Loading deepchem/models/tensorgraph/fcnet.py +6 −3 Original line number Diff line number Diff line Loading @@ -153,14 +153,17 @@ class MultiTaskClassifier(TensorGraph): feed_dict[self.task_weights[0]] = w_b yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = {} for layer, column in zip(self.features, feature_columns): tensors[layer] = tf.feature_column.input_layer(features, [column]) if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer(features, [weight_column]) tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = tf.one_hot(tf.cast(labels, tf.int32), self.n_classes) tensors[self.labels[0]] = tf.one_hot( tf.cast(labels, tf.int32), self.n_classes) return tensors def predict_proba(self, dataset, transformers=[], outputs=None): Loading deepchem/models/tensorgraph/tensor_graph.py +38 −16 Original line number Diff line number Diff line Loading @@ -839,7 +839,11 @@ class TensorGraph(Model): feed_dict[self._training_placeholder] = train_value yield feed_dict def make_estimator(self, feature_columns, weight_column=None, model_dir=None, metrics={}): def make_estimator(self, feature_columns, weight_column=None, model_dir=None, metrics={}): """Construct a Tensorflow Estimator from this model. tf.estimator.Estimator is the standard Tensorflow API for representing models. Loading Loading @@ -872,17 +876,22 @@ class TensorGraph(Model): # Check the inputs. if len(feature_columns) != len(self.features): raise ValueError('This model requires %d feature column(s)' % len(self.features)) raise ValueError( 'This model requires %d feature column(s)' % len(self.features)) if len(self.labels) != 1: raise ValueError('Can only create an Estimator from a model with exactly one Label input') raise ValueError( 'Can only create an Estimator from a model with exactly one Label input' ) if len(self.task_weights) > 1: raise ValueError('Cannot create an Estimator from a model with multiple Weight inputs') raise ValueError( 'Cannot create an Estimator from a model with multiple Weight inputs') if weight_column is None: if len(self.task_weights) > 0: raise ValueError('This model requires a weight column') else: if len(self.task_weights) == 0: raise ValueError('Cannot specify weight_column for a model with no Weight inputs') raise ValueError( 'Cannot specify weight_column for a model with no Weight inputs') if model_dir is None: model_dir = self.model_dir Loading @@ -891,8 +900,12 @@ class TensorGraph(Model): def create_tensors(layer, tensors, training): if layer in tensors: return tensors[layer] inputs = [create_tensors(in_layer, tensors, training) for in_layer in layer.in_layers] tensor = layer.create_tensor(in_layers=inputs, set_tensors=False, training=training) inputs = [ create_tensors(in_layer, tensors, training) for in_layer in layer.in_layers ] tensor = layer.create_tensor( in_layers=inputs, set_tensors=False, training=training) tensors[layer] = tensor layer.add_summary_to_tg(tensor) return tensor Loading @@ -902,7 +915,8 @@ class TensorGraph(Model): def model_fn(features, labels, mode): # Define the inputs. tensors = self.create_estimator_inputs(feature_columns, weight_column, features, labels, mode) tensors = self.create_estimator_inputs(feature_columns, weight_column, features, labels, mode) for layer, tensor in tensors.items(): layer.add_summary_to_tg(tensor) Loading @@ -922,8 +936,10 @@ class TensorGraph(Model): weights = tensors[self.task_weights[0]] eval_metric_ops = {} for name, function in metrics.items(): eval_metric_ops[name] = function(tensors[self.labels[0]], predictions, weights) return tf.estimator.EstimatorSpec(mode, loss=loss, eval_metric_ops=eval_metric_ops) eval_metric_ops[name] = function(tensors[self.labels[0]], predictions, weights) return tf.estimator.EstimatorSpec( mode, loss=loss, eval_metric_ops=eval_metric_ops) if mode == tf.estimator.ModeKeys.TRAIN: loss = create_tensors(self.loss, tensors, 1) global_step = tf.train.get_global_step() Loading @@ -936,7 +952,8 @@ class TensorGraph(Model): return tf.estimator.Estimator(model_fn=model_fn, model_dir=model_dir) def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): """This is called by make_estimator() to create tensors for the inputs. feature_columns and weight_column are the arguments passed to Loading @@ -949,16 +966,20 @@ class TensorGraph(Model): method. """ if self.