Merge remote-tracking branch 'origin/master'

This mirrors INNER join in merge_features_and_targets_for_individual_model.py:

data = pd.concat([sensor_features, targets[["target"]]], axis=1, join="inner")

Snakefile

@@ -164,6 +164,16 @@ for provider in config["PHONE_CONVERSATION"]["PROVIDERS"].keys():
         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")
 
+for provider in config["PHONE_ESM"]["PROVIDERS"].keys():
+    if config["PHONE_ESM"]["PROVIDERS"][provider]["COMPUTE"]:
+        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/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.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):
     for provider in config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"].keys():
@@ -403,9 +413,19 @@ for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys():
     if config["ALL_CLEANING_OVERALL"]["PROVIDERS"][provider]["COMPUTE"]:
         files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +".csv"))
 
-# Demographic features
-files_to_compute.extend(expand("data/raw/baseline_merged.csv"))
-files_to_compute.extend(expand("data/raw/{pid}/participant_baseline_raw.csv", pid=config["PIDS"]))
+# Baseline features
+if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]:
+    files_to_compute.extend(expand("data/raw/baseline_merged.csv"))
+    files_to_compute.extend(expand("data/raw/{pid}/participant_baseline_raw.csv", pid=config["PIDS"]))
+    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"]))
+    files_to_compute.extend(expand("data/processed/models/population_model/input.csv"))
+
+#files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv", pid=config["PIDS"], cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"]))
 
 rule all:
     input:

config.yaml

@@ -234,6 +234,15 @@ PHONE_DATA_YIELD:
       MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1, minimum percentage of valid minutes in an hour to be considered valid.
       SRC_SCRIPT: src/features/phone_data_yield/rapids/main.R
 
+PHONE_ESM:
+  CONTAINER: esm
+  PROVIDERS:
+    STRAW:
+      COMPUTE: True
+      SCALES: ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"]
+      FEATURES: [mean]
+      SRC_SCRIPT: src/features/phone_esm/straw/main.py
+
 # See https://www.rapids.science/latest/features/phone-keyboard/
 PHONE_KEYBOARD:
   CONTAINER: keyboard
@@ -561,7 +570,7 @@ HISTOGRAM_PHONE_DATA_YIELD:
 
 # 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:
-  PLOT: True
+  PLOT: False
   TIME: RELATIVE_TIME # ABSOLUTE_TIME or RELATIVE_TIME
 
 # See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#3-heatmap-of-recorded-phone-sensors
@@ -629,10 +638,16 @@ ALL_CLEANING_OVERALL:
 
 PARAMS_FOR_ANALYSIS:
   BASELINE:
+    COMPUTE: True
     FOLDER: data/external/baseline
     CONTAINER: [results-survey637813_final.csv,  # Slovenia
                 results-survey358134_final.csv,  # Belgium 1
                 results-survey413767_final.csv  # Belgium 2
     ]
-    FEATURES: [age, gender]
+    QUESTION_LIST: survey637813+question_text.csv
+    FEATURES: [age, gender, startlanguage, limesurvey_demand, limesurvey_control, limesurvey_demand_control_ratio, limesurvey_demand_control_ratio_quartile]
     CATEGORICAL_FEATURES: [gender]
+
+  TARGET:
+    COMPUTE: True
+    LABEL: PANAS_negative_affect_mean

docs/change-log.md

@@ -1,4 +1,9 @@
 # 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

@@ -0,0 +1,15 @@
+# `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

@@ -16,6 +16,7 @@ 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)

mkdocs.yml

@@ -85,6 +85,7 @@ 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

rules/features.smk

@@ -324,6 +324,27 @@ rule conversation_r_features:
     script:
         "../src/features/entry.R"
 
+rule preprocess_esm:
+    input: "data/raw/{pid}/phone_esm_with_datetime.csv"
+    params:
+        scales=lambda wildcards: config["PHONE_ESM"]["PROVIDERS"]["STRAW"]["SCALES"]
+    output: "data/interim/{pid}/phone_esm_clean.csv"
+    script:
+        "../src/features/phone_esm/straw/preprocess.py"
+
+rule esm_features:
+    input:
+        sensor_data = "data/interim/{pid}/phone_esm_clean.csv",
+        time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
+    params:
+        provider = lambda wildcards: config["PHONE_ESM"]["PROVIDERS"][wildcards.provider_key.upper()],
+        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"
+    script:
+        "../src/features/entry.py"
+
 rule phone_keyboard_python_features:
     input:
         sensor_data = "data/raw/{pid}/phone_keyboard_with_datetime.csv",

