1 >>> frame2 2 addr age name 3 0 beijing 12 zhang 4 1 shanghai 24 li 5 2 hangzhou 24 cao 6 >>> frame1 7 addr name 8 0 beijing zhang 9 1 shanghai li 10 2 hangzhou cao 11 3 shenzhen han 12 >>> pd.merge(frame1,frame2) 以name列为连接进行拼接 13 addr name age 14 0 beijing zhang 12 15 1 shanghai li 24 16 2 hangzhou cao 24 17 >>> pd.merge(frame1,frame2,on=‘name‘) 指定 列 和拼接方式 18 addr_x name addr_y age 19 0 beijing zhang beijing 12 20 1 shanghai li shanghai 24 21 2 hangzhou cao hangzhou 24 22 >>> pd.merge(frame1,frame2,on=‘name‘,how=‘outer‘) 23 addr_x name addr_y age 24 0 beijing zhang beijing 12.0 25 1 shanghai li shanghai 24.0 26 2 hangzhou cao hangzhou 24.0 27 3 shenzhen han NaN NaN 28 >>> pd.merge(frame1,frame2,on=‘name‘,how=‘inner‘) 29 addr_x name addr_y age 30 0 beijing zhang beijing 12 31 1 shanghai li shanghai 24 32 2 hangzhou cao hangzhou 24 33 >>> pd.merge(frame1,frame2,on=‘name‘,how=‘left‘) 34 addr_x name addr_y age 35 0 beijing zhang beijing 12.0 36 1 shanghai li shanghai 24.0 37 2 hangzhou cao hangzhou 24.0 38 3 shenzhen han NaN NaN 39 >>> pd.merge(frame1,frame2,on=‘name‘,how=‘right‘) 40 addr_x name addr_y age 41 0 beijing zhang beijing 12 42 1 shanghai li shanghai 24 43 2 hangzhou cao hangzhou 24 44 >>> pd.merge(frame1,frame2,on=‘name‘,left_index=True) 45 addr_x name addr_y age 46 0 beijing zhang beijing 12 47 1 shanghai li shanghai 24 48 2 hangzhou cao hangzhou 24 49 >>> pd.merge(frame1,frame2,on=‘name‘,right_index=True) 50 addr_x name addr_y age 51 0 beijing zhang beijing 12 52 1 shanghai li shanghai 24 53 2 hangzhou cao hangzhou 24 54 >>> pd.merge(frame1,frame2,on=‘addr‘,right_index=True) 55 addr name_x age name_y 56 0 beijing zhang 12 zhang 57 1 shanghai li 24 li 58 2 hangzhou cao 24 cao
1 >>> frame1.columns=[‘addr1‘,‘name1‘] 2 >>> frame1.join(frame2) 3 addr1 name1 addr age name 修改掉重复的列名称,然后join() 4 0 beijing zhang beijing 12.0 zhang 5 1 shanghai li shanghai 24.0 li 6 2 hangzhou cao hangzhou 24.0 cao 7 3 shenzhen han NaN NaN NaN
1 >>> array1 2 array([[0, 1, 2], 3 [3, 4, 5], 4 [6, 7, 8]]) 5 >>> array1=np.arange(9).reshape((3,3))+6 6 >>> array2=np.arange(9).reshape((3,3)) 7 >>> array1 8 array([[ 6, 7, 8], 9 [ 9, 10, 11], 10 [12, 13, 14]]) 11 >>> np.concatenate([array1,array2],axis=1) np模块中对元组进行concatenate() 12 array([[ 6, 7, 8, 0, 1, 2], 13 [ 9, 10, 11, 3, 4, 5], 14 [12, 13, 14, 6, 7, 8]]) 15 >>> np.concatenate([array1,array2],axis=0) 16 array([[ 6, 7, 8], 17 [ 9, 10, 11], 18 [12, 13, 14], 19 [ 0, 1, 2], 20 [ 3, 4, 5], 21 [ 6, 7, 8]]) 22 >>> 23 >>> np.concatenate([array1,array2]) 24 array([[ 6, 7, 8], 25 [ 9, 10, 11], 26 [12, 13, 14], 27 [ 0, 1, 2], 28 [ 3, 4, 5], 29 [ 6, 7, 8]])
