pandas2

最新推荐文章于 2023-12-25 07:00:00 发布

leobert2016

最新推荐文章于 2023-12-25 07:00:00 发布

阅读量130

点赞数

本文链接：https://blog.csdn.net/leobert2016/article/details/105717572

版权

import numpy as np
import pandas as pd
df = pd.read_csv(r"C:\SAIC\DataHunter\GitHub\joyful-pandas\data\table.csv",index_col='ID')
df.head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
1102	S_1	C_1	F	street_2	192	73	32.5	B+
1103	S_1	C_1	M	street_2	186	82	87.2	B+
1104	S_1	C_1	F	street_2	167	81	80.4	B-
1105	S_1	C_1	F	street_4	159	64	84.8	B+

df.loc[1103]

School          S_1
Class           C_1
Gender            M
Address    street_2
Height          186
Weight           82
Math           87.2
Physics          B+
Name: 1103, dtype: object

df.loc[[1102,2304]]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1102	S_1	C_1	F	street_2	192	73	32.5	B+
2304	S_2	C_3	F	street_6	164	81	95.5	A-

df.loc[2402::-1].head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
2402	S_2	C_4	M	street_7	166	82	48.7	B
2401	S_2	C_4	F	street_2	192	62	45.3	A
2305	S_2	C_3	M	street_4	187	73	48.9	B
2304	S_2	C_3	F	street_6	164	81	95.5	A-
2303	S_2	C_3	F	street_7	190	99	65.9	C

df.loc[:,'Height'].head()

ID
1101    173
1102    192
1103    186
1104    167
1105    159
Name: Height, dtype: int64

df.loc[:,'Height':'Math'].head()

	Height	Weight	Math
ID
1101	173	63	34.0
1102	192	73	32.5
1103	186	82	87.2
1104	167	81	80.4
1105	159	64	84.8

df.loc[1102:2401:3,'Height':'Math'].head()

	Height	Weight	Math
ID
1102	192	73	32.5
1105	159	64	84.8
1203	160	53	58.8
1301	161	68	31.5
1304	195	70	85.2

df.loc[lambda x:x['Gender']=='M'].head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
1103	S_1	C_1	M	street_2	186	82	87.2	B+
1201	S_1	C_2	M	street_5	188	68	97.0	A-
1203	S_1	C_2	M	street_6	160	53	58.8	A+
1301	S_1	C_3	M	street_4	161	68	31.5	B+

def f(x):
    return [1101,1103]
df.loc[f]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
1103	S_1	C_1	M	street_2	186	82	87.2	B+

df.loc[df['Address'].isin(['street_7','street_4'])].head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1105	S_1	C_1	F	street_4	159	64	84.8	B+
1202	S_1	C_2	F	street_4	176	94	63.5	B-
1301	S_1	C_3	M	street_4	161	68	31.5	B+
1303	S_1	C_3	M	street_7	188	82	49.7	B
2101	S_2	C_1	M	street_7	174	84	83.3	C

df.loc[[True if i[-1]=='4' or i[-1]=='7' else False for i in df['Address'].values]].head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1105	S_1	C_1	F	street_4	159	64	84.8	B+
1202	S_1	C_2	F	street_4	176	94	63.5	B-
1301	S_1	C_3	M	street_4	161	68	31.5	B+
1303	S_1	C_3	M	street_7	188	82	49.7	B
2101	S_2	C_1	M	street_7	174	84	83.3	C

df.iloc[3]

School          S_1
Class           C_1
Gender            F
Address    street_2
Height          167
Weight           81
Math           80.4
Physics          B-
Name: 1104, dtype: object

df.iloc[3:5]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1104	S_1	C_1	F	street_2	167	81	80.4	B-
1105	S_1	C_1	F	street_4	159	64	84.8	B+

df.iloc[:,3].head()

ID
1101    street_1
1102    street_2
1103    street_2
1104    street_2
1105    street_4
Name: Address, dtype: object

df.iloc[:,7::-2].head()

	Physics	Weight	Address	Class
ID
1101	A+	63	street_1	C_1
1102	B+	73	street_2	C_1
1103	B+	82	street_2	C_1
1104	B-	81	street_2	C_1
1105	B+	64	street_4	C_1

df.iloc[3::4,7::-2].head()

