import pandas as pd
import numpy as np
df = pd. read_csv( 'data/table.csv' )
df. head( )
School
Class
ID
Gender
Address
Height
Weight
Math
Physics
0
S_1
C_1
1101
M
street_1
173
63
34.0
A+
1
S_1
C_1
1102
F
street_2
192
73
32.5
B+
2
S_1
C_1
1103
M
street_2
186
82
87.2
B+
3
S_1
C_1
1104
F
street_2
167
81
80.4
B-
4
S_1
C_1
1105
F
street_4
159
64
84.8
B+
pd. Series( [ "a" , "b" , "c" , "a" ] , dtype= "category" )
0 a
1 b
2 c
3 a
dtype: category
Categories (3, object): [a, b, c]
temp_df = pd. DataFrame( { 'A' : pd. Series( [ "a" , "b" , "c" , "a" ] , dtype= "category" ) , 'B' : list ( 'abcd' ) } )
temp_df. dtypes
A category
B object
dtype: object
cat = pd. Categorical( [ "a" , "b" , "c" , "a" ] , categories= [ 'a' , 'b' , 'c' ] )
pd. Series( cat)
0 a
1 b
2 c
3 a
dtype: category
Categories (3, object): [a, b, c]
pd. cut( np. random. randint( 0 , 60 , 5 ) , [ 0 , 10 , 30 , 60 ] )
[(10, 30], (0, 10], (10, 30], (30, 60], (30, 60]]
Categories (3, interval[int64]): [(0, 10] < (10, 30] < (30, 60]]
pd. cut( np. random. randint( 0 , 60 , 5 ) , [ 0 , 10 , 30 , 60 ] , right= False , labels= [ '0-10' , '10-30' , '30-60' ] )
[10-30, 30-60, 30-60, 10-30, 30-60]
Categories (3, object): [0-10 < 10-30 < 30-60]
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. describe( )
count 4
unique 3
top a
freq 2
dtype: object
s. cat. categories
Index(['a', 'b', 'c', 'd'], dtype='object')
s. cat. ordered
False
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. cat. set_categories( [ 'new_a' , 'c' ] )
0 NaN
1 NaN
2 c
3 NaN
4 NaN
dtype: category
Categories (2, object): [new_a, c]
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. cat. rename_categories( [ 'new_%s' % i for i in s. cat. categories] )
0 new_a
1 new_b
2 new_c
3 new_a
4 NaN
dtype: category
Categories (4, object): [new_a, new_b, new_c, new_d]
s. cat. rename_categories( { 'a' : 'new_a' , 'b' : 'new_b' } )
0 new_a
1 new_b
2 c
3 new_a
4 NaN
dtype: category
Categories (4, object): [new_a, new_b, c, d]
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. cat. add_categories( [ 'e' ] )
0 a
1 b
2 c
3 a
4 NaN
dtype: category
Categories (5, object): [a, b, c, d, e]
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. cat. remove_categories( [ 'd' ] )
0 a
1 b
2 c
3 a
4 NaN
dtype: category
Categories (3, object): [a, b, c]
s = pd. Series( pd. Categorical( [ "a" , "b" , "c" , "a" , np. nan] , categories= [ 'a' , 'b' , 'c' , 'd' ] ) )
s. cat. remove_unused_categories( )
0 a
1 b
2 c
3 a
4 NaN
dtype: category
Categories (3, object): [a, b, c]
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' ) . cat. as_ordered( )
s
0 a
1 d
2 c
3 a
dtype: category
Categories (3, object): [a < c < d]
s. cat. as_unordered( )
0 a
1 d
2 c
3 a
dtype: category
Categories (3, object): [a, c, d]
pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' ) . cat. set_categories( [ 'a' , 'c' , 'd' ] , ordered= True )
0 a
1 d
2 c
3 a
dtype: category
Categories (3, object): [a < c < d]
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' )
s. cat. reorder_categories( [ 'a' , 'c' , 'd' ] , ordered= True )
0 a
1 d
2 c
3 a
dtype: category
Categories (3, object): [a < c < d]
s = pd. Series( np. random. choice( [ 'perfect' , 'good' , 'fair' , 'bad' , 'awful' ] , 50 ) ) . astype( 'category' )
s. cat. set_categories( [ 'perfect' , 'good' , 'fair' , 'bad' , 'awful' ] [ : : - 1 ] , ordered= True ) . head( )
0 good
1 fair
2 bad
3 perfect
4 perfect
dtype: category
Categories (5, object): [awful < bad < fair < good < perfect]
s. sort_values( ascending= False ) . head( )
29 perfect
17 perfect
31 perfect
3 perfect
4 perfect
dtype: category
Categories (5, object): [awful, bad, fair, good, perfect]
df_sort = pd. DataFrame( { 'cat' : s. values, 'value' : np. random. randn( 50 ) } ) . set_index( 'cat' )
df_sort. head( )
value
cat
good
-1.746975
fair
0.836732
bad
0.094912
perfect
-0.724338
perfect
-1.456362
df_sort. sort_index( ) . head( )
value
cat
awful
0.245782
awful
0.063991
awful
1.541862
awful
-0.062976
awful
0.472542
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' )
s == 'a'
0 True
1 False
2 False
3 True
dtype: bool
s == list ( 'abcd' )
0 True
1 False
2 True
3 False
dtype: bool
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' )
s == s
0 True
1 True
2 True
3 True
dtype: bool
s != s
0 False
1 False
2 False
3 False
dtype: bool
s_new = s. cat. set_categories( [ 'a' , 'd' , 'e' ] )
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' )
s = pd. Series( [ "a" , "d" , "c" , "a" ] ) . astype( 'category' ) . cat. reorder_categories( [ 'a' , 'c' , 'd' ] , ordered= True )
s >= s
0 True
1 True
2 True
3 True
dtype: bool
cat = pd. Categorical( [ 1 , 2 , 3 , 10 ] , categories= [ 1 , 2 , 3 , 4 , 10 ] )
s = pd. Series( cat, name= "cat" )
cat
[1, 2, 3, 10]
Categories (5, int64): [1, 2, 3, 4, 10]
s. iloc[ 0 : 2 ] = 10
cat
[10, 10, 3, 10]
Categories (5, int64): [1, 2, 3, 4, 10]
pd. read_csv( 'data/Earthquake.csv' ) . head( )
日期
时间
维度
经度
方向
距离
深度
烈度
0
2003.05.20
12:17:44 AM
39.04
40.38
west
0.1
10.0
0.0
1
2007.08.01
12:03:08 AM
40.79
30.09
west
0.1
5.2
4.0
2
1978.05.07
12:41:37 AM
38.58
27.61
south_west
0.1
0.0
0.0
3
1997.03.22
12:31:45 AM
39.47
36.44
south_west
0.1
10.0
0.0
4
2000.04.02
12:57:38 AM
40.80
30.24
south_west
0.1
7.0
0.0
官方文档的说法 ，即使没有出现的变量也会在变形后的汇总结果中出现，但事实上并不是这样，比如下面的例子就缺少了原本应该出现的行’c’和列’f’。基于这一问题，请尝试设计my_crosstab函数，在功能上能够返回正确的结果。foo = pd. Categorical( [ 'a' , 'b' ] , categories= [ 'a' , 'b' , 'c' ] )
bar = pd. Categorical( [ 'd' , 'e' ] , categories= [ 'd' , 'e' , 'f' ] )
pd. crosstab( foo, bar)
col_0
d
e
row_0
a
1
0
b
0
1
