Prepare Q045

data-preparation.py

@@ -45,7 +45,7 @@ def _fix_typos(data_df: pd.DataFrame) -> pd.DataFrame:
     return data_df
 
 
-def _remove_answers_from_non_developers(data_df: pd.DataFrame) -> pd.DataFrame:
+def _remove_invalid_answers(data_df: pd.DataFrame) -> pd.DataFrame:
     # cases in which respondents stated that they were not developing software
     # and hence could not answer the respective questions properly
     non_developers = [75, 100, 266, 324, 442, 506, 566, 572]
@@ -1059,7 +1059,6 @@ def _prepare_q038(data_df: pd.DataFrame) -> pd.DataFrame:
     data_df.loc[:, "Q038_comment"].mask(
         data_df.loc[:, "Q038"] == "A001", 1, inplace=True
     )
-
     return data_df
 
 
@@ -1197,6 +1196,10 @@ def _prepare_q044(data_df: pd.DataFrame) -> pd.DataFrame:
     return data_df
 
 
+def _prepare_q045(data_df: pd.DataFrame) -> pd.DataFrame:
+    data_df.loc[:, "Q045"] = None
+    return data_df
+
 def _check_existing_subquestions(data_df: pd.DataFrame,
                                  question: str) -> pd.DataFrame:
     """Set sub-question value to "Y" where implied in free text answer"""
@@ -1360,4 +1363,7 @@ data = _prepare_q037(data_df=data)
 data = _prepare_q038(data_df=data)
 data = _prepare_q043(data_df=data)
 data = _prepare_q044(data_df=data)
-data = _remove_answers_from_non_developers(data_df=data)
+data = _prepare_q045(data_df=data)
+data = _remove_invalid_answers(data_df=data)
+
+# TODO: Check if all free text answers are set None
\ No newline at end of file