	Physics	Weight	Address	Class
ID
1104	B-	81	street_2	C_1
1203	A+	53	street_6	C_2
1302	A-	57	street_1	C_3
2101	C	84	street_7	C_1
2105	A	81	street_4	C_1

df.iloc[lambda x:[3]].head()

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1104	S_1	C_1	F	street_2	167	81	80.4	B-

s = pd.Series(df['Math'],index=df.index)
s[1101]

34.0

s[lambda x: x.index[16::-6]]

ID
2102    50.6
1301    31.5
1105    84.8
Name: Math, dtype: float64

s[lambda x: [16::-6]]

  File "<ipython-input-21-ada17acead14>", line 1
    s[lambda x: [16::-6]]
                   ^
SyntaxError: invalid syntax

s[0:4]

ID
1101    34.0
1102    32.5
1103    87.2
1104    80.4
Name: Math, dtype: float64

s[s>80]

ID
1103    87.2
1104    80.4
1105    84.8
1201    97.0
1302    87.7
1304    85.2
2101    83.3
2205    85.4
2304    95.5
Name: Math, dtype: float64

df.loc[df['Math']>60,(df[:8]['Address']=='street_6').values].head()#??
#如果不加values就会索引对齐发生错误，Pandas中的索引对齐是一个重要特征，很多时候非常实用
#但是若不加以留意，就会埋下隐患

	Physics
ID
1103	B+
1104	B-
1105	B+
1201	A-
1202	B-

df[:8]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
1102	S_1	C_1	F	street_2	192	73	32.5	B+
1103	S_1	C_1	M	street_2	186	82	87.2	B+
1104	S_1	C_1	F	street_2	167	81	80.4	B-
1105	S_1	C_1	F	street_4	159	64	84.8	B+
1201	S_1	C_2	M	street_5	188	68	97.0	A-
1202	S_1	C_2	F	street_4	176	94	63.5	B-
1203	S_1	C_2	M	street_6	160	53	58.8	A+

df[df['Address'].isin(['street_1','street_4'])&df['Physics'].isin(['A','A+'])]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
2105	S_2	C_1	M	street_4	170	81	34.2	A
2203	S_2	C_2	M	street_4	155	91	73.8	A+

df[df[['Address','Physics']].isin({'Address':['street_1','street_4'],'Physics':['A','A+']}).all(1)]

	School	Class	Gender	Address	Height	Weight	Math	Physics
ID
1101	S_1	C_1	M	street_1	173	63	34.0	A+
2105	S_2	C_1	M	street_4	170	81	34.2	A
2203	S_2	C_2	M	street_4	155	91	73.8	A+

df.at[1101,'School']

'S_1'

%timeit df.at[1101,'School']最快
%timeit df.loc[1101,'School']
%timeit df.iat[0,0]
%timeit df.iloc[0,0]

3.74 µs ± 120 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
6.99 µs ± 993 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
4 µs ± 28 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
6.7 µs ± 618 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

pd.interval_range(start=0,end=5)
#closed参数可选'left''right''both''neither'，默认左开右闭

IntervalIndex([(0, 1], (1, 2], (2, 3], (3, 4], (4, 5]],
              closed='right',
              dtype='interval[int64]')

math_interval = pd.cut(df['Math'],bins=[0,40,60,80,100])
math_interval.head()

ID
1101      (0, 40]
1102      (0, 40]
1103    (80, 100]
1104    (80, 100]
1105    (80, 100]
Name: Math, dtype: category
Categories (4, interval[int64]): [(0, 40] < (40, 60] < (60, 80] < (80, 100]]

df_i = df.join(math_interval,rsuffix='_interval')[['Math','Math_interval']]\
            .reset_index().set_index('Math_interval')
df_i.head()

	ID	Math
Math_interval
(0, 40]	1101	34.0
(0, 40]	1102	32.5
(80, 100]	1103	87.2
(80, 100]	1104	80.4
(80, 100]	1105	84.8

df_i.loc[65].head()

	ID	Math
Math_interval
(60, 80]	1202	63.5
(60, 80]	1205	68.4
(60, 80]	1305	61.7
(60, 80]	2104	72.2
(60, 80]	2202	68.5

df_i.loc[[65,90]].head()

