pandas合并concat&merge和plot画图

3.6，3.7pandas合并concat&merge

头文件：

import pandas as pd
import numpy as np

concat基础合并用法

df1= pd.DataFrame(np.ones((3,4))*0,columns = ['a','b','c','d'])
df2= pd.DataFrame(np.ones((3,4))*1,columns = ['a','b','c','d'])
df3= pd.DataFrame(np.ones((3,4))*2,columns = ['a','b','c','d'])

res = pd.concat([df1,df2,df3],axis=0,ignore_index=True)   #axis=0 竖向合并  ignore_index是让索引重新排序

df1= pd.DataFrame(np.ones((3,4))*0,columns = ['a','b','c','d'])
df2= pd.DataFrame(np.ones((3,4))*1,columns = ['b','c','d','e'])

concat中join用法

#join='outer'可以对标签不一样的部分用NAN进行填充
#join = 'inter'时对标签不一样的部分去掉
res = pd.concat([df1,df2],join='outer',ignore_index=True)

join_axes (新版本删除了)

join_axes= [df1.index]设置合并后按照df1的索引进行保留

# res = pd.concat([df1,df2],axis=1,join_axes = [df1.index])

append添加数据

#添加整个数据
df1= pd.DataFrame(np.ones((3,4))*0,columns = ['a','b','c','d'])
df2= pd.DataFrame(np.ones((3,4))*1,columns = ['a','b','c','d'])
df3= pd.DataFrame(np.ones((3,4))*2,columns = ['a','b','c','d'])
res = df1.append([df2,df3],ignore_index=True)   #上下结合

#添加一行数据
s1 = pd.Series([1,2,3,4],index=['a','b','c','d'])
res = df1.append(s1,ignore_index=True)

merge按照key合并

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']
})
#按照key合并
res = pd.merge(left,right,on='key')
print(res)

merge考虑两个key,根据index进行数据合并

#若考虑两个key,根据index进行数据合并
res = pd.merge(left,right,on=['key1','ke2'])    #默认是'inner'：只考虑相同部分
res = pd.merge(left,right,on=['key1','ke2'],how='outer')    #outer：全部考虑，不存在的用nan填充

merge中indicator

indicator=True时，能展示合并后，哪部分是有某标签数据，哪部分是没有该标签数据的

res = pd.merge(left,right,on=['key1','ke2'],how='outer',indicator=True)

merge中left_index和right_index

根据数据索引进行结合
res = pd.merge(left,right,left_index=True,right_index=True,how=‘outer’)

merge中suffixes

suffixes来区分标签相同但是数值不同的数据

boys = pd.DataFrame({'K':['K0','K1','K2'],'age':[1,2,3]})
girls = pd.DataFrame({'K':['K0','K1','K2'],'age':[4,5,6]})

res = pd.merge(boys,girls,on='K',suffixes=['_boy','_girl'],how='inner')

3.8pandas plot画图

头文件：

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

Series的数据（类似数组）

data = pd.Series(np.random.randn(1000),index=np.arange(1000))
data = data.cumsum()    #对生成的1000个数据进行累加
data.plot()
plt.show()

DataFrame数据（类似矩阵）

折线图：

data = pd.DataFrame(np.random.randn(1000,4),
                    index = np.arange(1000),
                    columns = list("ABCD"))
data = data.cumsum()
data.plot()
plt.show()

散点图

ax = data.plot.scatter(x='A',y='B',color='DarkBlue',label = 'Class 1')
data.plot.scatter(x = 'A',y = 'C',color = 'DarkGreen',label='Class 2',ax=ax)
plt.show()