In [13]:

    

import pandas as pd


    

In [66]:

    

x_pbe = pd.read_csv('X_pbe.csv', header=None)
y_pbe = pd.read_csv('Y_pbe.csv', header=None)
z_pbe = pd.read_csv('q_pbe.csv', header=None)


    

In [67]:

    

print(x_pbe.shape)
print(z_pbe.shape)


    

    




(47733, 29)
(47733, 15)

In [68]:

    

x_pbe.head()


    

    
Out[68]:







  

    

      

      
0
      
1
      
2
      
3
      
4
      
5
      
6
      
7
      
8
      
9
      
...
      
19
      
20
      
21
      
22
      
23
      
24
      
25
      
26
      
27
      
28
    
  
  

    

      
0
      
C
      
1.350508
      
0.779024
      
0.663087
      
H
      
1.825709
      
1.257877
      
-0.189170
      
H
      
1.848891
      
...
      
0.559417
      
C
      
-1.832366
      
1.293790
      
-2.492349
      
N
      
-1.370433
      
2.318893
      
-2.582710
      
NaN
    
    

      
1
      
C
      
1.366716
      
0.804290
      
0.682895
      
H
      
1.759809
      
1.361483
      
-0.178094
      
H
      
1.814160
      
...
      
0.594701
      
C
      
-1.830842
      
1.305028
      
-2.473094
      
N
      
-1.354430
      
2.319260
      
-2.596931
      
NaN
    
    

      
2
      
C
      
1.438315
      
1.060388
      
0.832979
      
H
      
1.571861
      
1.944143
      
0.147314
      
H
      
1.577013
      
...
      
0.736083
      
C
      
-1.806108
      
1.415889
      
-2.311002
      
N
      
-1.218195
      
2.315162
      
-2.715039
      
NaN
    
    

      
3
      
C
      
1.948153
      
3.622904
      
2.081111
      
H
      
2.049626
      
3.765616
      
1.000288
      
H
      
2.693285
      
...
      
2.399583
      
C
      
-0.414736
      
2.940226
      
-2.453864
      
N
      
-0.876473
      
1.892105
      
-2.385047
      
NaN
    
    

      
4
      
C
      
2.649527
      
-0.695892
      
-3.065414
      
H
      
2.440014
      
-0.515189
      
-4.127145
      
H
      
-0.446906
      
...
      
-2.347429
      
C
      
0.249546
      
-3.627168
      
-3.224564
      
N
      
0.433013
      
-4.760249
      
-3.264235
      
NaN
    
  

5 rows × 29 columns

In [69]:

    

rm_col = range(0,32,4)
x_pbe = x_pbe.drop(rm_col, axis=1)
x_pbe.shape


    

    
Out[69]:





(47733, 21)

In [70]:

    

x_pbe.columns=['C1x', 'C1y', 'C1z', 'H1x', 'H1y', 'H1z', 'H2x', 'H2y', 'H2z', 'H3x', 'H3y', 'H3z', 'H4x', 'H4y', 'H4z', 'C2x', 'C2y', 'C2z', 'Nx', 'Ny', 'Nz']


    

In [71]:

    

y_pbe.columns=['energy_pbe']


    

In [72]:

    

rm_col = range(0,16,2)


    

In [73]:

    

z_pbe = z_pbe.drop(rm_col, axis=1)
z_pbe.head()


    

    
Out[73]:







  

    

      

      
1
      
3
      
5
      
7
      
9
      
11
      
13
    
  
  

    

      
0
      
6.55438
      
0.86062
      
0.86105
      
0.86199
      
0.86194
      
6.18917
      
6.81086
    
    

      
1
      
6.54250
      
0.86282
      
0.86075
      
0.86827
      
0.86548
      
6.18986
      
6.81033
    
    

      
2
      
5.93576
      
0.71892
      
0.83033
      
0.69595
      
0.81927
      
6.66135
      
7.33841
    
    

      
3
      
6.54921
      
0.86531
      
0.85578
      
0.87014
      
0.85956
      
6.17456
      
6.82544
    
    

      
4
      
6.45450
      
0.84487
      
0.82359
      
0.84965
      
0.85046
      
6.04506
      
7.13187
    
  

In [74]:

    

z_pbe.columns=['C1q', 'H1q','H2q','H3q','H4q','C2q','Nq']


    

In [75]:

    

xzy_pbe = pd.concat([x_pbe, z_pbe, y_pbe], axis=1)
xzy_pbe.head()


    

    
Out[75]:







  

    

      

      
C1x
      
C1y
      
C1z
      
H1x
      
H1y
      
H1z
      
H2x
      
H2y
      
H2z
      
H3x
      
...
      
Ny
      
Nz
      
C1q
      
H1q
      
H2q
      
H3q
      
H4q
      
C2q
      
Nq
      
energy_pbe
    
  
  

    

      
0
      
1.350508
      
0.779024
      
0.663087
      
1.825709
      
1.257877
      
-0.189170
      
1.848891
      
1.089646
      
1.577782
      
0.303730
      
...
      
