source [本地文件]

#-*- coding:utf-8 -*-
#author：M10
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import mysql.connector
conn = 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())

 price    comment
count 9616.00000  9616.000000
mean   64.49324   562.239601
std   176.10901  6078.909643
min    0.00000    0.000000
25%   20.00000   16.000000
50%   36.00000   58.000000
75%   66.00000   205.000000
max  7940.00000 454037.000000

#-*- coding:utf-8 -*-
#author：M10
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import mysql.connector
conn = 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]=None
x = 0
for i in data.columns:
  for j in range(len(data)):
    if (data[i].isnull()) [j]:
      data[i][j]='36'
      x+=1
print(x)
#44

#-*- coding:utf-8 -*-
#author：M10
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import mysql.connector
conn = 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]=None
x = 0
for i in data.columns:
  for j in range(len(data)):
    if (data[i].isnull()) [j]:
      data[i][j]='36'
      x+=1
print(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)

#-*- coding:utf-8 -*-
#author：M10
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import mysql.connector
conn = 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]=None
x = 0
for i in data.columns:
  for j in range(len(data)):
    if (data[i].isnull()) [j]:
      data[i][j]='36'
      x+=1
print(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58
cont_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()