__class__.default_generator is not TensorGraph.default_generator: raise ValueError("Class overrides default_generator() but not create_estimator_inputs()") raise ValueError( "Class overrides default_generator() but not create_estimator_inputs()" ) tensors = {} for layer, column in zip(self.features, feature_columns): tensors[layer] = tf.feature_column.input_layer(features, [column]) if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer(features, [weight_column]) tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = tf.cast(labels, self.labels[0].dtype) return tensors def _enqueue_batch(tg, generator, graph, sess, n_enqueued, final_sample): """ Function to load data into Loading Loading @@ -986,7 +1007,8 @@ def _enqueue_batch(tg, generator, graph, sess, n_enqueued, final_sample): layer_dims = len(layer.shape) if value_dims < layer_dims: if all(i == 1 for i in layer.shape[value_dims:]): value = value.reshape(list(value.shape)+[1]*(layer_dims-value_dims)) value = value.reshape( list(value.shape) + [1] * (layer_dims - value_dims)) if value_dims > layer_dims: if all(i == 1 for i in value.shape[layer_dims:]): value = value.reshape(value.shape[:layer_dims]) Loading deepchem/models/tensorgraph/tests/test_estimators.py 0 → 100644 +95 −0 Original line number Diff line number Diff line import unittest import numpy as np import tensorflow as tf import deepchem as dc from deepchem.data import NumpyDataset class TestEstimators(unittest.TestCase): """ Test converting TensorGraphs to Estimators. """ def test_multi_task_classifier(self): """Test creating an Estimator from a MultiTaskClassifier.""" n_samples = 10 n_features = 3 n_tasks = 1 # Create a dataset and an input function for processing it. np.random.seed(123) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y) def input_fn(epochs): x, y, weights = dataset.make_iterator( batch_size=n_samples, epochs=epochs).get_next() return {'x': x, 'weights': weights}, y # Create a TensorGraph model. model = dc.models.MultiTaskClassifier(n_tasks, n_features, dropouts=0) # Create an estimator from it. x_col = tf.feature_column.numeric_column('x', shape=(n_features,)) weight_col = tf.feature_column.numeric_column('weights') def accuracy(labels, predictions, weights): return tf.metrics.accuracy(labels, tf.round(predictions), weights) metrics = {'accuracy': accuracy} estimator = model.make_estimator( feature_columns=[x_col], weight_column=weight_col, metrics=metrics) # Train the model. estimator.train(input_fn=lambda: input_fn(100), steps=100) # Evaluate the model. results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['loss'] < 1e-4 assert results['accuracy'] > 0.9 def test_multi_task_regressor(self): """Test creating an Estimator from a MultiTaskRegressor.""" n_samples = 10 n_features = 3 n_tasks = 1 # Create a dataset and an input function for processing it. np.random.seed(123) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y) def input_fn(epochs): x, y, weights = dataset.make_iterator( batch_size=n_samples, epochs=epochs).get_next() return {'x': x, 'weights': weights}, y # Create a TensorGraph model. model = dc.models.MultiTaskRegressor(n_tasks, n_features, dropouts=0) # Create an estimator from it. x_col = tf.feature_column.numeric_column('x', shape=(n_features,)) weight_col = tf.feature_column.numeric_column('weights') metrics = {'error': tf.metrics.mean_absolute_error} estimator = model.make_estimator( feature_columns=[x_col], weight_column=weight_col, metrics=metrics) # Train the model. estimator.train(input_fn=lambda: input_fn(100), steps=100) # Evaluate the model. results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['loss'] < 1e-3 assert results['error'] < 0.1 Loading
