[WIP] Add a test for SensorFeatures.

Additional analysis for adherence.
Small corrections.

config/environment.yml

@@ -12,7 +12,7 @@ dependencies:
   - mypy
   - nodejs
   - pandas
-  - psycopg2
+  - psycopg2 >= 2.9.1
   - python-dotenv
   - pytz
   - pyprojroot

machine_learning/labels.py

@@ -35,6 +35,7 @@ class Labels:
             participants_usernames = participants.query_db.get_usernames(
                 collection_start=datetime.date.fromisoformat("2020-08-01")
             )
+            self.participants_label = "all"
         self.participants_usernames = participants_usernames
 
         self.df_esm = pd.DataFrame()

statistical_analysis/adherence.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.11.4
+#       jupytext_version: 1.12.0
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -96,13 +96,31 @@ df_session_counts_time = classify_sessions_by_completion_time(df_esm_preprocesse
 # Sessions are now classified according to the type of a session (a true questionnaire or simple single questions) and users response.
 
 # %%
-df_session_counts_time
+df_session_counts_time["session_response_cat"] = df_session_counts_time["session_response"].astype("category")
+df_session_counts_time["session_response_cat"] = df_session_counts_time["session_response_cat"].cat.remove_categories(['during_work_first', 'ema_unanswered', 'evening_first', 'morning', 'morning_first'])
+df_session_counts_time["session_response_cat"] = df_session_counts_time["session_response_cat"].cat.add_categories("interrupted")
+df_session_counts_time.loc[df_session_counts_time["session_response_cat"].isna(), "session_response_cat"] = "interrupted"
+#df_session_counts_time["session_response_cat"] = df_session_counts_time["session_response_cat"].cat.rename_categories({
+#    "ema_unanswered": "interrupted", 
+#    "morning_first": "interrupted", 
+#    "evening_first": "interrupted",
+#    "morning": "interrupted",
+#    "during_work_first": "interrupted"})
+
+# %%
+df_session_counts_time.session_response_cat
 
 # %%
 tbl_session_outcomes = df_session_counts_time.reset_index()[
-    "session_response"
+    "session_response_cat"
 ].value_counts()
 
+# %%
+tbl_session_outcomes_relative = tbl_session_outcomes / len(df_session_counts_time)
+
+# %%
+print(tbl_session_outcomes_relative.to_latex(escape=True))
+
 # %%
 print("All sessions:", len(df_session_counts_time))
 print("-------------------------------------")

test/test_features_sensor.py

@@ -0,0 +1,25 @@
+import unittest
+
+import yaml
+from pyprojroot import here
+
+from machine_learning.features_sensor import *
+
+
+class SensorFeaturesTest(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        with open(here("machine_learning/config/minimal_features.yaml"), "r") as file:
+            cls.sensor_features_params = yaml.safe_load(file)
+
+    def test_yaml(self):
+        with open(here("machine_learning/config/minimal_features.yaml"), "r") as file:
+            sensor_features_params = yaml.safe_load(file)
+        self.assertIsInstance(sensor_features_params, dict)
+        self.assertIsInstance(sensor_features_params.get("grouping_variable"), str)
+        self.assertIsInstance(sensor_features_params.get("features"), dict)
+        self.assertIsInstance(sensor_features_params.get("participants_usernames"), list)
+
+    def test_participants_label(self):
+        sensor_features = SensorFeatures(**self.sensor_features_params)
+        self.assertRaises(ValueError, sensor_features.calculate_features)