Loading deepchem/data/datasets.py +7 −2 Original line number Diff line number Diff line Loading @@ -451,6 +451,11 @@ class DiskDataset(Dataset): save_to_disk( (self.tasks, self.metadata_df), self._get_metadata_filename()) def move(self, new_data_dir): """Moves dataset to new directory.""" shutil.move(self.data_dir, new_data_dir) self.data_dir = new_data_dir def get_task_names(self): """ Gets learning tasks associated with this dataset. Loading deepchem/hyper/tests/test_hyperparam_opt.py +1 −1 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ import deepchem as dc from sklearn.ensemble import RandomForestClassifier from sklearn.ensemble import RandomForestRegressor class TestHyperparamOptAPI(unittest.TestCase): class TestHyperparamOpt(unittest.TestCase): """ Test hyperparameter optimization API. """ Loading deepchem/metrics/__init__.py +26 −11 Original line number Diff line number Diff line Loading @@ -145,16 +145,28 @@ class Metric(object): # user-space as a custom task_averager function. self.compute_energy_metric = compute_energy_metric def compute_metric(self, y_true, y_pred, w=None, n_classes=2, filter_nans=True): def compute_metric(self, y_true, y_pred, w=None, n_classes=2, filter_nans=True, per_task_metrics=False): """Compute a performance metric for each task. Args: y_true: A list of arrays containing true values for each task. y_pred: A list of arrays containing predicted values for each task. metric: Must be a class that inherits from Metric Parameters ---------- y_true: np.ndarray An np.ndarray containing true values for each task. y_pred: np.ndarray An np.ndarray containing predicted values for each task. w: np.ndarray, optional An np.ndarray containing weights for each datapoint. n_classes: int, optional Number of classes in data for classification tasks. filter_nans: bool, optional Remove NaN values in computed metrics per_task_metrics: bool, optional If true, return computed metric for each task on multitask dataset. Returns: A numpy array containing metric values for each task. Returns ------- A numpy nd.array containing metric values for each task. """ if len(y_true.shape) > 1: n_samples, n_tasks = y_true.shape[0], y_true.shape[1] Loading Loading @@ -194,8 +206,11 @@ class Metric(object): force_error = self.task_averager(computed_metrics[1:])*4961.47596096 print("Force error (metric: np.mean(%s)): %f kJ/mol/A" % (self.name, force_error)) return computed_metrics[0] else: elif not per_task_metrics: return self.task_averager(computed_metrics) else: return self.task_averager(computed_metrics), computed_metrics def compute_singletask_metric(self, y_true, y_pred, w): """Compute a metric value. Loading deepchem/models/models.py +11 −3 Original line number Diff line number Diff line Loading @@ -155,7 +155,8 @@ class Model(object): y_pred = np.reshape(y_pred, (n_samples,)) return y_pred def evaluate(self, dataset, metrics, transformers=[]): def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): """ Evaluates the performance of this model on specified dataset. Loading @@ -167,6 +168,8 @@ class Model(object): Evaluation metric transformers: list List of deepchem.transformers.Transformer per_task_metrics: bool If True, return per-task scores. Returns ------- Loading @@ -174,8 +177,13 @@ class Model(object): Maps tasks to scores under metric. """ evaluator = Evaluator(self, dataset, transformers) if not per_task_metrics: scores = evaluator.compute_model_performance(metrics) return scores else: scores, per_task_scores = evaluator.compute_model_performance( metrics, per_task_metrics=per_task_metrics) return scores, per_task_scores def predict_proba(self, dataset, transformers=[], batch_size=None, n_classes=2): Loading deepchem/models/multitask.py +1 −0 Original line number Diff line number Diff line Loading @@ -9,6 +9,7 @@ import os import sklearn import tempfile import numpy as np import shutil from deepchem.utils.save import log from deepchem.models import Model from deepchem.data import DiskDataset Loading Loading
