【Data Analysis and Visualization】 Pandas Series

import numpy as np
import pandas as pd

# 1 np直接创建series
s1 = pd.Series([1,2,3,4])
s1

0    1
1    2
2    3
3    4
dtype: int64

# 查看series值
s1.values

array([1, 2, 3, 4])

# 查看series索引状态
s1.index

RangeIndex(start=0, stop=4, step=1)

# 2 通过np辅助创建pd的series
s2 = pd.Series(np.arange(10))
s2

0    0
1    1
2    2
3    3
4    4
5    5
6    6
7    7
8    8
9    9
dtype: int64

# 3 字典创建series
s3 = pd.Series({'1':'1','2':'2','3':'3'})
s3

1    1
2    2
3    3
dtype: object

s3.values

array(['1', '2', '3'], dtype=object)

# 索引是字典的key 
s3.index

Index(['1', '2', '3'], dtype='object')

# 自定义索引
s4 = pd.Series([1,2,3,4],index=['A','B','C','D'])
s4

A    1
B    2
C    3
D    4
dtype: int64

s4.index

Index(['A', 'B', 'C', 'D'], dtype='object')

# series可以直接通过字典key获取值
s4['A']

1

# 取值范围value>2
s4[s4>2]

C    3
D    4
dtype: int64

# pd的series转换成字典
s4.to_dict()

{'A': 1, 'B': 2, 'C': 3, 'D': 4}

# series的index可以改变
index_1 = ['A', 'B', 'C', 'D', 'E']
s5 = pd.Series(s4, index=index_1)
s5

A    1.0
B    2.0
C    3.0
D    4.0
E    NaN
dtype: float64

# key对应的空值显示NaN,可以判断空值
pd.isnull(s5)

A    False
B    False
C    False
D    False
E     True
dtype: bool

pd.notnull(s5)

A     True
B     True
C     True
D     True
E    False
dtype: bool

# 给series添加描述信息name
s5.name = 'demo'
s5

A    1.0
B    2.0
C    3.0
D    4.0
E    NaN
Name: demo, dtype: float64

s5.index.name = 'demo index'
s5.index

Index(['A', 'B', 'C', 'D', 'E'], dtype='object', name='demo index')

s5.values

array([ 1.,  2.,  3.,  4., nan])