Loading deepchem/hyper/tests/test_gaussian_hyperparam_opt.py +37 −0 Original line number Diff line number Diff line Loading @@ -7,6 +7,7 @@ valuable test suite so leaving it in despite the flakiness. """ import numpy as np import sklearn import sklearn.ensemble import deepchem as dc import unittest import tempfile Loading Loading @@ -171,3 +172,39 @@ class TestGaussianHyperparamOpt(unittest.TestCase): assert "learning_rate" in hp_str assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 @flaky def test_multitask_example_nb_epoch(self): """Test a simple example of optimizing a multitask model with a gaussian process search.""" # Generate dummy dataset np.random.seed(123) train_dataset = dc.data.NumpyDataset( np.random.rand(10, 3), np.zeros((10, 2)), np.ones((10, 2)), np.arange(10)) valid_dataset = dc.data.NumpyDataset( np.random.rand(5, 3), np.zeros((5, 2)), np.ones((5, 2)), np.arange(5)) transformers = [] optimizer = dc.hyper.GaussianProcessHyperparamOpt( lambda **params: dc.models.MultitaskRegressor(n_tasks=2, n_features=3, dropouts=[0.], weight_init_stddevs=[np.sqrt(6) / np.sqrt(1000)], learning_rate=0.003, **params)) params_dict = {"batch_size": 10} metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean) best_model, best_hyperparams, all_results = optimizer.hyperparam_search( params_dict, train_dataset, valid_dataset, metric, transformers, nb_epoch=3, max_iter=1, use_max=False) valid_score = best_model.evaluate(valid_dataset, [metric], transformers) assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 deepchem/hyper/tests/test_grid_hyperparam_opt.py +35 −0 Original line number Diff line number Diff line Loading @@ -6,6 +6,7 @@ import tempfile import numpy as np import deepchem as dc import sklearn import sklearn.ensemble class TestGridHyperparamOpt(unittest.TestCase): Loading Loading @@ -158,3 +159,37 @@ class TestGridHyperparamOpt(unittest.TestCase): assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 def test_multitask_nb_epoch(self): """Test a simple example of optimizing a multitask model with a grid search.""" # Generate dummy dataset np.random.seed(123) train_dataset = dc.data.NumpyDataset( np.random.rand(10, 3), np.zeros((10, 2)), np.ones((10, 2)), np.arange(10)) valid_dataset = dc.data.NumpyDataset( np.random.rand(5, 3), np.zeros((5, 2)), np.ones((5, 2)), np.arange(5)) optimizer = dc.hyper.GridHyperparamOpt( lambda **params: dc.models.MultitaskRegressor(n_tasks=2, n_features=3, dropouts=[0.], weight_init_stddevs=[np.sqrt(6) / np.sqrt(1000)], learning_rate=0.003, **params)) params_dict = {"batch_size": [10, 20]} transformers = [] metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean) best_model, best_hyperparams, all_results = optimizer.hyperparam_search( params_dict, train_dataset, valid_dataset, metric, transformers, nb_epoch=3, use_max=False) valid_score = best_model.evaluate(valid_dataset, [metric]) assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 No newline at end of file Loading
deepchem/hyper/tests/test_gaussian_hyperparam_opt.py +37 −0 Original line number Diff line number Diff line Loading @@ -7,6 +7,7 @@ valuable test suite so leaving it in despite the flakiness. """ import numpy as np import sklearn import sklearn.ensemble import deepchem as dc import unittest import tempfile Loading Loading @@ -171,3 +172,39 @@ class TestGaussianHyperparamOpt(unittest.TestCase): assert "learning_rate" in hp_str assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 @flaky def test_multitask_example_nb_epoch(self): """Test a simple example of optimizing a multitask model with a gaussian process search.""" # Generate dummy dataset np.random.seed(123) train_dataset = dc.data.NumpyDataset( np.random.rand(10, 3), np.zeros((10, 2)), np.ones((10, 2)), np.arange(10)) valid_dataset = dc.data.NumpyDataset( np.random.rand(5, 3), np.zeros((5, 2)), np.ones((5, 2)), np.arange(5)) transformers = [] optimizer = dc.hyper.GaussianProcessHyperparamOpt( lambda **params: dc.models.MultitaskRegressor(n_tasks=2, n_features=3, dropouts=[0.], weight_init_stddevs=[np.sqrt(6) / np.sqrt(1000)], learning_rate=0.003, **params)) params_dict = {"batch_size": 10} metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean) best_model, best_hyperparams, all_results = optimizer.hyperparam_search( params_dict, train_dataset, valid_dataset, metric, transformers, nb_epoch=3, max_iter=1, use_max=False) valid_score = best_model.evaluate(valid_dataset, [metric], transformers) assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0
deepchem/hyper/tests/test_grid_hyperparam_opt.py +35 −0 Original line number Diff line number Diff line Loading @@ -6,6 +6,7 @@ import tempfile import numpy as np import deepchem as dc import sklearn import sklearn.ensemble class TestGridHyperparamOpt(unittest.TestCase): Loading Loading @@ -158,3 +159,37 @@ class TestGridHyperparamOpt(unittest.TestCase): assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 def test_multitask_nb_epoch(self): """Test a simple example of optimizing a multitask model with a grid search.""" # Generate dummy dataset np.random.seed(123) train_dataset = dc.data.NumpyDataset( np.random.rand(10, 3), np.zeros((10, 2)), np.ones((10, 2)), np.arange(10)) valid_dataset = dc.data.NumpyDataset( np.random.rand(5, 3), np.zeros((5, 2)), np.ones((5, 2)), np.arange(5)) optimizer = dc.hyper.GridHyperparamOpt( lambda **params: dc.models.MultitaskRegressor(n_tasks=2, n_features=3, dropouts=[0.], weight_init_stddevs=[np.sqrt(6) / np.sqrt(1000)], learning_rate=0.003, **params)) params_dict = {"batch_size": [10, 20]} transformers = [] metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean) best_model, best_hyperparams, all_results = optimizer.hyperparam_search( params_dict, train_dataset, valid_dataset, metric, transformers, nb_epoch=3, use_max=False) valid_score = best_model.evaluate(valid_dataset, [metric]) assert valid_score["mean-mean_squared_error"] == min(all_results.values()) assert valid_score["mean-mean_squared_error"] > 0 No newline at end of file
