Commit 4fde2603 authored by peastman's avatar peastman
Browse files

yapf

parent ca2ba7c2

examples/low_data/datasets.py

+41 −46
Original line number Diff line number Diff line
@@ -12,31 +12,31 @@ import tempfile 
import numpy as np

import deepchem as dc





def to_numpy_dataset(dataset):

  """Converts dataset to numpy dataset."""

  return dc.data.NumpyDataset(dataset.X, dataset.y, dataset.w, dataset.ids)





def load_tox21_ecfp(num_train=7200):

  """Load Tox21 datasets. Does not do train/test split"""

  # Set some global variables up top

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../../datasets/tox21.csv.gz")

  dataset_file = os.path.join(current_dir, "../../datasets/tox21.csv.gz")

  # Featurize Tox21 dataset

  print("About to featurize Tox21 dataset.")

  featurizer = dc.feat.CircularFingerprint(size=1024)

  tox21_tasks = ['NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER',

                 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5',

                 'SR-HSE', 'SR-MMP', 'SR-p53']

  tox21_tasks = [

      'NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD',

      'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53'

  ]



  loader = dc.data.CSVLoader(

      tasks=tox21_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.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]



  print("About to transform data")

  for transformer in transformers:
@@ -44,28 +44,27 @@ def load_tox21_ecfp(num_train=7200): 


  return tox21_tasks, dataset, transformers





def load_tox21_convmol(base_dir=None, num_train=7200):

  """Load Tox21 datasets. Does not do train/test split"""

  # Set some global variables up top

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../../datasets/tox21.csv.gz")

  dataset_file = os.path.join(current_dir, "../../datasets/tox21.csv.gz")



  # Featurize Tox21 dataset

  print("About to featurize Tox21 dataset.")

  featurizer = dc.feat.ConvMolFeaturizer()

  tox21_tasks = ['NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER',

                 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5',

                 'SR-HSE', 'SR-MMP', 'SR-p53']

  tox21_tasks = [

      'NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD',

      'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53'

  ]



  loader = dc.data.CSVLoader(

      tasks=tox21_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.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]



  print("About to transform data")

  for transformer in transformers:
@@ -73,69 +72,69 @@ def load_tox21_convmol(base_dir=None, num_train=7200): 


  return tox21_tasks, dataset, transformers





def load_muv_ecfp():

  """Load MUV datasets. Does not do train/test split"""

  # Load MUV dataset

  print("About to load MUV dataset.")

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../../datasets/muv.csv.gz")

  dataset_file = os.path.join(current_dir, "../../datasets/muv.csv.gz")

  # Featurize MUV dataset

  print("About to featurize MUV dataset.")

  featurizer = dc.feat.CircularFingerprint(size=1024)

  MUV_tasks = sorted(['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',

                      'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',

                      'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',

                      'MUV-466', 'MUV-832'])

  MUV_tasks = sorted([

      'MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644', 'MUV-548',

      'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712', 'MUV-737', 'MUV-858',

      'MUV-713', 'MUV-733', 'MUV-652', 'MUV-466', 'MUV-832'

  ])



  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]

  print("About to transform data")

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  return MUV_tasks, dataset, transformers





def load_muv_convmol():

  """Load MUV datasets. Does not do train/test split"""

  # Load MUV dataset

  print("About to load MUV dataset.")

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../../datasets/muv.csv.gz")

  dataset_file = os.path.join(current_dir, "../../datasets/muv.csv.gz")

  # Featurize MUV dataset

  print("About to featurize MUV dataset.")

  featurizer = dc.feat.ConvMolFeaturizer()

  MUV_tasks = sorted(['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',

                      'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',

                      'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',

                      'MUV-466', 'MUV-832'])

  MUV_tasks = sorted([

      'MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644', 'MUV-548',

      'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712', 'MUV-737', 'MUV-858',

      'MUV-713', 'MUV-733', 'MUV-652', 'MUV-466', 'MUV-832'

  ])



  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]

  print("About to transform data")

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  return MUV_tasks, dataset, transformers





def load_sider_ecfp():

  """Load SIDER datasets. Does not do train/test split"""

  # Featurize SIDER dataset

  print("About to featurize SIDER dataset.")

