Commit 3a03e958 authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #802 from peastman/wget 

Don't use wget
parents a1378530 d1dc4e10

deepchem/models/autoencoder_models/autoencoder.py

+5 −4
Original line number Diff line number Diff line
@@ -6,6 +6,7 @@ import warnings 
from deepchem.models import Model

from deepchem.models.autoencoder_models.model import MoleculeVAE

from deepchem.feat.one_hot import zinc_charset

from deepchem.utils import download_url

import os

from subprocess import call
@@ -64,8 +65,8 @@ class TensorflowMoleculeEncoder(Model): 
    weights_file = os.path.join(current_dir, weights_filename)



    if not os.path.exists(weights_file):

      wget_command = "wget -nv -c http://karlleswing.com/misc/keras-molecule/model.h5"

      call(wget_command.split())

      download_url("http://karlleswing.com/misc/keras-molecule/model.h5",

                   current_dir)

      mv_cmd = "mv model.h5 %s" % weights_file

      call(mv_cmd.split())

    return TensorflowMoleculeEncoder(
@@ -136,8 +137,8 @@ class TensorflowMoleculeDecoder(Model): 
    weights_file = os.path.join(current_dir, weights_filename)



    if not os.path.exists(weights_file):

      wget_command = "wget -nv -c http://karlleswing.com/misc/keras-molecule/model.h5"

      call(wget_command.split())

      download_url("http://karlleswing.com/misc/keras-molecule/model.h5",

                   current_dir)

      mv_cmd = "mv model.h5 %s" % weights_file

      call(mv_cmd.split())

    return TensorflowMoleculeDecoder(

deepchem/molnet/load_function/bace_datasets.py

+8 −16
Original line number Diff line number Diff line
@@ -14,18 +14,14 @@ def load_bace_regression(featurizer='ECFP', split='random', reload=True): 
  """Load bace datasets."""

  # Featurize bace dataset

  print("About to featurize bace dataset.")

  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "bace_r/" + featurizer + "/" + split)



  dataset_file = os.path.join(data_dir, "bace.csv")



  if not os.path.exists(dataset_file):

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/bace.csv'

    )
@@ -80,18 +76,14 @@ def load_bace_classification(featurizer='ECFP', split='random', reload=True): 
  """Load bace datasets."""

  # Featurize bace dataset

  print("About to featurize bace dataset.")

  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "bace_c/" + featurizer + "/" + split)



  dataset_file = os.path.join(data_dir, "bace.csv")



  if not os.path.exists(dataset_file):

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/bace.csv'

    )

deepchem/molnet/load_function/bbbp_datasets.py

+3 −7
Original line number Diff line number Diff line
@@ -13,17 +13,13 @@ def load_bbbp(featurizer='ECFP', split='random', reload=True): 
  """Load blood-brain barrier penetration datasets """

  # Featurize bbb dataset

  print("About to featurize bbbp dataset.")

  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "bbbp/" + featurizer + "/" + split)



  dataset_file = os.path.join(data_dir, "BBBP.csv")

  if not os.path.exists(dataset_file):

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/BBBP.csv'

    )

deepchem/molnet/load_function/chembl_datasets.py

+17 −28
Original line number Diff line number Diff line
@@ -16,45 +16,34 @@ def load_chembl(shard_size=2000, 
                split="random",

                reload=True):



  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "chembl/" + featurizer + "/" + split)



  dataset_path = os.path.join(data_dir, "chembl_%s.csv.gz" % set)

  if not os.path.exists(dataset_path):

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_5thresh.csv.gz'

    )

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_sparse.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_test.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_train.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_valid.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_test.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_train.csv.gz'

    )

    os.system(

        'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_valid.csv.gz'

    )

deepchem/molnet/load_function/clearance_datasets.py

+4 −8
Original line number Diff line number Diff line
@@ -14,17 +14,13 @@ def load_clearance(featurizer='ECFP', split='random', reload=True): 
  # Featurize clearance dataset

  print("About to featurize clearance dataset.")

  print("About to load clearance dataset.")

  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "clearance/" + featurizer + "/" + split)



  dataset_file = os.path.join(data_dir, "clearance.csv")

  if not os.path.exists(dataset_file):

    os.system(

        'wget -P ' + data_dir +

    deepchem.utils.download_url(

        'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/clearance.csv'

    )

CRA Git | Maintained and supported by SUSTech CRA and CCSE