Commit d073d041 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Cleanup

parent ed4a3f7c

deepchem/datasets/__init__.py

+0 −40
Original line number Diff line number Diff line
@@ -11,7 +11,6 @@ import multiprocessing as mp 
from functools import partial

from deepchem.utils.save import save_to_disk

from deepchem.utils.save import load_from_disk

#from deepchem.featurizers.featurize import FeaturizedSamples

from deepchem.utils.save import log



__author__ = "Bharath Ramsundar"
@@ -82,15 +81,6 @@ class Dataset(object): 
      assert X.shape[0] == y.shape[0]

      assert y.shape == w.shape

      assert len(ids) == X.shape[0]

    ############################### DEBUG

    #print("Dataset.write_dataframe()")

    #print("X is None, y is None, w is None")

    #print(X is None, y is None, w is None)

    #print("basename, data_dir")

    #print(basename, data_dir)

    #print("os.path.exists(data_dir)")

    #print(os.path.exists(data_dir))

    ############################### DEBUG

    return Dataset.write_data_to_disk(data_dir, basename, tasks, X, y, w, ids)



  @staticmethod
@@ -124,22 +114,8 @@ class Dataset(object): 
    out_w = "%s-w.joblib" % basename

    out_w_transformed = "%s-w-transformed.joblib" % basename

    out_ids = "%s-ids.joblib" % basename

    ############################### DEBUG

    #print("Dataset.write_data_to_disk()")

    #print("X is None, y is None, w is None")

    #print(X is None, y is None, w is None)

    ##import traceback

    ##traceback.print_stack()

    ############################### DEBUG



    if X is not None:

      ############################### DEBUG

      #print("Dataset.write_data_to_disk()")

      #print("basename")

      #print(basename)

      #print("os.path.join(data_dir, out_X)")

      #print(os.path.join(data_dir, out_X))

      ############################### DEBUG

      save_to_disk(X, os.path.join(data_dir, out_X))

      save_to_disk(X, os.path.join(data_dir, out_X_transformed))

      X_sums, X_sum_squares, X_n = compute_sums_and_nb_sample(X)
@@ -147,12 +123,6 @@ class Dataset(object): 
      save_to_disk(X_sum_squares, os.path.join(data_dir, out_X_sum_squares))

      save_to_disk(X_n, os.path.join(data_dir, out_X_n))

    if y is not None:

      ############################### DEBUG

      #print("Dataset.write_data_to_disk()")

      #print("Writing y to")

      #print("os.path.join(data_dir, out_y_transformed)")

      #print(os.path.join(data_dir, out_y_transformed))

      ############################### DEBUG

      save_to_disk(y, os.path.join(data_dir, out_y))

      save_to_disk(y, os.path.join(data_dir, out_y_transformed))

      y_sums, y_sum_squares, y_n = compute_sums_and_nb_sample(y, w)
@@ -321,11 +291,6 @@ class Dataset(object): 
    """

    total = 0

    for _, row in self.metadata_df.iterrows():

      ###################################### DEBUG

      #print("Dataset.__len__()")

      #print("self.data_dir, row['y-transformed']")

      #print(self.data_dir, row['y-transformed'])

      ###################################### DEBUG

      y = load_from_disk(os.path.join(self.data_dir, row['y-transformed']))

      total += len(y)

    return total
@@ -491,11 +456,6 @@ def _df_to_numpy(df, feature_types, tasks): 
      missing[ind, :] = 1

      continue

    tensors.append(features)

  ################################################## DEBUG

  #print("_df_to_numpy")

  #print("tensors, n_samples, feature_types")

  #print(tensors, n_samples, feature_types)

  ################################################## DEBUG

  x = np.stack(tensors)

  sorted_ids = df["mol_id"]

deepchem/datasets/tests/test_datasets.py

+0 −4
Original line number Diff line number Diff line
@@ -30,10 +30,6 @@ class TestBasicDatasetAPI(TestDatasetAPI): 
    assert solubility_dataset.get_task_names() == ["log-solubility"]



    multitask_dataset = self.load_multitask_data()

    ############################################ DEBUG

    print("multitask_dataset.get_task_names()")

    print(multitask_dataset.get_task_names())

    ############################################ DEBUG

    assert sorted(multitask_dataset.get_task_names()) == sorted(["task0",

        "task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8",

        "task9", "task10", "task11", "task12", "task13", "task14", "task15",

deepchem/featurizers/featurize.py

+0 −10
Original line number Diff line number Diff line
@@ -198,11 +198,6 @@ class DataFeaturizer(object): 
      basename = "shard-%d" % j

      metadata_rows.append(write_dataframe_partial((basename, df)))



    ################################################## DEBUG

    print("DataFeaturizer.featurize()")

    #print("data_dir, len(metadata_rows)")

    #print(data_dir, len(metadata_rows))

    ################################################## DEBUG

    dataset = Dataset(data_dir=data_dir,

                      metadata_rows=metadata_rows,

                      reload=reload, verbosity=self.verbosity)
@@ -313,11 +308,6 @@ class DataFeaturizer(object): 
          mol = elem

        if ind % self.log_every_n == 0:

          log("Featurizing sample %d" % ind, self.verbosity)

        ###################################### DEBUG

        #print("DataFeaturizer._featurize_mol")

        #print("mol, self.verbosity")

        #print(mol, self.verbosity)

        ###################################### DEBUG

        features.append(featurizer.featurize([mol], verbosity=self.verbosity))

    else:

      def featurize_wrapper(elem, dilled_featurizer):

deepchem/featurizers/tests/test_featurized_samples.py

+0 −49
Original line number Diff line number Diff line
@@ -26,45 +26,6 @@ class TestFeaturizedSamples(TestAPI): 
  """

  Test Featurized Samples class.

