Fix question IDs.

features/esm_COPE.py

@@ -136,7 +136,7 @@ def reassign_question_ids(df_cope_cleaned: pd.DataFrame) -> pd.DataFrame:
     )
     # Tabulate all possible answers to each question (group by question ID).
 
-    df_cope_fixed = df_cope_cleaned.copy()
+    # First, check that we anticipated all esm instructions.
     for q_id in dict_COPE_question_ids.keys():
         # Look for all questions ("instructions") occurring in the dataframe.
         actual_questions = df_esm_cope_unique_questions.loc[
@@ -154,6 +154,20 @@ def reassign_question_ids(df_cope_cleaned: pd.DataFrame) -> pd.DataFrame:
             raise KeyError(actual_questions[~questions_matches])
             # In case there is an unexpected answer, raise an exception.
 
+    # Next, replace question IDs.
+    df_cope_fixed = df_cope_cleaned.copy()
+    df_cope_fixed["question_id"] = df_cope_cleaned["esm_instructions"].apply(
+        lambda x: next(
+            (
+                key
+                for key, values in dict_COPE_question_ids.items()
+                if x.startswith(values)
+            ),
+            None,
+        )
+    )
+
+    # Finally, increment numeric answers.
     try:
         df_cope_fixed = df_cope_fixed.assign(
             esm_user_score=lambda x: x.esm_user_answer_numeric + 1