Debugging of multitask (241ce853) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+15 −1

Original line number	Diff line number	Diff line
		@@ -199,7 +199,21 @@ class Dataset(object):
		yield (X_batch, y_batch, w_batch, ids_batch)

		@staticmethod
		def from_numpy(data_dir, tasks, X, y, w, ids):
		def from_numpy(data_dir, X, y, w=None, ids=None, tasks=None):
		n_samples = len(X)
		# The -1 indicates that y will be reshaped to have length -1
		y = np.reshape(y, (n_samples, -1))
		n_tasks = y.shape[1]
		if ids is None:
		ids = np.arange(n_samples)
		if w is None:
		w = np.ones_like(y)
		if tasks is None:
		tasks = np.arange(n_tasks)
		########### DEBUG
		#print("ids.shape, X.shape, y.shape, w.shape")
		#print(ids.shape, X.shape, y.shape, w.shape)
		########### DEBUG
		raw_data = (ids, X, y, w)
		return Dataset(data_dir=data_dir, tasks=tasks, raw_data=raw_data)

deepchem/hyperparameters/tests/test_hyperparam_opt.py

+6 −4

Original line number	Diff line number	Diff line
		@@ -94,8 +94,9 @@ class TestHyperparamOptAPI(TestAPI):
		y_train = np.random.randint(2, size=(n_train, n_tasks))
		w_train = np.ones_like(y_train)
		ids_train = ["C"] * n_train
		train_dataset = Dataset.from_numpy(self.train_dir, tasks,
		X_train, y_train, w_train, ids_train)
		train_dataset = Dataset.from_numpy(self.train_dir,
		X_train, y_train, w_train, ids_train,
		tasks)

		# Define validation dataset
		n_valid = 10
		@@ -103,8 +104,9 @@ class TestHyperparamOptAPI(TestAPI):
		y_valid = np.random.randint(2, size=(n_valid, n_tasks))
		w_valid = np.ones_like(y_valid)
		ids_valid = ["C"] * n_valid
		valid_dataset = Dataset.from_numpy(self.valid_dir, tasks,
		X_valid, y_valid, w_valid, ids_valid)
		valid_dataset = Dataset.from_numpy(self.valid_dir,
		X_valid, y_valid, w_valid, ids_valid,
		tasks)
		params_dict = {
		"batch_size": [32],
		"data_shape": [train_dataset.get_data_shape()],

deepchem/metrics/init.py

+20 −2

Original line number	Diff line number	Diff line
		@@ -123,7 +123,7 @@ class Metric(object):
		assert mode in ["classification", "regression"]
		self.mode = mode

		def compute_metric(self, y_true, y_pred, w, n_classes=2):
		def compute_metric(self, y_true, y_pred, w=None, n_classes=2):
		"""Compute a performance metric for each task.

		Args:
		@@ -134,12 +134,25 @@ class Metric(object):
		Returns:
		A numpy array containing metric values for each task.
		"""
		#n_samples = len(y_true)
		#y_true = np.reshape(y_true, (n_samples, -1))
		#y_pred = np.reshape(y_pred, (n_samples, -1))
		############### DEBUG
		#print("Metric.compute_metric()")
		#print("y_true.shape, y_pred.shape, w.shape")
		#print(y_true.shape, y_pred.shape, w.shape)
		#print("r2_score(y_true, y_pred)")
		#print(r2_score(y_true, y_pred))
		############### DEBUG
		assert y_true.shape[0] == y_pred.shape[0] == w.shape[0]
		n_samples, n_tasks = y_true.shape[0], y_true.shape[1]
		if self.mode == "classification":
		y_pred = np.reshape(y_pred, (n_samples, n_tasks, n_classes))
		else:
		y_pred = np.reshape(y_pred, (n_samples, n_tasks))
		#y_true = np.reshape(y_true, (n_samples, n_tasks, n_classes))
		if w is None:
		w = np.ones_like(y_true)
		computed_metrics = []
		for task in xrange(n_tasks):
		y_task = y_true[:, task]
		@@ -149,6 +162,11 @@ class Metric(object):
		y_pred_task = y_pred[:, task, :]
		w_task = w[:, task]

		############################## DEBUG
		print("Metric.compute_metric()")
		print("y_task.shape, y_pred_task.shape, w_task.shape")
		print(y_task.shape, y_pred_task.shape, w_task.shape)
		############################## DEBUG
		metric_value = self.compute_singletask_metric(
		y_task, y_pred_task, w_task)
		computed_metrics.append(metric_value)
		@@ -183,8 +201,8 @@ class Metric(object):
		# If there are no nonzero examples, metric is ill-defined.
		if not y_true.size:
		return np.nan
		y_true = np.reshape(y_true, (n_samples,))

		y_true = np.reshape(y_true, (n_samples,))
		if self.mode == "classification":
		n_classes = y_pred.shape[-1]
		# TODO(rbharath): This has been a major source of bugs. Is there a more

deepchem/metrics/tests/metrics_test.py

+14 −2

Original line number	Diff line number	Diff line
		@@ -17,10 +17,10 @@


		import numpy as np

		from tensorflow.python.platform import googletest

		from deepchem.metrics import kappa_score
		from deepchem.metrics import Metric
		from deepchem import metrics


		class MetricsTest(googletest.TestCase):
		@@ -35,5 +35,17 @@ class MetricsTest(googletest.TestCase):
		1.0 - expected_agreement)
		self.assertAlmostEquals(kappa, expected_kappa)

		def test_r2_score(self):
		"""Test that R^2 metric passes basic sanity tests"""
		verbosity = "high"
		np.random.seed(123)
		n_samples = 10
		y_true = np.random.rand(n_samples,)
		y_pred = np.random.rand(n_samples,)
		regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
		assert np.isclose(metrics.r2_score(y_true, y_pred),
		regression_metric.compute_metric(y_true, y_pred))


		if __name__ == '__main__':
		googletest.main()

deepchem/models/init.py

+10 −0

Original line number	Diff line number	Diff line
		@@ -155,6 +155,11 @@ 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):
		@@ -169,6 +174,11 @@ 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)))

Admin message