Initial import

process-gradescope-grades.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+# Script to ...
+#
+# Minimally tested.  Seems to work.  Use at your own risk.
+#
+# By James Eagan <james.eagan@telecom-paris.fr>
+# https://james.eagan.fr
+
+import pandas as pd
+import re
+
+skipCols = ['SID', 'Email', 'Submission ID', 'Submission Time', 
+            'Lateness (H:M:S)', 'View Count', 'Submission Count',
+           ]
+
+def readCSV(fileName):
+    cols = list(pd.read_csv(fileName, nrows=1))
+    keepCols = [col for col in cols if col not in skipCols]
+    
+    df = pd.read_csv(fileName, usecols=keepCols)
+    df = df.sort_values(by='Nom')
+    return df
+
+pattern = re.compile(r'(\d+\.?\d*): (.+) \((\d+\.\d*) pts\)')
+def massageHeaders(df, args):
+    multiHeaders = [[], [], []]
+
+    for header in df.columns:
+        match = pattern.match(header)
+        if match:
+            # Question in the form: '11.4: types d'attributs (variables) (1.0 pts)'
+            multiHeaders[0].append('Q' + match.group(1)) # Q1, Q2, Q3.1, Q3.2, etc
+            multiHeaders[1].append(match.group(2)) # Question label
+            multiHeaders[2].append(float(match.group(3))) # Question points (e.g. 1, 2, 1.5)
+        else:
+            multiHeaders[0].append('')
+            multiHeaders[1].append('')
+            multiHeaders[2].append(header)
+
+    df.columns = pd.MultiIndex.from_arrays(multiHeaders)
+    return df
+
+def writeExcel(df, fileName):
+    with pd.ExcelWriter(fileName) as writer:
+        df.to_excel(writer)
+#     with open(basename + "-out.csv", 'w') as writer:
+#         writer.write(df.to_csv())
+
+if __name__ == '__main__':
+    import argparse
+    import sys
+    
+    def parse_args():
+        parser = argparse.ArgumentParser(description="Massage Gradescope data")
+        parser.add_argument("csv", help="csv file as exported from Gradescope")
+        parser.add_argument("-o", "--out", help="file to write output")
+        group = parser.add_mutually_exclusive_group()
+        group.add_argument("-,", "--commas", help="use commas for decimal separator", action="store_true")
+        group.add_argument("-.", "--dots", help="use dots for decimal separator", action="store_true")
+        group.add_argument("-d", "--decimal-separator", help="decimal separator for real numbers", default=",")
+        parser.add_argument("-s", "--sep", help="csv column separator (default: ',' when decimal separator is '.' and ';' for ',')")
+
+        args = parser.parse_args()
+        if args.commas:
+            args.decimal_separator = ","
+        elif args.dots:
+            args.decimal_separator = "."
+        
+        if not args.sep:
+            args.sep = ';' if args.decimal_separator == ',' else ','
+            
+        return args
+    
+    def writeOutput(df, args):
+        if args.out:
+            writeExcel(df, args.out)
+        else :
+            df.to_csv(sys.stdout, sep=args.sep, decimal=args.decimal_separator)
+    
+    def nowDoIt():
+        args = parse_args()
+        df = readCSV(args.csv)
+        massageHeaders(df, args)
+        writeOutput(df, args)
+
+    nowDoIt()
+