Word to vec using genism

word_to_vec_genism.py

from gensim.models import Word2Vec
# from tests import get_all_text


def save_model():
    # define training data
    sentences = get_all_text()
    # print(sentences)
    # train model
    model = Word2Vec(sentences, min_count=1)
    # summarize the loaded model
    print(model)
    # summarize vocabulary
    words = list(model.wv.vocab)
    print(words)
    # access vector for one word
    print(model['update'])
    # save model
    model.save('model.bin')


def load_model():
    # load model
    new_model = Word2Vec.load('model.bin')
    # print(new_model)
    return new_model


def get_similar(model, word1):
    # woman + king - man
    # return model.most_similar(positive=['woman', 'king'], negative=['man'])
    return model.most_similar(word1)


model = load_model()
print(get_similar(model, "wcc2"))