Commit 7efa6437 authored by miaecle's avatar miaecle
Browse files

style change

parent 3edcd2fc

deepchem/molnet/__init__.py

+0 −1
Original line number Diff line number Diff line 


from deepchem.molnet.load_function.chembl_datasets import load_chembl

from deepchem.molnet.load_function.clintox_datasets import load_clintox

from deepchem.molnet.load_function.delaney_datasets import load_delaney

deepchem/molnet/load_function/chembl_datasets.py

+58 −37
Original line number Diff line number Diff line
@@ -10,41 +10,60 @@ import deepchem as dc 


from deepchem.molnet.load_function.chembl_tasks import chembl_tasks



def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random"):



def load_chembl(shard_size=2000,

                featurizer="ECFP",

                set="5thresh",

                split="random"):



  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"



  dataset_path = os.path.join(

      data_dir, "chembl_%s.csv.gz" % set)

  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 + 

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

    os.system('wget -P ' + data_dir + 

    ' 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') + 

    ' 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') + 

    ' 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') + 

    ' 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') + 

    ' 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') + 

    ' 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') + 

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

    os.system(

        'wget -P ' + data_dir +

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

    )

    os.system(

        'wget -P ' + data_dir +

        ' 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') +

        ' 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') +

        ' 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') +

        ' 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') +

        ' 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') +

        ' 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') +

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

    )



  print("About to load ChEMBL dataset.")

  if split == "year":

    train_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_train.csv.gz" % set)

    valid_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_valid.csv.gz" % set)

    test_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_test.csv.gz" % set)

    train_files = os.path.join(

        data_dir, "./chembl_year_sets/chembl_%s_ts_train.csv.gz" % set)

    valid_files = os.path.join(

        data_dir, "./chembl_year_sets/chembl_%s_ts_valid.csv.gz" % set)

    test_files = os.path.join(

        data_dir, "./chembl_year_sets/chembl_%s_ts_test.csv.gz" % set)



  # Featurize ChEMBL dataset

  print("About to featurize ChEMBL dataset.")
@@ -60,34 +79,36 @@ def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random 


  if split == "year":

    print("Featurizing train datasets")

    train_dataset = loader.featurize(

        train_files, shard_size=shard_size)

    train_dataset = loader.featurize(train_files, shard_size=shard_size)

    print("Featurizing valid datasets")

    valid_dataset = loader.featurize(

        valid_files, shard_size=shard_size)

    valid_dataset = loader.featurize(valid_files, shard_size=shard_size)

    print("Featurizing test datasets")

    test_dataset = loader.featurize(

        test_files, shard_size=shard_size)

    test_dataset = loader.featurize(test_files, shard_size=shard_size)

  else:

    dataset = loader.featurize(dataset_path, shard_size=shard_size)

  # Initialize transformers

  print("About to transform data")

  if split == "year":

    transformers = [

        dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]

        dc.trans.NormalizationTransformer(

            transform_y=True, dataset=train_dataset)

    ]

    for transformer in transformers:

      train = transformer.transform(train_dataset)

      valid = transformer.transform(valid_dataset)

      test = transformer.transform(test_dataset)

  else:

    transformers = [

        dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

        dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)

    ]

    for transformer in transformers:

      dataset = transformer.transform(dataset)



  splitters = {'index': dc.splits.IndexSplitter(),

  splitters = {

      'index': dc.splits.IndexSplitter(),

      'random': dc.splits.RandomSplitter(),

               'scaffold': dc.splits.ScaffoldSplitter()}

      'scaffold': dc.splits.ScaffoldSplitter()

  }



  if split in splitters:

    splitter = splitters[split]

deepchem/molnet/load_function/chembl_tasks.py

+142 −138

File changed.

Preview size limit exceeded, changes collapsed.

deepchem/molnet/load_function/clintox_datasets.py

+13 −9
Original line number Diff line number Diff line
@@ -19,11 +19,12 @@ def load_clintox(featurizer='ECFP', split='index'): 
  else:

    data_dir = "/tmp"



  dataset_file = os.path.join(

      data_dir, "clintox.csv.gz")

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

  if not os.path.exists(dataset_file):

    os.system('wget -P ' + data_dir + 

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

    os.system(

        'wget -P ' + data_dir +

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

    )



  print("About to load clintox dataset.")

  dataset = dc.utils.save.load_from_disk(dataset_file)
@@ -48,15 +49,18 @@ def load_clintox(featurizer='ECFP', split='index'): 
  # Transform clintox dataset

  print("About to transform clintox dataset.")

  transformers = [

      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]

      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)

  ]

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  # Split clintox dataset

  print("About to split clintox dataset.")

  splitters = {'index': dc.splits.IndexSplitter(),

  splitters = {

      'index': dc.splits.IndexSplitter(),

      'random': dc.splits.RandomSplitter(),

               'scaffold': dc.splits.ScaffoldSplitter()}

      'scaffold': dc.splits.ScaffoldSplitter()

  }

  splitter = splitters[split]

  train, valid, test = splitter.train_valid_test_split(dataset)

deepchem/molnet/load_function/delaney_datasets.py

+16 −12
Original line number Diff line number Diff line
@@ -8,6 +8,7 @@ from __future__ import unicode_literals 
import os

import deepchem as dc





def load_delaney(featurizer='ECFP', split='index'):

  """Load delaney datasets."""

  # Featurize Delaney dataset
@@ -17,12 +18,13 @@ def load_delaney(featurizer='ECFP', split='index'): 
  else:

    data_dir = "/tmp"



  dataset_file = os.path.join(

      data_dir, "delaney-processed.csv")

  dataset_file = os.path.join(data_dir, "delaney-processed.csv")



  if not os.path.exists(dataset_file):

    os.system('wget -P ' + data_dir + 

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

    os.system(

        'wget -P ' + data_dir +

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

    )



  delaney_tasks = ['measured log solubility in mols per litre']

  if featurizer == 'ECFP':
@@ -34,20 +36,22 @@ def load_delaney(featurizer='ECFP', split='index'): 


  loader = dc.data.CSVLoader(

      tasks=delaney_tasks, smiles_field="smiles", featurizer=featurizer)

  dataset = loader.featurize(

      dataset_file, shard_size=8192)

  dataset = loader.featurize(dataset_file, shard_size=8192)



  # Initialize transformers 

  transformers = [

      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

      dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)

  ]



  print("About to transform data")

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  splitters = {'index': dc.splits.IndexSplitter(),

  splitters = {

      'index': dc.splits.IndexSplitter(),

      'random': dc.splits.RandomSplitter(),

               'scaffold': dc.splits.ScaffoldSplitter()}

      'scaffold': dc.splits.ScaffoldSplitter()

  }

  splitter = splitters[split]

  train, valid, test = splitter.train_valid_test_split(dataset)

  return delaney_tasks, (train, valid, test), transformers

CRA Git | Maintained and supported by SUSTech CRA and CCSE