	ID	Math
Math_interval
(60, 80]	1202	63.5
(60, 80]	1205	68.4
(60, 80]	1305	61.7
(60, 80]	2104	72.2
(60, 80]	2202	68.5

df_i.index.astype('interval')

IntervalIndex([(0, 40], (0, 40], (80, 100], (80, 100], (80, 100] ... (40, 60], (40, 60], (40, 60], (60, 80], (40, 60]],
              closed='right',
              dtype='interval[int64]')

df_i[df_i.index.astype('interval').overlaps(pd.Interval(70, 85))].head()

	ID	Math
Math_interval
(80, 100]	1103	87.2
(80, 100]	1104	80.4
(80, 100]	1105	84.8
(80, 100]	1201	97.0
(60, 80]	1202	63.5

tuples = [('A','a'),('A','b'),('B','a'),('B','b')]
mul_index = pd.MultiIndex.from_tuples(tuples, names=('Upper', 'Lower'))
mul_index

MultiIndex([('A', 'a'),
            ('A', 'b'),
            ('B', 'a'),
            ('B', 'b')],
           names=['Upper', 'Lower'])

pd.DataFrame({'Score':['perfect','good','fair','bad']},index=mul_index)

		Score
Upper	Lower
A	a	perfect
A	b	good
B	a	fair
B	b	bad

L1 = list('AABB')
L2 = list('abab')
tuples = list(zip(L1,L2))
mul_index = pd.MultiIndex.from_tuples(tuples, names=('Upper', 'Lower'))
pd.DataFrame({'Score':['perfect','good','fair','bad']},index=mul_index)

		Score
Upper	Lower
A	a	perfect
A	b	good
B	a	fair
B	b	bad

arrays = [['A','a'],['A','b'],['B','a'],['B','b']]
mul_index = pd.MultiIndex.from_tuples(arrays, names=('Upper', 'Lower'))
pd.DataFrame({'Score':['perfect','good','fair','bad']},index=mul_index)

		Score
Upper	Lower
A	a	perfect
A	b	good
B	a	fair
B	b	bad

mul_index

MultiIndex([('A', 'a'),
            ('A', 'b'),
            ('B', 'a'),
            ('B', 'b')],
           names=['Upper', 'Lower'])

L1 = ['A','B']
L2 = ['a','b']
pd.MultiIndex.from_product([L1,L2],names=('Upper', 'Lower'))

MultiIndex([('A', 'a'),
            ('A', 'b'),
            ('B', 'a'),
            ('B', 'b')],
           names=['Upper', 'Lower'])

df_using_mul = df.set_index(['Class','Address'])
df_using_mul.head()

		School	Gender	Height	Weight	Math	Physics
Class	Address
C_1	street_1	S_1	M	173	63	34.0	A+
	street_2	S_1	F	192	73	32.5	B+
	street_2	S_1	M	186	82	87.2	B+
	street_2	S_1	F	167	81	80.4	B-
	street_4	S_1	F	159	64	84.8	B+

#df_using_mul.loc['C_2','street_5']
#当索引不排序时，单个索引会报出性能警告
#df_using_mul.index.is_lexsorted()
#该函数检查是否排序
df_using_mul.sort_index().loc['C_2','street_5']
#df_using_mul.sort_index().index.is_lexsorted()

		School	Gender	Height	Weight	Math	Physics
Class	Address
C_2	street_5	S_1	M	188	68	97.0	A-
	street_5	S_1	F	162	63	33.8	B
	street_5	S_2	M	193	100	39.1	B

#df_using_mul.loc[('C_2','street_5'):] 报错
#当不排序时，不能使用多层切片
df_using_mul.sort_index().loc[('C_2','street_6'):('C_3','street_4')]
#注意此处由于使用了loc，因此仍然包含右端点

		School	Gender	Height	Weight	Math	Physics
Class	Address
C_2	street_6	S_1	M	160	53	58.8	A+
	street_6	S_1	F	167	63	68.4	B-
	street_7	S_2	F	194	77	68.5	B+
	street_7	S_2	F	183	76	85.4	B
C_3	street_1	S_1	F	175	57	87.7	A-
	street_2	S_1	M	195	70	85.2	A
	street_4	S_1	M	161	68	31.5	B+
	street_4	S_2	F	157	78	72.3	B+
	street_4	S_2	M	187	73	48.9	B

df_using_mul.sort_index().loc[('C_2','street_7'):'C_3'].head()
#非元组也是合法的，表示选中该层所有元素

