from gensim.models import Word2Vec
from sklearn.decomposition import PCA
from matplotlib import pyplot
# define training data
sentences = [['this', 'is', 'the', 'first', 'sentence', 'for', 'word2vec'],
['this', 'is', 'the', 'second', 'sentence'],
['yet', 'another', 'sentence'],
['one', 'more', 'sentence'],
['and', 'the', 'final', 'sentence']]
# train model
model = Word2Vec(sentences, min_count=1)
# fit a 2d PCA model to the vectors
X = model[model.wv.vocab]
pca = PCA(n_components=2)
result = pca.fit_transform(X)
# create a scatter plot of the projection
pyplot.scatter(result[:, 0], result[:, 1])
words = list(model.wv.vocab)
for i, word in enumerate(words):
pyplot.annotate(word, xy=(result[i, 0], result[i, 1]))
pyplot.show()
Word2vec向量可视化
最新推荐文章于 2024-06-02 11:00:00 发布