update

grader.py

@@ -9,7 +9,7 @@
 
 import requests
 
-from utility import execute_system_call, find_emails, extract_link, unzip
+from utility import execute_system_call, find_emails, extract_link, unzip, remove_duplicates
 
 NULL_EMAIL = 'null___@null__.___'
 
@@ -227,7 +227,7 @@ def grade(self, hw_str='hw00', output_file='grades.csv'):
         """
         # create a file to store the grades
         with open(output_file, 'w', encoding='utf-8') as grades_file:
-            grades_file.write('Name, ID, Email, Language, Score\n')
+            grades_file.write('Name,ID,Email,Language,Score\n')
             # Unzip the submission file
             if not os.path.exists(self.submission_dir):
                 print('Unzipping the submission file ...')
@@ -257,4 +257,10 @@ def grade(self, hw_str='hw00', output_file='grades.csv'):
                     cnt_passes, email, student_code = self.grade_exception_file(hw_str, student_dir)
                     data.append( (cnt_passes, email, student_code))
                     self.output(grades_file, i, student_info, data)
+
+        grades_file.close()
+        print(f'\nGrades saved in {output_file}\n')
+        print('Cleaning up ...')
+        remove_duplicates(output_file)
+        print('==============  Grading completed! =============\n\n')
 

requirements.txt

@@ -1,3 +1,4 @@
 requests
 bs4
-numpy
+numpy
+pandas

utility.py

@@ -7,6 +7,7 @@
 import re
 import zipfile
 import subprocess
+import pandas as pd
 from bs4 import BeautifulSoup
 
 def execute_system_call(command):
@@ -61,3 +62,17 @@ def unzip(file, file_dir, skip_dir=True):
                     continue
                 zip_info.filename = os.path.basename(zip_info.filename)
                 zip_ref.extract(zip_info, file_dir)
+
+def remove_duplicates(csv_file):
+    """
+    Remove duplicate IDs (remain the maximum score value) in the CSV file with panda
+    """
+    # Read the CSV file
+    df = pd.read_csv(csv_file)
+
+    # Remove duplicate IDs (remain the maximum score value)
+    df = df.sort_values('Score', ascending=False).drop_duplicates('ID').sort_index()
+
+    # Write the updated data to the CSV file
+    df.to_csv(csv_file, index=False)
+