LSTM实战电影评价情感分析

# encoding:utf-8

import numpy as np

wordsList = np.load('wordsList.npy')
print('载入word列表')
wordsList = wordsList.tolist()
wordsList = [word.decode('UTF-8')
             for word in wordsList]
wordVectors = np.load('wordVectors.npy')
print('载入文本向量')

print(len(wordsList))
# print("wordsList", wordsList)
# 'muguti', 'boidin', 'madueke', 'smikle', 'uteritz', 'gusin', ...40万个
print(wordVectors.shape)
#  print("wordVectors", wordVectors)
#  wordVectors [[ 0.         0.         0.        ...  0.         0.         0.       ]
#  [ 0.013441   0.23682   -0.16899   ... -0.56657    0.044691   0.30392  ]
#  [ 0.15164    0.30177   -0.16763   ... -0.35652    0.016413   0.10216  ]
#  ...
#  [-0.51181    0.058706   1.0913    ... -0.25003   -1.125      1.5863   ]
#  [-0.75898   -0.47426    0.4737    ...  0.78954   -0.014116   0.6448   ]
#  [-0.79149    0.86617    0.11998   ... -0.29996   -0.0063003  0.3954   ]]
# 40万*50 维的向量

import os
from os.path import isfile, join

pos_files = ['pos/' + f for f in os.listdir(
    'pos/') if isfile(join('pos/', f))]
neg_files = ['neg/' + f for f in os.listdir(
    'neg/') if isfile(join('neg/', f))]
num_words = []
for pf in pos_files:
    with open(pf, "r", encoding='utf-8') as f:
        line = f.readline()
        counter =