Fixed issue #17 and #18

config.yaml

@@ -65,5 +65,5 @@ BATTERY:
 SCREEN:
   DAY_SEGMENTS: *day_segments
   METRICS_EVENT: ["counton", "countunlock"]
-  METRICS_EPISODE: ["sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
+  METRICS_DELTAS: ["sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
   EPISODES: ["unlock"]

rules/features.snakefile

@@ -98,7 +98,7 @@ rule screen_metrics:
     params:
         day_segment = "{day_segment}",
         metrics_event = config["SCREEN"]["METRICS_EVENT"],
-        metrics_episode = config["SCREEN"]["METRICS_EPISODE"],
+        metrics_deltas = config["SCREEN"]["METRICS_DELTAS"],
         episodes = config["SCREEN"]["EPISODES"]
     output:
         "data/processed/{pid}/screen_{day_segment}.csv"

src/features/features_utils.py

@@ -40,8 +40,12 @@ def splitOvernightEpisodes(sensor_deltas, extra_cols, fixed_cols):
 
         # calculate new time_diff and extra_cols for split overnight periods
         overnight = computeTruncatedDifferences(overnight, extra_cols)
+    
+    # sort by local_start_date_time and reset the index
+    days = pd.concat([not_overnight, overnight], axis=0, sort=False)
+    days = days.sort_values(by=['local_start_date_time']).reset_index(drop=True)
 
-    return pd.concat([not_overnight, overnight], axis=0, sort=False)
+    return days
 
 def splitMultiSegmentEpisodes(sensor_deltas, day_segment, extra_cols):
     # extract episodes that start and end at the same epochs
@@ -74,4 +78,8 @@ def splitMultiSegmentEpisodes(sensor_deltas, day_segment, extra_cols):
     if not across_segments.empty:
         accross_segments = computeTruncatedDifferences(across_segments, extra_cols)
 
-    return pd.concat([exact_segments, across_segments], axis=0, sort=False)
+    # sort by local_start_date_time and reset the index
+    segments = pd.concat([exact_segments, across_segments], axis=0, sort=False)
+    segments = segments.sort_values(by=['local_start_date_time']).reset_index(drop=True)
+
+    return segments

src/features/screen_metrics.py

@@ -54,12 +54,12 @@ screen_data = pd.read_csv(snakemake.input["screen_events"], parse_dates=["local_
 screen_deltas = pd.read_csv(snakemake.input["screen_deltas"], parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
 day_segment = snakemake.params["day_segment"]
 metrics_event = snakemake.params["metrics_event"]
-metrics_episode = snakemake.params["metrics_episode"]
+metrics_deltas = snakemake.params["metrics_deltas"]
 episodes = snakemake.params["episodes"]
 
 if screen_data.empty:
-    metrics_episode_name = ["".join(metric) for metric in itertools.product(metrics_episode,episodes)]
+    metrics_deltas_name = ["".join(metric) for metric in itertools.product(metrics_deltas,episodes)]
-    screen_features = pd.DataFrame(columns=["local_date"]+["screen_" + day_segment + "_" + x for x in metrics_event + metrics_episode_name])
+    screen_features = pd.DataFrame(columns=["local_date"]+["screen_" + day_segment + "_" + x for x in metrics_event + metrics_deltas_name])
 else:    
     # drop consecutive duplicates of screen_status keeping the last one
     screen_data = screen_data.loc[(screen_data[["screen_status"]].shift(-1) != screen_data[["screen_status"]]).any(axis=1)].reset_index(drop=True)
@@ -75,9 +75,9 @@ else:
     event_features = getEventFeatures(screen_data, metrics_event)
     duration_features = pd.DataFrame()
     for episode in episodes:
-        duration_features = pd.concat([duration_features, getEpisodeDurationFeatures(screen_deltas, episode, metrics_episode)], axis=1)
+        duration_features = pd.concat([duration_features, getEpisodeDurationFeatures(screen_deltas, episode, metrics_deltas)], axis=1)
 
     screen_features = pd.concat([event_features, duration_features], axis = 1).fillna(0)
-    screen_features = screen_features.rename_axis('local_date').reset_index()
+    screen_features = screen_features.rename_axis("local_date").reset_index()
 
 screen_features.to_csv(snakemake.output[0], index=False)