Pandas tips One

Import Pandas as PD

DF1 = PD. Dataframe ({' col1 ': [0,1], ' col_left ': [' A ', ' B ']}) #按列定义
DF2 = PD. Dataframe ({' col1 ': [1,2,2], ' col_right ': [2,2,2]})

Print (DF1)
# # Col1 Col_left
# #0 0 A
# #1 1 B
Print (DF2)
# # Col1 Col_right
# #0 1 2
# #1 2 2
# #2 2 2

#indicator = True places the merged records in a new column
#根据col1进行合并
res = pd.merge (df1,df2,on = ' col1 ', how = ' outer ', indicator = True)
Print (RES)
# # col1 Col_left col_right _merge
# #0 0 A NaN left_only
# #1 1 B 2.0 both
# #2 2 NaN 2.0 right_only
# #3 2 NaN 2.0 right_only

Name of #自定义indicator column
res = pd.merge (df1,df2,on = ' col1 ', how = ' outer ', indicator = ' indicator_column ')
Print (RES)
# # col1 Col_left col_right Indicator_column
# #0 0 A NaN left_only
# #1 1 B 2.0 both
# #2 2 NaN 2.0 right_only
# #3 2 NaN 2.0 right_only

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)
# # A B
# #K0 A0 B0
# #K1 A1 B1
# #K2 A2 B2
Print (right)
# # C D
# #K0 C0 D0
# #K2 C2 D2
# #K3 C3 D3

#根据index进行合并, how = ' outer ', and print output
res = Pd.merge (Left,right,left_index = true, Right_index = true, how = ' outer ')
Print (RES)

#根据index进行合并, how = ' inner '
res = Pd.merge (Left,right,left_index = true, Right_index = true, how = ' inner ')
Print (RES)
# # A B C D
# #K0 A0 B0 C0 D0
# #K2 A2 B2 C2 D2

Boys = PD. Dataframe ({' K ': [' K0 ', ' K1 ', ' K2 '], ' age ': [1,2,3]})
Girls = PD. Dataframe ({' K ': [' K0 ', ' K1 ', ' K3 '], ' age ': [4,5,6]})

#使用suffixes后缀解决overlapping重叠的问题
res = Pd.merge (boys,girls,on= ' K ', suffixes = [' _boy ', ' _girl '],how = ' inner ')
Print (RES)
# # K Age_boy age_girl
# #0 K0 1 4
# #1 K1 2 5
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#数据的可视化 matplotlib--> plt.show ()
Import Pandas as PD
Import NumPy as NP
Import Matplotlib.pyplot as Plt

#随机生成1000个数据
data = PD. Series (NP.RANDOM.RANDN (1000), index = np.arange (1000))

#为了方便观看效果, accumulating data
Data.cumsum ()

#pandas数据可以直接观看可视化效果
Data.plot ()

Plt.show ()

#生成1000 the Dataframe of *4 and add them up
data = PD. Dataframe (Np.random.randn (1000,4),
index = np.arange (1000),
columns = List (' ABCD ')
)
Data.cumsum ()
Data.plot ()
Plt.show ()

#除了plot, scatter scatter, other bar,hist,box,kde,area,hexbin.
Ax = data.plot.scatter (x = ' A ', y = ' B ', color = ' darkblue ', label = ' Class1 ')
#画在同一个ax上面, select a different data column
Data.plot.scatter (x= ' A ', y = ' C ', color = ' lightgreen ', label = ' Class2 ', ax = ax)
Plt.show ()