手把手教你用Pandas庫對淘寶原始數(shù)據(jù)進(jìn)行數(shù)據(jù)處理和分詞處理

import reimport pandas as pdresult = []with open(r"淘寶數(shù)據(jù).csv") as f:    for line in f:        row = dict(re.findall("([^：\t]+)：([^：\t]+)", line))        if row:            result.append(row)df = pd.DataFrame(result)df.to_excel('new_data.xlsx', encoding='utf-8')print(df)

# 創(chuàng)建停用詞listdef stopwordslist(filepath):    stopwords = [line.strip() for line in open(filepath, 'r', encoding='gbk').readlines()]    return stopwords

# 對句子進(jìn)行分詞def seg_sentence(sentence):    sentence_seged = jieba.cut(sentence.strip())    stopwords = stopwordslist('stop_word.txt')  # 這里加載停用詞的路徑    outstr = ''    for word in sentence_seged:        if word not in stopwords:            if word != '\t':                outstr += word                outstr += " "    return outstr

#!/usr/bin/env python3# -*- coding:utf-8 -*-
import sysimport jiebaimport jieba.analyseimport xlwt  # 寫入Excel表的庫
# reload(sys)# sys.setdefaultencoding('utf-8')
if __name__ == "__main__":
    wbk = xlwt.Workbook(encoding='ascii')    sheet = wbk.add_sheet("wordCount")  # Excel單元格名字    word_lst = []    key_list = []    for line in open('1.txt', encoding='utf-8'):  # 1.txt是需要分詞統(tǒng)計(jì)的文檔
        item = line.strip('\n\r').split('\t')  # 制表格切分        # print item        tags = jieba.analyse.extract_tags(item[0])  # jieba分詞        for t in tags:            word_lst.append(t)
    word_dict = {}    with open("wordCount_all_lyrics.txt", 'w') as wf2:  # 打開文件
        for item in word_lst:            if item not in word_dict:  # 統(tǒng)計(jì)數(shù)量                word_dict[item] = 1            else:                word_dict[item] += 1
        orderList = list(word_dict.values())        orderList.sort(reverse=True)        # print orderList        for i in range(len(orderList)):            for key in word_dict:                if word_dict[key] == orderList[i]:                    wf2.write(key + ' ' + str(word_dict[key]) + '\n')  # 寫入txt文檔                    key_list.append(key)                    word_dict[key] = 0
    for i in range(len(key_list)):        sheet.write(i, 1, label=orderList[i])        sheet.write(i, 0, label=key_list[i])    wbk.save('wordCount_all_lyrics.xls')  # 保存為 wordCount.xls文件

def get_data(df):    # 將食品添加劑這一列空的數(shù)據(jù)設(shè)置為無    # print(df)    df.loc[:,'食品添加劑'] = df['食品添加劑'].fillna('無')    df.loc[:,'保質(zhì)期'] = df['保質(zhì)期'].fillna('無')    df.loc[:, '配料表'] = df['配料表'].fillna('無')
    #  分詞并擴(kuò)展提取    names = df.配料表.apply(jieba.lcut).explode()    #  過濾長度小于等于1的詞并去重    df1 = names[names.apply(len) > 1].value_counts()
    with pd.ExcelWriter("taobao.xlsx") as writer:        df1.to_excel(writer, sheet_name='配料')
    df2 = pd.read_excel('taobao.xlsx', header=None, skiprows=1, names=['column1', 'column2'])    print(df2)