Add tests for proximity.

data/example_proximity.csv

@@ -0,0 +1,63 @@
+id,timestamp,device_id,_id,double_proximity,accuracy,label,dateTime
+39017,1565802024310,f67354f7-d675-4b76-80c8-123cc4744a5b,2962,0,3,,2019-08-14T17:00:24Z
+39018,1565802051075,f67354f7-d675-4b76-80c8-123cc4744a5b,2963,0,3,,2019-08-14T17:00:51Z
+39019,1565802051354,f67354f7-d675-4b76-80c8-123cc4744a5b,2964,8,3,,2019-08-14T17:00:51Z
+39089,1565010418305,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,51,5,3,,2019-08-05T13:06:58Z
+39090,1565010772188,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,52,5,3,,2019-08-05T13:12:52Z
+39091,1565012334450,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,53,5,3,,2019-08-05T13:38:54Z
+39092,1565013000660,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,54,5,3,,2019-08-05T13:50:00Z
+39093,1565022742894,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,55,0,3,,2019-08-05T16:32:22Z
+39094,1565089295906,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,56,5,3,,2019-08-06T11:01:35Z
+39095,1565096030817,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,57,0,3,,2019-08-06T12:53:50Z
+39096,1565096367694,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,58,5,3,,2019-08-06T12:59:27Z
+39097,1565096408570,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,59,5,3,,2019-08-06T13:00:08Z
+39098,1565116821528,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,60,5,3,,2019-08-06T18:40:21Z
+39099,1565131345333,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,61,0,3,,2019-08-06T22:42:25Z
+39100,1565131375072,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,62,5,3,,2019-08-06T22:42:55Z
+39101,1565131386353,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,63,0,3,,2019-08-06T22:43:06Z
+39102,1565131389213,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,64,5,3,,2019-08-06T22:43:09Z
+39103,1565131448891,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,65,0,3,,2019-08-06T22:44:08Z
+39104,1565131454131,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,66,5,3,,2019-08-06T22:44:14Z
+39105,1565176143083,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,67,0,3,,2019-08-07T11:09:03Z
+39106,1565179569310,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,68,5,3,,2019-08-07T12:06:09Z
+39107,1565180699173,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,69,5,3,,2019-08-07T12:24:59Z
+39108,1565182538578,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,70,5,3,,2019-08-07T12:55:38Z
+39109,1565192592776,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,71,0,3,,2019-08-07T15:43:12Z
+39110,1565216023797,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,72,5,3,,2019-08-07T22:13:43Z
+39111,1565248358647,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,73,0,3,,2019-08-08T07:12:38Z
+39112,1565275859157,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,74,5,3,,2019-08-08T14:50:59Z
+39113,1565304201431,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,75,0,3,,2019-08-08T22:43:21Z
+39114,1565304229591,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,76,5,3,,2019-08-08T22:43:49Z
+39115,1565304262050,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,77,0,3,,2019-08-08T22:44:22Z
+39116,1565613142970,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,78,5,3,,2019-08-12T12:32:22Z
+39117,1565618266531,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,79,5,3,,2019-08-12T13:57:46Z
+39118,1565618410488,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,80,5,3,,2019-08-12T14:00:10Z
+39119,1565618704942,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,81,5,3,,2019-08-12T14:05:04Z
+39120,1565619005315,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,82,5,3,,2019-08-12T14:10:05Z
+39121,1565619405904,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,83,5,3,,2019-08-12T14:16:45Z
+39122,1565619678037,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,84,5,3,,2019-08-12T14:21:18Z
+39123,1565621206713,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,85,5,3,,2019-08-12T14:46:46Z
+39124,1565626622125,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,86,5,3,,2019-08-12T16:17:02Z
+39125,1565684876738,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,87,5,3,,2019-08-13T08:27:56Z
+39126,1565684956618,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,88,5,3,,2019-08-13T08:29:16Z
+39127,1565684965647,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,89,5,3,,2019-08-13T08:29:25Z
+39128,1565685092246,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,90,5,3,,2019-08-13T08:31:32Z
+39129,1565685136337,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,91,5,3,,2019-08-13T08:32:16Z
+39130,1565685147453,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,92,5,3,,2019-08-13T08:32:27Z
+39131,1565685212523,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,93,5,3,,2019-08-13T08:33:32Z
+39132,1565703397796,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,94,0,3,,2019-08-13T13:36:37Z
+39133,1565776203019,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,95,5,3,,2019-08-14T09:50:03Z
+39134,1565776434168,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,96,5,3,,2019-08-14T09:53:54Z
+39135,1565776435231,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,97,0,3,,2019-08-14T09:53:55Z
+39136,1565776443368,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,98,5,3,,2019-08-14T09:54:03Z
+39137,1565779277109,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,99,0,3,,2019-08-14T10:41:17Z
+39138,1565780016327,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,100,5,3,,2019-08-14T10:53:36Z
+39139,1565780027437,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,101,5,3,,2019-08-14T10:53:47Z
+39140,1565783470934,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,102,5,3,,2019-08-14T11:51:10Z
+39141,1565783801540,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,103,0,3,,2019-08-14T11:56:41Z
+39142,1565783802120,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,104,5,3,,2019-08-14T11:56:42Z
+39143,1565783861495,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,105,5,3,,2019-08-14T11:57:41Z
+39144,1565785318762,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,106,0,3,,2019-08-14T12:21:58Z
+39145,1565785319346,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,107,5,3,,2019-08-14T12:21:59Z
+39146,1565960121019,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,108,5,3,,2019-08-16T12:55:21Z
+39147,1565960226792,fdb06d4a-ee6e-4336-9a96-fc8d2715f243,109,5,3,,2019-08-16T12:57:06Z

