Merge pull request #859 from Dgelemi/untargz_function (7b6248db) · Commits · 钟慕尧 / deepchem

deepchem/molnet/load_function/qm9_datasets.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -24,8 +24,8 @@ def load_qm9(featurizer='CoulombMatrix', split='random', reload=True):
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/gdb9.tar.gz'
		)
		os.system('tar -zxvf ' + os.path.join(data_dir, 'gdb9.tar.gz') + ' -C ' +
		data_dir)
		deepchem.utils.untargz_file(
		os.path.join(data_dir, 'gdb9.tar.gz'), data_dir)
		else:
		dataset_file = os.path.join(data_dir, "qm9.csv")
		if not os.path.exists(dataset_file):

+21 −0

Original line number	Diff line number	Diff line
		@@ -11,6 +11,8 @@ import numpy as np
		import os
		import pandas as pd
		import tempfile
		import tarfile
		import sys

		from rdkit import Chem
		from rdkit.Chem.Scaffolds import MurckoScaffold
		@@ -83,6 +85,25 @@ def download_url(url, dest_dir=get_data_dir(), name=None):
		urlretrieve(url, os.path.join(dest_dir, name))


		def untargz_file(file, dest_dir=get_data_dir(), name=None):
		"""Untar and unzip a .tar.gz file to disk.

		Parameters
		----------
		file: str
		the filepath to decompress
		dest_dir: str
		the directory to save the file in
		name: str
		the file name to save it as. If omitted, it will use the file name
		"""
		if name is None:
		name = file
		tar = tarfile.open(name)
		tar.extractall(path=dest_dir)
		tar.close()


		class ScaffoldGenerator(object):
		"""
		Generate molecular scaffolds.