Loading deepchem/models/models.py +1 −51 Original line number Diff line number Diff line Loading @@ -80,18 +80,6 @@ class Model(BaseEstimator): raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def predict_proba_on_batch(self, X): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def reload(self): """ Reload trained model from disk. Loading Loading @@ -152,18 +140,9 @@ class Model(BaseEstimator): y_pred_batch = self.predict_on_batch(X_batch) # Discard any padded predictions y_pred_batch = y_pred_batch[:n_samples] y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) # The iterbatches does padding with zero-weight examples on the last batch. # Remove padded examples. n_samples = len(dataset) y_pred = np.reshape(y_pred, (n_samples, n_tasks)) # Special case to handle singletasks. if n_tasks == 1: y_pred = np.reshape(y_pred, (n_samples,)) y_pred = np.concatenate(y_preds) return y_pred def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): Loading Loading @@ -195,35 +174,6 @@ class Model(BaseEstimator): metrics, per_task_metrics=per_task_metrics) return scores, per_task_scores def predict_proba(self, dataset, transformers=[], batch_size=None, n_classes=2): """ TODO: Do transformers even make sense here? Returns: y_pred: numpy ndarray of shape (n_samples, n_classes*n_tasks) """ y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True): n_samples = len(X_batch) y_pred_batch = self.predict_proba_on_batch(X_batch) y_pred_batch = y_pred_batch[:n_samples] y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks, n_classes)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) # The iterbatches does padding with zero-weight examples on the last batch. # Remove padded examples. n_samples = len(dataset) y_pred = y_pred[:n_samples] y_pred = np.reshape(y_pred, (n_samples, n_tasks, n_classes)) return y_pred def get_task_type(self): """ Currently models can only be classifiers or regressors. Loading deepchem/models/multitask.py +6 −33 Original line number Diff line number Diff line Loading @@ -105,12 +105,13 @@ class SingletaskToMultitask(Model): """ n_tasks = len(self.tasks) n_samples = X.shape[0] y_pred = np.zeros((n_samples, n_tasks)) y_preds = [] for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict_on_batch(X) y_preds.append(task_model.predict_on_batch(X)) y_pred = np.stack(y_preds, axis=1) return y_pred def predict(self, dataset, transformers=[]): Loading @@ -119,44 +120,16 @@ class SingletaskToMultitask(Model): """ n_tasks = len(self.tasks) n_samples = len(dataset) y_pred = np.zeros((n_samples, n_tasks)) y_preds = [] for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict(dataset, []) y_preds.append(task_model.predict(dataset, [])) y_pred = np.stack(y_preds, axis=1) y_pred = undo_transforms(y_pred, transformers) return y_pred def predict_proba_on_batch(self, X, n_classes=2): """ Concatenates results from all singletask models. """ n_tasks = len(self.tasks) n_samples = X.shape[0] y_pred = np.zeros((n_samples, n_tasks, n_classes)) for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict_proba_on_batch(X) return y_pred def predict_proba(self, dataset, transformers=[], n_classes=2): """ Concatenates results from all singletask models. """ n_tasks = len(self.tasks) n_samples = len(dataset) y_pred = np.zeros((n_samples, n_tasks, n_classes)) for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = np.squeeze( task_model.predict_proba(dataset, transformers, n_classes)) return y_pred def save(self): """Save all models Loading deepchem/models/sklearn_models/__init__.py +4 −15 Original line number Diff line number Diff line Loading @@ -77,21 +77,10 @@ class SklearnModel(Model): Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict(X) def predict_proba_on_batch(self, X, pad_batch=False): """ Makes per-class predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ try: return self.model_instance.predict_proba(X) except AttributeError: return self.model_instance.predict(X) def predict(self, X, transformers=[]): """ Loading deepchem/models/tensorgraph/IRV.py +1 −11 