分类数据

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]

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])

[(30, 60], (30, 60], (30, 60], (10, 30], (10, 30]]
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'])

[30-60, 10-30, 30-60, 0-10, 0-10]
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      awful
1      awful
2      awful
3    perfect
4      awful
dtype: category
Categories (5, object): [awful < bad < fair < good < perfect]

s.sort_values(ascending=False).head()

49    perfect
33    perfect
3     perfect
10    perfect
16    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
awful	-0.397948
awful	-0.188164
awful	-0.543448
perfect	0.410447
awful	-1.689240

df_sort.sort_index().head()

	value
cat
awful	-0.397948
awful	-0.826390
awful	-1.087261
awful	-0.012140
awful	0.813705

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 == s_new #报错

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