1。 将本地sql文件写入mysql数据库

本文写入的是python数据库的taob表

source [本地文件]

其中总数据为9616行，列分别为title,link,price,comment

2。使用python链接并读取数据

查看数据概括

#-*- coding:utf-8 -*-#author：M10import numpy as npimport pandas as pdimport matplotlib.pylab as pltimport mysql.connectorconn = mysql.connector.connect(host='localhost', user='root', passwd='123456', db='python')#链接本地数据库sql = 'select * from taob'#sql语句data = pd.read_sql(sql,conn)#获取数据print(data.describe())

说明数据的导入是正确的,简单的分析发现问题并不是这么简单，因为comment均值562可能偏大，最大评论数454037也可能出现错误，price价格为0也不太可能出现。

price commentcount 9616.00000 9616.000000mean 64.49324 562.239601std 176.10901 6078.909643min 0.00000 0.00000025% 20.00000 16.00000050% 36.00000 58.00000075% 66.00000 205.000000max 7940.00000 454037.000000

3。缺失值处理

将价格为0的值设置为中位数36

#-*- coding:utf-8 -*-#author：M10import numpy as npimport pandas as pdimport matplotlib.pylab as pltimport mysql.connectorconn = mysql.connector.connect(host='localhost', user='root', passwd='123456', db='python')#链接本地数据库sql = 'select * from taob'#sql语句data = pd.read_sql(sql,conn)#获取数据data['price'][data['price']==0]=Nonex = 0for i in data.columns: for j in range(len(data)): if (data[i].isnull()) [j]: data[i][j]='36' x+=1print(x)#44

结果显示修改了44行的数据。

4。异常值处理

#-*- coding:utf-8 -*-#author：M10import numpy as npimport pandas as pdimport matplotlib.pylab as pltimport mysql.connectorconn = mysql.connector.connect(host='localhost', user='root', passwd='123456', db='python')#链接本地数据库sql = 'select * from taob'#sql语句data = pd.read_sql(sql,conn)#获取数据#缺失值处理data['price'][data['price']==0]=Nonex = 0for i in data.columns: for j in range(len(data)): if (data[i].isnull()) [j]: data[i][j]='36' x+=1print(x)#异常值处理#绘制散点图,价格为横轴data1 = data.T#转置price = data1.values[2]comment = data1.values[3]plt.plot(price,comment,'o')plt.show()#print(price)

结果如下图，价格为0左右时comment很大可能为异常值，comments为0时，价格极大这个有可能的。

接下来处理评论数异常值，假设异常值分割线设置为20w，

#-*- coding:utf-8 -*-#author：M10import numpy as npimport pandas as pdimport matplotlib.pylab as pltimport mysql.connectorconn = mysql.connector.connect(host='localhost', user='root', passwd='123456', db='python')#链接本地数据库sql = 'select * from taob'#sql语句data = pd.read_sql(sql,conn)#获取数据#缺失值处理data['price'][data['price']==0]=Nonex = 0for i in data.columns: for j in range(len(data)): if (data[i].isnull()) [j]: data[i][j]='36' x+=1print(x)#异常值处理da = data.values#重新赋值data#异常值处理，将commments大于200000的数据comments设置为58cont_clou = len(da)#获取行数#遍历数据进行处理for i in range(0,cont_clou): if(data.values[i][3]>200000): #print(data.values[i][3]) da[i][3]='58' #print(da[i][3])#绘制散点图,价格为横轴data1 = da.T#转置price = data1[2]comment = data1[3]plt.plot(price,comment,'o')plt.xlabel('price')plt.ylabel('comments')plt.show()

处理后的输出结果为：

以上这篇python实现数据清洗(缺失值与异常值处理)就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。