Original line number Diff line number Diff line Loading @@ -196,15 +196,5 @@ class TensorflowMultitaskIRVClassifier(TensorGraph): IRVRegularize(predictions, self.penalty, in_layers=[predictions]) self.set_loss(loss) outputs = Stack(axis=1, in_layers=outputs) outputs = Concat(axis=2, in_layers=[1 - outputs, outputs]) self.add_output(outputs) def predict(self, dataset, transformers=[], outputs=None): out = super(TensorflowMultitaskIRVClassifier, self).predict( dataset, transformers=transformers, outputs=outputs) out = np.round(out).astype(int) return out def predict_proba(self, dataset, transformers=[], outputs=None): out = super(TensorflowMultitaskIRVClassifier, self).predict_proba( dataset, transformers=transformers, outputs=outputs) return np.concatenate([1 - out, out], axis=2) deepchem/models/tensorgraph/fcnet.py +0 −30 Original line number Diff line number Diff line Loading @@ -168,36 +168,6 @@ class MultitaskClassifier(TensorGraph): tf.cast(labels, tf.int32), self.n_classes) return tensors def predict_proba(self, dataset, transformers=[], outputs=None): return super(MultitaskClassifier, self).predict(dataset, transformers, outputs) def predict(self, dataset, transformers=[], outputs=None): """ Uses self to make predictions on provided Dataset object. Parameters ---------- dataset: dc.data.Dataset Dataset to make prediction on transformers: list List of dc.trans.Transformers. outputs: object If outputs is None, then will assume outputs = self.outputs[0] (single output). If outputs is a Layer/Tensor, then will evaluate and return as a single ndarray. If outputs is a list of Layers/Tensors, will return a list of ndarrays. Returns ------- y_pred: numpy ndarray or list of numpy ndarrays """ # Results is of shape (n_samples, n_tasks, n_classes) retval = super(MultitaskClassifier, self).predict(dataset, transformers, outputs) # retval is of shape (n_samples, n_tasks) return np.argmax(retval, axis=2) class MultitaskRegressor(TensorGraph): Loading Loading
deepchem/models/models.py +1 −51 Original line number Diff line number Diff line Loading @@ -80,18 +80,6 @@ class Model(BaseEstimator): raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def predict_proba_on_batch(self, X): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def reload(self): """ Reload trained model from disk. Loading Loading @@ -152,18 +140,9 @@ class Model(BaseEstimator): y_pred_batch = self.predict_on_batch(X_batch) # Discard any padded predictions y_pred_batch = y_pred_batch[:n_samples] y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) # The iterbatches does padding with zero-weight examples on the last batch. # Remove padded examples. n_samples = len(dataset) y_pred = np.reshape(y_pred, (n_samples, n_tasks)) # Special case to handle singletasks. if n_tasks == 1: y_pred = np.reshape(y_pred, (n_samples,)) y_pred = np.concatenate(y_preds) return y_pred def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): Loading Loading @@ -195,35 +174,6 @@ class Model(BaseEstimator): metrics, per_task_metrics=per_task_metrics) return scores, per_task_scores def predict_proba(self, dataset, transformers=[], batch_size=None, n_classes=2): """ TODO: Do transformers even make sense here? Returns: y_pred: numpy ndarray of shape (n_samples, n_classes*n_tasks) """ y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True): n_samples = len(X_batch) y_pred_batch = self.predict_proba_on_batch(X_batch) y_pred_batch = y_pred_batch[:n_samples] y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks, n_classes)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) # The iterbatches does padding with zero-weight examples on the last batch. # Remove padded examples. n_samples = len(dataset) y_pred = y_pred[:n_samples] y_pred = np.reshape(y_pred, (n_samples, n_tasks, n_classes)) return y_pred def get_task_type(self): """ Currently models can only be classifiers or regressors. Loading
