python连接数据库分析餐饮数据、、可视化

import pandas as pd
from sqlalchemy import create_engine
import numpy as np
import matplotlib.pyplot as plt

enging = create_engine("mysql+mysqlconnector://root:root@localhost/tes_db")#设置数据库连接

#读入数据
data1=pd.read_sql("meal_order_detail1",con=enging)
data2=pd.read_sql("meal_order_detail2",con=enging)
data3=pd.read_sql("meal_order_detail3",con=enging)
# 数据按列合并
data = pd.concat([data1,data2,data3],axis=0)

# 数据预处理
# 计算收入
data['price'] = data['counts']*data['amounts']
# 日期转换为星期
ind = pd.DatetimeIndex(data['place_order_time']) # pd.to_datetime()
data['weekday_name'] = ind.weekday_name

# 每天销售总额
data['day'] = ind.day
data_gb = data[['day','price']].groupby(by='day')
number = data_gb.agg(np.sum)

散点图

# plt.scatter(range(1,32),number)
plt.scatter(range(1,32),number,marker='D')
plt.show()

效果

 

 

 

#绘制折线图

plt.plot(range(1,32),number,'r')
plt.title('2016年8月餐饮销售额趋势示意图')
plt.xlabel('日期')
plt.ylabel('销售额')
plt.xticks(range(1,32)[::6],range(1,32)[::6])

plt.text(number['price'].argmin(),number.min(),'最小值为'+str(number['price'].min()),va='top')
plt.text(number['price'].argmax(),number.max(),'最大值为'+str(number['price'].max()),va='bottom')
plt.show()

效果：

 

星期与销售额的数量情况

ind = ['Monday','Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday']
data_gb_weekday = data[['weekday_name','price']].groupby(by='weekday_name')
number_pie = data_gb_weekday.agg(np.sum)

number2 = number_pie.loc[ind,'price']

# 绘制直方图
plt.bar(range(1,len(number2)+1),number2,width=0.5,alpha=0.5)
plt.xticks(range(1,len(number2)+1), number2.index)
plt.plot(range(1,len(number2)+1),number2,'g')
plt.title('星期与销售额的数量情况')
for i,j in zip(range(1,len(number2)+1),number2):
    plt.text(i,j+1000,'%i'%j,ha='center',va='bottom')
plt.show()

 

 星期销售额占比情况

plt.style.use('ggplot')#
plt.figure(figsize=(5,5))#长  宽
plt.pie(number2,autopct='%.2f %%',labels=number2.index,wedgeprops=dict(width=0.6,edgecolor='w'))
plt.title('星期销售额占比情况')
plt.show()

wedgeprops属性可以设置为圆环图，无为饼状图

 

 数据整理

data_gb_or = data[['order_id','price','day']].groupby(by='day')
def myfun(data):
    return len(np.unique(data))

number3 = data_gb_or.agg({'price':np.sum,'order_id':myfun})
number3

 

 订单量、销售额与时间的关系

plt.scatter(range(1,32),number3['price'],s=number3['order_id'])  # 气泡图
# s的大小表示订单量的多少

plt.title('订单量、销售额与时间的关系')
plt.xlabel('时间')
plt.ylabel('销售额')
plt.show()