Refactor activity recognition features

config.yaml

@@ -81,7 +81,7 @@ BLUETOOTH:
 
 ACTIVITY_RECOGNITION:
   DAY_SEGMENTS: *day_segments
-  FEATURES: ['count','mostcommonactivity','countuniqueactivities','activitychangecount','sumstationary','summobile','sumvehicle']
+  FEATURES: ["count","mostcommonactivity","countuniqueactivities","activitychangecount","sumstationary","summobile","sumvehicle"]
 
 BATTERY:
   DAY_SEGMENTS: *day_segments

src/features/activity_recognition.py

@@ -1,63 +1,15 @@
 import pandas as pd
-import numpy as np
+from ar.ar_base import base_ar_features
-import scipy.stats as stats
-from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
 
-day_segment = snakemake.params["segment"]
+ar_data = pd.read_csv(snakemake.input[0],parse_dates=["local_date_time"])
-features = snakemake.params["features"]
-
-#Read csv into a pandas dataframe
-data = pd.read_csv(snakemake.input[0],parse_dates=["local_date_time"])
 ar_deltas = pd.read_csv(snakemake.input[1],parse_dates=["local_start_date_time", "local_end_date_time", "local_start_date", "local_end_date"])
-columns = list("ar_" + str(day_segment) + "_" + column for column in features)
+day_segment = snakemake.params["segment"]
-
+requested_features = snakemake.params["features"]
-if data.empty:
+ar_features = pd.DataFrame(columns=["local_date"])
-    finalDataset = pd.DataFrame(columns = columns)
-else:
-    finalDataset = pd.DataFrame()
-    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)
-
-    if(day_segment!='daily'):
-        resampledData = resampledData.loc[resampledData['local_day_segment'] == str(day_segment)]
-
-    if resampledData.empty:
-        finalDataset = pd.DataFrame(columns = columns)
-    else:
-        #Finding the count of samples of the day
-        if("count" in features):
-            finalDataset["ar_" + str(day_segment) + "_count"] = resampledData['activity_type'].resample('D').count()
-
-        #Finding most common activity of the day
-        if("mostcommonactivity" in features):
-            finalDataset["ar_" + str(day_segment) + "_mostcommonactivity"] = resampledData['activity_type'].resample('D').apply(lambda x: stats.mode(x)[0] if len(stats.mode(x)[0]) != 0 else None)
-
-        #finding different number of activities during a day
-        if("countuniqueactivities" in features):
-            finalDataset["ar_" + str(day_segment) + "_countuniqueactivities"] = resampledData['activity_type'].resample('D').nunique()
-        
-        #finding Number of times activity changed
-        if("activitychangecount" in features):
-            resampledData['activity_type_shift'] = resampledData['activity_type'].shift().fillna(resampledData['activity_type'].head(1))
-            resampledData['different_activity'] = np.where(resampledData['activity_type']!=resampledData['activity_type_shift'],1,0)
-            finalDataset["ar_" + str(day_segment) + "_activitychangecount"] = resampledData['different_activity'].resample('D').sum()
 
 
-        deltas_features = {'sumstationary':['still','tilting'], 
+ar_features = ar_features.merge(base_ar_features(ar_data, ar_deltas, day_segment, requested_features), on="local_date", how="outer")
-                        'summobile':['on_foot','walking','running','on_bicycle'],
-                        'sumvehicle':['in_vehicle']}
 
-        for column, activity_labels in deltas_features.items():
+assert len(requested_features) + 1 == ar_features.shape[1], "The number of features in the output dataframe (=" + str(ar_features.shape[1]) + ") does not match the expected value (=" + str(len(requested_features)) + " + 1). Verify your activity recognition feature extraction functions"
-            if column in features:
-                finalDataset["ar_" + str(day_segment) + "_"+str(column)] = (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.index.names = ['local_date']
+ar_features.to_csv(snakemake.output[0], index=False)
-finalDataset.to_csv(snakemake.output[0])

src/features/ar/ar_base.py

@@ -0,0 +1,61 @@
+import pandas as pd
+import numpy as np
+import scipy.stats as stats
+from features_utils import splitOvernightEpisodes, splitMultiSegmentEpisodes
+
+def base_ar_features(ar_data, ar_deltas, day_segment, requested_features):
+    # name of the features this function can compute
+    base_features_names = ["count","mostcommonactivity","countuniqueactivities","activitychangecount","sumstationary","summobile","sumvehicle"]
+    # the subset of requested features this function can compute
+    features_to_compute = list(set(requested_features) & set(base_features_names))
+
+    if ar_data.empty:
+        ar_features = pd.DataFrame(columns = ["local_date"] + ["ar_" + day_segment + "_" + x for x in features_to_compute])
+    else:
+        ar_features = pd.DataFrame()
+        ar_deltas = splitOvernightEpisodes(ar_deltas, [],["activity"])
+
+        if day_segment != "daily":
+            ar_deltas = splitMultiSegmentEpisodes(ar_deltas, day_segment, [])
+
+        ar_data.local_date_time = pd.to_datetime(ar_data.local_date_time)
+        resampledData = ar_data.set_index(ar_data.local_date_time)
+        resampledData.drop(columns=["local_date_time"], inplace=True)
+
+        if(day_segment!="daily"):
+            resampledData = resampledData.loc[resampledData["local_day_segment"] == day_segment]
+
+        if resampledData.empty:
+            ar_features = pd.DataFrame(columns = ["ar_" + day_segment + "_" + x for x in features_to_compute])
+        else:
+            #Finding the count of samples of the day
+            if "count" in features_to_compute:
+                ar_features["ar_" + day_segment + "_count"] = resampledData["activity_type"].resample("D").count()
+
+            #Finding most common activity of the day
+            if "mostcommonactivity" in features_to_compute:
+                ar_features["ar_" + day_segment + "_mostcommonactivity"] = resampledData["activity_type"].resample("D").apply(lambda x: stats.mode(x)[0] if len(stats.mode(x)[0]) != 0 else None)
+
+            #finding different number of activities during a day
+            if "countuniqueactivities" in features_to_compute:
+                ar_features["ar_" + day_segment + "_countuniqueactivities"] = resampledData["activity_type"].resample("D").nunique()
+            
+            #finding Number of times activity changed
+            if "activitychangecount" in features_to_compute:
+                resampledData["activity_type_shift"] = resampledData["activity_type"].shift().fillna(resampledData["activity_type"].head(1))
+                resampledData["different_activity"] = np.where(resampledData["activity_type"]!=resampledData["activity_type_shift"],1,0)
+                ar_features["ar_" + day_segment + "_activitychangecount"] = resampledData["different_activity"].resample("D").sum()
+
+
+            deltas_features = {"sumstationary":["still","tilting"], 
+                            "summobile":["on_foot","walking","running","on_bicycle"],
+                            "sumvehicle":["in_vehicle"]}
+            
+            for column, activity_labels in deltas_features.items():
+                if column in features_to_compute:
+                    ar_features["ar_" + day_segment + "_" + column] = ar_deltas[ar_deltas["activity"].isin(pd.Series(activity_labels))].groupby(["local_start_date"])["time_diff"].sum()
+        
+        ar_features.index.names = ["local_date"]
+        ar_features = ar_features.reset_index()
+
+    return ar_features