Loading deepchem/models/robust_multitask.py +19 −2 Original line number Diff line number Diff line Loading @@ -3,10 +3,12 @@ import tensorflow as tf import collections import logging import deepchem as dc from deepchem.metrics import to_one_hot from deepchem.models import KerasModel from deepchem.models.layers import Stack from deepchem.models.losses import SoftmaxCrossEntropy, L2Loss from typing import Tuple, Iterable, List logger = logging.getLogger(__name__) Loading Loading @@ -348,6 +350,21 @@ class RobustMultitaskRegressor(KerasModel): task_out = tf.keras.layers.Dense(1)(task_layer) task_outputs.append(task_out) outputs = tf.keras.layers.Concatenate(axis=1)(task_outputs) outputs = Stack(axis=1)(task_outputs) model = tf.keras.Model(inputs=mol_features, outputs=outputs) super(RobustMultitaskRegressor, self).__init__(model, L2Loss(), **kwargs) super(RobustMultitaskRegressor, self).__init__( model, L2Loss(), output_types=['prediction'], **kwargs) def default_generator( self, dataset: dc.data.Dataset, epochs: int = 1, mode: str = 'fit', deterministic: bool = True, pad_batches: bool = True) -> Iterable[Tuple[List, List, List]]: for epoch in range(epochs): for (X_b, y_b, w_b, ids_b) in dataset.iterbatches( batch_size=self.batch_size, deterministic=deterministic, pad_batches=pad_batches): yield ([X_b], [y_b], [w_b]) deepchem/models/tests/test_overfit.py +2 −2 Original line number Diff line number Diff line Loading @@ -538,8 +538,8 @@ def test_residual_regression_overfit(): assert scores[regression_metric.name] < .02 def test_tf_robust_multitask_regression_overfit(): """Test tf robust multitask overfits tiny data.""" def test_robust_multitask_regression_overfit(): """Test robust multitask overfits tiny data.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 10 Loading deepchem/models/tests/test_reload.py +58 −57 Original line number Diff line number Diff line Loading @@ -278,63 +278,64 @@ def test_robust_multitask_classification_reload(): assert scores[classification_metric.name] > .9 # TODO: THIS DOESN'T WORK!! #def test_robust_multitask_regressor_reload(): # """Test that RobustMultitaskRegressor can be reloaded correctly.""" # n_tasks = 10 # n_samples = 10 # n_features = 3 # # # Generate dummy dataset # np.random.seed(123) # ids = np.arange(n_samples) # X = np.random.rand(n_samples, n_features) # y = np.random.rand(n_samples, n_tasks) # w = np.ones((n_samples, n_tasks)) # # dataset = dc.data.NumpyDataset(X, y, w, ids) # regression_metric = dc.metrics.Metric(dc.metrics.mean_squared_error) # # model_dir = tempfile.mkdtemp() # model = dc.models.RobustMultitaskRegressor( # n_tasks, # n_features, # layer_sizes=[50], # bypass_layer_sizes=[10], # dropouts=[0.], # learning_rate=0.003, # weight_init_stddevs=[.1], # batch_size=n_samples) # # # Fit trained model # model.fit(dataset, nb_epoch=100) # # # Eval model on train # scores = model.evaluate(dataset, [regression_metric]) # assert scores[regression_metric.name] < .1 # # # Reload trained model # reloaded_model = dc.models.RobustMultitaskRegressor( # n_tasks, # n_features, # layer_sizes=[50], # bypass_layer_sizes=[10], # dropouts=[0.], # learning_rate=0.003, # weight_init_stddevs=[.1], # batch_size=n_samples) # reloaded_model.restore() # # # Check predictions match on random sample # Xpred = np.random.rand(n_samples, n_features) # predset = dc.data.NumpyDataset(Xpred) # origpred = model.predict(predset) # reloadpred = reloaded_model.predict(predset) # assert np.all(origpred == reloadpred) # # # Eval model on train # scores = reloaded_model.evaluate(dataset, [regression_metric]) # assert scores[regression_metric.name] < 0.1 def test_robust_multitask_regressor_reload(): """Test that RobustMultitaskRegressor can be reloaded correctly.""" n_tasks = 10 n_samples = 10 n_features = 3 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.random.rand(n_samples, n_tasks) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) regression_metric = dc.metrics.Metric(dc.metrics.mean_squared_error) model_dir = tempfile.mkdtemp() model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples, model_dir=model_dir) # Fit trained model model.fit(dataset, nb_epoch=100) # Eval model on train scores = model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] < .1 # Reload trained model reloaded_model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples, model_dir=model_dir) reloaded_model.restore() # Check predictions match on random sample Xpred = np.random.rand(n_samples, n_features) predset = dc.data.NumpyDataset(Xpred) origpred = model.predict(predset) reloadpred = reloaded_model.predict(predset) assert np.all(origpred == reloadpred) # Eval model on train scores = reloaded_model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] < 0.1 def test_IRV_multitask_classification_reload(): Loading deepchem/models/tests/test_robust.py 0 → 100644 +68 −0 Original line number Diff line number Diff line import numpy as np import tensorflow as tf import deepchem as dc def test_singletask_robust_multitask_classification(): """Test robust multitask singletask classification.""" n_tasks = 1 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) classification_metric = dc.metrics.Metric( dc.metrics.accuracy_score, task_averager=np.mean) model = dc.models.RobustMultitaskClassifier( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples) # Fit trained model model.fit(dataset, nb_epoch=1) def test_singletask_robust_multitask_regression(): """Test singletask robust multitask regression.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 1 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) regression_metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean, mode="regression") model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples) # Fit trained model model.fit(dataset, nb_epoch=1) Loading
deepchem/models/robust_multitask.py +19 −2 Original line number Diff line number Diff line Loading @@ -3,10 +3,12 @@ import tensorflow as tf import collections import logging import deepchem as dc from deepchem.metrics import to_one_hot from deepchem.models import KerasModel from deepchem.models.layers import Stack from deepchem.models.losses import SoftmaxCrossEntropy, L2Loss from typing import Tuple, Iterable, List logger = logging.getLogger(__name__) Loading Loading @@ -348,6 +350,21 @@ class RobustMultitaskRegressor(KerasModel): task_out = tf.keras.layers.Dense(1)(task_layer) task_outputs.append(task_out) outputs = tf.keras.layers.Concatenate(axis=1)(task_outputs) outputs = Stack(axis=1)(task_outputs) model = tf.keras.Model(inputs=mol_features, outputs=outputs) super(RobustMultitaskRegressor, self).__init__(model, L2Loss(), **kwargs) super(RobustMultitaskRegressor, self).__init__( model, L2Loss(), output_types=['prediction'], **kwargs) def default_generator( self, dataset: dc.data.Dataset, epochs: int = 1, mode: str = 'fit', deterministic: bool = True, pad_batches: bool = True) -> Iterable[Tuple[List, List, List]]: for epoch in range(epochs): for (X_b, y_b, w_b, ids_b) in dataset.iterbatches( batch_size=self.batch_size, deterministic=deterministic, pad_batches=pad_batches): yield ([X_b], [y_b], [w_b])
deepchem/models/tests/test_overfit.py +2 −2 Original line number Diff line number Diff line Loading @@ -538,8 +538,8 @@ def test_residual_regression_overfit(): assert scores[regression_metric.name] < .02 def test_tf_robust_multitask_regression_overfit(): """Test tf robust multitask overfits tiny data.""" def test_robust_multitask_regression_overfit(): """Test robust multitask overfits tiny data.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 10 Loading
