基于tflearn使用lstm实现文本分类

模型训练部分代码

# -*- coding: utf-8 -*-
from __future__ import division, print_function, absolute_import
import tflearn
import os
import numpy
import jieba
import sys
import random
import re
import fire
from sys import argv
import json
from tflearn.data_utils import to_categorical, pad_sequences
from tflearn.datasets import imdb

def load_data1( keywordPath,stopwords_set,filepath,dictfilepath,n_words, valid_portion=0.1,
               sort_by_len=True):
   

    #keywordPath = sys.argv[1]
    jieba.load_userdict(keywordPath)
    pathDir = os.listdir(filepath)

    data_set = []
    train_set_x = []
    train_set_y = []
    test_set_x = []
    test_set_y = []

    # 把停用词做成字典
    stopwords = {}
    fstop = open(stopwords_set, 'rb')
    for eachWord in fstop:
        stopwords[eachWord.strip().decode('utf-8', 'ignore')] = eachWord.strip().decode('utf-8', 'ignore')
    fstop.close()

    #写入词典
    f1 = open(dictfilepath, 'w', encoding='UTF-8')
    dic = dict()

    i = 0
    j = 0