaire * 1000, 'diffs'] = time_before_questionnaire * 1000
-            
-            extracted_ers["diffs"] = (extracted_ers["diffs"] / 1000).apply(lambda x: math.ceil(x))
-
-            extracted_ers["length"] = (extracted_ers["timestamp"] + extracted_ers["diffs"]).apply(lambda x: format_timestamp(x))
-            extracted_ers["shift"] = extracted_ers["diffs"].apply(lambda x: format_timestamp(x))
-
-    elif segmenting_method == "stress_event":
-        """
-        TODO: update documentation for this condition
-        This is a special case of the method as it consists of two important parts:
-            (1) Generating of the ERS file (same as the methods above) and
-            (2) Generating targets file alongside with the correct time segment labels.
-        
-        This extracts event-related segments, depended on the event time and duration specified by the participant in the next
-        questionnaire. Additionally, 5 minutes before the specified start time of this event is taken to take into a account the 
-        possiblity of the participant not remembering the start time percisely => this parameter can be manipulated with the variable
-        "time_before_event" which is defined below. 
-        
-        In case if the participant marked that no stressful event happened, the default of 30 minutes before the event is choosen. 
-        In this case, se_threat and se_challenge are NaN.
-        
-        By default, this method also excludes all events that are longer then 2.5 hours so that the segments are easily comparable. 
-        """
-
-        ioi = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["INTERVAL_OF_INTEREST"] * 60 # interval of interest in seconds
-        ioi_error_tolerance = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["IOI_ERROR_TOLERANCE"]  * 60 # interval of interest error tolerance in seconds 
-
-        # Get and join required data
-        extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index().rename(columns={'timestamp': 'session_length'}) # questionnaire length
-        extracted_ers = extracted_ers[extracted_ers["session_length"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire answering is 15 min
-        session_start_timestamp = esm_df.groupby(['device_id', 'esm_session'])['timestamp'].min().to_frame().rename(columns={'timestamp': 'session_start_timestamp'}) # questionnaire start timestamp
-        session_end_timestamp = esm_df.groupby(['device_id', 'esm_session'])['timestamp'].max().to_frame().rename(columns={'timestamp': 'session_end_timestamp'}) # questionnaire end timestamp
-        
-        # Users' answers for the stressfulness event (se) start times and durations 
-        se_time = esm_df[esm_df.questionnaire_id == 90.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_time'})
-        se_duration = esm_df[esm_df.questionnaire_id == 91.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_duration'})
-
-        # Make se_durations to the appropriate lengths
-
-        # 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_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'})
-
-        # 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') \
-                                     .join(session_end_timestamp, on=['device_id', 'esm_session'], how='inner') \
-                                     .join(se_stressfulness_event_tg, on=['device_id', 'esm_session'], how='inner') \
-                                     .join(se_time, on=['device_id', 'esm_session'], how='left') \
-                                     .join(se_duration, on=['device_id', 'esm_session'], how='left') \
-                                     .join(se_threat_tg, on=['device_id', 'esm_session'], how='left') \
-                                     .join(se_challenge_tg, on=['device_id', 'esm_session'], how='left')
-
-        # Filter-out the sessions that are not useful. Because of the ambiguity this excludes: 
-        # (1) straw event times that are marked as "0 - I don't remember"
-        extracted_ers = extracted_ers[~extracted_ers.se_time.astype(str).str.startswith("0 - ")]
-        extracted_ers.reset_index(drop=True, inplace=True)
-
-        extracted_ers.loc[extracted_ers.se_duration.astype(str).str.startswith("0 - "), 'se_duration'] = 0
-
-        # Add default duration in case if participant answered that no stressful event occured
-        extracted_ers["se_duration"] = extracted_ers["se_duration"].fillna(int((ioi + 2*ioi_error_tolerance) * 1000))
-
-        # Prepare data to fit the data structure in the CSV file ...
-        # Add the event time as the end of the questionnaire if no stress event occured
-        extracted_ers['se_time'] = extracted_ers['se_time'].fillna(extracted_ers['session_start_timestamp'])
-        # Type could be an int (timestamp [ms]) which stays the same, and datetime str which is converted to timestamp in miliseconds 
