Add prediction printing back in. (d92ea751) · Commits · 钟慕尧 / deepchem

deepchem/datasets/init.py

+9 −0

Original line number	Diff line number	Diff line
		@@ -222,6 +222,15 @@ class Dataset(object):
		return (np.vstack(Xs), np.vstack(ys), np.vstack(ws),
		np.concatenate(ids))

		def get_ids(self):
		"""
		Returns all molecule-ids for this dataset.
		"""
		ids = []
		for (_, _, _, ids_b) in self.itershards():
		ids.append(np.atleast_1d(np.squeeze(ids_b)))
		return np.concatenate(ids)

		def get_labels(self):
		"""
		Returns all labels for this dataset.

+9 −0

Original line number	Diff line number	Diff line
		@@ -75,6 +75,15 @@ class TestBasicDatasetAPI(TestDatasetAPI):
		assert w.shape == (N_samples, N_tasks)
		assert ids.shape == (N_samples,)

		def test_consistent_ordering(self):
		"""Test that ordering of labels is consistent over time."""
		solubility_dataset = self._load_solubility_data()

		ids1 = solubility_dataset.get_ids()
		ids2 = solubility_dataset.get_ids()

		assert np.array_equal(ids1, ids2)

		def test_get_statistics(self):
		"""Test statistics computation of this dataset."""
		solubility_dataset = self._load_solubility_data()

+1 −1

Original line number	Diff line number	Diff line
		@@ -77,7 +77,7 @@ class HyperparamOpt(object):

		evaluator = Evaluator(model, valid_dataset, output_transformers)
		multitask_scores = evaluator.compute_model_performance(
		[metric], valid_csv_out, valid_stats_out)
		[metric], valid_csv_out.name, valid_stats_out)
		valid_score = multitask_scores[metric.name]
		all_scores[hyperparameter_tuple] = valid_score

+2 −2

Original line number	Diff line number	Diff line
		@@ -80,14 +80,14 @@ class TestAPI(unittest.TestCase):
		with tempfile.NamedTemporaryFile() as train_csv_out:
		with tempfile.NamedTemporaryFile() as train_stats_out:
		_ = evaluator.compute_model_performance(
		metrics, train_csv_out, train_stats_out)
		metrics, train_csv_out.name, train_stats_out)

		# Eval model on test
		evaluator = Evaluator(model, test_dataset, transformers, verbosity=True)
		with tempfile.NamedTemporaryFile() as test_csv_out:
		with tempfile.NamedTemporaryFile() as test_stats_out:
		_ = evaluator.compute_model_performance(
		metrics, test_csv_out, test_stats_out)
		metrics, test_csv_out.name, test_stats_out)

		def _featurize_train_test_split(self, splittype, compound_featurizers,
		complex_featurizers,

+23 −3

Original line number	Diff line number	Diff line
		@@ -5,6 +5,7 @@ from __future__ import print_function
		from __future__ import division
		from __future__ import unicode_literals

		import csv
		import numpy as np
		import warnings
		from deepchem.utils.save import log
		@@ -38,7 +39,24 @@ class Evaluator(object):
		self.task_type = model.get_task_type().lower()
		self.verbosity = verbosity

		def compute_model_performance(self, metrics, csv_out, stats_file, threshold=None):
		def output_predictions(self, y_preds, csv_out):
		"""
		Writes predictions to file.

		Args:
		y_preds: np.ndarray
		csvfile: Open file object.
		"""
		mol_ids = self.dataset.get_ids()
		assert len(y_preds) == len(mol_ids)
		with open(csv_out, "wb") as csvfile:
		csvwriter = csv.writer(csvfile)
		csvwriter.writerow(["Compound"] + self.dataset.get_task_names())
		for mol_id, y_pred in zip(mol_ids, y_preds):
		csvwriter.writerow([mol_id] + list(y_pred))

		def compute_model_performance(self, metrics, csv_out=None, stats_file=None,
		threshold=None):
		"""
		Computes statistics of model on test data and saves results to csv.
		"""
		@@ -47,8 +65,10 @@ class Evaluator(object):
		y_pred = self.model.predict(self.dataset, self.transformers)
		multitask_scores = {}

		print("y.shape, y_pred.shape")
		print(y.shape, y_pred.shape)
		if csv_out is not None:
		log("Saving predictions to %s" % csv_out, self.verbosity)
		self.output_predictions(y_pred, csv_out)

		# Compute multitask metrics
		for metric in metrics:
		multitask_scores[metric.name] = metric.compute_metric(y, y_pred, w)