Merge branch 'labels' into run_test_participant

Snakefile

@@ -168,7 +168,8 @@ 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"]))
+        for feature in config["PHONE_ESM"]["PROVIDERS"][provider]["FEATURES"]:
+            files_to_compute.extend(expand("data/interim/{pid}/phone_esm_{feature}_clean.csv",pid=config["PIDS"],feature=feature))
         #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")
 

config.yaml

@@ -239,7 +239,7 @@ PHONE_ESM:
   PROVIDERS:
     STRAW:
       COMPUTE: True
-      FEATURES:
+      FEATURES: ["PANAS_positive_affect", "PANAS_negative_affect"]
       SRC_SCRIPT: src/features/phone_esm/rapids/main.py
 
 # See https://www.rapids.science/latest/features/phone-keyboard/

rules/features.smk

@@ -327,8 +327,8 @@ rule conversation_r_features:
 rule preprocess_esm:
     input: "data/raw/{pid}/phone_esm_with_datetime.csv"
     params:
-        questionnaire_ids = [8,9]
+        questionnaire_names = lambda wildcards: config["PHONE_ESM"]["PROVIDERS"][wildcards.feature]["FEATURES"]
-    output: "data/interim/{pid}/phone_esm_clean.csv"
+    output: "data/interim/{pid}/phone_esm_{feature}_clean.csv"
     script:
         "../src/features/phone_esm/straw/preprocess.py"
 

src/features/phone_esm/straw/esm_preprocess.py

@@ -19,48 +19,32 @@ ESM_TYPE = {
 
 QUESTIONNAIRE_IDS = {
     "sleep_quality": 1,
-    "PANAS": {
+    "PANAS_positive_affect": 8,
-        "positive_affect": 8,
+    "PANAS_negative_affect": 9,
-        "negative_affect": 9
+    "JCQ_job_demand": 10,
-    },
+    "JCQ_job_control": 11,
-    "job_content_questionnaire": {
+    "JCQ_supervisor_support": 12,
-        "job_demand": 10,
+    "JCQ_coworker_support": 13,
-        "job_control": 11,
+    "PFITS_supervisor": 14,
-        "supervisor_support": 12,
+    "PFITS_coworkers": 15,
-        "coworker_support": 13,
+    "UWES_vigor": 16,
-    },
+    "UWES_dedication": 17,
-    "PFITS": {
+    "UWES_absorption": 18,
-        "supervisor": 14,
+    "COPE_active": 19,
-        "coworkers": 15
+    "COPE_support": 20,
-    },
+    "COPE_emotions": 21,
-    "UWES": {
+    "balance_life_work": 22,
-        "vigor": 16,
+    "balance_work_life": 23,
-        "dedication": 17,
+    "recovery_experience_detachment": 24,
-        "absorption": 18
+    "recovery_experience_relaxation": 25,
-    },
-    "COPE": {
-        "active": 19,
-        "support": 20,
-        "emotions": 21
-    },
-    "work_life_balance": {
-        "life_work": 22,
-        "work_life": 23
-    },
-    "recovery_experience": {
-        "detachment": 24,
-        "relaxation": 25
-    },
     "symptoms": 26,
-    "stress_appraisal": {
+    "appraisal_stressfulness_event": 87,
-        "stressfulness_event": 87,
+    "appraisal_threat": 88,
-        "threat": 88,
+    "appraisal_challenge": 89,
-        "challenge": 89,
+    "appraisal_event_time": 90,
-        "event_time": 90,
+    "appraisal_event_duration": 91,
-        "event_duration": 91,
+    "appraisal_event_work_related": 92,
-        "event_work_related": 92,
+    "appraisal_stressfulness_period": 93,
-        "stressfulness_period": 93,
-    },
     "late_work": 94,
     "work_hours": 95,
     "left_work": 96,

src/features/phone_esm/straw/preprocess.py

@@ -1,12 +1,17 @@
 from esm_preprocess import *
 
+questionnaire_names = snakemake.params["questionnaire_names"]
+
 df_esm = pd.read_csv(snakemake.input[0])
 df_esm_preprocessed = preprocess_esm(df_esm)
-# TODO Enable getting the right questionnaire here.
-df_esm_PANAS = df_esm_preprocessed[
-    (df_esm_preprocessed["questionnaire_id"] == 8)
-    | (df_esm_preprocessed["questionnaire_id"] == 9)
-]
-df_esm_clean = clean_up_esm(df_esm_PANAS)
 
+for questionnaire_name in questionnaire_names:
+    try:
+        questionnaire_id = QUESTIONNAIRE_IDS[questionnaire_name]
+    except ValueError:
+        print("The requested questionnaire name should be one of the following:")
+        print(QUESTIONNAIRE_IDS.keys())
+    else:
+        df_esm_selected = df_esm_preprocessed[df_esm_preprocessed["questionnaire_id"] == questionnaire_id]
+        df_esm_clean = clean_up_esm(df_esm_selected)
         df_esm_clean.to_csv(snakemake.output[0])