Pandas-基本数据结构-Series & DataFrame

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

1. Series

obj = Series([4,7,-5,3])
obj

    0    4
    1    7
    2   -5
    3    3
    dtype: int64

obj[2]#获取单个元素

-5

obj[1:3]#Series切片

    1    7
    2   -5
    dtype: int64

#获取Series索引
obj.index

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

#获取值
obj.values

    array([ 4,  7, -5,  3], dtype=int64)

#Series中默认的索引是从0开始,也可进行自定义
ships = Series(['企业','拉菲','独角兽','长门','光辉'],index=['a','b','c','d','e'])
ships

    a     企业
    b     拉菲
    c    独角兽
    d     长门
    e     光辉
    dtype: object

ships['c']

    '独角兽'

ships[['a','c','e']]

    a     企业
    c    独角兽
    e     光辉
    dtype: object

#通过字典创建Series
students = {
  '01':'Rachel','02':'Zack','03':'Daniel'}
obj2 = Series(students)

obj2

    01    Rachel
    02      Zack
    03    Daniel
    dtype: object

#字典创建Series时以字典Keys为主
obj2_new = Series(students,index=['01','02','04'])
obj2_new
'''
在字典中逐个查找是否有与索引列表(Index)相对应的Key值.如果有
'''

    01    Rachel
    02      Zack
    04       NaN
    dtype: object

obj = Series(np.arange(4),index=list('abcd'))
obj

    a    0
    b    1
    c    2
    d    3
    dtype: int32

#通过花式索引选出符合条件的数据
mask =obj<2
mask #Boll值
obj[mask] #数据

    a    0
    b    1
    dtype: int32

d2 = np.random.randn(4,3)
df = DataFr