[WIP] Add a function to recode question IDs.

features/esm_COPE.py

@@ -1,3 +1,8 @@
+import pandas as pd
+
+COPE_ORIGINAL_MAX = 4
+COPE_ORIGINAL_MIN = 1
+
 dict_COPE_question_ids = {
     164: (
         "I took additional action to try to get rid of the problem",
@@ -120,3 +125,44 @@ dict_COPE_question_ids = {
         "Razburil sem se in razmišljal samo o tem",
     ),
 }
+
+
+def reassign_question_ids(df_cope_cleaned: pd.DataFrame) -> pd.DataFrame:
+    df_esm_cope_unique_questions = (
+        df_cope_cleaned.groupby("question_id")
+        .esm_instructions.value_counts()
+        .rename()
+        .reset_index()
+    )
+    # Tabulate all possible answers to each question (group by question ID).
+
+    df_cope_fixed = df_cope_cleaned.copy()
+    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[
+            df_esm_cope_unique_questions["question_id"] == q_id,
+            "esm_instructions",
+        ]
+        # These are all answers to a given question (by q_id).
+        questions_matches = actual_questions.str.startswith(
+            dict_COPE_question_ids.get(q_id)
+        )
+        # See if they are expected, i.e. included in the dictionary.
+        if ~actual_questions.all():
+            print("One of the questions that occur in the data was undefined.")
+            print("This were the questions found in the data: ")
+            raise KeyError(actual_questions[~questions_matches])
+            # In case there is an unexpected answer, raise an exception.
+
+    try:
+        df_cope_fixed = df_cope_fixed.assign(
+            esm_user_score=lambda x: x.esm_user_answer_numeric + 1
+        )
+        # Increment the original answer by 1
+        # to keep in line with traditional scoring
+        # (from COPE_ORIGINAL_MIN - COPE_ORIGINAL_MAX).
+    except AttributeError as e:
+        print("Please, clean the dataframe first using features.esm.clean_up_esm.")
+        print(e)
+
+    return df_cope_fixed