Loading deep_chem/models/deep.py +67 −3 Original line number Diff line number Diff line Loading @@ -5,8 +5,72 @@ import numpy as np from keras.models import Graph from keras.layers.core import Dense, Dropout from keras.optimizers import SGD from deep_chem.utils.preprocess import to_one_hot from deep_chem.models import Model #TODO(rbharath/enf): Make this real. It's a dummy now. class SingleTaskDNN(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") #TODO(rbharath/enf): Make this real. It's a dummy now. class MultiTaskDNN(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") 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 fit_multitask_mlp(train_data, task_types, **training_params): """ Loading Loading @@ -62,7 +126,7 @@ def fit_singletask_mlp(train_data, task_types, **training_params): def train_multitask_model(X, y, W, task_types, learning_rate=0.01, decay=1e-6, momentum=0.9, nesterov=True, activation="relu", dropout=0.5, nb_epoch=20, batch_size=50, n_hidden=500, dropout=0.5, nb_epoch=20, batch_size=50, nb_hidden=500, validation_split=0.1): """ Perform stochastic gradient descent optimization for a keras multitask MLP. Loading Loading @@ -106,7 +170,7 @@ def train_multitask_model(X, y, W, task_types, learning_rate=0.01, #model.add_input(name="input", ndim=n_inputs) model.add_input(name="input", input_shape=(n_inputs,)) model.add_node( Dense(n_hidden, init='uniform', activation=activation), Dense(nb_hidden, init='uniform', activation=activation), name="dense", input="input") model.add_node(Dropout(dropout), name="dropout", input="dense") top_layer = "dropout" Loading deep_chem/models/deep3d.py +1 −2 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ class DockingDNN(Model): """ def __init__(self, task_types, model_params, initialize_raw_model=True): if initialize_raw_model: (_, axis_length, _, _, n_channels) = model_params["data_shape"] (axis_length, _, _, n_channels) = model_params["data_shape"] learning_rate = model_params["learning_rate"] loss_function = model_params["loss_function"] Loading Loading @@ -88,4 +88,3 @@ class DockingDNN(Model): y_pred = self.raw_model.predict_on_batch(X) y_pred = np.squeeze(y_pred) return(y_pred) No newline at end of file deep_chem/models/model.py +13 −5 Original line number Diff line number Diff line """ Factory function to construct models. """ from __future__ import print_function from __future__ import division from __future__ import unicode_literals #from deep_chem.models.deep import SingleTaskDNN #from deep_chem.models.deep import MultiTaskDNN from deep_chem.models.deep3D import DockingDNN from deep_chem.models.deep import SingleTaskDNN from deep_chem.models.deep import MultiTaskDNN from deep_chem.models.deep3d import DockingDNN from deep_chem.models.standard import SklearnModel def model_builder(model_type, task_types, model_params): """ Factory function to construct model. """ if model_type == "singletask_deep_network": model = SingleTaskDNN(task_types, model_params) elif model_type == "multitask_deep_network": model = MultiTaskDNN(task_types, model_params) elif model_type== "3D_cnn": elif model_type == "convolutional_3D_regressor": model = DockingDNN(task_types, model_params) else: model = SklearnModel(task_types, model_params) return(model) return model deep_chem/models/standard.py +24 −0 Original line number Diff line number Diff line Loading @@ -9,6 +9,30 @@ from sklearn.linear_model import RidgeCV from sklearn.linear_model import LassoCV from sklearn.linear_model import ElasticNetCV from sklearn.linear_model import LassoLarsCV from deep_chem.models import Model class SklearnModel(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def fit_singletask_models(train_data, modeltype): """Fits singletask linear regression models to potency. Loading deep_chem/scripts/modeler.py +14 −9 Original line number Diff line number Diff line Loading @@ -57,7 +57,7 @@ def add_featurize_group(featurize_cmd): "--threshold", type=float, default=None, help="If specified, will be used to binarize real-valued target-fields.") featurize_group.add_argument( "--feature-dir", type=str, required=1, "--feature-dir", type=str, required=0, help="Directory where featurized dataset will be stored. \n" "Will be created if does not exist") featurize_group.set_defaults(func=featurize_inputs_wrapper) Loading Loading @@ -192,6 +192,9 @@ def add_model_command(subparsers): model_cmd.add_argument( "--skip-fit", action="store_true", help="If set, skip model fit step.") model_cmd.add_argument( "--base-dir", type=str, required=1, help="The base directory for the model.") add_featurize_group(model_cmd) train_test_group = model_cmd.add_argument_group("train_test_group") Loading Loading @@ -231,17 +234,19 @@ def extract_model_params(args): model_params = {param : getattr(args, param) for param in params} return(model_params) def ensure_exists(dirs): for directory in dirs: if not os.path.exists(directory): os.makedirs(directory) def create_model(args): """Creates a model""" feature_dir = args.feature_dir if not os.path.exists(feature_dir): os.makedirs(feature_dir) data_dir = args.data_dir if not os.path.exists(data_dir): os.makedirs(data_dir) base_dir = args.base_dir feature_dir = os.path.join(base_dir, "features") data_dir = os.path.join(base_dir, "data") model_dir = os.path.join(base_dir, "model") ensure_exists([base_dir, feature_dir, data_dir, model_dir]) model_dir = args.model_dir model_name = args.model print("+++++++++++++++++++++++++++++++++") Loading Loading