rules/models.smk

@@ -14,3 +14,38 @@ rule download_baseline_data:
         "data/raw/{pid}/participant_baseline_raw.csv"
     script:
         "../src/data/download_baseline_data.py"
+
+rule baseline_features:
+    input:
+        "data/raw/{pid}/participant_baseline_raw.csv"
+    params:
+        pid="{pid}",
+        features=config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["FEATURES"],
+        question_filename=config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["FOLDER"] + "/" + config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["QUESTION_LIST"]
+    output:
+        interim="data/interim/{pid}/baseline_questionnaires.csv",
+        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_rapids.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_rapids.csv",
+        demographic_features = expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]),
+    params:
+        target_variable=config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"]
+    output:
+        "data/processed/models/population_model/input.csv"
+    script:
+        "../src/models/merge_features_and_targets_for_population_model.py"
+

rules/preprocessing.smk

@@ -177,7 +177,6 @@ rule resample_episodes_with_datetime:
     script:
         "../src/data/datetime/readable_datetime.R"
 
-
 rule phone_application_categories:
     input:
         "data/raw/{pid}/phone_applications_{type}_with_datetime.csv"

src/data/baseline_features.py

@@ -0,0 +1,179 @@
+import numpy as np
+import pandas as pd
+
+pid = snakemake.params["pid"]
+requested_features = snakemake.params["features"]
+baseline_interim = pd.DataFrame(columns=["qid", "question", "score_original", "score"])
+baseline_features = pd.DataFrame(columns=requested_features)
+question_filename = snakemake.params["question_filename"]
+
+JCQ_DEMAND = "JobEisen"
+JCQ_CONTROL = "JobControle"
+
+dict_JCQ_demand_control_reverse = {
+    JCQ_DEMAND: {
+        3: " [Od mene se ne zahteva,",
+        4: " [Imam dovolj časa, da končam",
+        5: " [Pri svojem delu se ne srečujem s konfliktnimi",
+    },
+    JCQ_CONTROL: {
+        2: " |Moje delo vključuje veliko ponavljajočega",
+        6: " [Pri svojem delu imam zelo malo svobode",
+    },
+}
+
+LIMESURVEY_JCQ_MIN = 1
+LIMESURVEY_JCQ_MAX = 4
+
+DEMAND_CONTROL_RATIO_MIN = 5 / (9 * 4)
+DEMAND_CONTROL_RATIO_MAX = (4 * 5) / 9
+
+JCQ_NORMS = {
+    "F": {
+        0: DEMAND_CONTROL_RATIO_MIN,
+        1: 0.45,
+        2: 0.52,
+        3: 0.62,
+        4: DEMAND_CONTROL_RATIO_MAX,
+    },
+    "M": {
+        0: DEMAND_CONTROL_RATIO_MIN,
+        1: 0.41,
+        2: 0.48,
+        3: 0.56,
+        4: DEMAND_CONTROL_RATIO_MAX,
+    },
+}
+
+participant_info = pd.read_csv(snakemake.input[0], parse_dates=["date_of_birth"])
+
+if not participant_info.empty:
+    if "age" in requested_features:
+        now = pd.Timestamp("now")
+        baseline_features.loc[0, "age"] = (
+            now - participant_info.loc[0, "date_of_birth"]
+        ).days / 365.25245
+    if "gender" in requested_features:
+        baseline_features.loc[0, "gender"] = participant_info.loc[0, "gender"]
+    if "startlanguage" in requested_features:
+        baseline_features.loc[0, "startlanguage"] = participant_info.loc[
+            0, "startlanguage"
+        ]
+    if (
+        ("limesurvey_demand" in requested_features)
+        or ("limesurvey_control" in requested_features)
+        or ("limesurvey_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 (
+            "limesurvey_demand_control_ratio" in requested_features
+        ):
+            # Find questions about demand, but disregard time (duration of filling in questionnaire)
+            rows_demand = rows_baseline.str.startswith(
+                JCQ_DEMAND
+            ) & ~rows_baseline.str.endswith("Time")
+            limesurvey_demand = (
+                participant_info_t[rows_demand]
+                .reset_index()
+                .rename(columns={"index": "question", 0: "score_original"})
+            )
+            # Extract question IDs from names such as JobEisen[3]
+            limesurvey_demand["qid"] = (
+                limesurvey_demand["question"].str.extract(r"\[(\d+)\]").astype(int)
+            )
+            limesurvey_demand["score"] = limesurvey_demand["score_original"]
+            # Identify rows that include questions to be reversed.
+            rows_demand_reverse = limesurvey_demand["qid"].isin(
+                dict_JCQ_demand_control_reverse[JCQ_DEMAND].keys()
+            )
+            # Reverse the score, so that the maximum value becomes the minimum etc.
+            limesurvey_demand.loc[rows_demand_reverse, "score"] = (
+                LIMESURVEY_JCQ_MAX
