02-pandas数据Serious

import pandas as pd
from pandas import Series
import numpy as np
from pandas import DataFrame
obj=Series([1,2,3,4,5])#Series包含行索引，列索引。默认0，1，2，3，4
obj2=Series([1,2,3,4,5],index=["a","b","c","d","e"])#自定义索引

arr1=np.arange(10)
obj3=Series(arr1,index=["a","b","c","d","e","f","h","j","k","l"])#索引对不上就会报错，索引要唯一

obj3=Series({"11111":1234,"abcabc":2222})
gk=Series([150,150,150,300],index=["数学","英语","语文","理科综合"])

obj4=Series([11,12,13,14,15])
print(obj4[0:2])#前提索引是数字
# print(testobj.loc(3))#标识索引对象
print(obj4.loc[0])#loc下标取值

obj5=Series([11,12,13,14,15],index=["a","b","c","d","e"])
# print(obj5.loc[3])#非数字索引loc取值就会报错
print(obj5[0:3])#非数字索引但是常规取值可以
print(obj5["a":"c"])
print(obj5.loc["d"])#loc取值
print(obj5.iloc[0:2 ])
#自定义索引obj[]既可以是数字也可以是自定义
#obj.loc[]只能是自己定义索引
#loc按照实际索引
#iloc按照数字所以
"""
Series
A=对象
A[0]：根据数字索引取出数据
A[1:3]:根据数字索引切片
A["a"]:根据自定义索引取出数据
A["a","b"]:根据自定义索引切片
loc：#按照自定义索引
iloc:按照索引
"""


print(obj5.shape)#形状
print(obj5.size)#多少元素
print(obj5.values)#返回数组的数值，numpy
print(obj5.head())#查看默认前五行，输入10就是前十行
print(obj5.tail())#查看尾部

mydict={"a":1,"b":2,"c":3}
index=["a","b","x"]#不在索引的数据会被狐狸，Nan不存在
obj6=Series(mydict,index=index)

print(pd.isnull(obj6))#判断数据是否完整
print(pd.notnull(obj6))#判断数据不为空
obj6.name="自定义名称"
print(obj6.name)
print(obj6+2)#表示每个数都加二
print(obj6[obj6>1])#数据筛选

A=Series([1,2,3],index=["a","b","c"])
B=Series([11,22,33],index=["a","b","c"])
print(A+B)#计算索引要一致

A=Series([1,2,3],index=["a","b","c1"])
B=Series([11,22,33],index=["a","b","c"])
print(A.add(B,fill_value=0))#索引不对等的加上零
#a     12.0
# b     24.0
# c     33.0
# c1     3.0