deepchem/data/datasets.py +7 −2 Original line number Diff line number Diff line Loading @@ -451,6 +451,11 @@ class DiskDataset(Dataset): save_to_disk( (self.tasks, self.metadata_df), self._get_metadata_filename()) def move(self, new_data_dir): """Moves dataset to new directory.""" shutil.move(self.data_dir, new_data_dir) self.data_dir = new_data_dir def get_task_names(self): """ Gets learning tasks associated with this dataset. Loading
deepchem/hyper/tests/test_hyperparam_opt.py +1 −1 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ import deepchem as dc from sklearn.ensemble import RandomForestClassifier from sklearn.ensemble import RandomForestRegressor class TestHyperparamOptAPI(unittest.TestCase): class TestHyperparamOpt(unittest.TestCase): """ Test hyperparameter optimization API. """ Loading
deepchem/metrics/__init__.py +26 −11 Original line number Diff line number Diff line Loading @@ -145,16 +145,28 @@ class Metric(object): # user-space as a custom task_averager function. self.compute_energy_metric = compute_energy_metric def compute_metric(self, y_true, y_pred, w=None, n_classes=2, filter_nans=True): def compute_metric(self, y_true, y_pred, w=None, n_classes=2, filter_nans=True, per_task_metrics=False): """Compute a performance metric for each task. Args: y_true: A list of arrays containing true values for each task. y_pred: A list of arrays containing predicted values for each task. metric: Must be a class that inherits from Metric Parameters ---------- y_true: np.ndarray An np.ndarray containing true values for each task. y_pred: np.ndarray An np.ndarray containing predicted values for each task. w: np.ndarray, optional An np.ndarray containing weights for each datapoint. n_classes: int, optional Number of classes in data for classification tasks. filter_nans: bool, optional Remove NaN values in computed metrics per_task_metrics: bool, optional If true, return computed metric for each task on multitask dataset. Returns: A numpy array containing metric values for each task. Returns ------- A numpy nd.array containing metric values for each task. """ if len(y_true.shape) > 1: n_samples, n_tasks = y_true.shape[0], y_true.shape[1] Loading Loading @@ -194,8 +206,11 @@ class Metric(object): force_error = self.task_averager(computed_metrics[1:])*4961.47596096 print("Force error (metric: np.mean(%s)): %f kJ/mol/A" % (self.name, force_error)) return computed_metrics[0] else: elif not per_task_metrics: return self.task_averager(computed_metrics) else: return self.task_averager(computed_metrics), computed_metrics def compute_singletask_metric(self, y_true, y_pred, w): """Compute a metric value. Loading
deepchem/models/models.py +11 −3 Original line number Diff line number Diff line Loading @@ -155,7 +155,8 @@ class Model(object): y_pred = np.reshape(y_pred, (n_samples,)) return y_pred def evaluate(self, dataset, metrics, transformers=[]): def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): """ Evaluates the performance of this model on specified dataset. Loading @@ -167,6 +168,8 @@ class Model(object): Evaluation metric transformers: list List of deepchem.transformers.Transformer per_task_metrics: bool If True, return per-task scores. Returns ------- Loading @@ -174,8 +177,13 @@ class Model(object): Maps tasks to scores under metric. """ evaluator = Evaluator(self, dataset, transformers) if not per_task_metrics: scores = evaluator.compute_model_performance(metrics) return scores else: scores, per_task_scores = evaluator.compute_model_performance( metrics, per_task_metrics=per_task_metrics) return scores, per_task_scores def predict_proba(self, dataset, transformers=[], batch_size=None, n_classes=2): Loading
deepchem/models/multitask.py +1 −0 Original line number Diff line number Diff line Loading @@ -9,6 +9,7 @@ import os import sklearn import tempfile import numpy as np import shutil from deepchem.utils.save import log from deepchem.models import Model from deepchem.data import DiskDataset Loading