deep_chem/models/deep.py +67 −3 Original line number Diff line number Diff line Loading @@ -5,8 +5,72 @@ import numpy as np from keras.models import Graph from keras.layers.core import Dense, Dropout from keras.optimizers import SGD from deep_chem.utils.preprocess import to_one_hot from deep_chem.models import Model #TODO(rbharath/enf): Make this real. It's a dummy now. class SingleTaskDNN(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") #TODO(rbharath/enf): Make this real. It's a dummy now. class MultiTaskDNN(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") 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 fit_multitask_mlp(train_data, task_types, **training_params): """ Loading Loading @@ -62,7 +126,7 @@ def fit_singletask_mlp(train_data, task_types, **training_params): def train_multitask_model(X, y, W, task_types, learning_rate=0.01, decay=1e-6, momentum=0.9, nesterov=True, activation="relu", dropout=0.5, nb_epoch=20, batch_size=50, n_hidden=500, dropout=0.5, nb_epoch=20, batch_size=50, nb_hidden=500, validation_split=0.1): """ Perform stochastic gradient descent optimization for a keras multitask MLP. Loading Loading @@ -106,7 +170,7 @@ def train_multitask_model(X, y, W, task_types, learning_rate=0.01, #model.add_input(name="input", ndim=n_inputs) model.add_input(name="input", input_shape=(n_inputs,)) model.add_node( Dense(n_hidden, init='uniform', activation=activation), Dense(nb_hidden, init='uniform', activation=activation), name="dense", input="input") model.add_node(Dropout(dropout), name="dropout", input="dense") top_layer = "dropout" Loading
deep_chem/models/deep3d.py +1 −2 Original line number Diff line number Diff line Loading @@ -19,7 +19,7 @@ class DockingDNN(Model): """ def __init__(self, task_types, model_params, initialize_raw_model=True): if initialize_raw_model: (_, axis_length, _, _, n_channels) = model_params["data_shape"] (axis_length, _, _, n_channels) = model_params["data_shape"] learning_rate = model_params["learning_rate"] loss_function = model_params["loss_function"] Loading Loading @@ -88,4 +88,3 @@ class DockingDNN(Model): y_pred = self.raw_model.predict_on_batch(X) y_pred = np.squeeze(y_pred) return(y_pred) No newline at end of file
deep_chem/models/model.py +13 −5 Original line number Diff line number Diff line """ Factory function to construct models. """ from __future__ import print_function from __future__ import division from __future__ import unicode_literals #from deep_chem.models.deep import SingleTaskDNN #from deep_chem.models.deep import MultiTaskDNN from deep_chem.models.deep3D import DockingDNN from deep_chem.models.deep import SingleTaskDNN from deep_chem.models.deep import MultiTaskDNN from deep_chem.models.deep3d import DockingDNN from deep_chem.models.standard import SklearnModel def model_builder(model_type, task_types, model_params): """ Factory function to construct model. """ if model_type == "singletask_deep_network": model = SingleTaskDNN(task_types, model_params) elif model_type == "multitask_deep_network": model = MultiTaskDNN(task_types, model_params) elif model_type== "3D_cnn": elif model_type == "convolutional_3D_regressor": model = DockingDNN(task_types, model_params) else: model = SklearnModel(task_types, model_params) return(model) return model
deep_chem/models/standard.py +24 −0 Original line number Diff line number Diff line Loading @@ -9,6 +9,30 @@ from sklearn.linear_model import RidgeCV from sklearn.linear_model import LassoCV from sklearn.linear_model import ElasticNetCV from sklearn.linear_model import LassoLarsCV from deep_chem.models import Model class SklearnModel(Model): """ Abstract base class for different ML models. """ def __init__(self, task_types, model_params, initialize_raw_model=True): self.task_types = task_types self.model_params = model_params self.raw_model = None def fit_on_batch(self, X, y, w): """ Updates existing model with new information. """ raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): """ Makes predictions on given batch of new data. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def fit_singletask_models(train_data, modeltype): """Fits singletask linear regression models to potency. Loading
deep_chem/scripts/modeler.py +14 −9 Original line number Diff line number Diff line Loading @@ -57,7 +57,7 @@ def add_featurize_group(featurize_cmd): "--threshold", type=float, default=None, help="If specified, will be used to binarize real-valued target-fields.") featurize_group.add_argument( "--feature-dir", type=str, required=1, "--feature-dir", type=str, required=0, help="Directory where featurized dataset will be stored. \n" "Will be created if does not exist") featurize_group.set_defaults(func=featurize_inputs_wrapper) Loading Loading @@ -192,6 +192,9 @@ def add_model_command(subparsers): model_cmd.add_argument( "--skip-fit", action="store_true", help="If set, skip model fit step.") model_cmd.add_argument( "--base-dir", type=str, required=1, help="The base directory for the model.") add_featurize_group(model_cmd) train_test_group = model_cmd.add_argument_group("train_test_group") Loading Loading @@ -231,17 +234,19 @@ def extract_model_params(args): model_params = {param : getattr(args, param) for param in params} return(model_params) def ensure_exists(dirs): for directory in dirs: if not os.path.exists(directory): os.makedirs(directory) def create_model(args): """Creates a model""" feature_dir = args.feature_dir if not os.path.exists(feature_dir): os.makedirs(feature_dir) data_dir = args.data_dir if not os.path.exists(data_dir): os.makedirs(data_dir) base_dir = args.base_dir feature_dir = os.path.join(base_dir, "features") data_dir = os.path.join(base_dir, "data") model_dir = os.path.join(base_dir, "model") ensure_exists([base_dir, feature_dir, data_dir, model_dir]) model_dir = args.model_dir model_name = args.model print("+++++++++++++++++++++++++++++++++") Loading
