-
Notifications
You must be signed in to change notification settings - Fork 1
/
my_script.py
38 lines (32 loc) · 1.21 KB
/
my_script.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
import os
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
student_files = [doc for doc in os.listdir() if doc.endswith('.txt')]
student_notes =[open(File).read() for File in student_files]
vectorize = lambda Text: TfidfVectorizer().fit_transform(Text).toarray()
similarity = lambda doc1, doc2: cosine_similarity([doc1, doc2])
vectors = vectorize(student_notes)
s_vectors = list(zip(student_files, vectors))
def check_plagiarism():
plagiarism_results = set()
global s_vectors
for student_a, text_vector_a in s_vectors:
new_vectors =s_vectors.copy()
current_index = new_vectors.index((student_a, text_vector_a))
del new_vectors[current_index]
for student_b , text_vector_b in new_vectors:
sim_score = similarity(text_vector_a, text_vector_b)[0][1]
student_pair = sorted((student_a, student_b))
score = (student_pair[0], student_pair[1],sim_score)
plagiarism_results.add(score)
return plagiarism_results
data = check_plagiarism()
i =0
ans = 0
for res in data:
for r in res:
if i==2:
ans = round(r,2)
break
i+=1
print(ans*100)