-        extracted_ers['event_timestamp'] = extracted_ers['se_time'].apply(lambda x: x if isinstance(x, int) else pd.to_datetime(x).timestamp() * 1000).astype('int64')
-        extracted_ers['shift_direction'] = -1
-
-        """>>>>> begin section (could be optimized) <<<<<"""
-
-        # Checks whether the duration is marked with "1 - It's still ongoing" which means that the end of the current questionnaire
-        # is taken as end time of the segment. Else the user input duration is taken. 
-        extracted_ers['se_duration'] = \
-            np.where(
-                extracted_ers['se_duration'].astype(str).str.startswith("1 - "),
-                extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'], 
-                extracted_ers['se_duration']
-            )
-
-        # This converts the rows of timestamps in miliseconds and the rows with datetime... to timestamp in seconds.
-        extracted_ers['se_duration'] = \
-            extracted_ers['se_duration'].apply(lambda x: math.ceil(x / 1000) if isinstance(x, int) else (pd.to_datetime(x).hour * 60 + pd.to_datetime(x).minute) * 60)
-
-        # Check explicitley whether min duration is at least 0. This will eliminate rows that would be investigated after the end of the questionnaire.
-        extracted_ers = extracted_ers[extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'] >= 0]
-        # Double check whether min se_duration is at least 0. Filter-out the rest. Negative values are considered invalid.
-        extracted_ers = extracted_ers[extracted_ers["se_duration"] >= 0].reset_index(drop=True)
-
-        """>>>>> end section <<<<<"""
-
-        # Simply override all durations to be of an equal amount
-        extracted_ers['se_duration'] = ioi + 2*ioi_error_tolerance 
-
-        # If target is 0 then shift by the total stress event duration, otherwise shift it by ioi_tolerance
-        extracted_ers['shift'] = \
-            np.where(
-                extracted_ers['appraisal_stressfulness_event'] == 0,
-                extracted_ers['se_duration'], 
-                ioi_error_tolerance
-            )
-
-        extracted_ers['shift'] = extracted_ers['shift'].apply(lambda x: format_timestamp(int(x)))
-        extracted_ers['length'] = extracted_ers['se_duration'].apply(lambda x: format_timestamp(int(x)))
-
-        # Drop event_timestamp duplicates in case in the user is referencing the same event over multiple questionnaires
-        extracted_ers.drop_duplicates(subset=["event_timestamp"], keep='first', inplace=True)
-        extracted_ers.reset_index(drop=True, inplace=True)
-
-        extracted_ers["label"] = f"straw_event_{segmenting_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
-
-        # Write the csv of extracted ERS labels with targets related to stressfulness event   
-        extracted_ers[["label", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]].to_csv(snakemake.output[1], index=False)
-        
-    else:
-        raise Exception("Please select correct target method for the event-related segments.")
-        extracted_ers = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"])
-
-    return extracted_ers[["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]]
-
-
-"""
-Here the code is executed - this .py file is used both for extraction of the STRAW time_segments file for the individual
-participant, and also for merging all participant's files into one combined file which is later used for the time segments 
-to all sensors assignment.
-
-There are two files involved (see rules extract_event_information_from_esm and merge_event_related_segments_files in preprocessing.smk)
-(1) ERS file which contains all the information about the time segment timings and
-(2) targets file which has corresponding target value for the segment label which is later used to merge with other features in the cleaning script.
-For more information, see the comment in the method above.
-"""
-if snakemake.params["stage"] == "extract": 
-    esm_df = pd.read_csv(input_data_files['esm_raw_input'])
-
-    extracted_ers = extract_ers(esm_df)
-
-    extracted_ers.to_csv(snakemake.output[0], index=False)
-
-elif snakemake.params["stage"] == "merge":
-
-    input_data_files = dict(snakemake.input)
-    straw_events = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"])
-    stress_events_targets = pd.DataFrame(columns=["label", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"])
-
-    for input_file in input_data_files["ers_files"]:
-        ers_df = pd.read_csv(input_file)
-        straw_events = pd.concat([straw_events, ers_df], axis=0, ignore_index=True)
-
-    straw_events.to_csv(snakemake.output[0], index=False)
-
-    for input_file in input_data_files["se_files"]:
-        se_df = pd.read_csv(input_file)
-        stress_events_targets = pd.concat([stress_events_targets, se_df], axis=0, ignore_index=True)
-
-    stress_events_targets.to_csv(snakemake.output[1], index=False)
-
-
-

