Set appropriate calculations for speech senzor.

config.yaml

@@ -248,13 +248,12 @@ PHONE_ESM:
       FEATURES: [mean]
       SRC_SCRIPT: src/features/phone_esm/straw/main.py
 
-# Custom sensor
 PHONE_SPEECH:
   CONTAINER: speech
   PROVIDERS:
     STRAW:
       COMPUTE: True
-      FEATURES: ["countscans"]
+      FEATURES: ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
       SRC_SCRIPT: src/features/phone_speech/straw/main.py
 
 # See https://www.rapids.science/latest/features/phone-keyboard/

src/features/phone_speech/straw/main.py

@@ -1,67 +1,30 @@
 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"])
+    speech_data = pd.read_csv(sensor_data_files["sensor_data"])
     requested_features = provider["FEATURES"]
-    # name of the features this function can compute
+    # name of the features this function can compute+
-    requested_scales = provider["SCALES"]
+    base_features_names = ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
-    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)
+    speech_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:
+    if not speech_data.empty:
-            esm_features = pd.DataFrame()
+        speech_data = filter_data_by_segment(speech_data, time_segment)
-            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 not speech_data.empty:
-            if 'index' in esm_features: # In calse of empty esm_features df 
+            speech_features = pd.DataFrame()
-                esm_features.rename(columns={'index': 'local_segment'}, inplace=True)
+            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()
             
-    return esm_features
+            speech_features = speech_features.reset_index()
+
+    return speech_features