From 1bc996413e2af3c3f4a93bb13c374f9b55c013e7 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Wed, 18 Aug 2021 15:23:30 +0200
Subject: [PATCH] Clarify names for no_all calls/sms feature.

Add another test.
---
 features/communication.py  | 14 +++++++-------
 test/test_communication.py |  8 +++++++-
 2 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/features/communication.py b/features/communication.py
index c5d5056..30275d3 100644
--- a/features/communication.py
+++ b/features/communication.py
@@ -141,11 +141,11 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
             .add_prefix("no_")
         )
         # Count calls by type.
-        comm_counts["no_all"] = comm_counts.sum(axis=1)
+        comm_counts["no_calls_all"] = comm_counts.sum(axis=1)
         # Add a total count of calls.
         comm_counts = comm_counts.assign(
-            no_incoming_ratio=lambda x: x.no_incoming / x.no_all,
-            no_outgoing_ratio=lambda x: x.no_outgoing / x.no_all,
+            no_incoming_ratio=lambda x: x.no_incoming / x.no_calls_all,
+            no_outgoing_ratio=lambda x: x.no_outgoing / x.no_calls_all,
         )
         # Ratio of incoming and outgoing calls to all calls.
         comm_duration_total = (
@@ -181,11 +181,11 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
             .rename(columns=sms_types)
             .add_prefix("no_")
         )
-        comm_counts["no_all"] = comm_counts.sum(axis=1)
+        comm_counts["no_sms_all"] = comm_counts.sum(axis=1)
         # Add a total count of messages.
         comm_features = comm_counts.assign(
-            no_received_ratio=lambda x: x.no_received / x.no_all,
-            no_sent_ratio=lambda x: x.no_sent / x.no_all,
+            no_received_ratio=lambda x: x.no_received / x.no_sms_all,
+            no_sent_ratio=lambda x: x.no_sent / x.no_sms_all,
         )
         # Ratio of incoming and outgoing messages to all messages.
     else:
@@ -280,7 +280,7 @@ def calls_sms_features(df_calls: pd.DataFrame, df_sms: pd.DataFrame) -> pd.DataF
         .reset_index()  # Make participant_id a regular column
         .assign(
             proportion_calls=(
-                lambda x: x.no_all_calls / (x.no_all_calls + x.no_all_sms)
+                lambda x: x.no_calls_all / (x.no_calls_all + x.no_sms_all)
             ),
             proportion_calls_incoming=(
                 lambda x: x.no_incoming / (x.no_incoming + x.no_received)
diff --git a/test/test_communication.py b/test/test_communication.py
index a767255..9e951d2 100644
--- a/test/test_communication.py
+++ b/test/test_communication.py
@@ -5,7 +5,7 @@ import pandas as pd
 from numpy.random import default_rng
 from pandas.testing import assert_series_equal
 
-from features.communication import count_comms, enumerate_contacts, get_call_data
+from features.communication import *
 
 rng = default_rng()
 
@@ -78,8 +78,14 @@ class CallsFeatures(unittest.TestCase):
         self.features = count_comms(self.calls)
         print(self.features)
         self.assertIsInstance(self.features, pd.DataFrame)
+        self.assertCountEqual(self.features.columns.to_list(), FEATURES_CALLS)
 
     def test_count_comms_sms(self):
         self.features = count_comms(self.sms)
         print(self.features)
         self.assertIsInstance(self.features, pd.DataFrame)
+
+    def test_calls_sms_features(self):
+        self.features_call_sms = calls_sms_features(self.calls, self.sms)
+        print(self.features_call_sms.columns)
+        self.assertIsInstance(self.features_call_sms, pd.DataFrame)