  """

  #def _featurize_train_valid_test_split(self, splittype, input_file, tasks,

  #                                      frac_train, frac_valid, frac_test):

  #  # Featurize input

  #  compound_featurizers = [CircularFingerprint(size=1024)]

  #  complex_featurizers = []

  #  featurizers = compound_featurizers + complex_featurizers



  #  input_file = os.path.join(self.current_dir, input_file)

  #  featurizer = DataFeaturizer(tasks=tasks,

  #                              smiles_field=self.smiles_field,

  #                              compound_featurizers=compound_featurizers,

  #                              complex_featurizers=complex_featurizers,

  #                              verbosity="low")



  #  #Featurizes samples and transforms them into NumPy arrays suitable for ML.

  #  #returns an instance of class FeaturizedSamples()



  #  samples = featurizer.featurize(input_file, self.feature_dir, self.samples_dir)



  #  # Splits featurized samples into train/test

  #  assert splittype in ["random", "specified", "scaffold"]

  #  if splittype == "random":

  #    splitter = RandomSplitter()

  #  elif splittype == "specified":

  #    splitter = SpecifiedSplitter()

  #  elif splittype == "scaffold":

  #    splitter = ScaffoldSplitter()

  #  if frac_valid > 0:

  #    train_samples, valid_samples, test_samples = splitter.train_valid_test_split(

  #        samples, train_dir=self.train_dir, valid_dir=self.valid_dir,

  #        test_dir=self.test_dir, frac_train=frac_train,

  #        frac_valid=frac_valid, frac_test=frac_test)



  #    return train_samples, valid_samples, test_samples

  #  else:

  #    train_samples, test_samples = splitter.train_test_split(

  #        samples, train_dir=self.train_dir, test_dir=self.test_dir,

  #        frac_train=frac_train)

  #    return train_samples, test_samples



  def scaffold_test_train_valid_test_split(self):

    """Test of singletask RF ECFP regression API."""
@@ -168,10 +129,6 @@ class TestFeaturizedSamples(TestAPI): 
    splitter = RandomSplitter()

    train_dataset, test_dataset = splitter.train_test_split(

        dataset, self.train_dir, self.test_dir)

    #train_samples, test_samples = (

    #    self._featurize_train_valid_test_split(

    #        splittype, input_file, tasks, frac_train=.8,

    #        frac_valid=0, frac_test=.2))

    assert len(train_dataset) == 8

    assert len(test_dataset) == 2
@@ -180,12 +137,6 @@ class TestFeaturizedSamples(TestAPI): 
    verbosity = "high"

    data_dir = os.path.join(self.base_dir, "data")

    moved_data_dir = os.path.join(self.base_dir, "moved_data")

    ############################################## DEBUG

    print("data_dir")

    print(data_dir)

    print("moved_data_dir")

    print(moved_data_dir)

    ############################################## DEBUG

    dataset_file = os.path.join(

        self.current_dir, "example.csv")

deepchem/models/__init__.py

+0 −32
Original line number Diff line number Diff line
@@ -162,46 +162,14 @@ class Model(object): 
    for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches(batch_size):

      y_pred_batch = self.predict_proba_on_batch(X_batch)

      batch_size = len(y_batch)

      ######################################################### DEBUG

      #print("Model.predict_proba()")

      #print("y_pred_batch.shape")

      #print(y_pred_batch.shape)

      ######################################################### DEBUG

      #y_pred_batch = np.squeeze(

      #    np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes)))

      y_pred_batch = np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes))

      ######################################################### DEBUG

      #print("reshape")

      #print("y_pred_batch.shape")

      #print(y_pred_batch.shape)

      ######################################################### DEBUG

      y_pred_batch = undo_transforms(y_pred_batch, transformers)

      ######################################################### DEBUG

      #print("untransformed")

      #print("y_pred_batch.shape")

      #print(y_pred_batch.shape)

      ######################################################### DEBUG

      y_preds.append(y_pred_batch)

    ######################################################### DEBUG

    #print("[y_pred.shape for y_pred in y_preds]")

    #print([y_pred.shape for y_pred in y_preds])

    ######################################################### DEBUG

    y_pred = np.vstack(y_preds)

    ######################################################### DEBUG

    #print("y_pred.shape")

    #print(y_pred.shape)

    ######################################################### DEBUG

    # The iterbatches does padding with zero-weight examples on the last batch.

    # Remove padded examples.

    n_samples, n_tasks = len(dataset), len(self.tasks)

    y_pred = y_pred[:n_samples]

    ######################################################### DEBUG

    #print("Model.predict_proba()")

    #print("n_samples, y_pred.shape, y_batch.shape")

    #print(n_samples, y_pred.shape, y_batch.shape)

    #print("(n_samples, n_tasks, n_classes)")

    #print((n_samples, n_tasks, n_classes))

    ######################################################### DEBUG

    y_pred = np.reshape(y_pred, (n_samples, n_tasks, n_classes))

    return y_pred

CRA Git | Maintained and supported by SUSTech CRA and CCSE