Commit f7afbc25 authored by Vignesh's avatar Vignesh
Browse files

Added yapf formatting

parent 1f2102f0

deepchem/molnet/load_function/factors_datasets.py

+15 −10
Original line number Diff line number Diff line
@@ -25,7 +25,6 @@ TEST_FILENAME = "FACTORS_test2_disguised_combined_full.csv.gz" 




def remove_missing_entries(dataset):



  """Remove missing entries.



  Some of the datasets have missing entries that sneak in as zero'd out
@@ -43,7 +42,6 @@ def remove_missing_entries(dataset): 




def get_transformers(train_dataset):



  """Gets transformers applied to the dataset"""



  transformers = list()
@@ -52,8 +50,12 @@ def get_transformers(train_dataset): 
  return transformers





def gen_factors(FACTORS_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000):



def gen_factors(FACTORS_tasks,

                data_dir,

                train_dir,

                valid_dir,

                test_dir,

                shard_size=2000):

  """Loads the FACTORS dataset; does not do train/test split"""



  time1 = time.time()
@@ -78,7 +80,8 @@ def gen_factors(FACTORS_tasks, data_dir, train_dir, valid_dir, test_dir, shard_s 
  # Featurize the FACTORS dataset

  logger.info("About to featurize the FACTORS dataset")

  featurizer = deepchem.feat.UserDefinedFeaturizer(merck_descriptors)

  loader = deepchem.data.UserCSVLoader(tasks=FACTORS_tasks, id_field="Molecule", featurizer=featurizer)

  loader = deepchem.data.UserCSVLoader(

      tasks=FACTORS_tasks, id_field="Molecule", featurizer=featurizer)



  logger.info("Featurizing the train dataset...")

  train_dataset = loader.featurize(train_files, shard_size=shard_size)
@@ -103,7 +106,8 @@ def gen_factors(FACTORS_tasks, data_dir, train_dir, valid_dir, test_dir, shard_s 
  transformers = get_transformers(train_dataset)



  for transformer in transformers:

    logger.info("Performing transformations with {}".format(transformer.__class__.__name__))

    logger.info("Performing transformations with {}".format(

        transformer.__class__.__name__))



    logger.info("Transforming the training dataset...")

    train_dataset = transformer.transform(train_dataset)
@@ -135,11 +139,12 @@ def gen_factors(FACTORS_tasks, data_dir, train_dir, valid_dir, test_dir, shard_s 




def load_factors(shard_size=2000, featurizer=None, split=None, reload=True):



  """Loads FACTOR dataset; does not do train/test split"""



  FACTORS_tasks = ['T_00001', 'T_00002', 'T_00003', 'T_00004', 'T_00005', 'T_00006',

                   'T_00007', 'T_00008', 'T_00009', 'T_00010', 'T_00011', 'T_00012']

  FACTORS_tasks = [

      'T_00001', 'T_00002', 'T_00003', 'T_00004', 'T_00005', 'T_00006',

      'T_00007', 'T_00008', 'T_00009', 'T_00010', 'T_00011', 'T_00012'

  ]



  data_dir = deepchem.utils.get_data_dir()

  data_dir = os.path.join(data_dir, "factors")

deepchem/molnet/load_function/kinase_datasets.py

+33 −26
Original line number Diff line number Diff line
@@ -21,12 +21,10 @@ TRAIN_FILENAME = "KINASE_training_disguised_combined_full.csv.gz" 
VALID_FILENAME = "KINASE_test1_disguised_combined_full.csv.gz"

TEST_FILENAME = "KINASE_test2_disguised_combined_full.csv.gz"





logger = logging.getLogger(__name__)





def remove_missing_entries(dataset):



  """Remove missing entries.



  Some of the datasets have missing entries that sneak in as zero'd out
@@ -44,7 +42,6 @@ def remove_missing_entries(dataset): 




def get_transformers(train_dataset):



  """Gets transformers applied to the dataset"""

  #TODO: Check for this
@@ -53,7 +50,12 @@ def get_transformers(train_dataset): 
  return transformers





def gen_kinase(KINASE_tasks, train_dir, valid_dir, test_dir, data_dir, shard_size=2000):

def gen_kinase(KINASE_tasks,

               train_dir,

               valid_dir,

               test_dir,

               data_dir,

               shard_size=2000):



  time1 = time.time()
@@ -85,10 +87,12 @@ def gen_kinase(KINASE_tasks, train_dir, valid_dir, test_dir, data_dir, shard_siz 
      tasks=KINASE_tasks, id_field="Molecule", featurizer=featurizer)



  logger.info("Featurizing train datasets...")

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

  train_dataset = loader.featurize(

      input_files=train_files, shard_size=shard_size)



  logger.info("Featurizing validation datasets...")

