Commit da3a13ca authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Potential fix to leakage bug

parent d00f63c7

deepchem/datasets/__init__.py

+11 −0
Original line number Diff line number Diff line
@@ -403,6 +403,17 @@ def _df_to_numpy(df, feature_types, tasks): 
      feature_list.append(datapoint[feature_type])

    try:

      features = np.squeeze(np.concatenate(feature_list))

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

      #print("features.size: %s" % str(features.size))

      #print("features.size == 0")

      #print(features.size == 0)

      if features.size == 0:

        #print("CONTINUING")

        features = np.zeros(feature_shape)

        tensors.append(features)

        missing[ind, :] = 1

        continue

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

      for feature_ind, val in enumerate(features):

        if features[feature_ind] == "":

          features[feature_ind] = 0.

deepchem/featurizers/featurize.py

+8 −0
Original line number Diff line number Diff line
@@ -257,6 +257,14 @@ class DataFeaturizer(object): 
        if ind % self.log_every_n == 0:

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

        mol = Chem.MolFromSmiles(smiles)

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

        if mol is None:

          #print("RDKit loading failed at %s" % smiles)

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

          #print("featurizer returned %s" % str(output))

          #print("type(output)")

          #print(type(output))

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

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

    else:

      def featurize_wrapper(smiles, dilled_featurizer):

CRA Git | Maintained and supported by SUSTech CRA and CCSE