007_NLP_Task6 FastText模型进行文本分类

神经网络基础

学习链接：https://www.cnblogs.com/pinard/category/894694.html

FastText模型进行文本分类

#coding = utf-8
#Author:Shanv
#function:
import pandas as pd
import numpy as np
import datetime
import codecs
import jieba
import fastText
from prettytable import PrettyTable


#数据读取
def load_data(filePath):
    #读取文件
    f = codecs.open(filePath, 'r', encoding='utf-8')
    labels = []
    contents = []
    for line in f.readlines():
        try:
            label, content = line.strip().split('\t')
            if content:
                labels.append(label)
                contents.append(content)
        except:
            pass

    df = pd.DataFrame({'title':labels,'content':contents})

    return df

def cut_word(content):
    """结巴分词
    :param content: 分词文本
    :return: word：分好后的单词数据集（Series类型）
    """
    word = content.map(lambda x: [w for w in list(jieba.cut(x)) if len(w) != 1])
    return word

def make_fasttext_data(data_cuted, outFile, train=True, label=None):
    """把分好词后的数据转换成