电子商务网站行为分析

代码 1：

import os
import pandas as pd


# 修改工作路径到指定文件夹
os.chdir("d:/numberfx")

# 第一种连接方式
#from sqlalchemy import create_engine

#engine = create_engine('mysql+pymysql://root:123456@192.168.31.140:3306/test?charset=utf8')
#sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)

# 第二种连接方式
import pymysql as pm

con = pm.connect(host='127.0.0.1', user='root', password='123456', db='test', port=3306)
#con = pm.connect('localhost','root','123456','test',charset='utf8')
#con = con.cursor()
data = pd.read_sql('select * from all_gzdata',con=con)
con.close() #关闭连接

# 保存读取的数据
data.to_csv('d:/numberfx/all_gzdata.csv', index=False, encoding='utf-8')

 

 代码2：

import pandas as pd
from sqlalchemy import create_engine

engine = create_engine('mysql+pymysql://root:123456@127.0.0.1:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)
# 分析网页类型
counts = [i['fullURLId'].value_counts() for i in sql] #逐块统计
counts = counts.copy()
counts = pd.concat(counts).groupby(level=0).sum() # 合并统计结果，把相同的统计项合并（即按index分组并求和）
counts = counts.reset_index() # 重新设置index，将原来的index作为counts的一列。
counts.columns = ['index', 'num'] # 重新设置列名，主要是第二列，默认为0
counts['type'] = counts['index'].str.extract('(\d{3})') # 提取前三个数字作为类别id
counts_ = counts[['type', 'num']].groupby('type').sum() # 按类别合并
counts_.sort_values(by='num', ascending=False, inplace=True) # 降序排列
counts_['ratio'] = counts_.iloc[:,0] / counts_.iloc[:,0].sum()
print(counts_)

 

# 代码11-3

# 因为只有107001一类，但是可以继续细分成三类：知识内容页、知识列表页、知识首页
def count107(i): #自定义统计函数
j = i[['fullURL']][i['fullURLId'].str.contains('107')].copy() # 找出类别包含107的网址
j['type'] = None # 添加空列
j['type'][j['fullURL'].str.contains('info/.+?/')]= '知识首页'
j['type'][j['fullURL'].str.contains('info/.+?/.+?')]= '知识列表页'
j['type'][j['fullURL'].str.contains('/\d+?_*\d+?\.html')]= '知识内容页'
return j['type'].value_counts()
# 注意：获取一次sql对象就需要重新访问一下数据库(!!!)
#engine = create_engine('mysql+pymysql://root:123456@127.0.0.1:3306/test?charset=utf8')
sql = pd.read_sql('all_gzdata', engine, chunksize = 10000)

counts2 = [count107(i) for i in sql] # 逐块统计
counts2 = pd.concat(counts2).groupby(level=0).sum() # 合并统计结果
print(counts2)
#计算各个部分的占比
res107 = pd.DataFrame(counts2)
# res107.reset_index(inplace=True)
res107.index.name&#