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

  valid_dataset = loader.featurize(

      input_files=valid_files, shard_size=shard_size)



  logger.info("Featurizing test datasets....")

  test_dataset = loader.featurize(input_files=test_files, shard_size=shard_size)
@@ -107,7 +111,8 @@ def gen_kinase(KINASE_tasks, train_dir, valid_dir, test_dir, data_dir, shard_siz 
  transformers = get_transformers(train_dataset)



  for transformer in transformers:

    logger.info("Performing transformations with {}".format(transformer.__class__.__name__))

    logger.info("Performing transformations with {}".format(

        transformer.__class__.__name__))



    logger.info("Transforming the training dataset...")

    train_dataset = transformer.transform(train_dataset)
@@ -143,7 +148,8 @@ def load_kinase(shard_size=2000, featurizer=None, split=None, reload=True): 


  "Loads kinase datasets, does not do train/test split"



  KINASE_tasks = ['T_00013', 'T_00014', 'T_00015', 'T_00016', 'T_00017', 'T_00018',

  KINASE_tasks = [

      'T_00013', 'T_00014', 'T_00015', 'T_00016', 'T_00017', 'T_00018',

      'T_00019', 'T_00020', 'T_00021', 'T_00022', 'T_00023', 'T_00024',

      'T_00025', 'T_00026', 'T_00027', 'T_00028', 'T_00029', 'T_00030',

      'T_00031', 'T_00032', 'T_00033', 'T_00034', 'T_00035', 'T_00036',
@@ -159,7 +165,8 @@ def load_kinase(shard_size=2000, featurizer=None, split=None, reload=True): 
      'T_00091', 'T_00092', 'T_00093', 'T_00094', 'T_00095', 'T_00096',

      'T_00097', 'T_00098', 'T_00099', 'T_00100', 'T_00101', 'T_00102',

      'T_00103', 'T_00104', 'T_00105', 'T_00106', 'T_00107', 'T_00108',

                  'T_00109', 'T_00110', 'T_00111']

      'T_00109', 'T_00110', 'T_00111'

  ]



  data_dir = deepchem.utils.get_data_dir()

  data_dir = os.path.join(data_dir, "kinase")

deepchem/molnet/load_function/uv_datasets.py

+10 −10
Original line number Diff line number Diff line
@@ -52,7 +52,6 @@ def get_transformers(train_dataset): 




def gen_uv(UV_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000):



  """Loading the UV dataset; does not do train/test split"""



  time1 = time.time()
@@ -84,10 +83,12 @@ def gen_uv(UV_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000): 
      tasks=UV_tasks, id_field="Molecule", featurizer=featurizer)



  logger.info("Featurizing train datasets...")

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

  train_dataset = loader.featurize(

      input_files=train_files, shard_size=shard_size)



  logger.info("Featurizing validation datasets...")

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

  valid_dataset = loader.featurize(

      input_files=valid_files, shard_size=shard_size)



  logger.info("Featurizing test datasets....")

  test_dataset = loader.featurize(input_files=test_files, shard_size=shard_size)
@@ -107,7 +108,8 @@ def gen_uv(UV_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000): 
  transformers = get_transformers(train_dataset)



  for transformer in transformers:

    logger.info("Performing transformations with {}".format(transformer.__class__.__name__))

    logger.info("Performing transformations with {}".format(

        transformer.__class__.__name__))



    logger.info("Transforming the training dataset...")

    train_dataset = transformer.transform(train_dataset)
@@ -139,7 +141,6 @@ def gen_uv(UV_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000): 




def load_uv(shard_size=2000, featurizer=None, split=None, reload=True):



  """Load UV dataset; does not do train/test split"""



  data_dir = deepchem.utils.get_data_dir()
@@ -168,5 +169,4 @@ def load_uv(shard_size=2000, featurizer=None, split=None, reload=True): 


  transformers = get_transformers(train_dataset)



  return UV_tasks, (train_dataset, valid_dataset,

                    test_dataset), transformers
 
  return UV_tasks, (train_dataset, valid_dataset, test_dataset), transformers

deepchem/molnet/load_function/uv_tasks.py

+30 −28
Original line number Diff line number Diff line 
UV_tasks = ['w__210', 'w__211', 'w__212', 'w__213', 'w__214', 'w__215', 'w__216',

UV_tasks = [

    'w__210', 'w__211', 'w__212', 'w__213', 'w__214', 'w__215', 'w__216',

    'w__217', 'w__218', 'w__219', 'w__220', 'w__221', 'w__222', 'w__223',

    'w__224', 'w__225', 'w__226', 'w__227', 'w__228', 'w__229', 'w__230',

    'w__231', 'w__232', 'w__233', 'w__234', 'w__235', 'w__236', 'w__237',
@@ -25,4 +26,5 @@ UV_tasks = ['w__210', 'w__211', 'w__212', 'w__213', 'w__214', 'w__215', 'w__216' 
    'w__378', 'w__379', 'w__380', 'w__381', 'w__382', 'w__383', 'w__384',

    'w__385', 'w__386', 'w__387', 'w__388', 'w__389', 'w__390', 'w__391',

    'w__392', 'w__393', 'w__394', 'w__395', 'w__396', 'w__397', 'w__398',

            'w__399', 'w__400']
 
    'w__399', 'w__400'

]

CRA Git | Maintained and supported by SUSTech CRA and CCSE