src/features/phone_light/rapids/main.py

@@ -29,7 +29,7 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se
             if "medianlux" in features_to_compute:
                 light_features["medianlux"] = light_data.groupby(["local_segment"])["double_light_lux"].median()
             if "stdlux" in features_to_compute:
-                light_features["stdlux"] = light_data.groupby(["local_segment"])["double_light_lux"].std().fillna(0)
+                light_features["stdlux"] = light_data.groupby(["local_segment"])["double_light_lux"].std()
             
             light_features = light_features.reset_index()
 

src/features/phone_locations/barnett/daily_features.R

@@ -26,10 +26,8 @@ barnett_daily_features <- function(snakemake){
   location <- location %>% 
     mutate(is_daily = str_detect(assigned_segments, paste0(".*#", datetime_start_regex, ",", datetime_end_regex, ".*")))
   
-  does_not_span = nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)
+  if(nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)){
-
+    warning("Barnett's location features cannot be computed for data or time segments that do not span one or more entire days (00:00:00 to 23:59:59). Values below point to the problem:",
-  if(is.na(does_not_span) || does_not_span){
-      warning("Barnett's location features cannot be computed for data or time segments that do not span one or more entire days (00:00:00 to 23:59:59). Values below point to the problem:",
             "\nLocation data rows within a daily time segment: ", nrow(filter(location, is_daily)),
             "\nLocation data time span in days: ", round((max(location$timestamp) - min(location$timestamp)) / 86400000, 2)
             )

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/phone_locations/doryab/main.py

@@ -37,8 +37,7 @@ def variance_and_logvariance_features(location_data, location_features):
     location_data["longitude_for_wvar"] = (location_data["double_longitude"] - location_data["longitude_wavg"]) ** 2 * location_data["duration"] * 60
 
     location_features["locationvariance"] = ((location_data_grouped["latitude_for_wvar"].sum() + location_data_grouped["longitude_for_wvar"].sum()) / (location_data_grouped["duration"].sum() * 60 - 1)).fillna(0)
-    
+    location_features["loglocationvariance"] = np.log10(location_features["locationvariance"]).replace(-np.inf, np.nan)
-    location_features["loglocationvariance"] = np.log10(location_features["locationvariance"]).replace(-np.inf, -1000000)
 
     return location_features
 

src/features/phone_messages/rapids/main.R

@@ -65,15 +65,6 @@ rapids_features <- function(sensor_data_files, time_segment, provider){
         features <- message_features_of_type(messages_of_type, message_type, time_segment, requested_features)
         messages_features <- merge(messages_features, features, all=TRUE)
     }
-    # Fill seleted columns with a high number
+    messages_features <- messages_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count")), list( ~ replace_na(., 0)))
-    time_cols <- select(messages_features, contains("timefirstmessages") |  contains("timelastmessages")) %>% 
-    colnames(.)
-
-    messages_features <- messages_features %>% 
-        mutate_at(., time_cols, ~replace(., is.na(.), 1500))
-    
-    # Fill NA values with 0
-    messages_features <- messages_features %>% mutate_all(~replace(., is.na(.), 0))
-    
     return(messages_features)
 }