deepchem/models/tensorgraph/fcnet.py +6 −3 Original line number Diff line number Diff line Loading @@ -153,14 +153,17 @@ class MultiTaskClassifier(TensorGraph): feed_dict[self.task_weights[0]] = w_b yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = {} for layer, column in zip(self.features, feature_columns): tensors[layer] = tf.feature_column.input_layer(features, [column]) if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer(features, [weight_column]) tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = tf.one_hot(tf.cast(labels, tf.int32), self.n_classes) tensors[self.labels[0]] = tf.one_hot( tf.cast(labels, tf.int32), self.n_classes) return tensors def predict_proba(self, dataset, transformers=[], outputs=None): Loading
deepchem/models/tensorgraph/tensor_graph.py +38 −16 Original line number Diff line number Diff line Loading @@ -839,7 +839,11 @@ class TensorGraph(Model): feed_dict[self._training_placeholder] = train_value yield feed_dict def make_estimator(self, feature_columns, weight_column=None, model_dir=None, metrics={}): def make_estimator(self, feature_columns, weight_column=None, model_dir=None, metrics={}): """Construct a Tensorflow Estimator from this model. tf.estimator.Estimator is the standard Tensorflow API for representing models. Loading Loading @@ -872,17 +876,22 @@ class TensorGraph(Model): # Check the inputs. if len(feature_columns) != len(self.features): raise ValueError('This model requires %d feature column(s)' % len(self.features)) raise ValueError( 'This model requires %d feature column(s)' % len(self.features)) if len(self.labels) != 1: raise ValueError('Can only create an Estimator from a model with exactly one Label input') raise ValueError( 'Can only create an Estimator from a model with exactly one Label input' ) if len(self.task_weights) > 1: raise ValueError('Cannot create an Estimator from a model with multiple Weight inputs') raise ValueError( 'Cannot create an Estimator from a model with multiple Weight inputs') if weight_column is None: if len(self.task_weights) > 0: raise ValueError('This model requires a weight column') else: if len(self.task_weights) == 0: raise ValueError('Cannot specify weight_column for a model with no Weight inputs') raise ValueError( 'Cannot specify weight_column for a model with no Weight inputs') if model_dir is None: model_dir = self.model_dir Loading @@ -891,8 +900,12 @@ class TensorGraph(Model): def create_tensors(layer, tensors, training): if layer in tensors: return tensors[layer] inputs = [create_tensors(in_layer, tensors, training) for in_layer in layer.in_layers] tensor = layer.create_tensor(in_layers=inputs, set_tensors=False, training=training) inputs = [ create_tensors(in_layer, tensors, training) for in_layer in layer.in_layers ] tensor = layer.create_tensor( in_layers=inputs, set_tensors=False, training=training) tensors[layer] = tensor layer.add_summary_to_tg(tensor) return tensor Loading @@ -902,7 +915,8 @@ class TensorGraph(Model): def model_fn(features, labels, mode): # Define the inputs. tensors = self.create_estimator_inputs(feature_columns, weight_column, features, labels, mode) tensors = self.create_estimator_inputs(feature_columns, weight_column, features, labels, mode) for layer, tensor in tensors.items(): layer.add_summary_to_tg(tensor) Loading @@ -922,8 +936,10 @@ class TensorGraph(Model): weights = tensors[self.task_weights[0]] eval_metric_ops = {} for name, function in metrics.items(): eval_metric_ops[name] = function(tensors[self.labels[0]], predictions, weights) return tf.estimator.EstimatorSpec(mode, loss=loss, eval_metric_ops=eval_metric_ops) eval_metric_ops[name] = function(tensors[self.labels[0]], predictions, weights) return tf.estimator.EstimatorSpec( mode, loss=loss, eval_metric_ops=eval_metric_ops) if mode == tf.estimator.ModeKeys.TRAIN: loss = create_tensors(self.loss, tensors, 1) global_step = tf.train.get_global_step() Loading @@ -936,7 +952,8 @@ class TensorGraph(Model): return tf.estimator.Estimator(model_fn=model_fn, model_dir=model_dir) def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): """This is called by make_estimator() to create tensors for the inputs. feature_columns and weight_column are the arguments passed to Loading @@ -949,16 +966,20 @@ class TensorGraph(Model): method. """ if self.