cleanup code

inspect_submissions.py

@@ -3,6 +3,7 @@ import pandas as pd
 from datetime import datetime
 from utils.inspector import hash_submissions, suspicious_by_hash
 
+CSV_DIR = os.path.join(os.getcwd(), 'csv')
 
 def main():
     submissions_dir_name = ' '.join(sys.argv[1:]) if len(sys.argv) > 1 else exit(f'\nNo submissions dir name given. Provide the name as an argument.\n\nUsage: python {sys.argv[0]} [submissions dir name]\nExample: python {sys.argv[0]} AssignmentX\n')
@@ -10,15 +11,15 @@ def main():
     if not os.path.isdir(submissions_dir_path):
         exit(f'Directory {submissions_dir_path} does not exist.\nMake sure "{submissions_dir_name}" exists in "BB_submissions".')
     else:
-        hashes_csv_file_path = hash_submissions(submissions_dir_path)
+        hashes_csv_file_path = hash_submissions(submissions_dir_path)  # generate hashes for all files and return output csv file to load & find duplicate/suspicious hashes
-        
         csv = pd.read_csv(hashes_csv_file_path)
         df = pd.DataFrame(csv)  # df with all files and their hashes
-        df_suspicious = suspicious_by_hash(df)  # df with all files with duplicate hash, excludes files from the same student id
+        df_suspicious = suspicious_by_hash(df)  # df with all files with duplicate/suspicious hash, excludes files from the same student id
+        
         csv_name = f'{submissions_dir_name}_suspicious_{datetime.now().strftime("%Y%m%d-%H%M%S")}.csv'
-        csv_out = os.path.join('csv', csv_name)
+        csv_out = os.path.join(CSV_DIR, csv_name)
         df_suspicious.to_csv(csv_out, index=False)
 
 
 if __name__ == '__main__':    
-    main()
+    main()

utils/inspector.py

@@ -8,7 +8,7 @@ CSV_DIR = os.path.join(os.getcwd(), 'csv')
 
 def get_hashes_in_dir(dir_path: str) -> list:
     hash_list = []
-    for subdir, dirs, files in os.walk(dir_path):  # Loop through all files in the directory and generate hashes
+    for subdir, dirs, files in os.walk(dir_path):  # loop through all files in the directory and generate hashes
         for file in files:
             filepath = os.path.join(subdir, file)
             with open(filepath, 'rb') as f:
@@ -17,33 +17,34 @@ def get_hashes_in_dir(dir_path: str) -> list:
     return hash_list
 
 
-def hash_submissions(submissions_dir_path: str):
+def hash_submissions(submissions_dir_path: str) -> str:
     os.makedirs(CSV_DIR, exist_ok=True)
 
-    submissions_dir_name = os.path.abspath(submissions_dir_path).split(os.path.sep)[-1]
+    submissions_dir_name = os.path.abspath(submissions_dir_path).split(os.path.sep)[-1]  # get name of submission/assignment by separating path and use rightmost part
     csv_file_name = f'{submissions_dir_name}_file_hashes_{datetime.now().strftime("%Y%m%d-%H%M%S")}.csv'
     csv_file_path = os.path.join(CSV_DIR, csv_file_name)
-    with open(csv_file_path, 'w', newline='') as csvfile:      # Open the output CSV file for writing
+    with open(csv_file_path, 'w', newline='') as csvfile:  # open the output CSV file for writing
         fieldnames = ['Student ID', 'filepath', 'filename', 'sha256 hash']
         writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
         writer.writeheader()
 
-        for student_dir_name in os.listdir(submissions_dir_path):
+        for student_dir_name in os.listdir(submissions_dir_path):  # loop through each student dir to get hashes for all files per student
             student_dir_path = os.path.join(submissions_dir_path, student_dir_name)
-            hashes_dict = get_hashes_in_dir(student_dir_path)        
+            hashes_dict = get_hashes_in_dir(student_dir_path)  # dict with hashes for all student files 
             for d in hashes_dict:
                 d.update({'Student ID': student_dir_name})  # update hash records with student id
             writer.writerows(hashes_dict)
     return csv_file_path
 
+
 def get_suspicious_hashes(df: pd.DataFrame) -> list:
-    drop_columns = ['filepath', 'filename']
+    drop_columns = ['filepath', 'filename']  # only need to keep 'student id' and 'sha256 hash' for groupby later
     df = df.drop(columns=drop_columns).sort_values('sha256 hash')  # clear not needed colums & sort by hash
     duplicate_hash = df.loc[df.duplicated(subset=['sha256 hash'], keep=False), :]  # all files with duplicate hash - incl. files from the same student id
 
-    hash_with_multiple_student_ids = duplicate_hash.groupby('sha256 hash').agg(lambda x: len(x.unique())>1)  # true if more than 1 unique student ids (= multiple student ids with same hash), false if unique (= same student id re-submitting with the same hash)
+    hash_with_multiple_student_ids = duplicate_hash.groupby('sha256 hash').agg(lambda x: len(x.unique())>1)  # true if more than 1 unique student ids (= files with the same hash by multiple student ids), false if unique student id (= files from the same student id with the same hash)
 
-    suspicious_hashes_list = hash_with_multiple_student_ids[hash_with_multiple_student_ids['Student ID']==True].index.to_list()  # list with duplicate hashes - only if different student id (doesn't include attempts from same student id)
+    suspicious_hashes_list = hash_with_multiple_student_ids[hash_with_multiple_student_ids['Student ID']==True].index.to_list()  # list with duplicate hashes - only if different student id (doesn't include files from same student id)
     return suspicious_hashes_list