sklearn使用TFIDF进行文本关键字提取

# encoding=utf-8
from sklearn.feature_extraction.text import TfidfVectorizer, TfidfTransformer

corpus = [
     'This This is the first document.',
     'This This is the second second document.',
     'And the third one.',
     'Is this the first document?',
 ]
tfidf_model = TfidfVectorizer()
tfidf_matrix = tfidf_model.fit_transform(corpus)
word_dict=tfidf_model.get_feature_names()
print(word_dict)
print(tfidf_matrix)

实验结果：

"C:\Program Files\Anaconda3\python.exe" D:/pycharmprogram/csgwork/find_classification_keys/test_tfidfVectorizer.py
['and', 'document', 'first', 'is', 'one', 'second', 'the', 'third', 'this']
  (0, 8)	0.6986804246371375
  (0, 3)	0.34934021231856877
  (0, 6)	0.2856085141790751
  (0, 2)	0.43150466158747897
  (0, 1)	0.34934021231856877
  (1, 8)	0.49256714844677196
  (1, 3)	0.24628357422338598
  (1, 6)	0.20135295972313796
  (1, 1)	0.24628357422338598
  (1, 5)	0.7717016211057586
  (2, 6)	0.2884767487500274
  (2, 0)	0.5528053199908667
  (2, 7)	0.5528053199908667
  (2, 4)	0.5528053199908667
  (3, 8)	0.4387767428592343
  (3, 3)	0.4387767428592343
  (3, 6)	0.35872873824808993
  (3, 2)	0.5419765697264572
  (3, 1)	0.4387767428592343

Process finished with exit code 0