用Python画数据分析第三章的图

标签：数据分析 plt 第三章 学号 Python sale pd import data

import pandas as pd
catering_sale="D:\数据分析\catering_sale.xls"

data=pd.read_excel(catering_sale,index_col=u'日期')
print(data.describe())


import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.figure()
p=data.boxplot(return_type='dict')
x=p['fliers'][0].get_xdata()
y=p['fliers'][0].get_ydata()
y.sort()

for i in range(len(x)):
    if i>0:
        plt.annotate(y[i],xy=(x[i],y[i]),xytext=(x[i]+0.05 -0.8/(y[i]-y[i-1]),y[i]))
    else:
        plt.annotate(y[i],xy=(x[i],y[i]),xytext=(x[i]+0.08,y[i]))
plt.title('学号3108')
plt.show()

 

# 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 = "D:\数据分析\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)
print(data)
aggResult = data.groupby(by=['sale分层'])['sale'].agg({"count","count"})
print(aggResult)
pAggResult = round(aggResult/aggResult.sum(), 2, ) * 100
print(pAggResult)

import matplotlib.pyplot as plt
plt.figure(figsize=(10,6))  # 设置图框大小尺寸
pAggResult['count'].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('学号3108,季度销售额频率分布直方图',fontsize=20)
plt.show()

　　

 

import pandas as pd
import matplotlib.pyplot as plt
catering_dish_profit="D:\数据分析\catering_dish_profit.xls"
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('学号3108，菜品销售量分布（饼图）')
plt.axis('equal')
plt.show()

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('学号3108，菜品销售量分布（条形图）')
plt.show()

 

 

 

#部门之间销售金额比较
import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_excel("D:\数据分析\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('学号3108，部门之间销售金额比较')
plt.show()

data=pd.read_excel("D:\数据分析\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.show()

 

 

import pandas as pd
catering_sale="D:\数据分析\catering_sale.xls"
data=pd.read_excel(catering_sale,index_col='日期')
data=data[(data['销量']>400)&(data['销量']<5000)]
statistics=data.describe()
statistics.loc['range']=statistics.loc['max']-statistics.loc['min']
statistics.loc['var']=statistics.loc['std']/statistics.loc['mean']
statistics.loc['dis']=statistics.loc['75%']-statistics.loc['25%']
print(statistics)

 

 

import pandas as pd
import matplotlib.pyplot as plt
df_normal=pd.read_csv("D:/数据分析/user.csv")
plt.figure(figsize=(8,4))
plt.plot(df_normal["Date"],df_normal["Eletricity"])
plt.xlabel("日期")
x_major_locator=plt.MultipleLocator(7)
ax=plt.gca()
ax.xaxis.set_major_locator(x_major_locator)
plt.ylabel("每日电量")
plt.title("学号3108，正常用户电量趋势")
plt.rcParams['font.sans-serif']=['SimHei']
plt.show()

df_steal=pd.read_csv("D:\数据分析\Steal user.csv")
plt.figure(figsize=(10,9))
plt.plot(df_steal["Date"],df_steal["Eletricity"])
plt.xlabel("日期")
plt.ylabel("日期")
x_major_locator=plt.MultipleLocator(7)
ax=plt.gca()
ax.xaxis.set_major_locator(x_major_locator)
plt.title("学号3108，窃电用户电量趋势")
plt.rcParams['font.sans-serif']=['SimHei']
plt.show()

 

 

 

import pandas as pd
dish_profit="D:\数据分析\catering_dish_profit.xls"
data=pd.read_excel(dish_profit,index_col='菜品名')
data=data['盈利'].copy()
data.sort_values(ascending=False)
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.figure()
data.plot(kind='bar')
plt.ylabel('盈利（元）')
p=1.0*data.cumsum()/data.sum()
p.plot(color='pink',secondary_y=True,style='-o',linewidth=2)
plt.annotate(format(p[6],'.4%'),xy=(6,p[6]),xytext=(6*0.9,p[6]*0.9),
    arrowprops=dict(arrowstyle="->",connectionstyle="arc3,rad=.2"))
plt.ylabel('盈利（比例）')
plt.title('学号3108')
plt.show()

 

 

 

#餐饮销量数据相关性分析
import pandas as pd
catering_sale="D:\数据分析\catering_sale_all.xls"
data=pd.read_excel(catering_sale,index_col='日期')

print(data.corr())

print(data.corr()['百合酱蒸凤爪'])

print(data['百合酱蒸凤爪'].corr(data['翡翠蒸香茜饺']))

 

 

 

 

import matplotlib.pyplot as plt
import numpy as np
x=np.linspace(0,2*np.pi,50)
y=np.sin(x)
plt.plot(x,y,'bp--')
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt

labels='Frogs','Hogs','Dogs','Logs'
sizes=[15,30,45,10]
colors=['yellowgreen','gold','lightskyblue','lightcoral']
explode=(0,0.1,0,0)

plt.pie(sizes,explode=explode,labels=labels,colors=colors,autopct='%1.1f%%',
        shadow=True,startangle=90)
plt.axis('equal')
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt
import numpy as np
x=np.random.randn(1000)
plt.hist(x,10)
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
x=np.random.randn(1000)
D=pd.DataFrame([x,x+1]).T
D.plot(kind='box')
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
import numpy as np
import pandas as pd

x=pd.Series(np.exp(np.arange(20)))
plt.figure(figsize=(8,9))
ax1=plt.subplot(2,1,1)
x.plot(label='原始数据图',legend=True)

ax1=plt.subplot(2,1,2)
x.plot(logy=True,label='对数数据图',legend=True)
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
import numpy as np
import pandas as pd

error=np.random.randn(10)
y=pd.Series(np.sin(np.arange(10)))
y.plot(yerr=error)
plt.title('学号3108')
plt.show()

 

 

import matplotlib.pyplot as plt
years = [2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019]
turnovers = [0.5, 9.36, 52, 191, 350, 571, 912, 1027, 1682, 2135, 2684]
plt.figure()
plt.scatter(years, turnovers, c='pink', s=100, label='legend')
plt.xticks(range(2008, 2020, 3))
plt.yticks(range(0, 3200, 800))
plt.xlabel("Year", fontdict={'size': 16})
plt.ylabel("number", fontdict={'size': 16})
plt.title("Title", fontdict={'size': 20})
plt.legend(loc='best')
plt.title('学号3108')
plt.show()

 

 

 

总结：在数据可视化中，由于我们主要使用pandas作为数据探索和分析工具，因此介绍的绘图工具都是Matplotlib和pandas结合使用。一方面，Matplotlib是绘图工具的基础，pandas绘图依赖于它；另一方面，pandas绘图有着简单直接的优势，因此，两者互结合，往往能够以最高的效率做出符合我们需要的图。

标签：数据分析,plt,第三章,学号,Python,sale,pd,import,data
From： https://www.cnblogs.com/hxs6/p/17155700.html