数据挖掘作业

# 代码3-3 捞起生鱼片的季度销售情况
import pandas as pd
import numpy as np
catering_sale = 'C:/Users/23505/Desktop/学习资料/catering_fish_congee.xls' # 餐饮数据
data = pd.read_excel(catering_sale,names=['date','sale']) # 读取数据，指定“日期”列为索引

bins = [0,500,1000,1500,2000,2500,3000,3500,4000]
labels = ['[0,500)','[500,1000)','[1000,1500)','[1500,2000)',
'[2000,2500)','[2500,3000)','[3000,3500)','[3500,4000)']

data['sale分层'] = pd.cut(data.sale, bins, labels=labels)
aggResult = data.groupby(by='sale分层').agg({'sale': np.size})

pAggResult = round(aggResult/aggResult.sum(), 2, ) * 100

import matplotlib.pyplot as plt
plt.figure(figsize=(10,6)) # 设置图框大小尺寸
pAggResult['sale'].plot(kind='bar',width=0.8,fontsize=10) # 绘制频率直方图
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.title('季度销售额频率分布直方图2020310143047',fontsize=20)
plt.show()

##读取数据
url = 'C:/Users/23505/Desktop/学习资料/catering_fish_congee.xls'
data = pd.read_excel(url,names=['date','sale'])

plt.rcParams['font.sans-serif'] = ['SimHei'] #显示中文
plt.rcParams['axes.unicode_minus'] = False

#箱型图
plt.figure()
p = data.boxplot(return_type=('dict'))
x = p['fliers'][0].get_xdata()
y = p['fliers'][0].get_ydata()
y.sort()
plt.title('季度销售额箱型图--number：2020310143047') #加标题

 

 

 

 

import pandas as pd
import matplotlib.pyplot as plt
catering_dish_profit = 'C:/Users/23505/Desktop/学习资料/catering_dish_profit.xls' # 餐饮数据
data = pd.read_excel(catering_dish_profit)
x = data['盈利']
labels = data['菜品名']
plt.figure(figsize = (8,6))
plt.pie(x,labels = labels)
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.title('菜品销售分部（饼图）学号2020310143047')
plt.axis('equal')
plt.show()

catering_dish_profit = 'C:/Users/23505/Desktop/学习资料/catering_dish_profit.xls' # 餐饮数据
data = pd.read_excel(catering_dish_profit)
x = data['菜品名']
y = data['盈利']
plt.Figure(figsize = (8,4))
plt.bar(x,y)
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.xlabel('菜品')
plt.ylabel('销量')
plt.title('菜品销售分布量（条形图）学号2020310143047')
plt.show()

 

 

 

import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_excel('C:/Users/23505/Desktop/学习资料/dish_sale.xls')
plt.figure(figsize=(8,4))
plt.plot(data['月份'], data['A部门'],color='green',label='A部门',marker='o')
plt.plot(data['月份'], data['B部门'],color='red',label='B部门',marker='s')
plt.plot(data['月份'], data['C部门'],color='skyblue',label='C部门',marker='x')
plt.legend()
plt.ylabel('销售额（万元）')
plt.title('年度部门销售图-2020310143047',fontsize=20)
plt.show()

 

 

import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_excel('C:/Users/23505/Desktop/学习资料/dish_sale_b.xls')
plt.figure(figsize=(8,4))
plt.plot(data['月份'], data['2012年'],color='green',label='2012年',marker='o')
plt.plot(data['月份'], data['2013年'],color='red',label='2013年',marker='s')
plt.plot(data['月份'], data['2014年'],color='skyblue',label='2014年',marker='x')
plt.legend()
plt.ylabel('销售额（万元）')
plt.title('B部门近三年销售图-2020310143047',fontsize=20)
plt.show()

 

import numpy as np
import matplotlib.pyplot as plt #导入绘图包
import math

plt.rcParams['font.sans-serif'] = ['SimHei'] #解决中文显示问题
plt.rcParams['axes.unicode_minus'] = False # 解决中文显示问题

x=np.arange(0,2*math.pi,0.1)#以0.1为单位，生成0到6的数据
y=np.sin(x)

plt.figure(figsize=(12,8))
plt.plot(x,y,color='skyblue',label='f(x)=sin x',marker='o')
plt.title('f(x)=sin x在（0，2Π）的函数图象--number：2020310143047') #加标题
plt.xlabel('X')
plt.ylabel('Y')
plt.legend() #显示图例
plt.show()