features/proximity.py

@@ -5,6 +5,8 @@ import pandas as pd
 from config.models import Participant, Proximity
 from setup import db_engine, session
 
+FEATURES_PROXIMITY = ["freq_prox_near", "prop_prox_near"]
+
 
 def get_proximity_data(usernames: Collection) -> pd.DataFrame:
     """
@@ -56,7 +58,7 @@ def recode_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
 
 
 def count_proximity(
-    df_proximity: pd.DataFrame, group_by: Collection = ["participant_id"]
+    df_proximity: pd.DataFrame, group_by: Collection = None
 ) -> pd.DataFrame:
     """
     The function counts how many times a "near" value occurs in proximity
@@ -75,6 +77,8 @@ def count_proximity(
     df_proximity_features: pd.DataFrame
         A dataframe with the count of "near" proximity values and their relative count.
     """
+    if group_by is None:
+        group_by = ["participant_id"]
     if "bool_prox_near" not in df_proximity:
         df_proximity = recode_proximity(df_proximity)
     df_proximity["bool_prox_far"] = ~df_proximity["bool_prox_near"]

test/test_proximity.py

@@ -0,0 +1,31 @@
+import unittest
+
+from features.proximity import *
+
+
+class ProximityFeatures(unittest.TestCase):
+    df_proximity = pd.DataFrame()
+    df_proximity_recoded = pd.DataFrame()
+    df_proximity_features = pd.DataFrame()
+
+    @classmethod
+    def setUpClass(cls) -> None:
+        cls.df_proximity = pd.read_csv("../data/example_proximity.csv")
+        cls.df_proximity["participant_id"] = 99
+
+    def test_recode_proximity(self):
+        self.df_proximity_recoded = recode_proximity(self.df_proximity)
+        self.assertIn("bool_prox_near", self.df_proximity_recoded)
+        # Is the recoded column present?
+        self.assertIn(True, self.df_proximity_recoded.bool_prox_near)
+        # Are there "near" values in the data?
+        self.assertIn(False, self.df_proximity_recoded.bool_prox_near)
+        # Are there "far" values in the data?
+
+    def test_count_proximity(self):
+        self.df_proximity_recoded = recode_proximity(self.df_proximity)
+        self.df_proximity_features = count_proximity(self.df_proximity_recoded)
+        print(self.df_proximity_features.columns)
+        self.assertCountEqual(
+            self.df_proximity_features.columns.to_list(), FEATURES_PROXIMITY
+        )