Removed redundant and deprecated function calls from examples (e7d8d204) · Commits · 钟慕尧 / deepchem

examples/kaggle/KAGGLE_rf_model.py

+1 −2

Original line number	Diff line number	Diff line
		@@ -16,10 +16,9 @@ from kaggle_datasets import load_kaggle
		###Load data###
		np.random.seed(123)
		shard_size = 2000
		num_shards_per_batch = 4
		print("About to load KAGGLE data.")
		KAGGLE_tasks, datasets, transformers = load_kaggle(
		shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)
		shard_size=shard_size)
		train_dataset, valid_dataset, test_dataset = datasets

		print("Number of compounds in train set")

+1 −2

Original line number	Diff line number	Diff line
		@@ -18,10 +18,9 @@ np.random.seed(123)

		###Load data###
		shard_size = 2000
		num_shards_per_batch = 4
		print("About to load MERCK data.")
		KAGGLE_tasks, datasets, transformers = load_kaggle(
		shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)
		shard_size=shard_size)
		train_dataset, valid_dataset, test_dataset = datasets

		print("KAGGLE_tasks")

+1 −14

Original line number	Diff line number	Diff line
		@@ -17,33 +17,20 @@ from deepchem import metrics
		from deepchem.metrics import Metric
		from deepchem.models.sklearn_models import SklearnModel
		from deepchem.utils.evaluate import Evaluator
		from deepchem.splits import RandomSplitter

		np.random.seed(123)

		# Set some global variables up top

		reload = True
		verbosity = "high"
		force_transform = False

		base_dir = "/tmp/nci_rf"
		train_dir = os.path.join(base_dir, "train_dataset")
		valid_dir = os.path.join(base_dir, "valid_dataset")
		test_dir = os.path.join(base_dir, "test_dataset")
		model_dir = os.path.join(base_dir, "model")
		if os.path.exists(base_dir):
		shutil.rmtree(base_dir)
		os.makedirs(base_dir)

		nci_tasks, nci_dataset, transformers = load_nci(
		base_dir, reload=reload, force_transform=force_transform)

		print("About to perform train/valid/test split.")
		splitter = RandomSplitter(verbosity=verbosity)
		print("Performing new split.")
		train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
		nci_dataset, train_dir, valid_dir, test_dir)
		base_dir)

		classification_metric = Metric(metrics.roc_auc_score, np.mean,
		verbosity=verbosity,