Changes

deepchem/data/datasets.py

@@ -1051,7 +1051,6 @@ def __init__(self, data_dir: str) -> None:
       Location on disk of an existing `DiskDataset`.
     """
     self.data_dir = data_dir
-    self.legacy_metadata = legacy_metadata
 
     logger.info("Loading dataset from disk.")
     self.tasks, self.metadata_df = self.load_metadata()
@@ -1114,7 +1113,7 @@ def create_dataset(shard_generator: Iterable[Batch],
     DiskDataset._save_metadata(tasks, metadata_df, data_dir)
     time2 = time.time()
     logger.info("TIMING: dataset construction took %0.3f s" % (time2 - time1))
-    return DiskDataset(data_dir, legacy_metadata)
+    return DiskDataset(data_dir)
 
   def load_metadata(self) -> Tuple[List[str], pd.DataFrame]:
     """Helper method that loads metadata from disk."""
@@ -2193,23 +2192,23 @@ def get_shape(self) -> Tuple[Shape, Shape, Shape, Shape]:
       for shard_num in range(n_rows):
         row = self.metadata_df.iloc[shard_num]
         if row['X_shape'] is not None:
-          shard_X_shape = make_tuple(row['X_shape'])
+          shard_X_shape = make_tuple(str(row['X_shape']))
         else:
           shard_X_shape = tuple()
         if n_tasks > 0:
           if row['y_shape'] is not None:
-            shard_y_shape = make_tuple(row['y_shape'])
+            shard_y_shape = make_tuple(str(row['y_shape']))
           else:
             shard_y_shape = tuple()
           if row['w_shape'] is not None:
-            shard_w_shape = make_tuple(row['w_shape'])
+            shard_w_shape = make_tuple(str(row['w_shape']))
           else:
             shard_w_shape = tuple()
         else:
           shard_y_shape = tuple()
           shard_w_shape = tuple()
         if row['ids_shape'] is not None:
-          shard_ids_shape = make_tuple(row['ids_shape'])
+          shard_ids_shape = make_tuple(str(row['ids_shape']))
         else:
           shard_ids_shape = tuple()
         if shard_num == 0:

deepchem/models/tests/test_generalize.py

@@ -122,63 +122,65 @@ def model_builder(model_dir):
   assert score > .5
 
 
-#def test_sklearn_classification():
-#  """Test that sklearn models can learn on simple classification datasets."""
-#  np.random.seed(123)
-#  dataset = sklearn.datasets.load_digits(n_class=2)
-#  X, y = dataset.data, dataset.target
-
-#  frac_train = .7
-#  n_samples = len(X)
-#  n_train = int(frac_train*n_samples)
-#  X_train, y_train = X[:n_train], y[:n_train]
-#  X_test, y_test = X[n_train:], y[n_train:]
-#  train_dataset = dc.data.NumpyDataset(X_train, y_train)
-#  test_dataset = dc.data.NumpyDataset(X_test, y_test)
-
-#  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
-#  sklearn_model = LogisticRegression()
-#  model = dc.models.SklearnModel(sklearn_model)
-
-#  # Fit trained model
-#  model.fit(train_dataset)
-#  model.save()
-
-#  # Eval model on test
-#  scores = model.evaluate(test_dataset, [classification_metric])
-#  assert scores[classification_metric.name] > .5
-
-#def test_sklearn_multitask_classification():
-#  """Test that sklearn models can learn on simple multitask classification."""
-#  np.random.seed(123)
-#  n_tasks = 4
-#  tasks = range(n_tasks)
-#  dataset = sklearn.datasets.load_digits(n_class=2)
-#  X, y = dataset.data, dataset.target
-#  y = np.reshape(y, (len(y), 1))
-#  y = np.hstack([y] * n_tasks)
-#
-#  frac_train = .7
-#  n_samples = len(X)
-#  n_train = int(frac_train*n_samples)
-#  X_train, y_train = X[:n_train], y[:n_train]
-#  X_test, y_test = X[n_train:], y[n_train:]
-#  train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train)
-#  test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test)
-
-#  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
-#  def model_builder(model_dir):
-#    sklearn_model = LogisticRegression()
-#    return dc.models.SklearnModel(sklearn_model, model_dir)
-#  model = dc.models.SingletaskToMultitask(tasks, model_builder)
-
-#  # Fit trained model
-#  model.fit(train_dataset)
-#  model.save()
-#  # Eval model on test
-#  scores = model.evaluate(test_dataset, [classification_metric])
-#  for score in scores[classification_metric.name]:
-#    assert score > .5
+def test_sklearn_classification():
+  """Test that sklearn models can learn on simple classification datasets."""
+  np.random.seed(123)
+  dataset = sklearn.datasets.load_digits(n_class=2)
+  X, y = dataset.data, dataset.target
+
+  frac_train = .7
+  n_samples = len(X)
+  n_train = int(frac_train * n_samples)
+  X_train, y_train = X[:n_train], y[:n_train]
+  X_test, y_test = X[n_train:], y[n_train:]
+  train_dataset = dc.data.NumpyDataset(X_train, y_train)
+  test_dataset = dc.data.NumpyDataset(X_test, y_test)
+
+  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
+  sklearn_model = LogisticRegression()
+  model = dc.models.SklearnModel(sklearn_model)
+
+  # Fit trained model
+  model.fit(train_dataset)
+  model.save()
+
+  # Eval model on test
+  scores = model.evaluate(test_dataset, [classification_metric])
+  assert scores[classification_metric.name] > .5
+
+
+def test_sklearn_multitask_classification():
+  """Test that sklearn models can learn on simple multitask classification."""
+  np.random.seed(123)
+  n_tasks = 4
+  tasks = range(n_tasks)
+  dataset = sklearn.datasets.load_digits(n_class=2)
+  X, y = dataset.data, dataset.target
+  y = np.reshape(y, (len(y), 1))
+  y = np.hstack([y] * n_tasks)
+
+  frac_train = .7
+  n_samples = len(X)
+  n_train = int(frac_train * n_samples)
+  X_train, y_train = X[:n_train], y[:n_train]
+  X_test, y_test = X[n_train:], y[n_train:]
+  train_dataset = dc.data.DiskDataset.from_numpy(X_train, y_train)
+  test_dataset = dc.data.DiskDataset.from_numpy(X_test, y_test)
+
+  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
+
+  def model_builder(model_dir):
+    sklearn_model = LogisticRegression()
+    return dc.models.SklearnModel(sklearn_model, model_dir)
+
+  model = dc.models.SingletaskToMultitask(tasks, model_builder)
+
+  # Fit trained model
+  model.fit(train_dataset)
+  model.save()
+  # Eval model on test
+  scores = model.evaluate(test_dataset, [classification_metric])
+  assert scores['roc_auc_score'] > 0.5
 
 
 def test_xgboost_regression():