Commit 2246d0a7 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Fixes to multitask data loading.

parent b9b21c60

deepchem/datasets/tests/test_reload.py

+8 −0
Original line number Diff line number Diff line
@@ -72,6 +72,14 @@ class TestReload(TestAPI): 
    # TODO(rbharath): Transformers don't play nice with reload! Namely,

    # reloading will cause the transform to be reapplied. This is undesirable in

    # almost all cases. Need to understand a method to fix this.

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

    

    print("_run_muv_experiment()")

    print("train_dataset.get_labels()")

    print(train_dataset.get_labels())

    print("train_dataset.get_weights()")

    print(train_dataset.get_weights())

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

    transformers = [

        BalancingTransformer(transform_w=True, dataset=train_dataset)]

    print("Transforming datasets")

deepchem/featurizers/featurize.py

+3 −1
Original line number Diff line number Diff line
@@ -71,7 +71,9 @@ def _load_sdf_file(input_file): 
def _load_csv_file(filename, shard_size=None):

  """Load data as pandas dataframe."""

  # First line of user-specified CSV *must* be header.

  return pd.read_csv(filename, header=0, chunksize=shard_size)

  for df in pd.read_csv(filename, header=0, chunksize=shard_size):

    df = df.replace(np.nan, str(""), regex=True)

    yield df



def _get_input_type(input_file):

  """Get type of input file. Must be csv/pkl.gz/sdf file."""

CRA Git | Maintained and supported by SUSTech CRA and CCSE