[WIP] Start calculating concordance.

Note, workday and morning EMAs have not been properly dealt with, but assumed answered.

.gitignore

@@ -4,3 +4,4 @@ __pycache__/
 */__pycache__/
 /exploration/*.ipynb
 /config/*.ipynb
+/statistical_analysis/*.ipynb

features/esm.py

@@ -106,4 +106,7 @@ def classify_sessions_adherence(df_esm_preprocessed: pd.DataFrame) -> pd.DataFra
 
     # TODO What can be done about workday EMA.
 
-    return sessions_grouped.count()
+    df_session_counts.loc[df_session_counts.session_response.isna(), "session_response"] = "esm_finished"
+    # TODO But for now, simply take all other ESMs as answered.
+
+    return df_session_counts

statistical_analysis/concordance.py

@@ -0,0 +1,44 @@
+# ---
+# jupyter:
+#   jupytext:
+#     formats: ipynb,py:percent
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.11.2
+#   kernelspec:
+#     display_name: straw2analysis
+#     language: python
+#     name: straw2analysis
+# ---
+
+# %%
+import os
+import sys
+import datetime
+import seaborn as sns
+import pandas as pd
+
+nb_dir = os.path.split(os.getcwd())[0]
+if nb_dir not in sys.path:
+    sys.path.append(nb_dir)
+import participants.query_db
+from features.esm import *
+
+# %%
+baseline_si = pd.read_csv('E:/STRAWbaseline/results-survey637813.csv')
+baseline_be_1 = pd.read_csv('E:/STRAWbaseline/results-survey358134.csv')
+baseline_be_2 = pd.read_csv('E:/STRAWbaseline/results-survey413767.csv')
+baseline = pd.concat([baseline_si, baseline_be_1, baseline_be_2], join="inner").reset_index().drop(columns="index")
+
+# %%
+participants_inactive_usernames = participants.query_db.get_usernames(collection_start=datetime.date.fromisoformat("2020-08-01"))
+
+# %%
+baseline_inactive = baseline[baseline["Gebruikersnaam"].isin(participants_inactive_usernames)]
+
+# %%
+df_esm_inactive = get_esm_data(participants_inactive_usernames)
+df_esm_preprocessed = preprocess_esm(df_esm_inactive)
+