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../sider/sider.csv.gz")

  dataset_file = os.path.join(current_dir, "../sider/sider.csv.gz")

  featurizer = dc.feat.CircularFingerprint(size=1024)



  dataset = dc.utils.save.load_from_disk(dataset_file)
@@ -143,28 +142,26 @@ def load_sider_ecfp(): 
  print("SIDER tasks: %s" % str(SIDER_tasks))

  print("%d tasks in total" % len(SIDER_tasks))





  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)

  print("%d datapoints in SIDER dataset" % len(dataset))



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]

  print("About to transform data")

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  return SIDER_tasks, dataset, transformers





def load_sider_convmol():

  """Load SIDER datasets. Does not do train/test split"""

  # Featurize SIDER dataset

  print("About to featurize SIDER dataset.")

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "../sider/sider.csv.gz")

  dataset_file = os.path.join(current_dir, "../sider/sider.csv.gz")

  featurizer = dc.feat.ConvMolFeaturizer()



  dataset = dc.utils.save.load_from_disk(dataset_file)
@@ -172,15 +169,13 @@ def load_sider_convmol(): 
  print("SIDER tasks: %s" % str(SIDER_tasks))

  print("%d tasks in total" % len(SIDER_tasks))





  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)

  print("%d datapoints in SIDER dataset" % len(dataset))



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]

  print("About to transform data")

  for transformer in transformers:

    dataset = transformer.transform(dataset)

examples/pcba/pcba_datasets.py

+1 −3
Original line number Diff line number Diff line
@@ -57,9 +57,7 @@ def load_pcba(featurizer='ECFP', split='random'): 


  dataset = loader.featurize(dataset_file)

  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)

  ]

  transformers = [dc.trans.BalancingTransformer(dataset=dataset)]



  print("About to transform data")

  for transformer in transformers:

examples/sider/sider_datasets.py

+9 −8
Original line number Diff line number Diff line
@@ -10,13 +10,13 @@ import numpy as np 
import shutil

import deepchem as dc





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

  current_dir = os.path.dirname(os.path.realpath(__file__))



  # Load SIDER dataset

  print("About to load SIDER dataset.")

  dataset_file = os.path.join(

      current_dir, "./sider.csv.gz")

  dataset_file = os.path.join(current_dir, "./sider.csv.gz")

  dataset = dc.utils.save.load_from_disk(dataset_file)

  print("Columns of dataset: %s" % str(dataset.columns.values))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))
@@ -38,15 +38,16 @@ def load_sider(featurizer='ECFP', split='index'): 
  print("%d datapoints in SIDER dataset" % len(dataset))



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(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)

examples/toxcast/toxcast_datasets.py

+10 −9
Original line number Diff line number Diff line
@@ -10,14 +10,14 @@ import numpy as np 
import shutil

import deepchem as dc





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



  current_dir = os.path.dirname(os.path.realpath(__file__))



  # Load TOXCAST dataset

  print("About to load TOXCAST dataset.")

  dataset_file = os.path.join(

      current_dir, "./processing/toxcast_data.csv.gz")

  dataset_file = os.path.join(current_dir, "./processing/toxcast_data.csv.gz")

  dataset = dc.utils.save.load_from_disk(dataset_file)

  print("Columns of dataset: %s" % str(dataset.columns.values))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))
@@ -37,15 +37,16 @@ def load_toxcast(featurizer='ECFP', split='index'): 
  dataset = loader.featurize(dataset_file)



  # Initialize transformers

  transformers = [

      dc.trans.BalancingTransformer(dataset=dataset)]

  transformers = [dc.trans.BalancingTransformer(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)

CRA Git | Maintained and supported by SUSTech CRA and CCSE