复习数据分析task01 pandas入门

pandas

1. series
2. dataframe

##Series
3. 由一组数据和一组与之相关的数据标签（即索引）组成

obj = Series([4, 5, -5, 3])
obj
0 4
1 7
2 -5
3 3
#表现形式极为索引在左，值在右边

#如果需要表现获取数组表现形式和索引对象
#用values获取数值
obj.values
orray([4, 7, -5, 3])

#用index获取索引对象
obj.index
Int64Index([0, 1, 2, 3])

#series对每一个数据点标记索引
obj = Series([4, 7, -5, 3], index['a', 'b', 'c', 'd'])
obj

a 4
b 7
c -5
d 3

#通过索引方式选取series中的单个或一组值
obj['a']
4

obj['d'] = 6
obj['a', 'b', 'c', 'd']

a 4
b 7
c -5
d 6
#通过a索引到值4， 通过d 更改数值为 6

#布尔型数组进行过滤，标量乘法，应用数学函数不改变其索引和值之间的连接

#过滤
obj[obj > 0]

a 4
b 7
d 6

#标量乘法
obj*2

a 8
b 14
c -10
d 12

#函数
np.exp(obj) # a 4 b 7 c -5 

a 403.428793
b 1096.633158
d 0.006738

#可以用做判断,将series是为定长的有序字典
'b' in obj

true

#数据存放在字典里
sdata = {
   'ohio': 3500, 'texas': 71000, 'oregon': 16000, 'utah': 5000}
obj = Series(sdata)
obj

ohio 3500
texas 71000
oregon 16000
utah 5000

#若只传入一个字典，则结果series中的索引就是原字典的键（有序排列）
states = ['california', 'ohio', 'oregon', 'texas']
obj = Series(sdata, index=states)
obj

california NaN#not a number 表示缺失值 针对缺失值，可以使用isnull和 notnull 来检测
ohio 35000
oregon 16000
texas 71000

#pandas-isnull
pd.isnull(obj)
california  true
ohio       false
oregon     false
texas      false

#pandas-notnull
pd.notnull(obj)
california  false
ohio        true
oregon      true
texas       true

#series-isnull
obj.isnull()
california  true
ohio       false
oregon     false
texas      false

#series 最重要的功能，在算数运算时会自动对齐

#之前用abcd对应的数字 4 7 -5 3 现在使用index原地替换
obj.index = ['bob', 'steven', 'jeff', 'ryan']
obj

bob 4
steven 7
jeff -5 
ryan 3

##dataframe是表格型的数据结构

import pandas as pd
data = {
   'state': ['ohio', 'ohio', 'ohio', 'nevada', 'nevada'], 'year': [2000, 2001, 2002, 2001, 2002],
'pop' [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = pd.DataFrame(data)
frame
#这个命名错了好几次了，注意前后统一，少了个pd死活过不去啊
   state	year	pop
0	ohio	2000	1.5
1	ohio	2001	1.7
2	ohio	2002	3.6
3	nevada	2001	2.4
4	nevada	2002	2.9

#如果指定了顺序
pd.DataFrame(data, columns=['year', 'state', 'pop'])

    year	state	pop
0	2000	ohio	1.5
1	2001	ohio	1.7
2	2002	ohio	3.6
3	2001	nevada	2.4
4	2002	nevada	2.9

#若出现数据找不到，则表现NA
frame2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'], index=['one', 'two', 'three', 'four', 'five'])
frame2

	    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

#类字典标记，获取一个series
frame2['state']

one        ohio
two        ohio
three      ohio
four     nevada
five     nevada
Name: state, dtype: object

#通过赋值的方式进行修改
frame2['debt']=16.5
frame2
	    year	state	pop	debt
one	    2000	ohio	1.5	16.5
two	    2001	ohio	1.7	16.5
three	2002	ohio	3.6	16.5
four	2001	nevada	2.4	16.5
five	2002	nevada	2.9	16.5

#精准赋值
val = pd.Series([-1.2, -1.5, -1.7], index=['two', 'four', 'five'])
frame2['debt']=val
frame2

         year	state	pop	debt
one	    2000	ohio	1.5	NaN
two	    2001	ohio	1.7	-1.2
three	2002	ohio	3.6	NaN
four	2001	nevada	2.4	-1.5
five	2002	nevada	2.9	-1.7

