Python数据分析（4）pandas库的使用：数据的读写

怼烎@ 2022-05-23 13:09 172阅读 0赞

函数一览表：

![20180609151227167][]

#coding=gbk
    #pandas数据读写
    #1csv和文本文件的读取
    import numpy as np
    import pandas as pd
    mydata=pd.read_csv('D:\data\mydata.csv')    #读取数据
    print(mydata)
    #     color    object   name  others
    # 0     red      book   haha       1
    # 1   white       pen    NaN       4
    # 2  yellow  notebook   this      12
    # 3    blue      desk  smith       5
    # 4   black      door  jerry       7

mydata1=pd.read_table('D:\data\mydata.csv',sep=',') #csv也是文本格式，但是需要指定  分隔符，
    print(mydata1)
    #     color    object   name  others
    # 0     red      book   haha       1
    # 1   white       pen    NaN       4
    # 2  yellow  notebook   this      12
    # 3    blue      desk  smith       5
    # 4   black      door  jerry       7

#自定义表头
    mydata2=pd.read_csv('D:\data\mydata1.csv')
    print(mydata2)
    #       red      book   haha   1
    # 0   white       pen    NaN   4
    # 1  yellow  notebook   this  12
    # 2    blue      desk  smith   5
    # 3   black      door  jerry   7
    mydata3=pd.read_csv('D:\data\mydata1.csv',names=['color','object','name','others'])
    print(mydata3)      
    #     color    object   name  others    #添加了表头
    # 0     red      book   haha       1
    # 1   white       pen    NaN       4
    # 2  yellow  notebook   this      12
    # 3    blue      desk  smith       5
    # 4   black      door  jerry       7

#读取文本文件
    data1=pd.read_table('D:\data\data1.txt',sep='\s*')  #正则表达式为分隔符  空格\s
    print(data1)
    #    blue  black  white
    # 0     1      2      3
    # 1     4      5      6
    # 2     7      8      9
    #skiprows用法
    data2=pd.read_table('D:\data\data2.txt')
    print(data2)
    #             hahhahah -----
    # 0        -----------aha---
    # 1          fenge----------
    # 2  blue,black,white,yellow
    # 3           hahhahah -----
    # 4                  1,2,3,4
    # 5                  5,6,7,8
    # 6               1,22,33,44
    # 7                 6,8,9,10
    data3=pd.read_table('D:\data\data2.txt',sep=',',skiprows=[0,1,2,4]) #删除对应的行
    print(data3)
    #    blue  black  white  yellow
    # 0     1      2      3       4
    # 1     5      6      7       8
    # 2     1     22     33      44
    # 3     6      8      9      10
    #读取梯txt文件部分数据
    data4=pd.read_table('D:\data\data1.txt',sep='\s*',skiprows=[1],nrows=2) #skiprows定义起始行
    print(data4)
    #    blue  black  white
    # 0     4      5      6
    # 1     7      8      9

#在csv文件中写入数据
    mydata2=pd.read_csv('D:\data\mydata1.csv')
    print(mydata2)
    #       red      book   haha   1
    # 0   white       pen    NaN   4
    # 1  yellow  notebook   this  12
    # 2    blue      desk  smith   5
    # 3   black      door  jerry   7
    m=mydata2.to_csv('D:\data\data2.csv')
    print(m)
    #对于读取excel的xls同理，使用pd.read_excel();pd.to_excel()

#使用pandas对象实现序列化
    frame=pd.DataFrame(np.arange(16).reshape(4,4),index=['up','down','left','right'])
    print(frame)
    frame.to_pickle('D:\data\datapickle.pkl') #保存到对应的文件路径当中
    frame1=pd.read_pickle('D:\data\datapickle.pkl') #读取pkl格式的数据
    print(frame1)
    #         0   1   2   3
    # up      0   1   2   3
    # down    4   5   6   7
    # left    8   9  10  11
    # right  12  13  14  15

--------------------

![1240][]

[20180609151227167]: /images/20220523/114cf245f7b14da191bd8a4d69122922.png
[1240]: /images/20220523/1f8e1a0807f44850b98471c43378bc15.png