Add a method to get communication features.

features/communication.py

@@ -37,7 +37,7 @@ FEATURES_SMS = (
 #  "no_received_ratio", "no_sent_ratio",
 #  "no_contacts"]
 
-FEATURES_CONTACT = [
+FEATURES_CALLS_SMS_PROP = [
     "proportion_calls_all",
     "proportion_calls_incoming",
     "proportion_calls_outgoing",
@@ -45,6 +45,8 @@ FEATURES_CONTACT = [
     "proportion_calls_missed_sms_received",
 ]
 
+FEATURES_CALLS_SMS_ALL = FEATURES_CALLS + FEATURES_SMS + FEATURES_CALLS_SMS_PROP
+
 
 def get_call_data(usernames: Collection) -> pd.DataFrame:
     """

machine_learning/pipeline.py

@@ -69,6 +69,10 @@ class SensorFeatures:
             if feature_names == "all":
                 feature_names = proximity.FEATURES_PROXIMITY
             return self.df_proximity_counts[feature_names]
+        elif data_type == "communication":
+            if feature_names == "all":
+                feature_names = communication.FEATURES_CALLS_SMS_ALL
+            return self.df_calls_sms[feature_names]
         else:
             raise KeyError("This data type has not been implemented.")
 

test/test_communication.py

@@ -88,6 +88,5 @@ class CallsFeatures(unittest.TestCase):
         self.features_call_sms = calls_sms_features(self.calls, self.sms)
         self.assertIsInstance(self.features_call_sms, pd.DataFrame)
         self.assertCountEqual(
-            self.features_call_sms.columns.to_list(),
+            self.features_call_sms.columns.to_list(), FEATURES_CALLS_SMS_ALL
-            FEATURES_CALLS + FEATURES_SMS + FEATURES_CONTACT,
         )