Cruft cleanup (588901e2) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+0 −30

Original line number	Diff line number	Diff line
		@@ -211,13 +211,6 @@ class Dataset(object):
		if tasks is None:
		tasks = np.arange(n_tasks)
		raw_data = (ids, X, y, w)
		################### DEBUG
		#print("Dataset.from_numpy()")
		#print("type(y)")
		#print(type(y))
		#print("type(X)")
		#print(type(X))
		################### DEBUG
		return Dataset(data_dir=data_dir, tasks=tasks, raw_data=raw_data)

		def to_numpy(self):
		@@ -338,13 +331,6 @@ def write_dataset_single(val, data_dir, feature_types=None, tasks=None,
		ids, X, y, w = _df_to_numpy(df, feature_types, tasks)
		else:
		ids, X, y, w = raw_data
		################### DEBUG
		#print("write_dataset_single()")
		#print("type(y)")
		#print(type(y))
		#print("type(X)")
		#print(type(X))
		################### DEBUG
		df_file = ""
		assert X.shape[0] == y.shape[0]
		assert y.shape == w.shape
		@@ -399,22 +385,6 @@ def _df_to_numpy(df, feature_types, tasks):
		n_samples = df.shape[0]
		n_tasks = len(tasks)
		y = np.hstack([np.reshape(np.array(df[task].values), (n_samples, 1)) for task in tasks])
		############ DEBUG
		#print("Dataset._df_to_numpy()")
		#print("tasks")
		#print(tasks)
		#print("y.shape")
		#print(y.shape)
		#print("Before reshape")
		#print("y")
		#print(y)
		########### DEBUG
		#y = np.reshape(y, (n_samples, n_tasks))
		############ DEBUG
		#print("After reshape")
		#print("y")
		#print(y)
		############ DEBUG
		w = np.ones((n_samples, n_tasks))
		missing = np.zeros_like(y).astype(int)
		tensors = []

+0 −4

Original line number	Diff line number	Diff line
		@@ -113,18 +113,14 @@ class TestLoad(TestAPI):

		################## Do comparison
		for ind, task in enumerate(tasks):
		#X_multi_task = X_multi[ind]
		y_multi_task = y_multi[:, ind]
		w_multi_task = w_multi[:, ind]
		#ids_multi_task = ids_multi[ind]

		#X_task = X_tasks[ind]
		y_task = y_tasks[ind]
		w_task = w_tasks[ind]
		ids_task = ids_tasks[ind]

		#np.testing.assert_allclose(X_multi_task, X_task)
		np.testing.assert_allclose(y_multi_task.flatten(), y_task.flatten())
		np.testing.assert_allclose(w_multi_task.flatten(), w_task.flatten())
		#np.testing.assert_allclose(ids_multi_task, ids_task)
		shutil.rmtree(base_dir)

+0 −10

Original line number	Diff line number	Diff line
		@@ -155,11 +155,6 @@ class Model(object):
		n_samples, n_tasks = len(dataset), len(self.tasks)
		y_pred = y_pred[:n_samples]
		y_pred = np.reshape(y_pred, (n_samples, n_tasks))
		############## DEBUG
		#print("Model.predict()")
		#print("y_pred.shape")
		#print(y_pred.shape)
		############## DEBUG
		return y_pred

		def predict_proba(self, dataset, transformers=[], n_classes=2):
		@@ -174,11 +169,6 @@ class Model(object):
		n_tasks = len(self.tasks)
		for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches(batch_size):
		y_pred_batch = self.predict_proba_on_batch(X_batch)
		########################## DEBUG
		#print("Model.predict_proba()")
		#print("y_pred_batch.shape")
		#print(y_pred_batch.shape)
		########################## DEBUG
		batch_size = len(y_batch)
		y_pred_batch = np.squeeze(
		np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes)))

+0 −5

Original line number	Diff line number	Diff line
		@@ -42,11 +42,6 @@ class SklearnModel(Model):
		Fits SKLearn model to data.
		"""
		X, y, w, _ = dataset.to_numpy()
		###################### DEBUG
		#print("SklearnModel.fit()")
		#print("X.shape, y.shape, w.shape")
		#print(X.shape, y.shape, w.shape)
		###################### DEBUG
		y, w = np.squeeze(y), np.squeeze(w)
		# Logistic regression doesn't support weights
		if not isinstance(self.raw_model, LogisticRegression):