Merge branch 'speech_sensor'

Snakefile

@@ -174,6 +174,15 @@ 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_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):
     for provider in config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"].keys():

config.yaml

@@ -329,6 +329,15 @@ 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

rules/features.smk

@@ -345,6 +345,19 @@ rule esm_features:
     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"
+
 rule phone_keyboard_python_features:
     input:
         sensor_data = "data/raw/{pid}/phone_keyboard_with_datetime.csv",

src/data/streams/aware_postgresql/format.yaml

@@ -349,3 +349,24 @@ 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/features/phone_speech/straw/main.py

@@ -0,0 +1,30 @@
+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