src/features/phone_screen/rapids/main.py

@@ -15,7 +15,7 @@ def getEpisodeDurationFeatures(screen_data, time_segment, episode, features, ref
     if "avgduration" in features:
         duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].mean().rename(columns = {"duration":"avgduration" + episode})], axis = 1)
     if "stdduration" in features:
-        duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].std().fillna(0).rename(columns = {"duration":"stdduration" + episode})], axis = 1)
+        duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].std().rename(columns = {"duration":"stdduration" + episode})], axis = 1)
     if "firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) in features:
         screen_data_episode_after_hour = screen_data_episode.copy()
         screen_data_episode_after_hour["hour"] = pd.to_datetime(screen_data_episode["local_start_date_time"]).dt.hour

src/features/phone_speech/straw/main.py

@@ -1,30 +0,0 @@
-import pandas as pd
-
-
-def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
-    speech_data = pd.read_csv(sensor_data_files["sensor_data"])
-    requested_features = provider["FEATURES"]
-    # name of the features this function can compute+
-    base_features_names = ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
-    features_to_compute = list(set(requested_features) & set(base_features_names))
-    speech_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
-    
-    if not speech_data.empty:
-        speech_data = filter_data_by_segment(speech_data, time_segment)
-
-        if not speech_data.empty:
-            speech_features = pd.DataFrame()
-            if "meanspeech" in features_to_compute:
-                speech_features["meanspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].mean()
-            if "stdspeech" in features_to_compute:
-                speech_features["stdspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].std()
-            if "nlargest" in features_to_compute:
-                speech_features["nlargest"] = speech_data.groupby(["local_segment"])['speech_proportion'].apply(lambda x: x.nlargest(5).mean())
-            if "nsmallest" in features_to_compute:
-                speech_features["nsmallest"] = speech_data.groupby(["local_segment"])['speech_proportion'].apply(lambda x: x.nsmallest(5).mean())
-            if "medianspeech" in features_to_compute:
-                speech_features["medianspeech"] = speech_data.groupby(["local_segment"])['speech_proportion'].median()
-            
-            speech_features = speech_features.reset_index()
-
-    return speech_features

src/features/phone_wifi_visible/rapids/main.R

@@ -9,26 +9,21 @@ compute_wifi_feature <- function(data, feature, time_segment){
               "countscans" = data %>% summarise(!!feature := n()),
               "uniquedevices" = data %>% summarise(!!feature := n_distinct(bssid)))
     return(data)
-
    } else if(feature == "countscansmostuniquedevice"){
      # Get the most scanned device
     mostuniquedevice <- data %>% 
-      filter(bssid != "") %>% 
       group_by(bssid) %>% 
       mutate(N=n()) %>% 
       ungroup() %>%
       filter(N == max(N)) %>% 
       head(1) %>% # if there are multiple device with the same amount of scans pick the first one only
       pull(bssid)
-
     data <- data %>% filter_data_by_segment(time_segment)
-
     return(data %>% 
              filter(bssid == mostuniquedevice) %>%
              group_by(local_segment) %>% 
-             summarise(!!feature := n())
+             summarise(!!feature := n()) %>%
-    )
+             replace(is.na(.), 0))
-
   }
 }
 
@@ -48,6 +43,6 @@ rapids_features <- function(sensor_data_files, time_segment, provider){
     feature <- compute_wifi_feature(wifi_data, feature_name, time_segment)
     features <- merge(features, feature, by="local_segment", all = TRUE)
   }
-  features <- features %>% mutate_all(~replace(., is.na(.), 0))
+
   return(features)
 }

