lafrite/recopytex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Feat: remove hard coded field in get_questions_scores

Browse Source
This commit is contained in:
Bertrand Benjamin 2021-04-06 19:41:56 +02:00
parent 94f94dae84
commit 9fce390304
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recopytex/store/filesystem/loader.py
View File

@ -156,7 +156,7 @@ class CSVLoader(Loader):
>>> questions = loader.get_exam_questions(exams) >>> questions = loader.get_exam_questions(exams)
>>> scores = loader.get_questions_scores(questions) >>> scores = loader.get_questions_scores(questions)
>>> scores.columns >>> scores.columns
Index(['id', 'origin', 'student_name', 'score'], dtype='object') Index(['origin', 'question_id', 'student_name', 'score'], dtype='object')
>>> scores["student_name"].unique() >>> scores["student_name"].unique()
array(['Star Tice', 'Umberto Dingate', 'Starlin Crangle', array(['Star Tice', 'Umberto Dingate', 'Starlin Crangle',
'Humbert Bourcq', 'Gabriella Handyside', 'Stewart Eaves', 'Humbert Bourcq', 'Gabriella Handyside', 'Stewart Eaves',
@ -170,20 +170,27 @@ class CSVLoader(Loader):
group_questions = questions.groupby("origin") group_questions = questions.groupby("origin")
for origin, questions_df in group_questions: for origin, questions_df in group_questions:
scores_df = pd.read_csv(origin) scores_df = pd.read_csv(origin)
student_names = [
c
for c in scores_df.columns
if c not in self._config["csv_fields"].values()
]
common_columns = [c for c in questions_df.columns if c in scores_df.columns] common_columns = [c for c in questions_df.columns if c in scores_df.columns]
scores_df = pd.merge(scores_df, questions_df, on=common_columns) scores_df = pd.merge(scores_df, questions_df, on=common_columns)
scores_df = scores_df.drop( scores_df = scores_df.drop(
columns=list(self._config["csv_fields"].values()) + ["exam_id"] columns=list(self._config["csv_fields"].values()) + ["exam_id"]
) )
kept_columns = ["id", "origin"]
student_names = [c for c in scores_df.columns if c not in kept_columns] kept_columns = [c for c in scores_df if c not in student_names]
scores_df = pd.melt( scores_df = pd.melt(
scores_df, scores_df,
id_vars=kept_columns, id_vars=kept_columns,
value_vars=student_names, value_vars=student_names,
var_name="student_name", var_name="student_name",
value_name="score", value_name="score",
) ).rename(columns={"id": "question_id"})
scores.append(scores_df) scores.append(scores_df)
return pd.concat(scores) return pd.concat(scores)