Unverified Commit a38c4f11 authored by Suzukazole's avatar Suzukazole
Browse files

fixed whitespace errors in molnet

parent 7ed24e5a

deepchem/molnet/load_function/factors_datasets.py

+6 −6
Original line number Diff line number Diff line
@@ -128,7 +128,7 @@ def gen_factors(FACTORS_tasks, 


  time2 = time.time()



  ########## TIMING ################

  # TIMING

  logger.info("TIMING: FACTORS fitting took %0.3f s" % (time2 - time1))



  return train_dataset, valid_dataset, test_dataset
@@ -192,8 +192,8 @@ def load_factors(shard_size=2000, featurizer=None, split=None, reload=True): 


  else:

    logger.info("Featurizing datasets")

    train_dataset, valid_dataset, test_dataset = \

    gen_factors(FACTORS_tasks=FACTORS_tasks, data_dir=data_dir, train_dir=train_dir,

    train_dataset, valid_dataset, test_dataset = gen_factors(

      FACTORS_tasks=FACTORS_tasks, data_dir=data_dir, train_dir=train_dir,

      valid_dir=valid_dir, test_dir=test_dir, shard_size=shard_size)



  transformers = get_transformers(train_dataset)

deepchem/molnet/load_function/kaggle_datasets.py

+5 −5
Original line number Diff line number Diff line
@@ -47,9 +47,9 @@ def gen_kaggle(KAGGLE_tasks, 
               data_dir,

               shard_size=2000):

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

  ############################################################## TIMING

  # TIMING

  time1 = time.time()

  ############################################################## TIMING

  # TIMING

  # Set some global variables up top

  train_files = os.path.join(data_dir,

                             "KAGGLE_training_disguised_combined_full.csv.gz")
@@ -108,10 +108,10 @@ def gen_kaggle(KAGGLE_tasks, 
  valid_dataset.move(valid_dir)

  test_dataset.move(test_dir)



  ############################################################## TIMING

  # TIMING

  time2 = time.time()

  logger.info("TIMING: KAGGLE fitting took %0.3f s" % (time2 - time1))

  ############################################################## TIMING

  # TIMING



  return train_dataset, valid_dataset, test_dataset

deepchem/molnet/load_function/kinase_datasets.py

+7 −7
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ import deepchem 
from deepchem.molnet.load_function.kaggle_features import merck_descriptors



TRAIN_URL = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/KINASE_training_disguised_combined_full.csv.gz"

VALID_UR = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/KINASE_test1_disguised_combined_full.csv.gz"

VALID_URL = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/KINASE_test1_disguised_combined_full.csv.gz"

TEST_URL = "https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/KINASE_test2_disguised_combined_full.csv.gz"



TRAIN_FILENAME = "KINASE_training_disguised_combined_full.csv.gz"
@@ -133,7 +133,7 @@ def gen_kinase(KINASE_tasks, 


  time2 = time.time()



  ##### TIMING ######

  # TIMING



  logger.info("TIMING: KINASE fitting took %0.3f s" % (time2 - time1))
@@ -212,8 +212,8 @@ def load_kinase(shard_size=2000, featurizer=None, split=None, reload=True): 


  else:

    logger.info("Featurizing datasets")

    train_dataset, valid_dataset, test_dataset = \

    gen_kinase(KINASE_tasks=KINASE_tasks, train_dir=train_dir,

    train_dataset, valid_dataset, test_dataset = gen_kinase(

      KINASE_tasks=KINASE_tasks, train_dir=train_dir,

      valid_dir=valid_dir, test_dir=test_dir, data_dir=data_dir,

      shard_size=shard_size)

deepchem/molnet/load_function/uv_datasets.py

+4 −4
Original line number Diff line number Diff line
@@ -130,7 +130,7 @@ def gen_uv(UV_tasks, data_dir, train_dir, valid_dir, test_dir, shard_size=2000): 


  time2 = time.time()



  ##### TIMING ###########

  # TIMING

  logger.info("TIMING: UV fitting took %0.3f s" % (time2 - time1))



  return train_dataset, valid_dataset, test_dataset
@@ -188,8 +188,8 @@ def load_uv(shard_size=2000, featurizer=None, split=None, reload=True): 


  else:

    logger.info("Featurizing datasets")

    train_dataset, valid_dataset, test_dataset = \

    gen_uv(UV_tasks=UV_tasks, data_dir=data_dir, train_dir=train_dir,

    train_dataset, valid_dataset, test_dataset = gen_uv(

      UV_tasks=UV_tasks, data_dir=data_dir, train_dir=train_dir,

      valid_dir=valid_dir, test_dir=test_dir, shard_size=shard_size)



  transformers = get_transformers(train_dataset)

deepchem/molnet/run_benchmark.py

+4 −4
Original line number Diff line number Diff line
@@ -81,7 +81,7 @@ def run_benchmark(datasets, 
        'pcba_2475', 'sider', 'tox21', 'toxcast'

    ]:

      mode = 'classification'

      if metric == None:

      if metric is None:

        metric = [

            deepchem.metrics.Metric(deepchem.metrics.roc_auc_score, np.mean),

        ]
@@ -91,14 +91,14 @@ def run_benchmark(datasets, 
        'thermosol'

    ]:

      mode = 'regression'

      if metric == None:

      if metric is None:

        metric = [

            deepchem.metrics.Metric(deepchem.metrics.pearson_r2_score, np.mean)

        ]

    else:

      raise ValueError('Dataset not supported')



    if featurizer == None and isinstance(model, str):

    if featurizer is None and isinstance(model, str):

      # Assigning featurizer if not user defined

      pair = (dataset, model)

      if pair in CheckFeaturizer:
@@ -107,7 +107,7 @@ def run_benchmark(datasets, 
      else:

        continue



    if not split in [None] + CheckSplit[dataset]:

    if split not in [None] + CheckSplit[dataset]:

      continue



    loading_functions = {

CRA Git | Maintained and supported by SUSTech CRA and CCSE