[PYTHON-TSNE]可视化Word Vector

需要的几个文件：

1.wordList.txt，即你要转化成vector的word list：

spring
maven
junit
ant
swing
xml
jre
jdk
jbutton
jpanel
swt
japplet
jdialog
jcheckbox
jlabel
jmenu
slf4j
test
unit

2.label.txt, 即图中显示的label，可以与wordlist.txt中的word不同。

spring
maven
junit
ant
swing
xml
jre
jdk
jbutton
jpanel
swt
japplet
jdialog
jcheckbox
jlabel
jmenu
slf4j
test
unit

3.model，用gensim生成的word2vec model；

4.运行buildWordVectorFromW2V.py，用于生成wordvectorlist：

from gensim.models.word2vec import Word2Vec
from pathutil import get_base_path

modelpath = 'XXX/model'

model = Word2Vec.load(modelpath)
sentenceFilePath = 'wordList.txt'
vectorFilePath = 'word2vec.txt'

sentence = []
writeStr = ''
with open(sentenceFilePath, 'r') as f:
    for line in f:
        sentWordList = line.strip().split(' ')
        for word in sentWordList:
            if word not in model:
                print 'error!'
            vec = model[word]
            for vecTmp in vec:
                writeStr += (str(vecTmp) + ' ')
        writeStr += '
'

f = open(vectorFilePath, "w")
f.write(writeStr.strip())

5.运行visualization.py，用于生成图片：

import numpy as np
from gensim.models.word2vec import Word2Vec
import matplotlib.pyplot as plt
from pathutil import get_base_path

modelpath = 'XXX/model'
model = Word2Vec.load(modelpath)
sentenceFilePath = 'wordlist.txt'
labelFilePath = 'wordlist.txt'

visualizeVecs = []
with open(sentenceFilePath, 'r') as f:
    for line in f:
        word = line.strip()
        vec = model[word.lower()]
        visualizeVecs.append(vec)

visualizeWords = []
with open(labelFilePath, 'r') as f:
    for line in f:
        word = line.strip()
        visualizeWords.append(word.lower())

visualizeVecs = np.array(visualizeVecs).astype(np.float64)
# Y = tsne(visualizeVecs, 2, 200, 20.0);
# # Plot.scatter(Y[:,0], Y[:,1], 20,labels);
# # ChineseFont1 = FontProperties('SimHei')
# for i in xrange(len(visualizeWords)):
#     # if i<len(visualizeWords)/2:
#     #     color='green'
#     # else:
#     #     color='red'
#     color = 'red'
#     plt.text(Y[i, 0], Y[i, 1], visualizeWords[i],bbox=dict(facecolor=color, alpha=0.1))
# plt.xlim((np.min(Y[:, 0]), np.max(Y[:, 0])))
# plt.ylim((np.min(Y[:, 1]), np.max(Y[:, 1])))
# plt.show()


# vis_norm = np.sqrt(np.sum(temp**2, axis=1, keepdims=True))
# temp = temp / vis_norm
temp = (visualizeVecs - np.mean(visualizeVecs, axis=0))
covariance = 1.0 / visualizeVecs.shape[0] * temp.T.dot(temp)
U, S, V = np.linalg.svd(covariance)
coord = temp.dot(U[:, 0:2])
for i in xrange(len(visualizeWords)):
    print i
    print coord[i, 0]
    print coord[i, 1]
    color = 'red'
    plt.text(coord[i, 0], coord[i, 1], visualizeWords[i], bbox=dict(facecolor=color, alpha=0.1),
             fontsize=22)  # fontproperties = ChineseFont1
plt.xlim((np.min(coord[:, 0]), np.max(coord[:, 0])))
plt.ylim((np.min(coord[:, 1]), np.max(coord[:, 1])))
plt.show()

　　

运行结果：