Loading deepchem/hyper/gaussian_process.py +3 −0 Original line number Diff line number Diff line Loading @@ -25,6 +25,7 @@ class GaussianProcessHyperparamOpt(HyperparamOpt): valid_dataset, output_transformers, metric, direction=True, n_features=1024, n_tasks=1, max_iter=20, Loading Loading @@ -57,6 +58,8 @@ class GaussianProcessHyperparamOpt(HyperparamOpt): transformers for evaluation metric: list of dc.metrics.Metric metric used for evaluation direction: bool maximization(True) or minimization(False) n_features: int number of input features n_tasks: int Loading deepchem/molnet/run_benchmark.py +5 −0 Original line number Diff line number Diff line Loading @@ -24,6 +24,7 @@ def run_benchmark(datasets, model, split=None, metric=None, direction=True, featurizer=None, n_features=0, out_path='.', Loading Loading @@ -52,6 +53,9 @@ def run_benchmark(datasets, choice of splitter function, None = using the default splitter metric: string, optional (default=None) choice of evaluation metrics, None = using the default metrics(AUC & R2) direction: bool, optional(default=True) Optimization direction when doing hyperparameter search Maximization(True) or minimization(False) featurizer: string or dc.feat.Featurizer, optional (default=None) choice of featurization, None = using the default corresponding to model (string only applicable to deepchem models) Loading Loading @@ -164,6 +168,7 @@ def run_benchmark(datasets, valid_dataset, transformers, metric, direction=direction, n_features=n_features, n_tasks=len(tasks), max_iter=max_iter, Loading examples/benchmark.py +19 −19 Original line number Diff line number Diff line Loading @@ -102,28 +102,28 @@ if len(datasets) == 0: ] metrics = { 'qm7': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm7b': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm8': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm9': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'delaney': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'sampl': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'lipo': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'pdbbind': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'pcba': [dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], 'muv': [dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], 'hiv': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'tox21': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'toxcast': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'sider': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'clintox': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'bace_c': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'bbbp': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')] 'qm7': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm7b': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm8': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm9': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'delaney': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'sampl': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'lipo': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'pdbbind': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'pcba': [[dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], True], 'muv': [[dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], True], 'hiv': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'tox21': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'toxcast': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'sider': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'clintox': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'bace_c': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'bbbp': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True] } for dataset in datasets: for split in splitters: for model in models: np.random.seed(seed) dc.molnet.run_benchmark( [dataset], str(model), split=split, metric=metrics[dataset], hyper_param_search=True, test=False, seed=seed) [dataset], str(model), split=split, metric=metrics[dataset][0], direction=metrics[dataset][1], hyper_param_search=True, test=False, seed=seed) Loading
deepchem/hyper/gaussian_process.py +3 −0 Original line number Diff line number Diff line Loading @@ -25,6 +25,7 @@ class GaussianProcessHyperparamOpt(HyperparamOpt): valid_dataset, output_transformers, metric, direction=True, n_features=1024, n_tasks=1, max_iter=20, Loading Loading @@ -57,6 +58,8 @@ class GaussianProcessHyperparamOpt(HyperparamOpt): transformers for evaluation metric: list of dc.metrics.Metric metric used for evaluation direction: bool maximization(True) or minimization(False) n_features: int number of input features n_tasks: int Loading
deepchem/molnet/run_benchmark.py +5 −0 Original line number Diff line number Diff line Loading @@ -24,6 +24,7 @@ def run_benchmark(datasets, model, split=None, metric=None, direction=True, featurizer=None, n_features=0, out_path='.', Loading Loading @@ -52,6 +53,9 @@ def run_benchmark(datasets, choice of splitter function, None = using the default splitter metric: string, optional (default=None) choice of evaluation metrics, None = using the default metrics(AUC & R2) direction: bool, optional(default=True) Optimization direction when doing hyperparameter search Maximization(True) or minimization(False) featurizer: string or dc.feat.Featurizer, optional (default=None) choice of featurization, None = using the default corresponding to model (string only applicable to deepchem models) Loading Loading @@ -164,6 +168,7 @@ def run_benchmark(datasets, valid_dataset, transformers, metric, direction=direction, n_features=n_features, n_tasks=len(tasks), max_iter=max_iter, Loading
examples/benchmark.py +19 −19 Original line number Diff line number Diff line Loading @@ -102,28 +102,28 @@ if len(datasets) == 0: ] metrics = { 'qm7': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm7b': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm8': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'qm9': [dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], 'delaney': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'sampl': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'lipo': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'pdbbind': [dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], 'pcba': [dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], 'muv': [dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], 'hiv': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'tox21': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'toxcast': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'sider': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'clintox': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'bace_c': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], 'bbbp': [dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')] 'qm7': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm7b': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm8': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'qm9': [[dc.metrics.Metric(dc.metrics.mean_absolute_error, np.mean, mode='regression')], False], 'delaney': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'sampl': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'lipo': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'pdbbind': [[dc.metrics.Metric(dc.metrics.rms_score, np.mean, mode='regression')], False], 'pcba': [[dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], True], 'muv': [[dc.metrics.Metric(dc.metrics.prc_auc_score, np.mean, mode='classification')], True], 'hiv': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'tox21': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'toxcast': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'sider': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'clintox': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'bace_c': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True], 'bbbp': [[dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean, mode='classification')], True] } for dataset in datasets: for split in splitters: for model in models: np.random.seed(seed) dc.molnet.run_benchmark( [dataset], str(model), split=split, metric=metrics[dataset], hyper_param_search=True, test=False, seed=seed) [dataset], str(model), split=split, metric=metrics[dataset][0], direction=metrics[dataset][1], hyper_param_search=True, test=False, seed=seed)