#为不存在的列赋值会创建出新的列
frame2['eastern'] = frame2.state == 'ohio'
frame2

         year	state	pop	debt	eastern
one	    2000	ohio	1.5	NaN	    True
two	    2001	ohio	1.7	-1.2	True
three	2002	ohio	3.6	NaN	     True
four	2001	nevada	2.4	-1.5	False
five	2002	nevada	2.9	-1.7	False

#关键字用del删除即可

del frame2['eastern']
frame2.columns
Index(['year', 'state', 'pop', 'debt'], dtype='object')

#嵌套字典-外层字典的键作为列，内层键作为行
pop = {
   'nevada': {
   2001: 2.4, 2002: 2.9}, 'ohio': {
   2000: 1.5, 2001: 1.7, 2002: 3.6}}
frame3 = pd.DataFrame(pop)
​frame3

        nevada	ohio
2001	2.4	1.7
2002	2.9	3.6
2000	NaN	1.5

#转置-横纵坐标对调
	    2001	2002	2000
nevada	2.4	2.9	NaN
ohio	1.7	3.6	1.5

#内层字典的键会被合并，排序以形成最终的索引
pd.DataFrame(pop, index=[2001, 2002, 2003])
        nevada	ohio
2001	2.4	1.7
2002	2.9	3.6
2003	NaN	NaN

#还可以给行和列设置属性
frame3.index.name = 'year'; frame3.columns.name = 'state'
frame3

state	nevada	ohio
year		
2001	2.4	1.7
2002	2.9	3.6
2000	NaN	1.5

#values 属性也会以ndarray的形式返回
frame3.values

array([[2.4, 1.7],
       [2.9, 3.6],
       [nan, 1.5]])
#各列的数据类型不同，则值数组的数据类型就会选用能兼容所有列的数据类型
frame2.values
array([[2000, 'ohio', 1.5, nan],
       [2001, 'ohio', 1.7, -1.2],
       [2002, 'ohio', 3.6, nan],
       [2001, 'nevada', 2.4, -1.5],
       [2002, 'nevada', 2.9, -1.7]], dtype=object)

重新索引

#reindex---传建一个适应新索引的对象
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


#reindex将会根据新索引进行重排
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


#因为存在空值，令它等于0
obj.reindex(['a', 'b', 'c', 'd', 'e'], fill_value=0)
a   -5.3
b    7.2
c    3.6
d    4.5
e    0.0
dtype: float64

#对于有序数据，索引时需要插值处理
obj3 = pd.Series(['blue', 'purple', 'yellow'], index=[0, 2, 4])
obj3

0      blue
2    purple
4    yellow
dtype: object

obj3.reindex(range(6), method='ffill')#前补后
0      blue
1      blue
2    purple
3    purple
4    yellow
5    yellow
dtype: object

obj3.reindex(range(6), method='bfill')#后补前
0      blue
1    purple
2    purple
3    yellow
4    yellow
5       NaN
dtype: object

#reindex可以修改行或列索引，只传递一个序列时，会重新索引结果的行
import numpy as np
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


frame2 = frame.reindex(['a', 'b', 'c', 'd'])
frame2 

	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

#列可以用columns重新索引
states = ['texas', 'utah', 'california']
frame.reindex(columns=states)

	texas	utah	california
a	1	     NaN	2
c	4	     NaN	5
d	7	     NaN	8

#丢弃指定值上面的项
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

#drop返回的是一个在指定轴上删除了指定值的新对象
#arange返回的是一个数据

obj = pd.Series(np.arange(5.), index=['a', 'b', 'c', 'd', 'e'])
new_obj = obj.drop('c')
new_obj
a    0.0
b    1.0
d    3.0
e    4.0
dtype: float64

#用drop会从行标签axis 0删除
data.drop(['colorado', 'ohio'])
	    one	two	three	four
utah	8	9	10	11
newyork	12	13	14	15

#axis=1 或axis= 'columns'可以删除列的值
data.drop('two', axis=1)

           one	three	four
ohio	    0