pandas合并merge&pandas plot

import numpy as np
import pandas as pd

left = pd.DataFrame({'key':['K0','K1','K2','K3'],
                    'A':['A0','A1','A2','A3'],
                    'B':['B0','B1','B2','B3']})
right = pd.DataFrame({'key':['K0','K1','K2','K3'],
                    'C':['C0','C1','C2','C3'],
                    'D':['D0','D1','D2','D3']})
print(left)
print(right)

res = pd.merge(left,right,on='key')
#on='key'代表合并的依据按key
res

left = pd.DataFrame({'key1':['K0','K0','K1','K2'],
                     'key2':['K0','K1','K0','K1'],
                    'A':['A0','A1','A2','A3'],
                    'B':['B0','B1','B2','B3']})
right = pd.DataFrame({'key1':['K0','K1','K1','K3'],
                      'key2':['K0','K0','K0','K0'],
                    'C':['C0','C1','C2','C3'],
                    'D':['D0','D1','D2','D3']})
print(left)
print(right)

res = pd.merge(left,right,on=['key1','key2'],how='outer')
#,on=['key1','key2']代表合并的依据按key1,key2两个整体
#how默认为inner，how = ['left','right','inner','outer']
#inner代表尽量将所有的值都合并起来
res

res = pd.merge(left,right,on=['key1','key2'],how='inner')
#,on=['key1','key2']代表合并的依据按key1,key2两个整体
#how默认为inner，how = ['left','right','inner','outer']
#inner只将大家都有的连接起来
res

res = pd.merge(left,right,on=['key1','key2'],how='left')
#只考虑左边的key1,key2
res

res = pd.merge(left,right,on=['key1','key2'],how='right')
#只考虑右边的key1,key2
res

res = pd.merge(left,right,on=['key1','key2'],how='outer',
               indicator=True)
#indicator=True显示merge信息
#,on=['key1','key2']代表合并的依据按key1,key2两个整体
#how默认为inner，how = ['left','right','inner','outer']
res

res = pd.merge(left,right,on=['key1','key2'],how='outer',
               indicator='indicator_column')
#显示merge信息
res

left = pd.DataFrame({'A':['A0','A1','A2'],
                    'B':['B0','B1','B2']},
                    index = ['K0','K1','K2'])
right = pd.DataFrame({'C':['C0','C2','C3'],
                    'D':['D0','D2','D3']},
                     index = ['K0','K2','K3'])
print(left)
print(right)

res = pd.merge(left,right,left_index=True,right_index=True
              ,how='outer')
#根据index进行合并
res

boys =pd.DataFrame({'k':['K0','K1','K2'],'age':[1,2,3]})

girls =pd.DataFrame({'k':['K0','K0','K2'],'age':[4,5,6]})

print(boys)
print(girls)

res = pd.merge(boys,girls,on='k',suffixes=['_boy','_girl'],
               how='outer')
#根据k进行合并
#suffixes=['_boy','_girl']是为了区分开两个表的age
#这种可用于两个表有相同的列，但要把两个列在合并时分开的场景
res

pandas plot

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt 

data = pd.Series(np.random.randn(1000),
                 index=np.arange(1000))
#randn函数返回一个或者一组样本，具有标准正态分布
data = data.cumsum()#把这些值给累加起来
data.plot()#绘制出来
plt.show()

data = pd.DataFrame(np.random.randn(1000,4),
                    index=np.arange(1000),
                   columns=['A','B','C','D'])
#randn函数返回一个或者一组样本
#这里生成4组1000个数据，具有标准正态分布
data = data.cumsum()#把这些值给累加起来
print(data.head())#打印前面的5行，不写默认为5行

data.plot()
plt.show()

#散点图
ax = data.plot.scatter(x='A',y='B',
                       color='Blue',label='class 1')

data.plot.scatter(x='A',y='C',color='Red',
                  label='class 2',ax=ax)
plt.show()