1 >>> ser1=pd.Series(np.random.rand(4)) pd模块中也有concat() 2 >>> ser1 3 0 0.998915 4 1 0.117503 5 2 0.747180 6 3 0.641508 7 dtype: float64 8 >>> ser1=pd.Series(np.random.rand(4)*100) 9 >>> ser1 10 0 8.818592 11 1 42.317816 12 2 43.274021 13 3 23.245148 14 dtype: float64 15 >>> ser2=pd.Series(np.random.rand(4)*100,index=[5,6,7,8]) 16 >>> ser2 17 5 58.416554 18 6 11.840838 19 7 38.146851 20 8 0.135517 21 dtype: float64 22 >>> pd.concat([ser1,ser2]) 23 0 8.818592 24 1 42.317816 25 2 43.274021 26 3 23.245148 27 5 58.416554 28 6 11.840838 29 7 38.146851 30 8 0.135517 31 dtype: float64 32 >>> pd.concat([ser1,ser2],axis=1) 33 0 1 34 0 8.818592 NaN 35 1 42.317816 NaN 36 2 43.274021 NaN 37 3 23.245148 NaN 38 5 NaN 58.416554 39 6 NaN 11.840838 40 7 NaN 38.146851 41 8 NaN 0.135517
1 >> pd.concat([ser1,ser2],axis=1,keys=[1,2]) 2 1 2 3 0 8.818592 NaN 4 1 42.317816 79.632793 5 2 43.274021 96.700070 6 3 23.245148 64.573269 7 4 NaN 68.629709 8 >>> ser2.index=[2,4,5,6] 9 >>> ser2 10 2 79.632793 11 4 96.700070 12 5 64.573269 13 6 68.629709 14 dtype: float64 15 >>> ser1.combine_first(ser2) 对缺额的数据进行填充 combin_first() 16 0 8.818592 17 1 42.317816 18 2 43.274021 19 3 23.245148 20 4 96.700070 21 5 64.573269 22 6 68.629709 23 dtype: float64
1 >>> ser1 2 0 a 3 1 b 4 2 c 5 3 d 6 dtype: object 7 >>> ser2 8 2 0 9 4 1 10 5 2 11 6 3 12 dtype: int32 13 >>> ser2.combine_first(ser1) ser1在后 14 0 a 15 1 b 16 2 0 17 3 d 18 4 1 19 5 2 20 6 3 21 dtype: object 22 >>> ser1[:2].combine_first(ser2) ser1在前 23 0 a 24 1 b 25 2 0 26 4 1 27 5 2 28 6 3 29 dtype: object
1 >>> frame1=pd.DataFrame({‘name‘:[‘zhang‘,‘li‘,‘wang‘],‘age‘:[12,45,34],‘addr‘:[‘beijing‘,‘shanghai‘,‘shenzhen‘]}) 2 >>> frame1 3 addr age name 4 0 beijing 12 zhang 5 1 shanghai 45 li 6 2 shenzhen 34 wang 7 >>> frame1.stack() frame的进栈和出栈 8 0 addr beijing 9 age 12 10 name zhang 11 1 addr shanghai 12 age 45 13 name li 14 2 addr shenzhen 15 age 34 16 name wang 17 dtype: object 18 >>> frame1.stack().unstack() 19 addr age name 20 0 beijing 12 zhang 21 1 shanghai 45 li 22 2 shenzhen 34 wang 23 >>> frame1.stack().unstack(0) 列和索引转换 24 0 1 2 25 addr beijing shanghai shenzhen 26 age 12 45 34 27 name zhang li wang
1 >>> longframe=pd.DataFrame({‘color‘:[‘white‘,‘white‘,‘white‘,‘red‘,‘red‘,‘red‘,‘black‘,‘black‘,‘black‘],‘item‘:[‘ball‘,‘pen‘,‘mug‘,‘ball‘,‘pen‘,‘mug‘,‘ball‘,‘pen‘,‘mug‘],‘value‘:np.random.rand(9)}) 2 >>> longframe 3 color item value 对冗余的消除,将longframe转换为wideframe 4 0 white ball 0.260358 5 1 white pen 0.543955 6 2 white mug 0.456874 7 3 red ball 0.967021 8 4 red pen 0.657271 9 5 red mug 0.984256 10 6 black ball 0.550236 11 7 black pen 0.731625 12 8 black mug 0.006728 13 >>> wideframe=longframe.pivot(‘color‘,‘item‘) 14 >>> wideframe 15 value 16 item ball mug pen 17 color 18 black 0.550236 0.006728 0.731625 19 red 0.967021 0.984256 0.657271 20 white 0.260358 0.456874 0.543955 21 >>> frame1 22 addr age name 23 0 beijing 12 zhang 24 1 shanghai 12 li 25 2 beijing 12 wang 26 >>> del frame[‘addr‘] 27 Traceback (most recent call last): 28 File "<pyshell#103>", line 1, in <module> 29 del frame[‘addr‘] 30 NameError: name ‘frame‘ is not defined 31 >>> del frame1[‘addr‘] 32 >>> frame1 33 age name 34 0 12 zhang 35 1 12 li 36 2 12 wang
时间: 2024-10-22 12:04:09