import pandas as pd
#读取college数据集
college = pd.read_csv('data/college.csv', index_col='INSTNM')
#查看CITY的前5行
college.head()
CITY | STABBR | HBCU | MENONLY | WOMENONLY | RELAFFIL | SATVRMID | SATMTMID | DISTANCEONLY | UGDS | ... | UGDS_2MOR | UGDS_NRA | UGDS_UNKN | PPTUG_EF | CURROPER | PCTPELL | PCTFLOAN | UG25ABV | MD_EARN_WNE_P10 | GRAD_DEBT_MDN_SUPP | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INSTNM | |||||||||||||||||||||
Alabama A & M University | Normal | AL | 1.0 | 0.0 | 0.0 | 0 | 424.0 | 420.0 | 0.0 | 4206.0 | ... | 0.0000 | 0.0059 | 0.0138 | 0.0656 | 1 | 0.7356 | 0.8284 | 0.1049 | 30300 | 33888 |
University of Alabama at Birmingham | Birmingham | AL | 0.0 | 0.0 | 0.0 | 0 | 570.0 | 565.0 | 0.0 | 11383.0 | ... | 0.0368 | 0.0179 | 0.0100 | 0.2607 | 1 | 0.3460 | 0.5214 | 0.2422 | 39700 | 21941.5 |
Amridge University | Montgomery | AL | 0.0 | 0.0 | 0.0 | 1 | NaN | NaN | 1.0 | 291.0 | ... | 0.0000 | 0.0000 | 0.2715 | 0.4536 | 1 | 0.6801 | 0.7795 | 0.8540 | 40100 | 23370 |
University of Alabama in Huntsville | Huntsville | AL | 0.0 | 0.0 | 0.0 | 0 | 595.0 | 590.0 | 0.0 | 5451.0 | ... | 0.0172 | 0.0332 | 0.0350 | 0.2146 | 1 | 0.3072 | 0.4596 | 0.2640 | 45500 | 24097 |
Alabama State University | Montgomery | AL | 1.0 | 0.0 | 0.0 | 0 | 425.0 | 430.0 | 0.0 | 4811.0 | ... | 0.0098 | 0.0243 | 0.0137 | 0.0892 | 1 | 0.7347 | 0.7554 | 0.1270 | 26600 | 33118.5 |
5 rows × 26 columns
显示所有列的表名
college.columns #显示所有列的表名
''' Index(['CITY', 'STABBR', 'HBCU', 'MENONLY', 'WOMENONLY', 'RELAFFIL',
'SATVRMID', 'SATMTMID', 'DISTANCEONLY', 'UGDS', 'UGDS_WHITE',
'UGDS_BLACK', 'UGDS_HISP', 'UGDS_ASIAN', 'UGDS_AIAN', 'UGDS_NHPI',
'UGDS_2MOR', 'UGDS_NRA', 'UGDS_UNKN', 'PPTUG_EF', 'CURROPER', 'PCTPELL',
'PCTFLOAN', 'UG25ABV', 'MD_EARN_WNE_P10', 'GRAD_DEBT_MDN_SUPP'],
dtype='object')'''
iloc可以通过整数选取
# iloc可以通过整数选取; iloc-先行后列,索引值的下标
city = college['CITY']
city.iloc[1]
#'Birmingham'
iloc系列展示方式要带双中括号[[]]
#seriesSeries所以带列表名,主要看最后一列的显示即可。在iloc中多添加一个数字,下表中就增加一行
city.iloc[[2]]
'''
INSTNM
Amridge University Montgomery
Name: CITY, dtype: object
'''
iloc通过整数列表选取多行,返回结果是Series
# iloc通过整数列表选取多行,返回结果是Series,
city.iloc[[2,3,3]]
'''
INSTNM
Amridge University Montgomery
University of Alabama in Huntsville Huntsville
University of Alabama in Huntsville Huntsville
Name: CITY, dtype: object
'''
选择等分的数据
# 选择等分的数据,可以使用切片语法
city.iloc[4:50:10] #从1到50,每隔10个取一个值,4到49,所以取值4,14,24,34,44
'''
INSTNM
Alabama State University Montgomery
Enterprise State Community College Enterprise
Heritage Christian University Florence
Marion Military Institute Marion
Reid State Technical College Evergreen
Name: CITY, dtype: object
'''