Fix bugs with empty dataframes in screen and gar metrics

Snakefile

@@ -9,7 +9,7 @@ rule all:
         expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["SENSORS"]),
         expand("data/processed/{pid}/battery_deltas.csv", pid=config["PIDS"]),
         expand("data/processed/{pid}/screen_deltas.csv", pid=config["PIDS"]),
-        expand("data/processed/{pid}/google_activity_recognition_deltas.csv", pid=config["PIDS"]),
+        expand("data/processed/{pid}/plugin_google_activity_recognition_deltas.csv", pid=config["PIDS"]),
         expand("data/interim/{pid}/phone_valid_sensed_days.csv", pid=config["PIDS"]),
         expand("data/interim/{pid}/phone_sensed_bins.csv", pid=config["PIDS"]),
         expand("data/processed/{pid}/sms_{sms_type}_{day_segment}.csv",

src/features/google_activity_recognition.py

@@ -28,6 +28,9 @@ else:
     if(day_segment!='daily'):
         resampledData = resampledData.loc[resampledData['local_day_segment'] == str(day_segment)]
 
+    if resampledData.empty:
+        finalDataset = pd.DataFrame(columns = columns)
+    else:
         count = resampledData['activity_type'].resample('D').count()
 
         #Finding most common activity of the day
@@ -44,7 +47,7 @@ else:
 
         deltas_metrics = {'sumstationary':['still','tilting'], 
                         'summobile':['on_foot','running','on_bicycle'],
-                    'sumvehicle':['on_vehicle']}
+                        'sumvehicle':['in_vehicle']}
     
         for column, activity_labels in deltas_metrics.items():
             metric = (ar_deltas[ar_deltas['activity'].isin(pd.Series(activity_labels))]  

src/features/screen_metrics.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import numpy as np
 import datetime
+import itertools
 from datetime import datetime, timedelta, time
 from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
 
@@ -73,6 +74,11 @@ else:
 
     # extract features for events and episodes
     event_features = getEventFeatures(screen_data, metrics_event)
+
+    if screen_deltas.empty:
+        metrics_deltas_name = ["".join(metric) for metric in itertools.product(metrics_deltas,episodes)]
+        duration_features = pd.DataFrame(columns=["screen_" + day_segment + "_" + x for x in metrics_deltas_name])
+    else:
         duration_features = pd.DataFrame()
         for episode in episodes:
             duration_features = pd.concat([duration_features, getEpisodeDurationFeatures(screen_deltas, episode, metrics_deltas)], axis=1)