def jieba_cut_and_save_file(inputList, n_weight, a_weight, output_cleaned_file=False):

   """
   1. 读取中文文件并分词句子
   2. 可以将分词后的结果保存到文件
   """

    output_file = os.path.join('./data/', 'cleaned_' + 'trainMatrix.txt')
    lines = []
    tags = []

    for line in inputList:
        result = pseg.cut(clean_str(line))
        a = []
        b = []
        for word, flag in result:
            # 对分词后的新闻
            if word != ' ':
                # 若非空
                a.append(word)
                if flag.find('n')==0:
                    # 若是名词
                    b.append(n_weight)

                elif flag.find('a')==0:
                    # 若形容词
                    b.append(a_weight)
                else:
                    b.append(1)

        lines.append(a)
        tags.append(b)

    if output_cleaned_file:
        with open(output_file, 'w') as f:
            for line in lines:
                f.write(" ".join(line) + '\n')

    vocabulary = createVocabList(lines)

    # 根据词典生成词向量化器,并进行词向量化
    setOfWords2Vec = setOfWords2VecFactory(vocabulary)
    vectorized = []
    for i,news in enumerate(lines):
        vector = setOfWords2Vec(news, tags[i])
        vectorized.append(vector)

    return vectorized, vocabulary

import bayes
from data_helpers import *
from sklearn.externals import joblib


posFile = "./data/train_food.txt"
negFile = "./data/train_notfood.txt"



print("正在获取训练矩阵及其分类向量")
trainList,classVec = loadTrainDataset(posFile,negFile)

print("正在将训练矩阵分词，并生成词表")
n_weight = 3
# 名词权重
a_weight = 1
# 形容词权重

vectorized, vocabulary = jieba_cut_and_save_file(trainList, n_weight, a_weight, True)
bayes_ = bayes.oldNB(vocabulary)

# 初始化模型
print("正在训练模型")
bayes_.train(vectorized, classVec)

# 训练
print("保存模型")

joblib.dump(bayes_, "./arguments/train_model.m")