python 学习第五天补充 字符串的抽取和分割

字符串的抽取

from pandas import read_csv;

df = read_csv("D://PA//4.6//data.csv");

df['tel'] = df['tel'].astype(str);

#运营商
bands = df['tel'].str.slice(0, 3);
#地区
areas = df['tel'].str.slice(3, 7);
#号码段
nums = df['tel'].str.slice(7, 11);

　　字符串的分割

from pandas import Series;
from pandas import DataFrame;
from pandas import read_csv;

df = read_csv("D:\Python\3.2\2.csv");

newDF = df['name'].str.split(' ', 1, True);

newDF.columns = ['band', 'name'];   #重新定义列名

　　特定条件的提取

import pandas;
from pandas import read_csv;

df = read_csv("D://PA//4.8//data.csv", sep="|");

df[df.comments>10000];

df[df.comments.between(1000, 10000)]

df[pandas.isnull(df.title)]

df[df.title.str.contains('台电', na=False)]

df[(df.comments>=1000) & (df.comments<=10000)]

　　随机抽取

import numpy;
from pandas import read_csv;

df = read_csv("D://PA//4.9//data.csv");

#numpy.random.randint(start,end,num)  ,其中start表示范围的开始值，end表示范围的结束值，num随机抽样个数

r = numpy.random.randint(0, 10, 3);

df.loc[r, :];