word2vec_demo

# -*- coding: utf-8 -*-

from gensim.models.word2vec import Word2Vec
import gensim.downloader as api

#corpus = api.load('word2vec-google-news-300')
#corpus = api.load('glove-wiki-gigaword-100')
#model = api.load('glove-wiki-gigaword-100')
corpus = api.load('text8')  # download the corpus and return it opened as an iterable
model = Word2Vec(corpus)  # train a model from the corpus

model.most_similar("soccer",topn=3)


model.wv.most_similar(positive=['woman', 'king'], negative=['man'])

def analogy(x1, x2, y1):
    result = model.wv.most_similar(positive=[y1, x2], negative=[x1])
    return result[0][0]
	
analogy('china', 'chinese', 'japan')

import matplotlib.pyplot as plt
import numpy as np
plt.style.use('ggplot')

from sklearn.decomposition import PCA

def display_pca_scatterplot(model, words=None, sample=0):
    if words == None:
        if sample > 0:
            words = np.random.choice(list(model.vocab.keys()), sample)
        else:
            words = [ word for word in model.vocab ]
        
    word_vectors = np.array([model[w] for w in words])

    twodim = PCA().fit_transform(word_vectors)[:,:2]
    
    plt.figure(figsize=(6,6))
    plt.scatter(twodim[:,0], twodim[:,1], edgecolors='k', c='r')
    for word, (x,y) in zip(words, twodim):
        plt.text(x+0.05, y+0.05, word)

display_pca_scatterplot(model, 
                        ['coffee', 'tea', 'beer', 'wine','pizza',
                         'dog', 'horse', 'cat','football','tennis'])

display_pca_scatterplot(model, sample=100)