#!/usr/bin/env python
# coding: utf-8

# In[1]:


import os
import pandas
import pandas_profiling
import pandas as pd


# In[2]:


from rdkit import Chem
from rdkit import RDConfig
from rdkit.Chem import rdBase 
from rdkit.Chem import Descriptors
from rdkit.Chem.Descriptors import _descList
from rdkit.ML.Descriptors import MoleculeDescriptors


# In[3]:


print(rdBase.rdkitVersion)
datadir =  os.path.join( RDConfig.RDDocsDir, "Book/data/cdk2.sdf" )


# In[4]:


mols = [mol for mol in Chem.SDMolSupplier(datadir) if mol != None]


# In[5]:


desc_name = [desc[0] for desc in _descList]
calc = MoleculeDescriptors.MolecularDescriptorCalculator(desc_name)
descs_list = [calc.CalcDescriptors(mol) for mol in mols]


# In[6]:


print(len(descs_list))
print(len(descs_list[0]))


# In[7]:


data = {}
for name in desc_name:
    data[name] = []


# In[8]:


for descs in descs_list:
    for i, desc in enumerate(descs):
        data[desc_name[i]].append(desc)


# In[9]:


df = pd.DataFrame(data)


# In[10]:


print(df.shape)


# In[11]:


pandas_profiling.ProfileReport(df)


# In[ ]: