Pandas按照字母排序选取

按照字母切片,必须先对数据进行sort_index排序才能对字母进行排序 

import pandas as pd
#读取college数据集
college = pd.read_csv('data/college.csv', index_col='INSTNM')
# 对college进行排序
college = college.sort_index()
college = college.head()
# 再尝试选取字母顺序在‘Sp’和‘Su’之间的学校
pd.options.display.max_rows = 6
college.loc['AB':'Al']

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
ABC Beauty Academy	Garland	TX	0.0	0.0	0.0	0	NaN	NaN	0.0	30.0	...	0.0000	0.0000	0.0000	0.0000	0	0.7857	0.0000	0.8286	NaN	PrivacySuppressed
ABC Beauty College Inc	Arkadelphia	AR	0.0	0.0	0.0	0	NaN	NaN	0.0	38.0	...	0.0000	0.0000	0.0000	0.2105	1	0.9815	1.0000	0.4688	PrivacySuppressed	16500
AI Miami International University of Art and Design	Miami	FL	0.0	0.0	0.0	0	NaN	NaN	0.0	2778.0	...	0.0018	0.0025	0.4644	0.2185	1	0.5507	0.6966	0.3262	29900	31000

3 rows × 26 columns

# 可以用is_monotonic_increasing或is_monotonic_decreasing检测字母排序的顺序
college = college.sort_index(ascending=False)
college.index.is_monotonic_decreasing
# 再尝试选取字母顺序在‘Sp’和‘Su’之间的学校
pd.options.display.max_rows = 6
college.loc['Al':'AB']

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
AI Miami International University of Art and Design	Miami	FL	0.0	0.0	0.0	0	NaN	NaN	0.0	2778.0	...	0.0018	0.0025	0.4644	0.2185	1	0.5507	0.6966	0.3262	29900	31000
ABC Beauty College Inc	Arkadelphia	AR	0.0	0.0	0.0	0	NaN	NaN	0.0	38.0	...	0.0000	0.0000	0.0000	0.2105	1	0.9815	1.0000	0.4688	PrivacySuppressed	16500
ABC Beauty Academy	Garland	TX	0.0	0.0	0.0	0	NaN	NaN	0.0	30.0	...	0.0000	0.0000	0.0000	0.0000	0	0.7857	0.0000	0.8286	NaN	PrivacySuppressed

3 rows × 26 columns