Basic tests for HyperparamOpt class (0d704cdd) · Commits · 钟慕尧 / deepchem

deepchem/hyperparameters/init.py

+9 −7

Original line number	Diff line number	Diff line
		@@ -14,13 +14,15 @@ class HyperparamOpt(object):
		Provides simple hyperparameter search capabilities.
		"""

		def __init__(self, model_class, task_types):
		def __init__(self, model_class, task_types, verbosity=None):
		self.model_class = model_class
		self.task_types = task_types
		assert verbosity in [None, "low", "high"]
		self.verbosity = verbosity

		def hyperparam_search(self, params_dict, train_dataset, valid_dataset,
		output_transformers, metric, use_max=True,
		verbosity=None, logdir=None):
		logdir=None):
		"""Perform hyperparams search according to params_dict.

		Each key to hyperparams_dict is a model_param. The values should be a list
		@@ -55,8 +57,8 @@ class HyperparamOpt(object):

		evaluator = Evaluator(model, valid_dataset, output_transformers)
		df, score = evaluator.compute_model_performance(
		valid_csv_out, valid_stats_out)
		valid_score = score.iloc[0][metric]
		[metric], valid_csv_out, valid_stats_out)
		valid_score = score.iloc[0][metric.name]
		all_scores[hyperparameter_tuple] = valid_score

		if (use_max and valid_score > best_validation_score) or (
		@@ -71,15 +73,15 @@ class HyperparamOpt(object):
		shutil.rmtree(model_dir)

		print("Model %d/%d, Metric %s, Validation set %s: %f" %
		(ind, number_combinations, metric, ind, valid_score))
		(ind, number_combinations, metric.name, ind, valid_score))
		print("\tbest_validation_score so far: %f" % best_validation_score)

		train_csv_out = tempfile.NamedTemporaryFile()
		train_stats_out = tempfile.NamedTemporaryFile()
		train_evaluator = Evaluator(best_model, train_dataset, output_transformers)
		train_df, train_score = train_evaluator.compute_model_performance(
		train_csv_out, train_stats_out)
		train_score = train_score.iloc[0][metric]
		[metric], train_csv_out, train_stats_out)
		train_score = train_score.iloc[0][metric.name]
		print("Best hyperparameters: %s" % str(zip(hyperparams, best_hyperparams)))
		print("train_score: %f" % train_score)
		print("validation_score: %f" % best_validation_score)

deepchem/models/test/init.py

+9 −0

Original line number	Diff line number	Diff line
		@@ -26,6 +26,7 @@ from deepchem.models.sklearn_models import SklearnModel
		from deepchem.transformers import NormalizationTransformer
		from deepchem.transformers import LogTransformer
		from deepchem.transformers import ClippingTransformer
		from deepchem.hyperparameters import HyperparamOpt
		from sklearn.ensemble import RandomForestRegressor

		class TestAPI(unittest.TestCase):
		@@ -52,6 +53,14 @@ class TestAPI(unittest.TestCase):
		# debug.
		#shutil.rmtree(self.model_dir)

		def _hyperparam_opt(self, model_builder, params_dict, train_dataset,
		valid_dataset, output_transformers, task_types, metric):

		optimizer = HyperparamOpt(model_builder, task_types)
		best_model, best_hyperparams, all_results = optimizer.hyperparam_search(
		params_dict, train_dataset, valid_dataset, output_transformers,
		metric)

		def _create_model(self, train_dataset, test_dataset, model, transformers,
		metrics):
		"""Helper method to create model for test."""

deepchem/models/test/test_api.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -33,7 +33,7 @@ from sklearn.ensemble import RandomForestRegressor

		class TestKerasSklearnAPI(TestAPI):
		"""
		Test top-level API for ML models."
		Test top-level API for ML models.
		"""
		def test_singletask_sklearn_rf_ECFP_regression_API(self):
		"""Test of singletask RF ECFP regression API."""

Admin message