__class__.default_generator is not TensorGraph.default_generator: raise ValueError("Class overrides default_generator() but not create_estimator_inputs()") raise ValueError( "Class overrides default_generator() but not create_estimator_inputs()" ) tensors = {} for layer, column in zip(self.features, feature_columns): tensors[layer] = tf.feature_column.input_layer(features, [column]) if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer(features, [weight_column]) tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = tf.cast(labels, self.labels[0].dtype) return tensors def _enqueue_batch(tg, generator, graph, sess, n_enqueued, final_sample): """ Function to load data into Loading Loading @@ -986,7 +1007,8 @@ def _enqueue_batch(tg, generator, graph, sess, n_enqueued, final_sample): layer_dims = len(layer.shape) if value_dims < layer_dims: if all(i == 1 for i in layer.shape[value_dims:]): value = value.reshape(list(value.shape)+[1]*(layer_dims-value_dims)) value = value.reshape( list(value.shape) + [1] * (layer_dims - value_dims)) if value_dims > layer_dims: if all(i == 1 for i in value.shape[layer_dims:]): value = value.reshape(value.shape[:layer_dims]) Loading
deepchem/models/tensorgraph/tests/test_estimators.py 0 → 100644 +95 −0 Original line number Diff line number Diff line import unittest import numpy as np import tensorflow as tf import deepchem as dc from deepchem.data import NumpyDataset class TestEstimators(unittest.TestCase): """ Test converting TensorGraphs to Estimators. """ def test_multi_task_classifier(self): """Test creating an Estimator from a MultiTaskClassifier.""" n_samples = 10 n_features = 3 n_tasks = 1 # Create a dataset and an input function for processing it. np.random.seed(123) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y) def input_fn(epochs): x, y, weights = dataset.make_iterator( batch_size=n_samples, epochs=epochs).get_next() return {'x': x, 'weights': weights}, y # Create a TensorGraph model. model = dc.models.MultiTaskClassifier(n_tasks, n_features, dropouts=0) # Create an estimator from it. x_col = tf.feature_column.numeric_column('x', shape=(n_features,)) weight_col = tf.feature_column.numeric_column('weights') def accuracy(labels, predictions, weights): return tf.metrics.accuracy(labels, tf.round(predictions), weights) metrics = {'accuracy': accuracy} estimator = model.make_estimator( feature_columns=[x_col], weight_column=weight_col, metrics=metrics) # Train the model. estimator.train(input_fn=lambda: input_fn(100), steps=100) # Evaluate the model. results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['loss'] < 1e-4 assert results['accuracy'] > 0.9 def test_multi_task_regressor(self): """Test creating an Estimator from a MultiTaskRegressor.""" n_samples = 10 n_features = 3 n_tasks = 1 # Create a dataset and an input function for processing it. np.random.seed(123) X = np.random.rand(n_samples, n_features) y = np.zeros((n_samples, n_tasks)) dataset = dc.data.NumpyDataset(X, y) def input_fn(epochs): x, y, weights = dataset.make_iterator( batch_size=n_samples, epochs=epochs).get_next() return {'x': x, 'weights': weights}, y # Create a TensorGraph model. model = dc.models.MultiTaskRegressor(n_tasks, n_features, dropouts=0) # Create an estimator from it. x_col = tf.feature_column.numeric_column('x', shape=(n_features,)) weight_col = tf.feature_column.numeric_column('weights') metrics = {'error': tf.metrics.mean_absolute_error} estimator = model.make_estimator( feature_columns=[x_col], weight_column=weight_col, metrics=metrics) # Train the model. estimator.train(input_fn=lambda: input_fn(100), steps=100) # Evaluate the model. results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['loss'] < 1e-3 assert results['error'] < 0.1
