Guest User

Plagiarism detector

a guest
Oct 14th, 2021
5,866
1
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 1.11 KB | None | 1 0
  1. import os
  2. from numpy import vectorize
  3. from sklearn.feature_extraction.text import TfidfVectorizer
  4. from sklearn.metrics.pairwise import cosine_similarity
  5.  
  6. sample_files = [doc for doc in os.listdir() if doc.endswith('.txt')]
  7. sample_contents = [open(File).read() for File in sample_files]
  8.  
  9. vectorize = lambda Text: TfidfVectorizer().fit_transform(Text).toarray()
  10. similarity = lambda doc1, doc2: cosine_similarity([doc1, doc2])
  11.  
  12. vectors = vectorize(sample_contents)
  13. s_vectors = list(zip(sample_files, vectors))
  14.  
  15. def check_plagiarism():
  16.     results = set()
  17.     global s_vectors
  18.     for sample_a, text_vector_a in s_vectors:
  19.         new_vectors = s_vectors.copy()
  20.         current_index = new_vectors.index((sample_a, text_vector_a))
  21.         del new_vectors[current_index]
  22.         for sample_b, text_vector_b in new_vectors:
  23.             sim_score = similarity(text_vector_a, text_vector_b)[0][1]
  24.             sample_pair = sorted((sample_a, sample_b))
  25.             score = sample_pair[0], sample_pair[1], sim_score
  26.             results.add(score)
  27.     return results
  28.  
  29. for data in check_plagiarism():
  30.     print(data)    
Advertisement
Add Comment
Please, Sign In to add comment