python数据分析与挖掘实战1

import numpy as np
import pandas as pd

df = pd.read_excel('E:\桌面\catering_sale.xls')
df.fillna(0)
#print(df.isnull())
#print(df['销量'].sum())
import matplotlib.pyplot as plt
#将(0,1)点和(2,4)连起来

plt.plot(df['日期'],df['销量'])
plt.title('3118')
plt.show()
p=df.boxplot()
plt.title('3118')
plt.show()

x=np.linspace(0,2*np.pi,256)
y=np.sin(x)
plt.plot(x,y)
plt.title('3118')
plt.show()

x = np.linspace(-2*np.pi,2*np.pi,60,endpoint=True)
s = np.sin(x)
plt.figure()
plt.plot(x,s,'b-*',)
plt.xlabel("x",fontdict={'size':16})
plt.ylabel("y",fontdict={'size':16})
plt.legend("sin(x)")
plt.title('3118')
plt.show()

catering_sale = 'E:\桌面\catering_fish_congee.xls' 
data = pd.read_excel(catering_sale,names=['date','sale'])  
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'])['sale'].agg({'sale': np.size})
pAggResult = round(aggResult/aggResult.sum(), 2, ) * 100
plt.figure(figsize=(10,6))  
pAggResult['sale'].plot(kind='bar',width=0.8,fontsize=10)  
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.title('季度销售额频率分布直方图3118',fontsize=20)
plt.show()

 

 

 

 

 

 

import pandas as pd
import matplotlib.pyplot as plt
catering_dish_profit='E:/桌面/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('菜品销量分布(饼图)3118')
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('3118')
plt.show()

 

 

 

 

 

 

 

import pandas as pd
import matplotlib.pyplot as plt
catering_dish_profit='E:/桌面/dish_sale.xls'
data=pd.read_excel(catering_dish_profit)
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.show()


data=pd.read_excel("E:/桌面/dish_sale_b(1).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
import matplotlib.pyplot as plt
df_normal = pd.read_csv("E:/桌面/user.csv",engine='python')
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.rcParams['font.sans-serif'] = ['SimHei']
plt.title('3118',fontsize=20)
plt.show()
df_steal = pd.read_csv("E:/桌面/Steal user.csv",engine='python')
plt.figure(figsize=(10,9))
plt.plot(df_steal["Date"],df_steal["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.rcParams['font.sans-serif'] = ['SimHei']
plt.title('3118',fontsize=20)
plt.show()

 

 

 

import pandas as pd
import matplotlib.pyplot as plt
dish_profit = 'E:/桌面/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)
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='r',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('3118',fontsize=20)
plt.show()

 

 

 

import numpy as np
import matplotlib.pyplot as plt
plt.figure(figsize=(7,5))
plt.rcParams['axes.unicode_minus'] = False
x = np.linspace(0,2*np.pi,50)
y = np.sin(x)
plt.plot(x,y,'bp--')
plt.title('3118',fontsize=20)
plt.show()

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('3118',fontsize=20)
plt.show()

x = np.random.randn(1000)
plt.hist(x,10)
plt.title('3118',fontsize=20)
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('3118',fontsize=20)
plt.show()



plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
x = pd.Series(np.exp(np.arange(20)))
plt.figure(figsize=(8,9))
ax1 = plt.subplot(2,1,1)
plt.title('3118',fontsize=20)
x.plot(label='原始数据图',legend=True)
ax1 = plt.subplot(2,1,2)
plt.title('3118',fontsize=20)
x.plot(logy=True,label='对数数据图',legend=True)
plt.show()


error = np.random.randn(10)
y = pd.Series(np.sin(np.arange(10)))
y.plot(yerr=error)
plt.title('3118',fontsize=20)
plt.show()

 

 

 

 

总结：在数据分析和挖掘中，所画的图一般要用matplotlib，numpy，pandas这几个库，只要运用熟练就能很轻松的画出所需的数据图。