deepchem/models/multitask.py +6 −33 Original line number Diff line number Diff line Loading @@ -105,12 +105,13 @@ class SingletaskToMultitask(Model): """ n_tasks = len(self.tasks) n_samples = X.shape[0] y_pred = np.zeros((n_samples, n_tasks)) y_preds = [] for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict_on_batch(X) y_preds.append(task_model.predict_on_batch(X)) y_pred = np.stack(y_preds, axis=1) return y_pred def predict(self, dataset, transformers=[]): Loading @@ -119,44 +120,16 @@ class SingletaskToMultitask(Model): """ n_tasks = len(self.tasks) n_samples = len(dataset) y_pred = np.zeros((n_samples, n_tasks)) y_preds = [] for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict(dataset, []) y_preds.append(task_model.predict(dataset, [])) y_pred = np.stack(y_preds, axis=1) y_pred = undo_transforms(y_pred, transformers) return y_pred def predict_proba_on_batch(self, X, n_classes=2): """ Concatenates results from all singletask models. """ n_tasks = len(self.tasks) n_samples = X.shape[0] y_pred = np.zeros((n_samples, n_tasks, n_classes)) for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = task_model.predict_proba_on_batch(X) return y_pred def predict_proba(self, dataset, transformers=[], n_classes=2): """ Concatenates results from all singletask models. """ n_tasks = len(self.tasks) n_samples = len(dataset) y_pred = np.zeros((n_samples, n_tasks, n_classes)) for ind, task in enumerate(self.tasks): task_model = self.model_builder(self.task_model_dirs[task]) task_model.reload() y_pred[:, ind] = np.squeeze( task_model.predict_proba(dataset, transformers, n_classes)) return y_pred def save(self): """Save all models Loading
deepchem/models/sklearn_models/__init__.py +4 −15 Original line number Diff line number Diff line Loading @@ -77,21 +77,10 @@ class SklearnModel(Model): Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict(X) def predict_proba_on_batch(self, X, pad_batch=False): """ Makes per-class predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ try: return self.model_instance.predict_proba(X) except AttributeError: return self.model_instance.predict(X) def predict(self, X, transformers=[]): """ Loading
deepchem/models/tensorgraph/IRV.py +1 −11 Original line number Diff line number Diff line Loading @@ -196,15 +196,5 @@ class TensorflowMultitaskIRVClassifier(TensorGraph): IRVRegularize(predictions, self.penalty, in_layers=[predictions]) self.set_loss(loss) outputs = Stack(axis=1, in_layers=outputs) outputs = Concat(axis=2, in_layers=[1 - outputs, outputs]) self.add_output(outputs) def predict(self, dataset, transformers=[], outputs=None): out = super(TensorflowMultitaskIRVClassifier, self).predict( dataset, transformers=transformers, outputs=outputs) out = np.round(out).astype(int) return out def predict_proba(self, dataset, transformers=[], outputs=None): out = super(TensorflowMultitaskIRVClassifier, self).predict_proba( dataset, transformers=transformers, outputs=outputs) return np.concatenate([1 - out, out], axis=2)
deepchem/models/tensorgraph/fcnet.py +0 −30 Original line number Diff line number Diff line Loading @@ -168,36 +168,6 @@ class MultitaskClassifier(TensorGraph): tf.cast(labels, tf.int32), self.n_classes) return tensors def predict_proba(self, dataset, transformers=[], outputs=None): return super(MultitaskClassifier, self).predict(dataset, transformers, outputs) def predict(self, dataset, transformers=[], outputs=None): """ Uses self to make predictions on provided Dataset object. Parameters ---------- dataset: dc.data.Dataset Dataset to make prediction on transformers: list List of dc.trans.Transformers. outputs: object If outputs is None, then will assume outputs = self.outputs[0] (single output). If outputs is a Layer/Tensor, then will evaluate and return as a single ndarray. If outputs is a list of Layers/Tensors, will return a list of ndarrays. Returns ------- y_pred: numpy ndarray or list of numpy ndarrays """ # Results is of shape (n_samples, n_tasks, n_classes) retval = super(MultitaskClassifier, self).predict(dataset, transformers, outputs) # retval is of shape (n_samples, n_tasks) return np.argmax(retval, axis=2) class MultitaskRegressor(TensorGraph): Loading
