利用Python进行数据分析笔记－pandas基础

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

Series基础

obj = pd.Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])
obj

d    4
b    7
a   -5
c    3
dtype: int64

# 命名
obj.name = 'Series Name'
obj.index.name = 'index'
obj

index
d    4
b    7
a   -5
c    3
Name: Series Name, dtype: int64

print('左边的index：', obj.index)
print('右边的values：', obj.values)
print('索引a：', obj['a'])
print('判断：', 'b' in obj)

print('\n索引b/d/c： \n', obj[['b','d','c']])
print('\n大于0的：\n',obj[obj > 0])

左边的index： Index(['d', 'b', 'a', 'c'], dtype='object', name='index')
右边的values： [ 4  7 -5  3]
索引a： -5
判断： True

索引b/d/c： 
 index
b    7
d    4
c    3
Name: Series Name, dtype: int64

大于0的：
 index
d    4
b    7
c    3
Name: Series Name, dtype: int64

# isnul 及 notnull
obj[obj>0].isnull()

index
d    False
b    False
c    False
Name: Series Name, dtype: bool

DataFrame基础

data = {
  'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada'], 
        'year': [2000, 2001, 2002, 2001, 2002, 2003], 
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
frame = pd.DataFrame(data)
frame

	pop	state	year
0	1.5	Ohio	2000
1	1.7	Ohio	2001
2	3.6	Ohio	2002
3	2.4	Nevada	2001
4	2.9	Nevada	2002
5	3.2	Nevada	2003

# 自定义排序
df = pd.DataFrame(frame, columns=['year', 'state', 'pop'])
# 返回前面多少行  head()默认5行
df.head(3)

	year	state	pop
0	2000	Ohio	1.5
1	2001	Ohio	1.7
2	2002	Ohio	3.6

# 返回尾部多少行  tail()默认5行
df.tail(3)

	year	state	pop
3	2001	Nevada	2.4
4	2002	Nevada	2.9
5	2003	Nevada	3.2

# 导入一个不存在的列名，会显示为缺失数据NaN
# 更改 index
df2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'], 
                      index=['one', 'two', 'three', 'four', 'five', 'six'])
df2

	year	state	pop	debt
one	2000	Ohio	1.5	NaN
two	2001	Ohio	1.7	NaN
three	2002	Ohio	3.6	NaN
four	2001	Nevada	2.4	NaN
five	2002	Nevada	2.9	NaN
six	2003	Nevada	3.2	NaN

# 查看某列数据 方法一
df2['year'].head(3)

one      2000
two      2001
three    2002
Name: year, dtype: int64

# 查看某列数据 方法二
df2.year

one      2000
two      2001
three    2002
four     2001
five     2002
six      2003
Name: year, dtype: int64

注意：df2[column]能应对任何列名，但df2.column的情况下，列名必须是有效的python变量名才行。

# 查看某行数据
df2.loc['three']

year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object

# 查看某行数据，利用index
df2.iloc[2:5]

	year	state	pop	debt
three	2002	Ohio	3.6	NaN
four	2001	Nevada	2.4	NaN
five	2002	Nevada	2.9	NaN

# 每隔两个元素选一个元素
df2.iloc[::2]

	year	state	pop	debt
one	2000	Ohio	1.5	NaN
three	2002	Ohio	3.6	NaN
five	2002	Nevada	2.9	NaN

# 给debt列赋值
df2['debt'] = np.arange(6.)
df2

	year	state	pop	debt
one	2000	Ohio	1.5	0.0
two	2001	Ohio	1.7	1.0
three	2002	Ohio	3.6	2.0
four	2001	Nevada	2.4	3.0
five	2002	Nevada	2.9	4.0
six	2003	Nevada	3.2	5.0

# 给不存列赋值会新增列
df2['eastern'] = df2.state == 'Ohio'
df2

	year	state	pop	debt	eastern
one	2000	Ohio	1.5	0.0	True
two	2001	Ohio	1.7	1.0	True
three	2002	Ohio	3.6	2.0	True
four	2001	Nevada	2.4	3.0	False
five	2002	Nevada	2.9	4.0	False
six	2003	Nevada	3.2	5.0	False

# 删除列
del df2['eastern']
df.columns # 注意：columns返回的是一个view，而不是新建了一个copy。因此，任何对series的改变，会反映在DataFrame上

Index(['year', 'state', 'pop'], dtype='object')

# DataFrame可以像numpy数组一样做转置
df2.T

	one	two	three	four	five	six
year	2000	2001	2002	2001	2002	2003
state	Ohio	Ohio	Ohio	Nevada	Nevada	Nevada
pop	1.5	1.7	3.6	2.4	2.9	3.2
debt	0	1	2	3	4	5

# 给DataFrame的index和column命名
df2.index.name = '索引名'
df2.columns.name = '行名'
df2

行名	year	state	pop	debt
索引名
one	2000	Ohio	1.5	0.0
two	2001