deepchem/models/tests/test_reload.py +58 −57 Original line number Diff line number Diff line Loading @@ -278,63 +278,64 @@ def test_robust_multitask_classification_reload(): assert scores[classification_metric.name] > .9 # TODO: THIS DOESN'T WORK!! #def test_robust_multitask_regressor_reload(): # """Test that RobustMultitaskRegressor can be reloaded correctly.""" # n_tasks = 10 # n_samples = 10 # n_features = 3 # # # Generate dummy dataset # np.random.seed(123) # ids = np.arange(n_samples) # X = np.random.rand(n_samples, n_features) # y = np.random.rand(n_samples, n_tasks) # w = np.ones((n_samples, n_tasks)) # # dataset = dc.data.NumpyDataset(X, y, w, ids) # regression_metric = dc.metrics.Metric(dc.metrics.mean_squared_error) # # model_dir = tempfile.mkdtemp() # model = dc.models.RobustMultitaskRegressor( # n_tasks, # n_features, # layer_sizes=[50], # bypass_layer_sizes=[10], # dropouts=[0.], # learning_rate=0.003, # weight_init_stddevs=[.1], # batch_size=n_samples) # # # Fit trained model # model.fit(dataset, nb_epoch=100) # # # Eval model on train # scores = model.evaluate(dataset, [regression_metric]) # assert scores[regression_metric.name] < .1 # # # Reload trained model # reloaded_model = dc.models.RobustMultitaskRegressor( # n_tasks, # n_features, # layer_sizes=[50], # bypass_layer_sizes=[10], # dropouts=[0.], # learning_rate=0.003, # weight_init_stddevs=[.1], # batch_size=n_samples) # reloaded_model.restore() # # # Check predictions match on random sample # Xpred = np.random.rand(n_samples, n_features) # predset = dc.data.NumpyDataset(Xpred) # origpred = model.predict(predset) # reloadpred = reloaded_model.predict(predset) # assert np.all(origpred == reloadpred) # # # Eval model on train # scores = reloaded_model.evaluate(dataset, [regression_metric]) # assert scores[regression_metric.name] < 0.1 def test_robust_multitask_regressor_reload(): """Test that RobustMultitaskRegressor can be reloaded correctly.""" n_tasks = 10 n_samples = 10 n_features = 3 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.random.rand(n_samples, n_tasks) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) regression_metric = dc.metrics.Metric(dc.metrics.mean_squared_error) model_dir = tempfile.mkdtemp() model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples, model_dir=model_dir) # Fit trained model model.fit(dataset, nb_epoch=100) # Eval model on train scores = model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] < .1 # Reload trained model reloaded_model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples, model_dir=model_dir) reloaded_model.restore() # Check predictions match on random sample Xpred = np.random.rand(n_samples, n_features) predset = dc.data.NumpyDataset(Xpred) origpred = model.predict(predset) reloadpred = reloaded_model.predict(predset) assert np.all(origpred == reloadpred) # Eval model on train scores = reloaded_model.evaluate(dataset, [regression_metric]) assert scores[regression_metric.name] < 0.1 def test_IRV_multitask_classification_reload(): Loading
deepchem/models/tests/test_robust.py 0 → 100644 +68 −0 Original line number Diff line number Diff line import numpy as np import tensorflow as tf import deepchem as dc def test_singletask_robust_multitask_classification(): """Test robust multitask singletask classification.""" n_tasks = 1 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) classification_metric = dc.metrics.Metric( dc.metrics.accuracy_score, task_averager=np.mean) model = dc.models.RobustMultitaskClassifier( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples) # Fit trained model model.fit(dataset, nb_epoch=1) def test_singletask_robust_multitask_regression(): """Test singletask robust multitask regression.""" np.random.seed(123) tf.random.set_seed(123) n_tasks = 1 n_samples = 10 n_features = 3 n_classes = 2 # Generate dummy dataset np.random.seed(123) ids = np.arange(n_samples) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) w = np.ones((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y, w, ids) regression_metric = dc.metrics.Metric( dc.metrics.mean_squared_error, task_averager=np.mean, mode="regression") model = dc.models.RobustMultitaskRegressor( n_tasks, n_features, layer_sizes=[50], bypass_layer_sizes=[10], dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[.1], batch_size=n_samples) # Fit trained model model.fit(dataset, nb_epoch=1)
