In [1]:

    

import pandas as pd
import numpy as np
import csv
import re


    

In [2]:

    

# read original species data into a DataFrame named original_species
MW = pd.read_csv('cti_MW.txt',header=None)
original_species = MW.iloc[:,[0,3,4,5]]
original_species.columns = ['name','C_num','H_num','O_num']


    

In [3]:

    

original_species


    

    
Out[3]:






  

    

      

      
name
      
C_num
      
H_num
      
O_num
    
  
  

    

      
0
      
'CH3OH'    : [32
      
[1
      
4.0
      
1 ]
    
    

      
1
      
'ETOH'     : [46
      
[2
      
6.0
      
1 ]
    
    

      
2
      
'ALD3'     : [58
      
[3
      
6.0
      
1 ]
    
    

      
3
      
'PLIGH'    : [436
      
[22
      
28.0
      
9 ]
    
    

      
4
      
'LIGH'     : [437
      
NaN
      
NaN
      
NaN
    
    

      
5
      
'PLIGO'    : [422
      
[20
      
22.0
      
10]
    
    

      
6
      
'LIGO'     : [423
      
NaN
      
NaN
      
NaN
    
    

      
7
      
'PLIGC'    : [300
      
[17
      
16.0
      
5 ]
    
    

      
8
      
'LIGC'     : [301
      
NaN
      
NaN
      
NaN
    
    

      
9
      
'PLIGM2'   : [378
      
NaN
      
NaN
      
NaN
    
    

      
10
      
'LIGM2'    : [379
      
NaN
      
NaN
      
NaN
    
    

      
11
      
'PLIG'     : [258
      
NaN
      
NaN
      
NaN
    
    

      
12
      
'LIG'      : [259
      
NaN
      
NaN
      
NaN
    
    

      
13
      
'PADIOM2'  : [227
      
NaN
      
NaN
      
NaN
    
    

      
14
      
'ADIOM2'   : [228
      
NaN
      
NaN
      
NaN
    
    

      
15
      
'PADIO'    : [167
      
NaN
      
NaN
      
NaN
    
    

      
16
      
'ADIO'     : [168
      
NaN
      
NaN
      
NaN
    
    

      
17
      
'PFET3'    : [165
      
NaN
      
NaN
      
NaN
    
    

      
18
      
'PFET3M2'  : [225
      
NaN
      
NaN
      
NaN
    
    

      
19
      
'SYNAPYL'  : [210
      
NaN
      
NaN
      
NaN
    
    

      
20
      
'COUMARYL' : [150
      
NaN
      
NaN
      
NaN
    
    

      
21
      
'PKETM2'   : [225
      
NaN
      
NaN
      
NaN
    
    

      
22
      
'KETM2'    : [226
      
NaN
      
NaN
      
NaN
    
    

      
23
      
'KET'      : [166
      
NaN
      
NaN
      
NaN
    
    

      
24
      
'KETDM2'   : [208
      
NaN
      
NaN
      
NaN
    
    

      
25
      
'KETD'     : [148
      
NaN
      
NaN
      
NaN
    
    

      
26
      
'MGUAI'    : [154
      
NaN
      
NaN
      
NaN
    
    

      
27
      
'PHENOL'   : [94
      
NaN
      
NaN
      
NaN
    
    

      
28
      
'C10H2M4'  : [244
      
NaN
      
NaN
      
NaN
    
    

      
29
      
'C10H2M2'  : [182
      
NaN
      
NaN
      
NaN
    
    

      
...
      
...
      
...
      
...
      
...
    
    

      
63
      
'C2H6'     : [30
      
[2
      
6.0
      
0 ]]
    
    

      
64
      
'PCH3'     : [15
      
NaN
      
NaN
      
NaN
    
    

      
65
      
'CH3CHO'   : [44
      
[2
      
4.0
      
1 ]]
    
    

      
66
      
'CO2'      : [44
      
[1
      
0.0
      
2 ]]
    
    

      
67
      
'CH2CO'    : [42
      
[2
      
2.0
      
1 ]]
    
    

      
68
      
'OH'       : [17
      
[0
      
1.0
      
1 ]]
    
    

      
69
      
'C3H6'     : [42
      
[3
      
6.0
      
0 ]]
    
    

      
70
      
'C3H6O2'   : [74
      
[3
      
6.0
      
2 ]
    
    

      
71
      
'C3H4O2'   : [72
      
[3
      
4.0
      
2 ]
    
    

      
72
      
'RC3H7O2'  : [75
      
[3
      
7.0
      
2 ]
    
    

