In [1]:

    

from ARXIV_171202734.chembl_repository import ChemblRepository
import json
import matplotlib.pyplot as plt
from multiprocessing import Pool
import numpy as np
import os
import pandas as pd
import rdkit
import sqlite3

%load_ext autoreload
%autoreload 2
%matplotlib inline


    

In [2]:

    

chembl_repository = ChemblRepository(os.path.abspath('Data'))


    

In [3]:

    

memento_file_path = os.path.abspath(os.path.join('Data', 'arXiv_171202734_Memento.json'))


    

In [4]:

    

memento = {}

if os.path.isfile(memento_file_path):
    memento = json.load(open(memento_file_path))
else:
    memento['last_processed_compound_id'] = -1


    

In [5]:

    

chembl_repository.get_total_compound_count()


    

    
Out[5]:





2101843

In [6]:

    

chembl_repository.get_remaining_compound_count(memento['last_processed_compound_id'])


    

    
Out[6]:





2101843

In [7]:

    

# TODO: Save memento back to JSON file after each processed batch!