src/features/utils/merge_standardized_sensor_features_for_all_participants.R

@@ -1,17 +0,0 @@
-source("renv/activate.R")
-
-library(tidyr)
-library(purrr)
-library("dplyr", warn.conflicts = F)
-library(stringr)
-
-feature_files  <- snakemake@input[["feature_files"]]
-
-
-features_of_all_participants <- tibble(filename = feature_files) %>% # create a data frame
-  mutate(file_contents = map(filename, ~ read.csv(., stringsAsFactors = F, colClasses = c(local_segment = "character", local_segment_label = "character", local_segment_start_datetime="character", local_segment_end_datetime="character"))),
-         pid = str_match(filename, ".*/(.*)/z_all_sensor_features.csv")[,2]) %>%
-  unnest(cols = c(file_contents)) %>%
-  select(-filename)
-
-write.csv(features_of_all_participants, snakemake@output[[1]], row.names = FALSE)

src/features/utils/utils.py

@@ -88,13 +88,11 @@ def chunk_episodes(sensor_episodes):
 
     return merged_sensor_episodes
 
-def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file, calc_windows=False):
+def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_files, time_segments_file):
     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()))
@@ -108,68 +106,30 @@ 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)
-            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)
+            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.)")
-            # In case of calc_window = True
+            features.columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features.columns]
-            if isinstance(features, tuple):
+            sensor_features = pd.concat([sensor_features, features], axis=0, sort=False)
-                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', '')
+    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]])
 
-    if calc_windows:
+    return sensor_features
-        segment_colums = pd.DataFrame()
-        sensor_fo_features['local_segment'] = sensor_fo_features['local_segment'].str.replace(r'_RR\d+SS', '')
-        split_segemnt_columns = sensor_fo_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_fo_features.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
 
-        segment_colums = pd.DataFrame()
+def run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files):
-        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_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, target=False):
     from importlib import import_module, util
     print("{} Processing {} {}".format(rapids_log_tag, sensor_key, provider_key))
 
     cleaning_module = import_path(provider["SRC_SCRIPT"])
     cleaning_function = getattr(cleaning_module,  provider_key.lower() + "_cleaning")
-
+    sensor_features = cleaning_function(sensor_data_files, provider)
-    if target:
-        sensor_features = cleaning_function(sensor_data_files, provider, target)
-    else:
-        sensor_features = cleaning_function(sensor_data_files, provider)
 
     return sensor_features

src/models/helper.py

@@ -1,19 +0,0 @@
-import pandas as pd
-import sys
-import warnings
-
-def retain_target_column(df_input: pd.DataFrame, target_variable_name: str):
-    column_names = df_input.columns
-    esm_names_index = column_names.str.startswith("phone_esm_straw")
-    # Find all columns coming from phone_esm, since these are not features for our purposes and we will drop them.
-    esm_names = column_names[esm_names_index]
-    target_variable_index = esm_names.str.contains(target_variable_name)
-    if all(~target_variable_index):
-        warnings.warn(f"The requested target (, {target_variable_name} ,)cannot be found in the dataset. Please check the names of phone_esm_ columns in cleaned python file")
-        return None
-
-    sensor_features_plus_target = df_input.drop(esm_names, axis=1)
-    sensor_features_plus_target["target"] = df_input[esm_names[target_variable_index]]
-    # We will only keep one column related to phone_esm and that will be our target variable.
-    # Add it back to the very and of the data frame and rename it to target.
-    return sensor_features_plus_target

src/models/merge_features_and_targets_for_population_model.py

@@ -1,24 +0,0 @@
-import pandas as pd
-
-from helper import retain_target_column
-
-sensor_features = pd.read_csv(snakemake.input["cleaned_sensor_features"])
-
-all_baseline_features = pd.DataFrame()
-for baseline_features_path in snakemake.input["demographic_features"]:
-    pid = baseline_features_path.split("/")[3]
-    baseline_features = pd.read_csv(baseline_features_path)
-    baseline_features = baseline_features.assign(pid=pid)
-    all_baseline_features = pd.concat([all_baseline_features, baseline_features], axis=0)
-
-# merge sensor features and baseline features
-if not sensor_features.empty:
-    features = sensor_features.merge(all_baseline_features, on="pid", how="left")
-
-    target_variable_name = snakemake.params["target_variable"]
-    model_input = retain_target_column(features, target_variable_name)
-
-    model_input.to_csv(snakemake.output[0], index=False)
-    
-else:
-    sensor_features.to_csv(snakemake.output[0], index=False)

src/models/select_targets.py

@@ -1,13 +0,0 @@
-import pandas as pd
-
-from helper import retain_target_column
-
-cleaned_sensor_features = pd.read_csv(snakemake.input["cleaned_sensor_features"])
-target_variable_name = snakemake.params["target_variable"]
-
-model_input = retain_target_column(cleaned_sensor_features, target_variable_name)
-
-if model_input is None:
-    pd.DataFrame().to_csv(snakemake.output[0])
-else:
-    model_input.to_csv(snakemake.output[0], index=False)

src/visualization/heatmap_sensors_per_minute_per_time_segment.py

@@ -24,12 +24,12 @@ def colors2colorscale(colors):
 def getDataForPlot(phone_data_yield_per_segment):
     # calculate the length (in minute) of per segment instance
     phone_data_yield_per_segment["length"] = phone_data_yield_per_segment["timestamps_segment"].str.split(",").apply(lambda x: int((int(x[1])-int(x[0])) / (1000 * 60)))
+    # calculate the number of sensors logged at least one row of data per minute.
+    phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(["local_segment", "length", "local_date", "local_hour", "local_minute"])[["sensor", "local_date_time"]].max().reset_index()
     # extract local start datetime of the segment from "local_segment" column
     phone_data_yield_per_segment["local_segment_start_datetimes"] = pd.to_datetime(phone_data_yield_per_segment["local_segment"].apply(lambda x: x.split("#")[1].split(",")[0]))
     # calculate the number of minutes after local start datetime of the segment
     phone_data_yield_per_segment["minutes_after_segment_start"] = ((phone_data_yield_per_segment["local_date_time"] - phone_data_yield_per_segment["local_segment_start_datetimes"]) / pd.Timedelta(minutes=1)).astype("int")
-    # calculate the number of sensors logged at least one row of data per minute.
-    phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(["local_segment", "length", "local_segment_start_datetimes", "minutes_after_segment_start"])[["sensor"]].max().reset_index()
     
     # impute missing rows with 0
     columns_for_full_index = phone_data_yield_per_segment[["local_segment_start_datetimes", "length"]].drop_duplicates(keep="first")

tests/scripts/missing_vals.py

@@ -1,39 +0,0 @@
-import pandas as pd
-import seaborn as sns
-import matplotlib.pyplot as plt
-
-
-participant = "p01"
-all_sensors = ["eda", "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/phone_feats.py

