Loading deepchem/models/keras_models/fcnet.py +1 −17 Original line number Diff line number Diff line Loading @@ -13,6 +13,7 @@ from keras.layers.core import Dense, Dropout, Activation from keras.layers.normalization import BatchNormalization from keras.optimizers import SGD from deepchem.models.keras_models import KerasModel from deepchem.utils.evaluate import to_one_hot class MultiTaskDNN(KerasModel): """ Loading Loading @@ -139,20 +140,3 @@ class SingleTaskDNN(MultiTaskDNN): super(SingleTaskDNN, self).__init__(task_types, model_params, initialize_raw_model=initialize_raw_model, verbosity=verbosity) def to_one_hot(y): """Transforms label vector into one-hot encoding. Turns y into vector of shape [n_samples, 2] (assuming binary labels). y: np.ndarray A vector of shape [n_samples, 1] """ n_samples = np.shape(y)[0] y_hot = np.zeros((n_samples, 2)) for index, val in enumerate(y): if val == 0: y_hot[index] = np.array([1, 0]) elif val == 1: y_hot[index] = np.array([0, 1]) return y_hot deepchem/models/tensorflow_models/fcnet.py +2 −1 Original line number Diff line number Diff line Loading @@ -79,6 +79,7 @@ from tensorflow.python.platform import logging from deepchem.models.tensorflow_models import TensorflowClassifier from deepchem.models.tensorflow_models import model_ops from deepchem.utils.evaluate import to_one_hot class TensorflowMultiTaskClassifier(TensorflowClassifier): """Implements an icml model as configured in a model_config.proto.""" Loading Loading @@ -157,7 +158,7 @@ class TensorflowMultiTaskClassifier(TensorflowClassifier): feed_dict = {} feed_dict[self.mol_features] = X_b for task in xrange(self.num_tasks): feed_dict[self.labels[task]] = y_b[:, task] feed_dict[self.labels[task]] = to_one_hot(y_b[:, task]) feed_dict[self.weights[task]] = w_b[:, task] return feed_dict Loading deepchem/utils/dataset.pydeleted 100644 → 0 +0 −0 Empty file deleted. deepchem/utils/evaluate.py +17 −0 Original line number Diff line number Diff line Loading @@ -20,6 +20,23 @@ __author__ = "Bharath Ramsundar" __copyright__ = "Copyright 2015, Stanford University" __license__ = "LGPL" def to_one_hot(y): """Transforms label vector into one-hot encoding. Turns y into vector of shape [n_samples, 2] (assuming binary labels). y: np.ndarray A vector of shape [n_samples, 1] """ n_samples = np.shape(y)[0] y_hot = np.zeros((n_samples, 2)) for index, val in enumerate(y): if val == 0: y_hot[index] = np.array([1, 0]) elif val == 1: y_hot[index] = np.array([0, 1]) return y_hot def threshold_predictions(y, threshold): y_out = np.zeros_like(y) for ind, pred in enumerate(y): Loading Loading
deepchem/models/keras_models/fcnet.py +1 −17 Original line number Diff line number Diff line Loading @@ -13,6 +13,7 @@ from keras.layers.core import Dense, Dropout, Activation from keras.layers.normalization import BatchNormalization from keras.optimizers import SGD from deepchem.models.keras_models import KerasModel from deepchem.utils.evaluate import to_one_hot class MultiTaskDNN(KerasModel): """ Loading Loading @@ -139,20 +140,3 @@ class SingleTaskDNN(MultiTaskDNN): super(SingleTaskDNN, self).__init__(task_types, model_params, initialize_raw_model=initialize_raw_model, verbosity=verbosity) def to_one_hot(y): """Transforms label vector into one-hot encoding. Turns y into vector of shape [n_samples, 2] (assuming binary labels). y: np.ndarray A vector of shape [n_samples, 1] """ n_samples = np.shape(y)[0] y_hot = np.zeros((n_samples, 2)) for index, val in enumerate(y): if val == 0: y_hot[index] = np.array([1, 0]) elif val == 1: y_hot[index] = np.array([0, 1]) return y_hot
deepchem/models/tensorflow_models/fcnet.py +2 −1 Original line number Diff line number Diff line Loading @@ -79,6 +79,7 @@ from tensorflow.python.platform import logging from deepchem.models.tensorflow_models import TensorflowClassifier from deepchem.models.tensorflow_models import model_ops from deepchem.utils.evaluate import to_one_hot class TensorflowMultiTaskClassifier(TensorflowClassifier): """Implements an icml model as configured in a model_config.proto.""" Loading Loading @@ -157,7 +158,7 @@ class TensorflowMultiTaskClassifier(TensorflowClassifier): feed_dict = {} feed_dict[self.mol_features] = X_b for task in xrange(self.num_tasks): feed_dict[self.labels[task]] = y_b[:, task] feed_dict[self.labels[task]] = to_one_hot(y_b[:, task]) feed_dict[self.weights[task]] = w_b[:, task] return feed_dict Loading
deepchem/utils/evaluate.py +17 −0 Original line number Diff line number Diff line Loading @@ -20,6 +20,23 @@ __author__ = "Bharath Ramsundar" __copyright__ = "Copyright 2015, Stanford University" __license__ = "LGPL" def to_one_hot(y): """Transforms label vector into one-hot encoding. Turns y into vector of shape [n_samples, 2] (assuming binary labels). y: np.ndarray A vector of shape [n_samples, 1] """ n_samples = np.shape(y)[0] y_hot = np.zeros((n_samples, 2)) for index, val in enumerate(y): if val == 0: y_hot[index] = np.array([1, 0]) elif val == 1: y_hot[index] = np.array([0, 1]) return y_hot def threshold_predictions(y, threshold): y_out = np.zeros_like(y) for ind, pred in enumerate(y): Loading