2.318893
      
-2.582710
      
6.55438
      
0.86062
      
0.86105
      
0.86199
      
0.86194
      
6.18917
      
6.81086
      
-131.356978
    
    

      
1
      
1.366716
      
0.804290
      
0.682895
      
1.759809
      
1.361483
      
-0.178094
      
1.814160
      
1.125417
      
1.600315
      
0.283706
      
...
      
2.319260
      
-2.596931
      
6.54250
      
0.86282
      
0.86075
      
0.86827
      
0.86548
      
6.18986
      
6.81033
      
-131.353254
    
    

      
2
      
1.438315
      
1.060388
      
0.832979
      
1.571861
      
1.944143
      
0.147314
      
1.577013
      
1.523847
      
1.780924
      
0.419598
      
...
      
2.315162
      
-2.715039
      
5.93576
      
0.71892
      
0.83033
      
0.69595
      
0.81927
      
6.66135
      
7.33841
      
-131.317326
    
    

      
3
      
1.948153
      
3.622904
      
2.081111
      
2.049626
      
3.765616
      
1.000288
      
2.693285
      
2.923731
      
2.344320
      
2.305255
      
...
      
1.892105
      
-2.385047
      
6.54921
      
0.86531
      
0.85578
      
0.87014
      
0.85956
      
6.17456
      
6.82544
      
-131.353906
    
    

      
4
      
2.649527
      
-0.695892
      
-3.065414
      
2.440014
      
-0.515189
      
-4.127145
      
-0.446906
      
-2.739519
      
-2.943782
      
3.260095
      
...
      
-4.760249
      
-3.264235
      
6.45450
      
0.84487
      
0.82359
      
0.84965
      
0.85046
      
6.04506
      
7.13187
      
-131.348082
    
  

5 rows × 29 columns

In [76]:

    

xzy_pbe_u = xzy_pbe.drop_duplicates(inplace=False)


    

In [77]:

    

print xzy_pbe.shape
print xzy_pbe_u.shape


    

    




(47733, 29)
(47717, 29)

In [78]:

    

x_b3lyp = pd.read_csv('X_b3lyp.csv', header=None)
y_b3lyp = pd.read_csv('Y_b3lyp.csv', header=None)


    

In [79]:

    

print(x_b3lyp.shape)
print(y_b3lyp.shape)


    

    




(17756, 29)
(17756, 1)

In [80]:

    

rm_col = range(0,32,4)
x_b3lyp = x_b3lyp.drop(rm_col, axis=1)
x_b3lyp.shape


    

    
Out[80]:





(17756, 21)

In [81]:

    

x_b3lyp.columns=['C1x', 'C1y', 'C1z', 'H1x', 'H1y', 'H1z', 'H2x', 'H2y', 'H2z', 'H3x', 'H3y', 'H3z', 'H4x', 'H4y', 'H4z', 'C2x', 'C2y', 'C2z', 'Nx', 'Ny', 'Nz']


    

In [82]:

    

y_b3lyp.columns=['energy_b3lyp']


    

In [83]:

    

xy_b3lyp = pd.concat([x_b3lyp, y_b3lyp], axis=1)


    

In [84]:

    

xy_b3lyp.head()


    

    
Out[84]:







  

    

      

      
C1x
      
C1y
      
C1z
      
H1x
      
H1y
      
H1z
      
H2x
      
H2y
      
H2z
      
H3x
      
...
      
H4x
      
H4y
      
H4z
      
C2x
      
C2y
      
C2z
      
Nx
      
Ny
      
Nz
      
energy_b3lyp
    
  
  

    

      
0
      
1.350508
      
0.779024
      
0.663087
      
1.825709
      
1.257877
      
-0.189170
      
1.848891
      
1.089646
      
1.577782
      
0.303730
      
...
      
1.423537
      
-0.300512
      
0.559417
      
-1.832366
      
1.293790
      
-2.492349
      
-1.370433
      
2.318893
      
-2.582710
      
-133.198709
    
    

      
1
      
1.366716
      
0.804290
      
0.682895
      
1.759809
      
1.361483
      
-0.178094
      
1.814160
      
1.125417
      
1.600315
      
0.283706
      
...
      
1.449777
      
-0.299335
      
0.594701
      
-1.830842
      
1.305028
      
-2.473094
      
-1.354430
      
2.319260
      
-2.596931
      
-133.195259
    
    

      
2
      
-3.803611
      
-2.267309
      
0.764900
      
-3.796598
      
-3.150483
      
1.493531
      
-4.393698
      
-1.399793
      
1.007952
      
-4.217465
      
...
      
