pandasNote2

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

重新索引

重新索引不会改变原数据

• 行索引
  • Series.reindex
  • DF.reindex()
• 列索引
  • 通过columns关键字指定

obj = pd.Series([4.5, 7.2, -5.3, 3.6], index=['d', 'b', 'a', 'c'])
obj

d    4.5
b    7.2
a   -5.3
c    3.6
dtype: float64

# S型数据重新排序索引
obj2 = obj.reindex(['a', 'b', 'c', 'd', 'e'])
obj2

a   -5.3
b    7.2
c    3.6
d    4.5
e    NaN
dtype: float64

obj3 = pd.Series(['blue', 'purple', 'yellow'], index=[0, 2, 4])
obj3

0      blue
2    purple
4    yellow
dtype: object

# ffill前项填充：填充的是前一个数值
obj3.reindex(range(6), method='ffill')

0      blue
1      blue
2    purple
3    purple
4    yellow
5    yellow
dtype: object

# DF重新索引
frame = pd.DataFrame(np.arange(9).reshape((3, 3)),
                     index=['a', 'c', 'd'],
                     columns=['Ohio', 'Texas', 'California'])
frame

	Ohio	Texas	California
a	0	1	2
c	3	4	5
d	6	7	8

# DF重新索引
frame.reindex(["a", "b", "c", "d"])

	Ohio	Texas	California
a	0.0	1.0	2.0
b	NaN	NaN	NaN
c	3.0	4.0	5.0
d	6.0	7.0	8.0

# 重新索引列
frame.reindex(columns=["Ohio", "Utah", "California"])

	Ohio	Utah	California
a	0	NaN	2
c	3	NaN	5
d	6	NaN	8

# drop等函数默认是就地修改，不改变原有数据
# 使用inplace=True改变原有数据
print(obj)
obj.drop('c', inplace=True)
obj

d    4.5
b    7.2
a   -5.3
c    3.6
dtype: float64

d    4.5
b    7.2
a   -5.3
dtype: float64

舍弃指定轴上的数据

• drop(index)
• drop([index1, index2])

obj = pd.Series(np.arange(5.), index=['a', 'b', 'c', 'd', 'e'])
obj

a    0.0
b    1.0
c    2.0
d    3.0
e    4.0
dtype: float64

# 舍弃一行数据
new_obj = obj.drop('c')
new_obj

a    0.0
b    1.0
d    3.0
e    4.0
dtype: float64

删除数据

• 行：axis=0，默认
• 列：axis=1，或者axis=columns
• 删除一个通过标签形式
• 删除多个是传入列表形式

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                    index=['Ohio', 'Colorado', 'Utah', 'New York'],
                    columns=['one', 'two', 'three', 'four'])
data

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

# 默认是删除行数据
data.drop(['Colorado', 'Ohio'])

	one	two	three	four
Utah	8	9	10	11
New York	12	13	14	15

# axis=1：删除列数据
data.drop('two', axis=1)

	one	three	four
Ohio	0	2	3
Colorado	4	6	7
Utah	8	10	11
New York	12	14	15

# 删除多列数据
data.drop(['two', 'four'], axis='columns')

	one	three
Ohio	0	2
Colorado	4	6
Utah	8	10
New York	12	14

选取行数据

• loc：轴标签
• iloc：整数索引

data

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

# 标签索引
data.loc['Colorado', ['two', 'three']]

two      5
three    6
Name: Colorado, dtype: int32

# 切片形式：前面表示行所用，后面表示列
data.loc[:'Utah', 'two']

Ohio        1
Colorado    5
Utah        9
Name: two, dtype: int32

# 整数数值索引
data.iloc[2, [3, 0, 1]]

four    11
one      8
two      9
Name: Utah, dtype: int32

data.iloc[[1, 2], [3, 0, 1]]

	four	one	two
Colorado	7	4	5
Utah	11	8	9

整数索引

ser = pd.Series(np.arange(3.))
ser

0    0.0
1    1.0
2    2.0
dtype: float64

ser2 = pd.Series(np.arange(3.), index=['a', 'b', 'c'])
ser2[-1]

2.0

# 索引不包含末尾
ser[:1]

0    0.0
dtype: float64

ser.loc[:2]

0    0.0
1    1.0
2    2.0
dtype: float64

ser.iloc[:2]

0    0.0
1    1.0
dtype: float64

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                    index=['Ohio', 'Colorado', 'Utah', 'New York'],
                    columns=['one', 'two', 'three', 'four'])
data

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data[['three', 'one']]

	three	one
Ohio	2	0
Colorado	6	4
Utah	10	8
New York	14	12

data[data['three'] > 5]

	one	two	three	four
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data < 5

	one	two	three	four
Ohio	True	True	True	True
Colorado	True	False	False	False
Utah	False	False	False	False
New York	False	False	False	False

data[data < 5] = 0
data

	one	two	three	four
Ohio	0	0	0	0
Colorado	0	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data.loc['Colorado', ['two', 'three']]

two      5
three    6
Name: Colorado, dtype: int32

# 所有行的前三列，再选择大于5的数值
data.iloc[:, :3][data.three > 5]

	one	two	three
Colorado	0	5	6
Utah	8	9	10
New York	12	13	14

Stay Foolish Stay Hungry