python词频统计等

import pandas as pd
raw = pd.read_csv('work/金庸-射雕英雄传txt精校版.txt',names=['txt'],sep="aaa",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