Doc2vec similarity

from gensim.models import doc2vec
from scipy import spatial

d2v_model = doc2vec.Doc2Vec.load(model_file)

fisrt_text = '..'
second_text = '..'

vec1 = d2v_model.infer_vector(fisrt_text.split())
vec2 = d2v_model.infer_vector(second_text.split())

similairty = spatial.distance.cosine(vec1, vec2)
# similarity is how much two text differ from each other, higher values mean more distinct texts

Source: stackoverflow.com

Similar codes

1 vote162 views1 answer
Spacy tokineze stream
Python
0 vote148 views1 answer
(Word or Phrase to Phone-Number Generator) python
Python
1 vote133 views1 answer
Count number of repeats in list python
Python
-1 vote140 views1 answer
Opencv python rgb to hsv
Python
6 votes144 views2 answers
Get_or_create django
Python Django
2 votes148 views1 answer
Reverse order np array
Python
0 vote155 views1 answer
Cv2 read rgb image
Python
2 votes144 views1 answer
Superscript print python
Python
0 vote161 views1 answer
57 *2
Python
0 vote154 views2 answers
Addinput() python
Python