		School	Gender	Height	Weight	Math	Physics
Class	Address
C_2	street_7	S_2	F	194	77	68.5	B+
C_2	street_7	S_2	F	183	76	85.4	B
C_3	street_1	S_1	F	175	57	87.7	A-
	street_2	S_1	M	195	70	85.2	A
	street_4	S_1	M	161	68	31.5	B+

df_using_mul.sort_index().loc[[('C_2','street_7'),('C_3','street_2')]]

		School	Gender	Height	Weight	Math	Physics
Class	Address
C_2	street_7	S_2	F	194	77	68.5	B+
C_2	street_7	S_2	F	183	76	85.4	B
C_3	street_2	S_1	M	195	70	85.2	A

L1,L2 = ['A','B','C'],['a','b','c']
mul_index1 = pd.MultiIndex.from_product([L1,L2],names=('Upper', 'Lower'))
L3,L4 = ['D','E','F'],['d','e','f']
mul_index2 = pd.MultiIndex.from_product([L3,L4],names=('Big', 'Small'))
df_s = pd.DataFrame(np.random.rand(9,9),index=mul_index1,columns=mul_index2)
df_s

	Big	D			E			F
	Small	d	e	f	d	e	f	d	e	f
Upper	Lower
A	a	0.868146	0.779973	0.040035	0.312931	0.742738	0.400927	0.719805	0.098784	0.808752
	b	0.640475	0.871246	0.300074	0.559656	0.032805	0.815044	0.909367	0.617527	0.071200
	c	0.564827	0.720181	0.168413	0.605086	0.815405	0.919883	0.767163	0.099041	0.510799
B	a	0.645498	0.212847	0.239187	0.664830	0.243526	0.907248	0.760947	0.811720	0.898771
	b	0.598414	0.095890	0.124890	0.379378	0.723209	0.842317	0.817238	0.257404	0.982154
	c	0.332865	0.472630	0.017562	0.741558	0.254717	0.023202	0.131158	0.988882	0.026893
C	a	0.715418	0.653554	0.738060	0.161244	0.851520	0.902496	0.843573	0.761424	0.366131
	b	0.994121	0.362501	0.292338	0.016310	0.532978	0.890472	0.621069	0.709472	0.949864
	c	0.378175	0.358023	0.968979	0.021041	0.198345	0.901327	0.165456	0.930577	0.554062

idx=pd.IndexSlice

df_s.loc[idx['B':,df_s['D']['d']>0.3],idx[df_s.sum()>4]]
#df_s.sum()默认为对列求和，因此返回一个长度为9的数值列表

	Big	D		E		F
	Small	d	e	e	f	d	e	f
Upper	Lower
B	a	0.645498	0.212847	0.243526	0.907248	0.760947	0.811720	0.898771
	b	0.598414	0.095890	0.723209	0.842317	0.817238	0.257404	0.982154
	c	0.332865	0.472630	0.254717	0.023202	0.131158	0.988882	0.026893
C	a	0.715418	0.653554	0.851520	0.902496	0.843573	0.761424	0.366131
	b	0.994121	0.362501	0.532978	0.890472	0.621069	0.709472	0.949864
	c	0.378175	0.358023	0.198345	0.901327	0.165456	0.930577	0.554062

df_using_mul.swaplevel(i=1,j=0,axis=0).sort_index().head()

		School	Gender	Height	Weight	Math	Physics
Address	Class
street_1	C_1	S_1	M	173	63	34.0	A+
	C_2	S_2	M	175	74	47.2	B-
	C_3	S_1	F	175	57	87.7	A-
street_2	C_1	S_1	F	192	73	32.5	B+
street_2	C_1	S_1	M	186	82	87.2	B+

df_using_mul.swaplevel(i=1,j=0,axis=0).sort_index().head()

好多方法仅仅是看了一遍，周六再仔细看看

leobert2016

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
pandas2

import numpy as npimport pandas as pddf = pd.read_csv(r"C:\SAIC\DataHunter\GitHub\joyful-pandas\data\table.csv",index_col='ID')df.head() School Class Gender ...
复制链接

扫一扫