@@ -1,285 +0,0 @@
-import pandas as pd
-import seaborn as sns
-import matplotlib.pyplot as plt
-
-
-path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv"
-df = pd.read_csv(path)
-
-# activity_recognition
-
-cols = [col for col in df.columns if "activity_recognition" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'activity_recognition_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_activity_recognition_values', bbox_inches='tight')
-plt.close()
-
-# applications_foreground
-
-cols = [col for col in df.columns if "applications_foreground" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'applications_foreground_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_applications_foreground_values', bbox_inches='tight')
-plt.close()
-
-# battery
-
-cols = [col for col in df.columns if "phone_battery" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_battery_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_battery_values', bbox_inches='tight')
-plt.close()
-
-# bluetooth_doryab
-
-cols = [col for col in df.columns if "bluetooth_doryab" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'bluetooth_doryab_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_bluetooth_doryab_values', bbox_inches='tight')
-plt.close()
-
-# bluetooth_rapids
-
-cols = [col for col in df.columns if "bluetooth_rapids" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'bluetooth_rapids_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_bluetooth_rapids_values', bbox_inches='tight')
-plt.close()
-
-# calls
-
-cols = [col for col in df.columns if "phone_calls" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_calls_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_calls_values', bbox_inches='tight')
-plt.close()
-
-# data_yield
-
-cols = [col for col in df.columns if "data_yield" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'data_yield_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_data_yield_values', bbox_inches='tight')
-plt.close()
-
-# esm
-
-cols = [col for col in df.columns if "phone_esm" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_esm_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_esm_values', bbox_inches='tight')
-plt.close()
-
-# light
-
-cols = [col for col in df.columns if "phone_light" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_light_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_light_values', bbox_inches='tight')
-plt.close()
-
-# locations_doryab
-
-cols = [col for col in df.columns if "locations_doryab" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'locations_doryab_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_locations_doryab_values', bbox_inches='tight')
-plt.close()
-
-# locations_barnett
-
-# Not working
-
-# messages
-
-cols = [col for col in df.columns if "phone_messages" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_messages_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_messages_values', bbox_inches='tight')
-plt.close()
-
-# screen
-
-cols = [col for col in df.columns if "phone_screen" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'phone_screen_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_phone_screen_values', bbox_inches='tight')
-plt.close()
-
-# wifi_visible
-
-cols = [col for col in df.columns if "wifi_visible" in col]
-df_x = df[cols]
-
-print(len(cols))
-print(df_x)
-
-df_x = df_x.dropna(axis=0, how="all")
-sns.heatmap(df_x.isna(), xticklabels=1)
-plt.savefig(f'wifi_visible_values', bbox_inches='tight')
-
-df_q = pd.DataFrame()
-for col in df_x:
-    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
-
-sns.heatmap(df_q, cbar=False, xticklabels=1)
-plt.savefig(f'cut_wifi_visible_values', bbox_inches='tight')
-plt.close()
-
-# All features
-
-print(len(df))
-print(df)
-
-# df = df.dropna(axis=0, how="all")
-# df = df.dropna(axis=1, how="all")
-sns.heatmap(df.isna())
-plt.savefig(f'all_features', bbox_inches='tight')
-
-print(df.columns[df.isna().all()].tolist())
-print("All NaNs:", df.isna().sum().sum())
-print("Df shape NaNs:", df.shape)

tests/scripts/phone_vals.py

@@ -1,23 +0,0 @@
-import pandas as pd
-import numpy as np
-import seaborn as sns
-import matplotlib.pyplot as plt
-import os, sys
-
-participant = "p032"
-
-folder = f"/rapids/data/processed/features/{participant}/"
-for filename in os.listdir(folder):
-    if filename.startswith("phone_"):
-        df = pd.read_csv(f"{folder}{filename}")
-        plt.figure()
-        sns.heatmap(df[[col for col in df if col.startswith('phone_')]], cbar=True)
-        plt.savefig(f'{participant}_{filename}.png', bbox_inches='tight')
-        plt.close()
-
-        plt.figure()
-        sns.heatmap(df[[col for col in df if col.startswith('phone_')]].isna(), cbar=True)
-        plt.savefig(f'is_na_{participant}_{filename}.png', bbox_inches='tight')
-        plt.close()
-        
-        