+                + LIMESURVEY_JCQ_MIN
+                - limesurvey_demand.loc[rows_demand_reverse, "score_original"]
+            )
+            baseline_interim = pd.concat([baseline_interim, limesurvey_demand], axis=0, ignore_index=True)
+            if "demand" in requested_features:
+                baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
+                    "score"
+                ].sum()
+
+        if ("limesurvey_control" in requested_features) or (
+            "limesurvey_demand_control_ratio" in requested_features
+        ):
+            # Find questions about control, but disregard time (duration of filling in questionnaire)
+            rows_control = rows_baseline.str.startswith(
+                JCQ_CONTROL
+            ) & ~rows_baseline.str.endswith("Time")
+            limesurvey_control = (
+                participant_info_t[rows_control]
+                .reset_index()
+                .rename(columns={"index": "question", 0: "score_original"})
+            )
+            # Extract question IDs from names such as JobControle[3]
+            limesurvey_control["qid"] = (
+                limesurvey_control["question"].str.extract(r"\[(\d+)\]").astype(int)
+            )
+            limesurvey_control["score"] = limesurvey_control["score_original"]
+            # Identify rows that include questions to be reversed.
+            rows_control_reverse = limesurvey_control["qid"].isin(
+                dict_JCQ_demand_control_reverse[JCQ_CONTROL].keys()
+            )
+            # Reverse the score, so that the maximum value becomes the minimum etc.
+            limesurvey_control.loc[rows_control_reverse, "score"] = (
+                LIMESURVEY_JCQ_MAX
+                + LIMESURVEY_JCQ_MIN
+                - limesurvey_control.loc[rows_control_reverse, "score_original"]
+            )
+
+            baseline_interim = pd.concat([baseline_interim, limesurvey_control], axis=0, ignore_index=True)
+
+            if "limesurvey_control" in requested_features:
+                baseline_features.loc[0, "limesurvey_control"] = limesurvey_control[
+                    "score"
+                ].sum()
+
+        if "limesurvey_demand_control_ratio" in requested_features:
+            limesurvey_demand_control_ratio = (
+                limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
+            )
+            if (
+                JCQ_NORMS[participant_info.loc[0, "gender"]][0]
+                <= limesurvey_demand_control_ratio
+                < JCQ_NORMS[participant_info.loc[0, "gender"]][1]
+            ):
+                limesurvey_quartile = 1
+            elif (
+                JCQ_NORMS[participant_info.loc[0, "gender"]][1]
+                <= limesurvey_demand_control_ratio
+                < JCQ_NORMS[participant_info.loc[0, "gender"]][2]
+            ):
+                limesurvey_quartile = 2
+            elif (
+                JCQ_NORMS[participant_info.loc[0, "gender"]][2]
+                <= limesurvey_demand_control_ratio
+                < JCQ_NORMS[participant_info.loc[0, "gender"]][3]
+            ):
+                limesurvey_quartile = 3
+            elif (
+                JCQ_NORMS[participant_info.loc[0, "gender"]][3]
+                <= limesurvey_demand_control_ratio
+                < JCQ_NORMS[participant_info.loc[0, "gender"]][4]
+            ):
+                limesurvey_quartile = 4
+            else:
+                limesurvey_quartile = np.nan
+
+            baseline_features.loc[
+                0, "limesurvey_demand_control_ratio"
+            ] = limesurvey_demand_control_ratio
+            baseline_features.loc[
+                0, "limesurvey_demand_control_ratio_quartile"
+            ] = limesurvey_quartile
+
+if not baseline_interim.empty:
+    baseline_interim.to_csv(snakemake.output["interim"], index=False, encoding="utf-8")
+
+baseline_features.to_csv(snakemake.output["features"], index=False, encoding="utf-8")

src/data/merge_baseline_data.py

@@ -24,10 +24,6 @@ baseline = (
 )
 
 baseline.rename(columns=VARIABLES_TO_TRANSLATE, copy=False, inplace=True)
-now = pd.Timestamp("now")
-baseline = baseline.assign(
-    age=lambda x: (now - x.date_of_birth).dt.days / 365.25245,
-)
 
 baseline.to_csv(snakemake.output[0],
                 index=False,

src/data/streams/aware_micro_mysql/container.R

@@ -0,0 +1,85 @@
+# 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

@@ -0,0 +1,337 @@
+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

@@ -183,6 +183,21 @@ PHONE_CONVERSATION:
       SCRIPTS: # List any python or r scripts that mutate your raw data
         - "src/data/streams/mutations/phone/aware/conversation_ios_timestamp.R"
 