      
73
      
'RC3H5O2'  : [73
      
[3
      
5.0
      
2 ]
    
    

      
74
      
'RC3H3O'   : [55
      
[3
      
3.0
      
1 ]
    
    

      
75
      
'PRLIGH'   : [435
      
NaN
      
NaN
      
NaN
    
    

      
76
      
'PRLIGH2'  : [435
      
NaN
      
NaN
      
NaN
    
    

      
77
      
'RMGUAI'   : [153
      
NaN
      
NaN
      
NaN
    
    

      
78
      
'RLIGH'    : [436
      
NaN
      
NaN
      
NaN
    
    

      
79
      
'PCOHP2'   : [29
      
NaN
      
NaN
      
NaN
    
    

      
80
      
'VADIOM2'  : [228
      
[11
      
16.0
      
5 ]
    
    

      
81
      
'VKETM2'   : [226
      
[11
      
14.0
      
5 ]
    
    

      
82
      
'VKETDM2'  : [208
      
[11
      
12.0
      
4 ]
    
    

      
83
      
'VSYNAPYL' : [210
      
[11
      
14.0
      
4 ]
    
    

      
84
      
'VMGUAI'   : [154
      
[8
      
10.0
      
3 ]
    
    

      
85
      
'VCOUMARYL': [150
      
[9
      
10.0
      
2 ]
    
    

      
86
      
'VADIO'    : [168
      
[9
      
12.0
      
3 ]
    
    

      
87
      
'VKET'     : [166
      
[9
      
10.0
      
3 ]
    
    

      
88
      
'VKETD'    : [148
      
[9
      
8.0
      
2 ]
    
    

      
89
      
'VPHENOL'  : [94
      
[6
      
6.0
      
1 ]
    
    

      
90
      
'C3H4O'    : [56
      
[3
      
4.0
      
1 ]
    
    

      
91
      
'C3H8O2'   : [76
      
[3
      
8.0
      
2 ]
    
    

      
92
      
'CH4'      : [16
      
[1
      
4.0
      
0 ]]
    
  

93 rows × 4 columns

In [4]:

    

#clear the data of species name and fit them into new dataframe called species
species = pd.DataFrame()
species_name = []

for i in original_species.name:
    species_name.append(i.split(':')[0].split()[0])

species['name'] = species_name


    

In [5]:

    

#clear the data of C_num
C_num_list = []
for i in range(93):
    if original_species.C_num[i] is np.nan:
        C_num_list.append(str(np.nan))
    else:
        #print(original_species.C_num[i])
        C_num = str(int(re.findall(r"\d+\.?\d*",original_species.C_num[i])[0]))
        C_num_list.append(C_num)

species['C_num'] = C_num_list


    

In [6]:

    

#clear the data of H_num
H_num_list = []
for i in range(93):
    if original_species.C_num[i] is np.nan:
        H_num_list.append(str(np.nan))
    else:
        H_num = str(int(original_species.H_num[i]))
        H_num_list.append(H_num)

species['H_num'] = H_num_list


    

In [7]:

    

#clear the data of O_num
O_num_list = []
for i in range(93):
    if original_species.O_num[i] is np.nan:
        O_num_list.append(str(np.nan))
    else:
        O_num = str(int(re.findall(r"\d+\.?\d*",original_species.O_num[i])[0]))
        O_num_list.append(O_num)

species['O_num'] = O_num_list


    

In [8]:

    

species.head()


    

    
Out[8]:






  

    

      

      
name
      
C_num
      
H_num
      
O_num
    
  
  

    

      
0
      
'CH3OH'
      
1
      
4
      
1
    
    

      
1
      
'ETOH'
      
2
      
6
      
1
    
    

      
2
      
'ALD3'
      
3
      
6
      
1
    
    

      
3
      
'PLIGH'
      
22
      
28
      
9
    
    

      
4
      
'LIGH'
      
nan
      
nan
      
nan
    
  

In [9]:

    

df = pd.DataFrame()
species_list = []
for i in range(93):
    #write species name part
    content_name = "species"+"(name="+species.name[i]
    #write species atoms part
    if original_species.C_num[i] is np.nan:
        content_atoms = ")"
        content = content_name+content_atoms
        species_list.append(content)
    else:
        content_atoms = ",atoms='C:"+species.C_num[i]+" "+"H:"+species.H_num[i]+" "+"O:"+species.O_num[i]+"')"
        content = content_name+content_atoms
        species_list.append(content)

df['Species_data'] = species_list


    

In [25]:

    

df


    

    
Out[25]:






  

    

      

      
Species_data
    
  
  

    