tests/scripts/standardization_methods_test.py

@@ -1,70 +0,0 @@
-import pandas as pd
-import numpy as np
-import matplotlib.pyplot as plt 
-from sklearn.preprocessing import StandardScaler
-import sys
-
-sys.path.append('/rapids/')
-from src.features import cr_features_helper_methods as crhm
-
-pd.set_option("display.max_columns", None)
-features_win = pd.read_csv("data/interim/p031/empatica_temperature_features/empatica_temperature_python_cr_windows.csv", usecols=[0, 1, 2, 3, 4, 5])
-
-# First standardization method
-excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', "empatica_temperature_cr_level_1"]
-z1_windows = features_win.copy()
-z1_windows.loc[:, ~z1_windows.columns.isin(excluded_columns)] = StandardScaler().fit_transform(z1_windows.loc[:, ~z1_windows.columns.isin(excluded_columns)])
-z1 = crhm.extract_second_order_features(z1_windows, ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'], prefix="empatica_temperature_cr_")
-z1 = z1.iloc[:,4:]
-# print(z1)
-
-# Second standardization method
-so_features_reg = crhm.extract_second_order_features(features_win, ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'], prefix="empatica_temperature_cr_")
-so_features_reg = so_features_reg.iloc[:,4:]
-z2 = pd.DataFrame(StandardScaler().fit_transform(so_features_reg), columns=so_features_reg.columns)
-# print(z2)
-
-# Standardization of the first standardization method values
-z1_z = pd.DataFrame(StandardScaler().fit_transform(z1), columns=z1.columns)
-# print(z1_z)
-
-# For SD
-fig, axs = plt.subplots(3, figsize=(8, 10))
-axs[0].plot(z1['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'])
-axs[0].set_title("Z1 - standardizirana okna, nato ekstrahiranje značilk SO")
-
-axs[1].plot(z2['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'])
-axs[1].set_title("Z2 - ekstrahirane značilke SO 'normalnih' vrednosti, nato standardizacija")
-
-axs[2].plot(z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'])
-axs[2].set_title("Standardiziran Z1")
-
-fig.suptitle('Z-Score methods for temperature_squareSumOfComponent_SO_sd')
-plt.savefig('z_score_comparison_temperature_squareSumOfComponent_X_SO_sd', bbox_inches='tight')
-
-showcase = pd.DataFrame()
-showcase['Z1__SD'] = z1['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']
-showcase['Z2__SD'] = z2['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']
-showcase['Z1__SD_STANDARDIZED'] = z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']
-print(showcase)
-
-# For 
-fig, axs = plt.subplots(3, figsize=(8, 10))
-axs[0].plot(z1['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'])
-axs[0].set_title("Z1 - standardizirana okna, nato ekstrahiranje značilk SO")
-
-axs[1].plot(z2['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'])
-axs[1].set_title("Z2")
-
-axs[2].plot(z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'])
-axs[2].set_title("Standardized Z1")
-
-fig.suptitle('Z-Score methods for temperature_squareSumOfComponent_SO_nlargest')
-plt.savefig('z_score_comparison_temperature_squareSumOfComponent_X_SO_nlargest', bbox_inches='tight')
-
-showcase2 = pd.DataFrame()
-showcase2['Z1__nlargest'] = z1['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']
-showcase2['Z2__nlargest'] = z2['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']
-showcase2['Z1__nlargest_STANDARDIZED'] = z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']
-print(showcase2)
-

tests/scripts/test_acc.py

@@ -1,38 +0,0 @@
-import numpy as np
-import pandas as pd
-import matplotlib.pyplot as plt
-
-import sys
-
-df = pd.read_csv(f"/rapids/data/raw/p03/empatica_accelerometer_raw.csv")
-
-
-df['date'] = pd.to_datetime(df['timestamp'],unit='ms')
-df.set_index('date', inplace=True)
-print(df)
-df = df['double_values_0'].resample("31ms").mean()
-print(df)
-
-st='2021-05-21 12:28:27'
-en='2021-05-21 12:59:12'
-
-df = df.loc[(df.index > st) & (df.index < en)]
-plt.plot(df)
-
-plt.savefig(f'NaN.png')
-sys.exit()
-
-
-plt.plot(df)
-
-esm = pd.read_csv(f"/rapids/data/raw/p03/phone_esm_raw.csv")
-
-esm['date'] = pd.to_datetime(esm['timestamp'],unit='ms')
-esm = esm[esm['date']]
-esm.set_index('date', inplace=True)
-print(esm)
-
-esm = esm['esm_session'].resample("2900ms").mean()
-
-plt.plot(esm)
-plt.savefig(f'NaN.png')

tests/scripts/zero_vals.py

@@ -1,48 +0,0 @@
-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)
-
-