-2.655651
      
-0.866691
      
1.937266
      
-2.613919
      
0.179199
      
2.330572
      
-2.536911
      
1.241336
      
2.765962
      
-133.215182
    
    

      
3
      
-2.927686
      
0.153773
      
-2.512119
      
-2.469427
      
0.822793
      
-1.821670
      
-2.475899
      
-0.852233
      
-2.570246
      
-3.057747
      
...
      
-4.018957
      
0.011604
      
-1.970984
      
-3.879463
      
-0.205050
      
0.063446
      
-4.423705
      
-0.138430
      
1.097049
      
-133.191188
    
    

      
4
      
-3.450782
      
3.334512
      
4.114650
      
-4.447155
      
3.741390
      
4.341071
      
-4.552629
      
0.118057
      
4.181421
      
-3.188349
      
...
      
-2.697286
      
3.171041
      
4.908800
      
-4.440723
      
-0.970431
      
3.946023
      
-4.649342
      
-2.117911
      
3.776332
      
-133.232016
    
  

5 rows × 22 columns

In [87]:

    

xy_b3lyp_u = xy_b3lyp.drop_duplicates(inplace=False)
print(xy_b3lyp.shape)
print(xy_b3lyp_u.shape)


    

    




(17756, 22)
(17751, 22)

In [94]:

    

jcols = list(xzy_pbe_u.columns)[:-8]
print(jcols)


    

    




['C1x', 'C1y', 'C1z', 'H1x', 'H1y', 'H1z', 'H2x', 'H2y', 'H2z', 'H3x', 'H3y', 'H3z', 'H4x', 'H4y', 'H4z', 'C2x', 'C2y', 'C2z', 'Nx', 'Ny', 'Nz']

In [97]:

    

xy = xzy_pbe_u.merge(right=xy_b3lyp_u, how='right', on=jcols, suffixes=('_b3lyp', '_pbe'))
print(xy.shape)
xy.head()


    

    




(17751, 30)






    
Out[97]:







  

    

      

      
C1x
      
C1y
      
C1z
      
H1x
      
H1y
      
H1z
      
H2x
      
H2y
      
H2z
      
H3x
      
...
      
Nz
      
C1q
      
H1q
      
H2q
      
H3q
      
H4q
      
C2q
      
Nq
      
energy_pbe
      
energy_b3lyp
    
  
  

    

      
0
      
1.350508
      
0.779024
      
0.663087
      
1.825709
      
1.257877
      
-0.189170
      
1.848891
      
1.089646
      
1.577782
      
0.303730
      
...
      
-2.582710
      
6.55438
      
0.86062
      
0.86105
      
0.86199
      
0.86194
      
6.18917
      
6.81086
      
-131.356978
      
-133.198709
    
    

      
1
      
1.366716
      
0.804290
      
0.682895
      
1.759809
      
1.361483
      
-0.178094
      
1.814160
      
1.125417
      
1.600315
      
0.283706
      
...
      
-2.596931
      
6.54250
      
0.86282
      
0.86075
      
0.86827
      
0.86548
      
6.18986
      
6.81033
      
-131.353254
      
-133.195259
    
    

      
2
      
1.948153
      
3.622904
      
2.081111
      
2.049626
      
3.765616
      
1.000288
      
2.693285
      
2.923731
      
2.344320
      
2.305255
      
...
      
-2.385047
      
6.54921
      
0.86531
      
0.85578
      
0.87014
      
0.85956
      
6.17456
      
6.82544
      
-131.353906
      
-133.191297
    
    

      
3
      
-4.295067
      
-3.402007
      
-0.431639
      
-3.743290
      
-3.885034
      
0.405351
      
-4.703227
      
-2.395147
      
-0.357631
      
-4.912492
      
...
      
2.771718
      
6.46360
      
0.84451
      
0.84585
      
0.84602
      
0.82700
      
6.04259
      
7.13044
      
-131.361634
      
-133.232957
    
    

      
4
      
-4.329216
      
-3.413882
      
-0.419582
      
-3.788901
      
-3.958677
      
0.381595
      
-4.796726
      
-2.417300
      
-0.361777
      
-4.924910
      
...
      
2.769733
      
6.46663
      
0.84255
      
0.84259
      
0.84821
      
0.82560
      
6.04077
      
7.13365
      
-131.359263
      
-133.231602
    
  

5 rows × 30 columns

In [98]:

    

print(list(xy.columns))


    

    




['C1x', 'C1y', 'C1z', 'H1x', 'H1y', 'H1z', 'H2x', 'H2y', 'H2z', 'H3x', 'H3y', 'H3z', 'H4x', 'H4y', 'H4z', 'C2x', 'C2y', 'C2z', 'Nx', 'Ny', 'Nz', 'C1q', 'H1q', 'H2q', 'H3q', 'H4q', 'C2q', 'Nq', 'energy_pbe', 'energy_b3lyp']

In [99]:

    

xy.to_csv('pbe_b3lyp_partQ.csv')


    

In [ ]: