NLTK包和语料库的准备

 

import pandas as pd
raw = pd.read_table('../data/金庸-射雕英雄传txt精校版.txt', names=['txt'], encoding="GBK")
print(len(raw))
raw

#  章节判断用变量预处理
def m_head(tmpstr):
    return tmpstr[:1]

def m_mid(tmpstr):
    return tmpstr.find("回 ")

raw['head'] = raw.txt.apply(m_head)
raw['mid'] = raw.txt.apply(m_mid)
raw['len'] = raw.txt.apply(len)
raw.head(50)

#  章节判断
chapnum = 0
for i in range(len(raw)):
    if raw['head'][i] == "第" and raw['mid'][i] > 0 and raw['len'][i] < 30:
        chapnum += 1
    if chapnum >= 40 and raw['txt'][i] == "附录一：成吉思汗家族":
        chapnum = 0
    raw.loc[i, 'chap'] = chapnum
                             
raw.head(50)

#  删除临时变量
del raw['head']
del raw['mid']
del raw['len']
raw.head(50)

rawgrp = raw.groupby('chap')
chapter = rawgrp.agg(sum)  # 只有字符串的情况下，sum函数自动转为合并字符串
chapter = chapter[chapter.index != 0]
chapter