1from gensim.models.keyedvectors import KeyedVectors
2
3kv=KeyedVectors.load("silicone-dyda_da-utterance-tokens.wordvectors")
4
5print(model.wv.most_similar_cosmul('peter',topn=25))
6
7[('steven', 0.889095664024353),
8 ('alice', 0.8783409595489502),
9 ('li', 0.8624751567840576),
10 ('benjamin', 0.8622595071792603),
11 ('mrs', 0.8615201711654663),
12 ('lin', 0.8603521585464478),
13 ('david', 0.8597986698150635),
14 ('dr', 0.8588740825653076),
15 ('wang', 0.8527941107749939),
16 ('mary', 0.8522424697875977),
17 ('mike', 0.8521847724914551),
18 ('john', 0.8494851589202881),
19 ('michael', 0.84917151927948),
20 ('linda', 0.8488836288452148),
21 ('lucy', 0.8375136256217957),
22 ('jane', 0.8359535336494446),
23 ('monica', 0.834464430809021),
24 ('smith', 0.8331072926521301),
25 ('susan', 0.8329276442527771),
26 ('zhang', 0.8323286771774292),
27 ('professor', 0.8316935896873474),
28 ('ellen', 0.8311569094657898),
29 ('daniel', 0.8285720944404602),
30 ('charles', 0.8285550475120544),
31 ('james', 0.8280013203620911)]