+PHONE_ESM:
+  ANDROID:
+    RAPIDS_COLUMN_MAPPINGS:
+      TIMESTAMP: double_esm_user_answer_timestamp
+      DEVICE_ID: device_id
+      ESM_STATUS: esm_status
+      ESM_USER_ANSWER: esm_user_answer
+      ESM_JSON: esm_json
+      ESM_TRIGGER: esm_trigger
+      ESM_SESSION: esm_session
+      ESM_NOTIFICATION_ID: esm_notification_id
+    MUTATION:
+      COLUMN_MAPPINGS:
+      SCRIPTS:
+
 PHONE_KEYBOARD:
   ANDROID:
     RAPIDS_COLUMN_MAPPINGS:

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(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(as.numeric(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

@@ -67,6 +67,16 @@ PHONE_CONVERSATION:
   - DOUBLE_CONVO_START
   - DOUBLE_CONVO_END
 
+PHONE_ESM:
+  - TIMESTAMP
+  - DEVICE_ID
+  - ESM_STATUS
+  - ESM_USER_ANSWER
+  - ESM_JSON
+  - ESM_TRIGGER
+  - ESM_SESSION
+  - ESM_NOTIFICATION_ID
+
 PHONE_KEYBOARD:
   - TIMESTAMP
   - DEVICE_ID

src/features/phone_esm/straw/esm_JCQ.py

@@ -0,0 +1,108 @@
+import pandas as pd
+
+JCQ_ORIGINAL_MAX = 4
+JCQ_ORIGINAL_MIN = 1
+
+dict_JCQ_demand_control_reverse = {
+    75: (
+        "I was NOT asked",
+        "Men legde mij geen overdreven",
+        "Men legde mij GEEN overdreven",  # Capitalized in some versions
+        "Od mene se NI zahtevalo",
+    ),
+    76: (
+        "I had enough time to do my work",
+        "Ik had voldoende tijd om mijn werk",
+        "Imela sem dovolj časa, da končam",
+        "Imel sem dovolj časa, da končam",
+    ),
+    77: (
+        "I was free of conflicting demands",
+        "Er werden mij op het werk geen tegenstrijdige",
+        "Er werden mij op het werk GEEN tegenstrijdige",  # Capitalized in some versions
+        "Pri svojem delu se NISEM srečeval",
+    ),
+    79: (
+        "My job involved a lot of repetitive work",
+        "Mijn taak omvatte veel repetitief werk",
+        "Moje delo je vključevalo veliko ponavljajočega",
+    ),
+    85: (
+        "On my job, I had very little freedom",
+        "In mijn taak had ik zeer weinig vrijheid",
+        "Pri svojem delu sem imel zelo malo svobode",
+        "Pri svojem delu sem imela zelo malo svobode",
+    ),
+}
+
+
+def reverse_jcq_demand_control_scoring(
+    df_esm_jcq_demand_control: pd.DataFrame,
+) -> pd.DataFrame:
+    """
+    This function recodes answers in Job content questionnaire by first incrementing them by 1,
+    to be in line with original (1-4) scoring.
+    Then, some answers are reversed (i.e. 1 becomes 4 etc.), because the questions are negatively phrased.
+    These answers are listed in dict_JCQ_demand_control_reverse and identified by their question ID.
+    However, the existing data is checked against literal phrasing of these questions
+        to protect against wrong numbering of questions (differing question IDs).
+
+    Parameters
+    ----------
+    df_esm_jcq_demand_control: pd.DataFrame
+        A cleaned up dataframe, which must also include esm_user_answer_numeric.
+
+    Returns
+    -------
+    df_esm_jcq_demand_control: pd.DataFrame
+        The same dataframe with a column esm_user_score containing answers recoded and reversed.
+    """
+    df_esm_jcq_demand_control_unique_answers = (
+        df_esm_jcq_demand_control.groupby("question_id")
+        .esm_instructions.value_counts()
+        .rename()
+        .reset_index()
+    )
+    # Tabulate all possible answers to each question (group by question ID).
+    for q_id in dict_JCQ_demand_control_reverse.keys():
+        # Look through all answers that need to be reversed.
+        possible_answers = df_esm_jcq_demand_control_unique_answers.loc[
+            df_esm_jcq_demand_control_unique_answers["question_id"] == q_id,
+            "esm_instructions",
+        ]
+        # These are all answers to a given question (by q_id).
+        answers_matches = possible_answers.str.startswith(
+            dict_JCQ_demand_control_reverse.get(q_id)
+        )
+        # See if they are expected, i.e. included in the dictionary.
+        if ~answers_matches.all():
+            print("One of the answers that occur in the data should not be reversed.")
+            print("This was the answer found in the data: ")
+            raise KeyError(possible_answers[~answers_matches])
+            # In case there is an unexpected answer, raise an exception.
+
+    try:
+        df_esm_jcq_demand_control = df_esm_jcq_demand_control.assign(
+            esm_user_score=lambda x: x.esm_user_answer_numeric + 1
+        )
+        # Increment the original answer by 1
+        # to keep in line with traditional scoring (JCQ_ORIGINAL_MIN - JCQ_ORIGINAL_MAX).
+        df_esm_jcq_demand_control[
+            df_esm_jcq_demand_control["question_id"].isin(
+                dict_JCQ_demand_control_reverse.keys()
+            )
+        ] = df_esm_jcq_demand_control[
+            df_esm_jcq_demand_control["question_id"].isin(
+                dict_JCQ_demand_control_reverse.keys()
+            )
+        ].assign(
+            esm_user_score=lambda x: JCQ_ORIGINAL_MAX
+            + JCQ_ORIGINAL_MIN
+            - x.esm_user_score
+        )
+        # Reverse the items that require it.
+    except AttributeError as e:
+        print("Please, clean the dataframe first using features.esm.clean_up_esm.")
+        print(e)
+
+    return df_esm_jcq_demand_control

src/features/phone_esm/straw/esm_preprocess.py

@@ -0,0 +1,135 @@
+import json
+
+import numpy as np
+import pandas as pd
+
+ESM_TYPE = {
+    "text": 1,
+    "radio": 2,
+    "checkbox": 3,
+    "likert": 4,
+    "quick_answers": 5,
+    "scale": 6,
+    "datetime": 7,
+    "pam": 8,
+    "number": 9,
+    "web": 10,
+    "date": 11,
+}
+
+QUESTIONNAIRE_IDS = {
+    "sleep_quality": 1,
+    "PANAS_positive_affect": 8,
+    "PANAS_negative_affect": 9,
+    "JCQ_job_demand": 10,
+    "JCQ_job_control": 11,
+    "JCQ_supervisor_support": 12,
+    "JCQ_coworker_support": 13,
+    "PFITS_supervisor": 14,
+    "PFITS_coworkers": 15,
+    "UWES_vigor": 16,
+    "UWES_dedication": 17,
+    "UWES_absorption": 18,
+    "COPE_active": 19,
+    "COPE_support": 20,
+    "COPE_emotions": 21,
+    "balance_life_work": 22,
+    "balance_work_life": 23,
+    "recovery_experience_detachment": 24,
+    "recovery_experience_relaxation": 25,
+    "symptoms": 26,
+    "appraisal_stressfulness_event": 87,
+    "appraisal_threat": 88,
+    "appraisal_challenge": 89,
+    "appraisal_event_time": 90,
+    "appraisal_event_duration": 91,
+    "appraisal_event_work_related": 92,
+    "appraisal_stressfulness_period": 93,
+    "late_work": 94,
+    "work_hours": 95,
+    "left_work": 96,
+    "activities": 97,
+    "coffee_breaks": 98,
+    "at_work_yet": 99,
+}
+
+ESM_STATUS_ANSWERED = 2
+
+GROUP_SESSIONS_BY = ["participant_id", "device_id", "esm_session"]
+
+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.
+
+
+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_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 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_TYPE.get("radio"),
+        ESM_TYPE.get("scale"),
+        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

@@ -0,0 +1,63 @@
+import pandas as pd
+
+QUESTIONNAIRE_IDS = {
+    "sleep_quality": 1,
+    "PANAS_positive_affect": 8,
+    "PANAS_negative_affect": 9,
+    "JCQ_job_demand": 10,
+    "JCQ_job_control": 11,
+    "JCQ_supervisor_support": 12,
+    "JCQ_coworker_support": 13,
+    "PFITS_supervisor": 14,
+    "PFITS_coworkers": 15,
+    "UWES_vigor": 16,
+    "UWES_dedication": 17,
+    "UWES_absorption": 18,
+    "COPE_active": 19,
+    "COPE_support": 20,
+    "COPE_emotions": 21,
+    "balance_life_work": 22,
+    "balance_work_life": 23,
+    "recovery_experience_detachment": 24,
+    "recovery_experience_relaxation": 25,
+    "symptoms": 26,
+    "appraisal_stressfulness_event": 87,
+    "appraisal_threat": 88,
+    "appraisal_challenge": 89,
+    "appraisal_event_time": 90,
+    "appraisal_event_duration": 91,
+    "appraisal_event_work_related": 92,
+    "appraisal_stressfulness_period": 93,
+    "late_work": 94,
+    "work_hours": 95,
+    "left_work": 96,
+    "activities": 97,
+    "coffee_breaks": 98,
+    "at_work_yet": 99,
+}
+
+
+def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+    esm_data = pd.read_csv(sensor_data_files["sensor_data"])
+    requested_features = provider["FEATURES"]
+    # name of the features this function can compute
+    requested_scales = provider["SCALES"]
+    base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"]
+    #TODO Check valid questionnaire and feature names.
+    # the subset of requested features this function can compute
+    features_to_compute = list(set(requested_features) & set(base_features_names))
+    esm_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
+    if not esm_data.empty:
+        esm_data = filter_data_by_segment(esm_data, time_segment)
+
+        if not esm_data.empty:
+            esm_features = pd.DataFrame()
+
+            for scale in requested_scales:
+                questionnaire_id = QUESTIONNAIRE_IDS[scale]
+                mask = esm_data["questionnaire_id"] == questionnaire_id
+                esm_features[scale + "_mean"] = esm_data.loc[mask].groupby(["local_segment"])["esm_user_score"].mean()
+                #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
+
+            esm_features = esm_features.reset_index()
+    return esm_features

src/features/phone_esm/straw/preprocess.py

@@ -0,0 +1,25 @@
+from esm_preprocess import *
+from esm_JCQ import reverse_jcq_demand_control_scoring
+
+requested_scales = snakemake.params["scales"]
+
+df_esm = pd.read_csv(snakemake.input[0])
+df_esm_preprocessed = preprocess_esm(df_esm)
+
+if not all([scale in QUESTIONNAIRE_IDS for scale in requested_scales]):
+    unknown_scales = set(requested_scales) - set(QUESTIONNAIRE_IDS.keys())
+    print("The requested questionnaire name should be one of the following:")
+    print(QUESTIONNAIRE_IDS.keys())
+    raise ValueError("You requested scales not collected: ", unknown_scales)
+
+df_esm_clean = clean_up_esm(df_esm_preprocessed)
+df_esm_clean["esm_user_score"] = df_esm_clean["esm_user_answer_numeric"]
+
+for scale in requested_scales:
+    questionnaire_id = QUESTIONNAIRE_IDS[scale]
+    mask = df_esm_clean["questionnaire_id"] == questionnaire_id
+    if scale.startswith("JCQ"):
+        df_esm_clean.loc[mask] = reverse_jcq_demand_control_scoring(df_esm_clean.loc[mask])
+    #TODO Reverse other questionnaires if needed and/or adapt esm_user_score to original scoring.
+
+df_esm_clean.to_csv(snakemake.output[0], index=False)

src/features/phone_locations/barnett/daily_features.R

@@ -26,7 +26,9 @@ barnett_daily_features <- function(snakemake){
   location <- location %>% 
     mutate(is_daily = str_detect(assigned_segments, paste0(".*#", datetime_start_regex, ",", datetime_end_regex, ".*")))
 
-  if(nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)){
+  does_not_span = nrow(segment_labels) == 0 || nrow(location) == 0 || all(location$is_daily == FALSE) || (max(location$timestamp) - min(location$timestamp) < 86400000)
+
+  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/models/helper.py

@@ -0,0 +1,18 @@
+import pandas as pd
+
+
+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):
+        raise ValueError("The requested target (", target_variable_name,
+                         ")cannot be found in the dataset.",
+                         "Please check the names of phone_esm_ columns in all_sensor_features_cleaned_rapids.csv")
+    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

@@ -0,0 +1,20 @@
+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
+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)

src/models/select_targets.py

@@ -0,0 +1,11 @@
+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)
+model_input.dropna(axis ="index", how="any", subset=["target"], inplace=True)
+
+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")