Test that an extra column is not kept

tests/preprocessing/test_apps.py

@@ -15,6 +15,7 @@ def test_app_features():
     screen["group"] = "group1"
     battery["group"] = "group1"
     test = app.extract_features_app(data, battery, screen, features=None)
+    data["extra_column"] = "extra"
 
     user_comm = test[(test["user"] == "dvWdLQesv21a") & (test["app_group"] == "comm")]
     user_work = test[(test["user"] == "dvWdLQesv21a") & (test["app_group"] == "work")]
@@ -45,3 +46,4 @@ def test_app_features():
     assert user_work.loc["2019-08-06 04:00:00+03:00"]["count"] == 2
     assert user_comm.loc["2019-08-05 20:00:00+03:00"]["duration"] == 3569.00
     assert user_work.loc["2019-08-06 04:00:00+03:00"]["duration"] == 2578
+    assert "extra_column" not in test.columns

tests/preprocessing/test_audio.py

@@ -13,7 +13,11 @@
 
 def test_audio_features():
     data["group"] = "group1"
+    data["extra_column"] = "extra"
     test = audio.extract_features_audio(data)
+
+    assert "group" in test.columns
+    assert "extra_column" not in test.columns
 
     test_user1 = test[test["user"] == "jd9INuQ5BBlW"]
     assert test_user1["audio_count_silent"].sum() == 0

tests/preprocessing/test_battery.py

@@ -30,6 +30,7 @@
 def test_format_battery_data():
     df = df11.copy()
     battery = niimpy.preprocessing.battery.format_battery_data(df, {})
+
     assert battery.loc[Timestamp('2019-01-17 09:20:14.049999872+02:00'), 'battery_level'] == 96
     assert battery.loc[Timestamp('2019-01-17 09:21:26.036000+02:00'), 'battery_health'] == '2'
     assert battery.loc[Timestamp('2019-01-17 09:48:59.438999808+02:00'), 'battery_status'] == '-2'
@@ -39,8 +40,11 @@ def test_format_battery_data():
 
 def test_battery_occurrences():
     df = df11.copy()
+    df["extra_column"] = "extra"
     k = niimpy.preprocessing.battery.battery_occurrences
     occurrences = niimpy.preprocessing.battery.extract_features_battery(df, features={k: {}})
+
+    assert "extra_column" not in occurrences.columns
     occurrences_user = occurrences[occurrences["user"] == "wAzQNrdKZZax"]
     assert occurrences_user.loc[Timestamp('2019-01-17 09:00:00+02:00')]["occurrences"] == 3
     occurrences_user = occurrences[occurrences["user"] == "lb983ODxEFUD"]

tests/preprocessing/test_communication.py

@@ -108,8 +108,10 @@ def test_message_features_with_google_chat(google_takeout_zipped):
             sentiment_batch_size = 2
         )
         data["group"] = "group1"
+        data["extra_column"] = "extra"
 
     test = comms.extract_features_comms(data, features=None)
+    assert "extra_column" not in test.columns
     print(test.loc[pd.Timestamp("2024-01-30 13:00:00+00:00", tz='Europe/Helsinki')])
     assert test.loc[pd.Timestamp("2024-01-30 13:00:00+00:00", tz='Europe/Helsinki')]["outgoing_count"] == 2
     assert test.loc[pd.Timestamp("2024-01-30 13:00:00+00:00", tz='Europe/Helsinki')]["group"] == "group1"

tests/preprocessing/test_location.py

@@ -32,7 +32,9 @@ def test_distance_matrix():
 
 def test_location_features():
     # extract featuers
+    data["extra_column"] = "extra"
     features = nilo.extract_features_location(data)
+    assert "extra_column" not in features.columns
 
     sps = features['n_sps'].dropna()
     assert ((sps > 0) & (sps < 100)).all(), "Number of SPs not reasonable"

tests/preprocessing/test_screen.py

@@ -13,7 +13,10 @@
 
 def test_audio_features():
 
+    data["extra_column"] = "extra"
     test = sc.extract_features_screen(data, bat, features=None)
+    assert "extra_column" not in test.columns
+
     time = pd.Timestamp("2020-01-09 02:30:00", tz='Europe/Helsinki')
 
     test_user = test[test["user"] == "jd9INuQ5BBlW"]

tests/preprocessing/test_tracker.py

@@ -12,8 +12,11 @@ def test_step_summary():
     # Converting the index as date
     df.index = pd.to_datetime(df.index)
     df = df.rename(columns={"subject_id": "user"})
+    df["extra_column"] = "extra"
 
     summary_df = tracker.step_summary(df, {'value_col': 'steps'})
+
+    assert "extra_column" not in summary_df.columns
     assert summary_df['max_sum_step'].values[0] == 13025
     assert summary_df['min_sum_step'].values[0] == 5616
     assert round(summary_df['avg_sum_step'].values[0], 2) == 8437.38