Add Speech sensor - preparation.

Snakefile

@@ -174,6 +174,14 @@ for provider in config["PHONE_ESM"]["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_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_clean.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"]))
+
 # 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():

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: ['p03'] #['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']
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
@@ -248,6 +248,15 @@ PHONE_ESM:
       FEATURES: [mean]
       SRC_SCRIPT: src/features/phone_esm/straw/main.py
 
+# Custom sensor
+PHONE_SPEECH:
+  CONTAINER: speech
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: ["countscans"]
+      SRC_SCRIPT: src/features/phone_speech/straw/main.py
+
 # See https://www.rapids.science/latest/features/phone-keyboard/
 PHONE_KEYBOARD:
   CONTAINER: keyboard
@@ -349,6 +358,7 @@ PHONE_WIFI_VISIBLE:
 
 
 
+
 ########################################################################################################################
 #                                                 FITBIT                                                               #
 ########################################################################################################################

rules/features.smk

@@ -345,6 +345,19 @@ rule esm_features:
     script:
         "../src/features/entry.py"
 
+rule phone_speech_python_features:
+    input:
+        sensor_data = "data/interim/{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"
+
 rule phone_keyboard_python_features:
     input:
         sensor_data = "data/raw/{pid}/phone_keyboard_with_datetime.csv",

src/features/phone_speech/straw/main.py

@@ -0,0 +1,67 @@
+import pandas as pd
+
+# TODO: adjust features files
+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", 
+                            "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))
+    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()
+            if 'index' in esm_features: # In calse of empty esm_features df 
+                esm_features.rename(columns={'index': 'local_segment'}, inplace=True)
+
+    return esm_features