      
0
      
species(name='CH3OH',atoms='C:1 H:4 O:1')
    
    

      
1
      
species(name='ETOH',atoms='C:2 H:6 O:1')
    
    

      
2
      
species(name='ALD3',atoms='C:3 H:6 O:1')
    
    

      
3
      
species(name='PLIGH',atoms='C:22 H:28 O:9')
    
    

      
4
      
species(name='LIGH')
    
    

      
5
      
species(name='PLIGO',atoms='C:20 H:22 O:10')
    
    

      
6
      
species(name='LIGO')
    
    

      
7
      
species(name='PLIGC',atoms='C:17 H:16 O:5')
    
    

      
8
      
species(name='LIGC')
    
    

      
9
      
species(name='PLIGM2')
    
    

      
10
      
species(name='LIGM2')
    
    

      
11
      
species(name='PLIG')
    
    

      
12
      
species(name='LIG')
    
    

      
13
      
species(name='PADIOM2')
    
    

      
14
      
species(name='ADIOM2')
    
    

      
15
      
species(name='PADIO')
    
    

      
16
      
species(name='ADIO')
    
    

      
17
      
species(name='PFET3')
    
    

      
18
      
species(name='PFET3M2')
    
    

      
19
      
species(name='SYNAPYL')
    
    

      
20
      
species(name='COUMARYL')
    
    

      
21
      
species(name='PKETM2')
    
    

      
22
      
species(name='KETM2')
    
    

      
23
      
species(name='KET')
    
    

      
24
      
species(name='KETDM2')
    
    

      
25
      
species(name='KETD')
    
    

      
26
      
species(name='MGUAI')
    
    

      
27
      
species(name='PHENOL')
    
    

      
28
      
species(name='C10H2M4')
    
    

      
29
      
species(name='C10H2M2')
    
    

      
...
      
...
    
    

      
63
      
species(name='C2H6',atoms='C:2 H:6 O:0')
    
    

      
64
      
species(name='PCH3')
    
    

      
65
      
species(name='CH3CHO',atoms='C:2 H:4 O:1')
    
    

      
66
      
species(name='CO2',atoms='C:1 H:0 O:2')
    
    

      
67
      
species(name='CH2CO',atoms='C:2 H:2 O:1')
    
    

      
68
      
species(name='OH',atoms='C:0 H:1 O:1')
    
    

      
69
      
species(name='C3H6',atoms='C:3 H:6 O:0')
    
    

      
70
      
species(name='C3H6O2',atoms='C:3 H:6 O:2')
    
    

      
71
      
species(name='C3H4O2',atoms='C:3 H:4 O:2')
    
    

      
72
      
species(name='RC3H7O2',atoms='C:3 H:7 O:2')
    
    

      
73
      
species(name='RC3H5O2',atoms='C:3 H:5 O:2')
    
    

      
74
      
species(name='RC3H3O',atoms='C:3 H:3 O:1')
    
    

      
75
      
species(name='PRLIGH')
    
    

      
76
      
species(name='PRLIGH2')
    
    

      
77
      
species(name='RMGUAI')
    
    

      
78
      
species(name='RLIGH')
    
    

      
79
      
species(name='PCOHP2')
    
    

      
80
      
species(name='VADIOM2',atoms='C:11 H:16 O:5')
    
    

      
81
      
species(name='VKETM2',atoms='C:11 H:14 O:5')
    
    

      
82
      
species(name='VKETDM2',atoms='C:11 H:12 O:4')
    
    

      
83
      
species(name='VSYNAPYL',atoms='C:11 H:14 O:4')
    
    

      
84
      
species(name='VMGUAI',atoms='C:8 H:10 O:3')
    
    

      
85
      
species(name='VCOUMARYL',atoms='C:9 H:10 O:2')
    
    

      
86
      
species(name='VADIO',atoms='C:9 H:12 O:3')
    
    

      
87
      
species(name='VKET',atoms='C:9 H:10 O:3')
    
    

      
88
      
species(name='VKETD',atoms='C:9 H:8 O:2')
    
    

      
89
      
species(name='VPHENOL',atoms='C:6 H:6 O:1')
    
    

      
90
      
species(name='C3H4O',atoms='C:3 H:4 O:1')
    
    

      
91
      
species(name='C3H8O2',atoms='C:3 H:8 O:2')
    
    

      
92
      
species(name='CH4',atoms='C:1 H:4 O:0')
    
  

93 rows × 1 columns

In [19]:

    

df.to_csv('cti_species_data.txt', index=False,quoting=csv.QUOTE_NONE,escapechar='\\')