Commit d1248a68 authored by alat-rights's avatar alat-rights
Browse files

yapf/flake8/mypy

parent 5b5ba9c2

deepchem/data/data_loader.py

+23 −23
Original line number Diff line number Diff line
@@ -488,8 +488,8 @@ class UserCSVLoader(CSVLoader): 
    shard[feature_fields] = shard[feature_fields].apply(pd.to_numeric)

    X_shard = shard[feature_fields].to_numpy()

    time2 = time.time()

    logger.info("TIMING: user specified processing took %0.3f s" %

                (time2 - time1))

    logger.info(

        "TIMING: user specified processing took %0.3f s" % (time2 - time1))

    return (X_shard, np.ones(len(X_shard), dtype=bool))
@@ -831,7 +831,8 @@ class SDFLoader(DataLoader): 
    Iterator[pd.DataFrame]

      Iterator over shards

    """

    return load_sdf_files(input_files=input_files,

    return load_sdf_files(

        input_files=input_files,

        clean_mols=self.sanitize,

        tasks=self.tasks,

        shard_size=shard_size)
@@ -914,9 +915,9 @@ class FASTALoader(DataLoader): 
      Keep False if your FASTA file already includes [CLS] and [SEP] annotations.

   """

    charsets = {

        "protein": ('A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L',

                    'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',

                    'Y', 'Z', '*', '-'),

        "protein":

        ('A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N',

         'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '*', '-'),

        "nucleic": ('A', 'C', 'G', 'T', 'U', '(i)', 'R', 'Y', 'K', 'M', 'S',

                    'W', 'B', 'D', 'H', 'V', 'N', '-'),

        "ATCGN": ('A', 'T', 'C', 'G'),
@@ -944,8 +945,8 @@ class FASTALoader(DataLoader): 
    # Initialize featurizer

    try:

      if self.charset is not None and self.max_length != -1:

        featurizer = featurizer(charset=self.charset,

                                max_length=self.max_length)

        featurizer = featurizer(

            charset=self.charset, max_length=self.max_length)

      elif self.charset is not None and self.max_length == -1:

        featurizer = featurizer(charset=self.charset)

      elif self.charset is None and self.max_length != -1:
@@ -1153,12 +1154,11 @@ class ImageLoader(DataLoader): 


    if in_memory:

      if data_dir is None:

        return NumpyDataset(load_image_files(image_files),

                            y=labels,

                            w=weights,

                            ids=image_files)

        return NumpyDataset(

            load_image_files(image_files), y=labels, w=weights, ids=image_files)

      else:

        dataset = DiskDataset.from_numpy(load_image_files(image_files),

        dataset = DiskDataset.from_numpy(

            load_image_files(image_files),

            y=labels,

            w=weights,

            ids=image_files,
@@ -1307,8 +1307,8 @@ class InMemoryLoader(DataLoader): 


  # FIXME: Signature of "_featurize_shard" incompatible with supertype "DataLoader"

  def _featurize_shard(  # type: ignore[override]

      self, shard: List, global_index: int) -> Tuple[np.ndarray, np.ndarray,

                                                     np.ndarray, np.ndarray]:

      self, shard: List, global_index: int

  ) -> Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:

    """Featurizes a shard of an input data.



    Parameters

deepchem/data/tests/test_data_loader.py

+16 −21
Original line number Diff line number Diff line
@@ -12,9 +12,8 @@ def test_unlabelled(): 
  current_dir = os.path.dirname(os.path.abspath(__file__))

  input_file = os.path.join(current_dir, "../../data/tests/no_labels.csv")

  featurizer = dc.feat.CircularFingerprint(size=1024)

  loader = dc.data.CSVLoader(tasks=[],

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=[], feature_field="smiles", featurizer=featurizer)

  dataset = loader.create_dataset(input_file)

  assert len(dataset.X)
@@ -27,9 +26,8 @@ def test_scaffold_test_train_valid_test_split(): 
  featurizer = dc.feat.CircularFingerprint(size=1024)



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

  loader = dc.data.CSVLoader(tasks=tasks,

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=tasks, feature_field="smiles", featurizer=featurizer)



  dataset = loader.create_dataset(input_file)
@@ -50,9 +48,8 @@ def test_scaffold_test_train_test_split(): 
  featurizer = dc.feat.CircularFingerprint(size=1024)



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

  loader = dc.data.CSVLoader(tasks=tasks,

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=tasks, feature_field="smiles", featurizer=featurizer)



  dataset = loader.create_dataset(input_file)
@@ -71,9 +68,8 @@ def test_random_test_train_valid_test_split(): 
  featurizer = dc.feat.CircularFingerprint(size=1024)



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

  loader = dc.data.CSVLoader(tasks=tasks,

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=tasks, feature_field="smiles", featurizer=featurizer)



  dataset = loader.create_dataset(input_file)
@@ -92,9 +88,8 @@ def test_random_test_train_test_split(): 
  tasks = ["log-solubility"]

  input_file = os.path.join(current_dir, "../../models/tests/example.csv")

  featurizer = dc.feat.CircularFingerprint(size=1024)

  loader = dc.data.CSVLoader(tasks=tasks,

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=tasks, feature_field="smiles", featurizer=featurizer)



  dataset = loader.create_dataset(input_file)
@@ -112,7 +107,8 @@ def test_log_solubility_dataset(): 
  input_file = os.path.join(current_dir, input_file)



  tasks = ["log-solubility"]

  loader = dc.data.CSVLoader(tasks=tasks,

  loader = dc.data.CSVLoader(

      tasks=tasks,

      feature_field="smiles",

      featurizer=dc.feat.CircularFingerprint(size=1024))

  dataset = loader.create_dataset(input_file)
@@ -130,9 +126,8 @@ def test_dataset_move(): 


  featurizer = dc.feat.CircularFingerprint(size=1024)

  tasks = ["log-solubility"]

  loader = dc.data.CSVLoader(tasks=tasks,

                             feature_field="smiles",

                             featurizer=featurizer)

  loader = dc.data.CSVLoader(

      tasks=tasks, feature_field="smiles", featurizer=featurizer)

  featurized_dataset = loader.create_dataset(dataset_file, data_dir)

  n_dataset = len(featurized_dataset)

deepchem/feat/molecule_featurizers/one_hot_featurizer.py

+1 −2
Original line number Diff line number Diff line
@@ -53,8 +53,7 @@ class OneHotFeaturizer(Featurizer): 
    else:

      self.max_length = None



  def featurize(self,

                datapoints: Iterable[Any],

  def featurize(self, datapoints: Iterable[Any],

                log_every_n: int = 1000) -> np.ndarray:

    """Featurize strings or mols.

deepchem/data/tests/test_fasta_loader.py

+1 −1

File changed.

Contains only whitespace changes.

CRA Git | Maintained and supported by SUSTech CRA and CCSE