Add Episodes GAR Metrics

rules/features.snakefile

@@ -42,7 +42,7 @@ rule google_activity_recognition_deltas:
     input:
         "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv"
     output:
-        "data/processed/{pid}/google_activity_recognition_deltas.csv"
+        "data/processed/{pid}/plugin_google_activity_recognition_deltas.csv"
     script:
         "../src/features/google_activity_recognition_deltas.R"
 
@@ -70,8 +70,8 @@ rule bluetooth_metrics:
         
 rule activity_metrics:
     input:
-        "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv",
+        gar_events = "data/raw/{pid}/plugin_google_activity_recognition_with_datetime.csv",
-        "data/raw/{pid}/plugin_google_activity_recognition_deltas.csv"
+        gar_deltas = "data/processed/{pid}/plugin_google_activity_recognition_deltas.csv"
     params:
         segment = "{day_segment}",
         metrics = config["GOOGLE_ACTIVITY_RECOGNITION"]["METRICS"]

src/features/google_activity_recognition.py

@@ -1,17 +1,26 @@
 import pandas as pd
 import numpy as np
 import scipy.stats as stats
+from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
 
 day_segment = snakemake.params["segment"]
 
 #Read csv into a pandas dataframe
-data = pd.read_csv(snakemake.input[0])
+data = pd.read_csv(snakemake.input['gar_events'],parse_dates=['local_date_time'])
-columns = ['count','most_common_activity','count_unique_activities','activity_change_count']
+ar_deltas = pd.read_csv(snakemake.input['gar_deltas'],parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
+columns = ['count','most_common_activity','count_unique_activities','activity_change_count','sumstationary','summobile','sumvehicle']
 columns = list("ar_" + str(day_segment) + "_" + column for column in columns)
 
+
 if data.empty:
     finalDataset = pd.DataFrame(columns = columns)
 else:
+
+    ar_deltas = splitOvernightEpisodes(ar_deltas, [],['activity'])
+
+    if day_segment != "daily":
+        ar_deltas = splitMultiSegmentEpisodes(ar_deltas, day_segment, [])
+
     data.local_date_time = pd.to_datetime(data.local_date_time)
     resampledData = data.set_index(data.local_date_time)
     resampledData.drop(columns=['local_date_time'],inplace=True)
@@ -33,6 +42,17 @@ else:
     countChanges = resampledData['different_activity'].resample('D').sum()
     finalDataset = pd.concat([count, mostCommonActivity, uniqueActivities, countChanges],axis=1)
 
+    deltas_metrics = {'sumstationary':['still','tilting'], 
+                    'summobile':['on_foot','running','on_bicycle'],
+                    'sumvehicle':['on_vehicle']}
+  
+    for column, activity_labels in deltas_metrics.items():
+        metric = (ar_deltas[ar_deltas['activity'].isin(pd.Series(activity_labels))]  
+                .groupby(['local_start_date'])['time_diff']  
+                .agg({"ar_" + str(day_segment) + "_" + str(column) :'sum'}))  
+        finalDataset = finalDataset.merge(metric,how='outer',left_index=True,right_index=True)
+    
+finalDataset.fillna(0,inplace=True)
 finalDataset.index.names = ['local_date']
 finalDataset.columns=columns
 finalDataset.to_csv(snakemake.output[0])