Unverified Commit 30f2dd5e authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #1251 from miaecle/move_mean 

Performance fix for qm7
parents e3b63891 9ef09f2a

deepchem/molnet/load_function/bace_datasets.py

+10 −3
Original line number Diff line number Diff line
@@ -12,13 +12,20 @@ from deepchem.molnet.load_function.bace_features import bace_user_specified_feat 
logger = logging.getLogger(__name__)





def load_bace_regression(featurizer='ECFP', split='random', reload=True):

def load_bace_regression(featurizer='ECFP',

                         split='random',

                         reload=True,

                         move_mean=True):

  """Load bace datasets."""

  # Featurize bace dataset

  logger.info("About to featurize bace dataset.")

  data_dir = deepchem.utils.get_data_dir()

  if reload:

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

    if move_mean:

      dir_name = "bace_r/" + featurizer + "/" + str(split)

    else:

      dir_name = "bace_r/" + featurizer + "_mean_unmoved/" + str(split)

    save_dir = os.path.join(data_dir, dir_name)



  dataset_file = os.path.join(data_dir, "bace.csv")
@@ -53,7 +60,7 @@ def load_bace_regression(featurizer='ECFP', split='random', reload=True): 
  # Initialize transformers

  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=dataset)

          transform_y=True, dataset=dataset, move_mean=move_mean)

  ]



  logger.info("About to transform data")

deepchem/molnet/load_function/clearance_datasets.py

+10 −4
Original line number Diff line number Diff line
@@ -11,15 +11,21 @@ import deepchem 
logger = logging.getLogger(__name__)





def load_clearance(featurizer='ECFP', split='random', reload=True):

def load_clearance(featurizer='ECFP',

                   split='random',

                   reload=True,

                   move_mean=True):

  """Load clearance datasets."""

  # Featurize clearance dataset

  logger.info("About to featurize clearance dataset.")

  logger.info("About to load clearance dataset.")

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir,

                            "clearance/" + featurizer + "/" + str(split))

    if move_mean:

      dir_name = "clearance/" + featurizer + "/" + str(split)

    else:

      dir_name = "clearance/" + featurizer + "_mean_unmoved/" + str(split)

    save_dir = os.path.join(data_dir, dir_name)



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

  if not os.path.exists(dataset_file):
@@ -51,7 +57,7 @@ def load_clearance(featurizer='ECFP', split='random', reload=True): 
  # Initialize transformers

  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=dataset)

          transform_y=True, dataset=dataset, move_mean=move_mean)

  ]



  logger.info("About to transform data")

deepchem/molnet/load_function/delaney_datasets.py

+7 −4
Original line number Diff line number Diff line
@@ -11,14 +11,17 @@ import deepchem 
logger = logging.getLogger(__name__)





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

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

  """Load delaney datasets."""

  # Featurize Delaney dataset

  logger.info("About to featurize Delaney dataset.")

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir,

                            "delaney/" + featurizer + "/" + str(split))

    if move_mean:

      dir_name = "delaney/" + featurizer + "/" + str(split)

    else:

      dir_name = "delaney/" + featurizer + "_mean_unmoved/" + str(split)

    save_dir = os.path.join(data_dir, dir_name)



  dataset_file = os.path.join(data_dir, "delaney-processed.csv")
@@ -50,7 +53,7 @@ def load_delaney(featurizer='ECFP', split='index', reload=True): 
  # Initialize transformers

  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=dataset)

          transform_y=True, dataset=dataset, move_mean=move_mean)

  ]



  logger.info("About to transform data")

deepchem/molnet/load_function/lipo_datasets.py

+7 −3
Original line number Diff line number Diff line
@@ -11,14 +11,18 @@ import deepchem 
logger = logging.getLogger(__name__)





def load_lipo(featurizer='ECFP', split='index', reload=True):

def load_lipo(featurizer='ECFP', split='index', reload=True, move_mean=True):

  """Load Lipophilicity datasets."""

  # Featurize Lipophilicity dataset

  logger.info("About to featurize Lipophilicity dataset.")

  logger.info("About to load Lipophilicity dataset.")

  data_dir = deepchem.utils.get_data_dir()

  if reload:

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

    if move_mean:

      dir_name = "lipo/" + featurizer + "/" + str(split)

    else:

      dir_name = "lipo/" + featurizer + "_mean_unmoved/" + str(split)

    save_dir = os.path.join(data_dir, dir_name)



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

  if not os.path.exists(dataset_file):
@@ -50,7 +54,7 @@ def load_lipo(featurizer='ECFP', split='index', reload=True): 
  # Initialize transformers

  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=dataset)

          transform_y=True, dataset=dataset, move_mean=move_mean)

  ]



  logger.info("About to transform data")

deepchem/molnet/load_function/qm7_datasets.py

+16 −7
Original line number Diff line number Diff line
@@ -12,10 +12,15 @@ import scipy.io 


def load_qm7_from_mat(featurizer='CoulombMatrix',

                      split='stratified',

                      reload=True):

                      reload=True,

                      move_mean=True):

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "qm7/" + featurizer + "/" + str(split))

    if move_mean:

      dir_name = "qm7/" + featurizer + "/" + str(split)

    else:

      dir_name = "qm7/" + featurizer + "_mean_unmoved/" + str(split)

    save_dir = os.path.join(data_dir, dir_name)



  qm7_tasks = ["u0_atom"]
@@ -83,7 +88,7 @@ def load_qm7_from_mat(featurizer='CoulombMatrix', 


    transformers = [

        deepchem.trans.NormalizationTransformer(

            transform_y=True, dataset=train_dataset)

            transform_y=True, dataset=train_dataset, move_mean=move_mean)

    ]



    for transformer in transformers:
@@ -99,7 +104,8 @@ def load_qm7_from_mat(featurizer='CoulombMatrix', 


def load_qm7b_from_mat(featurizer='CoulombMatrix',

                       split='stratified',

                       reload=True):

                       reload=True,

                       move_mean=True):

  data_dir = deepchem.utils.get_data_dir()

  dataset_file = os.path.join(data_dir, "qm7b.mat")
@@ -129,7 +135,7 @@ def load_qm7b_from_mat(featurizer='CoulombMatrix', 


    transformers = [

        deepchem.trans.NormalizationTransformer(

            transform_y=True, dataset=train_dataset)

            transform_y=True, dataset=train_dataset, move_mean=move_mean)

    ]



    for transformer in transformers:
@@ -141,7 +147,10 @@ def load_qm7b_from_mat(featurizer='CoulombMatrix', 
    return qm7_tasks, (train_dataset, valid_dataset, test_dataset), transformers





def load_qm7(featurizer='CoulombMatrix', split='random', reload=True):

def load_qm7(featurizer='CoulombMatrix',

             split='random',

             reload=True,

             move_mean=True):

  """Load qm7 datasets."""

  # Featurize qm7 dataset

  print("About to featurize qm7 dataset.")
@@ -178,7 +187,7 @@ def load_qm7(featurizer='CoulombMatrix', split='random', reload=True): 


  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=train_dataset)

          transform_y=True, dataset=train_dataset, move_mean=move_mean)

  ]



  for transformer in transformers:

CRA Git | Maintained and supported by SUSTech CRA and CCSE