Python3.5 Pandas模块之Series用法实例分析

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author:ZhengzhengLiu

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#1.Series通过numpy一维数组创建
print("=========Series通过numpy一维数组创建==========")
arr = np.array([1,2,3,4,5])
s1 = pd.Series(arr)
print(s1)
print(s1.index)
print(s1.values)

#2.Series直接通过一维数组创建
print("=========Series直接通过一维数组创建==========")
s2 = pd.Series([10.5,20,38,40])
print(s2)
#修改索引值
s2.index = ['a','b','c','d']
print(s2)

#Series通过一维数组创建，可以在创建的同时自定义索引值，
# 也可以之后通过赋值的形式去修改
print("=========Series创建的同时自定义索引值和数据类型==========")
s3 = pd.Series(data=[89,78,90,87],dtype=np.float64,
        index=['语文','数学','英语','科学'])
print(s3)

#3.Series通过字典创建,字典的键对应索引，值对应数据
print("=========Series通过字典创建==========")
dict = {'a':1,'b':2,"c":3,"d":4}
s4 = pd.Series(dict)
print(s4)

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#4.Series值的获取
print("=========Series值的获取==========")
s2 = pd.Series([10.5,20,38,40])
#修改索引值
s2.index = ['a','b','c','d']
print(s2)
print(s2[0])    #方括号+下标值的形式获取Series值
print(s2["a"])   #方括号+索引的形式获取Series值

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#5.Series值的运算
#Series中元素级别的运算结果，包含索引值并且键值关系保持不变
print("=========Series值的运算==========")
s6 = pd.Series({'a':1,'b':2,"c":3,"d":4})
print(s6)
print("=========打印Series大于2的值==========")
print(s6[s6>2])
print("=========打印Series的值除以2==========")
print(s6/2)

#numpy中的通用函数在Series中也支持
s7= pd.Series([1,2,-3,-4])
print(np.exp(s7))

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#6.Series缺失值检验
scores = Series({"a":88,"b":79,"c":98,"d":100})
print(scores)

new = ["a","b","e","c","d"]
scores = Series(scores,index=new)
print(scores)

print("======过滤出为缺失值的项=======")
print(scores.isnull())       #NAN值返回True
#print(pd.isnull(scores))      #与上面一句等价

print("======过滤出为非缺失值的项=======")
print(pd.notnull(scores))      #非NAN值返回True

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#7.Series自动对齐

s8 = Series([12,28,46],index=["p1","p2","p3"])
s9 = Series([2,4,6,8],index=["p2","p3","p4","p5"])
print("=======s8=======")
print(s8)
print("=======s9=======")
print(s9)
print("=======s8+s9=======")
print(s8+s9)

#模块引入
import numpy as np
import pandas as pd
from pandas import Series,DataFrame

#8.Series及其name属性
s10 = Series({"jack":18,"amy":20,"lili":23,"susan":15})
print(s10)

print("=======设置name属性后=======")
s10.name = "年龄"    #数据名称标签
s10.index.name = "姓名"    #索引名称标签

print(s10)