Basic functionality includes identifying similar words:
model.wv.most_similar(positive=['iphone'],
restrict_vocab=15000)
term similarity
0 android 0.600454
1 smartphone 0.581685
2 app 0.559129
We can also validate individual analogies using positive and negative contributions accordingly:
model.wv.most_similar(positive=['france', 'london'],
negative=['paris'],
restrict_vocab=15000)
term similarity
0 united_kingdom 0.606630
1 germany 0.585644
2 netherlands 0.578868