#学習させる
#https://www.pytry3g.com/entry/gensim-word2vec-tutorial

#学習済み
#http://cedro3.com/ai/word2vec-gensim/
#http://aial.shiroyagi.co.jp/2017/02/japanese-word2vec-model-builder/
#http://www.cl.ecei.tohoku.ac.jp/~m-suzuki/jawiki_vector/

 
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt


import codecs
from gensim.models import word2vec

#with codecs.open("./mecab_out/output_after_mecab.txt","r", "utf-8") as f:
with codecs.open("./mecab_out/output_after_mecab2.txt","r", "utf-8") as f:
    corpus1 = f.read().splitlines()


corpus=corpus1
corpus = [sentence.split() for sentence in corpus]
#モデルを作る
model = word2vec.Word2Vec(corpus, size=200, min_count=20, window=10)

# モデルを保存
model.save("ptenken_usa.model")