Loading deepchem/models/tensorgraph/models/symmetry_function_regression.py +110 −57 Original line number Diff line number Diff line Loading @@ -16,7 +16,7 @@ import tensorflow as tf import deepchem as dc from deepchem.models.tensorgraph.layers import Dense, Concat, WeightedError, Stack, Layer, ANIFeat, Exp from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature, Dropout, WeightDecay from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature, Dropout, WeightDecay, ReduceSum, Reshape from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.models.tensorgraph.graph_layers import DTNNEmbedding from deepchem.models.tensorgraph.symmetry_functions import DistanceMatrix, \ Loading Loading @@ -49,12 +49,18 @@ class BPSymmetryFunctionRegression(TensorGraph): super(BPSymmetryFunctionRegression, self).__init__(**kwargs) self.build_graph() self._build_graph() def build_graph(self): self.atom_flags = Feature(shape=(None, self.max_atoms, self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms, self.n_feat)) previous_layer = self.atom_feats def _build_graph(self): self.atom_flags = Feature(shape=(None, self.max_atoms * self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms * self.n_feat)) reshaped_atom_feats = Reshape( in_layers=[self.atom_feats], shape=(-1, self.max_atoms, self.n_feat)) reshaped_atom_flags = Reshape( in_layers=[self.atom_flags], shape=(-1, self.max_atoms, self.max_atoms)) previous_layer = reshaped_atom_feats Hiddens = [] for n_hidden in self.layer_structures: Loading @@ -65,23 +71,27 @@ class BPSymmetryFunctionRegression(TensorGraph): Hiddens.append(Hidden) previous_layer = Hiddens[-1] costs = [] self.labels_fd = [] for task in range(self.n_tasks): regression = Dense( out_channels=1, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather(self.max_atoms, in_layers=[regression, self.atom_flags]) out_channels=1 * self.n_tasks, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather( self.max_atoms, in_layers=[regression, reshaped_atom_flags]) self.add_output(output) label = Label(shape=(None, 1)) self.labels_fd.append(label) cost = L2Loss(in_layers=[label, output]) costs.append(cost) label = Label(shape=(None, self.n_tasks, 1)) loss = ReduceSum(L2Loss(in_layers=[label, output])) weights = Weights(shape=(None, self.n_tasks)) weighted_loss = WeightedError(in_layers=[loss, weights]) self.set_loss(weighted_loss) all_cost = Stack(in_layers=costs, axis=1) self.weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[all_cost, self.weights]) self.set_loss(loss) def compute_features_on_batch(self, X_b): flags = np.sign(np.array(X_b[:, :, 0])) atom_flags = np.stack([flags] * self.max_atoms, axis=2) * \ np.stack([flags] * self.max_atoms, axis=1) atom_feats = np.array(X_b[:, :, 1:], dtype=np.float32) return [atom_feats, atom_flags] def default_generator(self, dataset, Loading @@ -99,17 +109,33 @@ class BPSymmetryFunctionRegression(TensorGraph): feed_dict = dict() if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] feed_dict[self.labels[0]] = y_b if w_b is not None and not predict: feed_dict[self.weights] = w_b feed_dict[self.task_weights[0]] = w_b atom_feats, atom_flags = self.compute_features_on_batch(X_b) feed_dict[self.atom_feats] = atom_feats feed_dict[self.atom_flags] = atom_flags flags = np.sign(np.array(X_b[:, :, 0])) feed_dict[self.atom_flags] = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) feed_dict[self.atom_feats] = np.array(X_b[:, :, 1:], dtype=float) yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = dict() for layer, column in zip(self.features, feature_columns): feature_col = tf.feature_column.input_layer(features, [column]) if feature_col.dtype != column.dtype: feature_col = tf.cast(feature_col, column.dtype) tensors[layer] = feature_col if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = labels return tensors class ANIRegression(TensorGraph): Loading Loading @@ -304,11 +330,16 @@ class ANIRegression(TensorGraph): def build_graph(self): self.atom_numbers = Feature(shape=(None, self.max_atoms), dtype=tf.int32) self.atom_flags = Feature(shape=(None, self.max_atoms, self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms, 4)) self.atom_flags = Feature(shape=(None, self.max_atoms * self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms * 4)) reshaped_atom_flags = Reshape( in_layers=[self.atom_flags], shape=(-1, self.max_atoms, self.max_atoms)) reshaped_atom_feats = Reshape( in_layers=[self.atom_feats], shape=(-1, self.max_atoms, 4)) previous_layer = ANIFeat( in_layers=self.atom_feats, max_atoms=self.max_atoms) in_layers=reshaped_atom_feats, max_atoms=self.max_atoms) self.featurized = previous_layer Loading @@ -323,25 +354,31 @@ class ANIRegression(TensorGraph): Hiddens.append(Hidden) previous_layer = Hiddens[-1] costs = [] self.labels_fd = [] for task in range(self.n_tasks): regression = Dense( out_channels=1, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather(self.max_atoms, in_layers=[regression, self.atom_flags]) out_channels=1 * self.n_tasks, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather( self.max_atoms, in_layers=[regression, reshaped_atom_flags]) self.add_output(output) label = Label(shape=(None, 1)) self.labels_fd.append(label) cost = L2Loss(in_layers=[label, output]) costs.append(cost) label = Label(shape=(None, self.n_tasks, 1)) loss = ReduceSum(L2Loss(in_layers=[label, output])) weights = Weights(shape=(None, self.n_tasks)) all_cost = Stack(in_layers=costs, axis=1) self.weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[all_cost, self.weights]) weighted_loss = WeightedError(in_layers=[loss, weights]) if self.exp_loss: loss = Exp(in_layers=[loss]) self.set_loss(loss) weighted_loss = Exp(in_layers=[weighted_loss]) self.set_loss(weighted_loss) def compute_features_on_batch(self, X_b): flags = np.sign(np.array(X_b[:, :, 0])) atom_flags = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) atom_numbers = np.array(X_b[:, :, 0], dtype=np.int32) atom_feats = np.array(X_b[:, :, :], dtype=np.float32) return [atom_feats, atom_numbers, atom_flags] def default_generator(self, dataset, Loading @@ -359,18 +396,34 @@ class ANIRegression(TensorGraph): feed_dict = dict() if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] feed_dict[self.labels[0]] = y_b if w_b is not None and not predict: feed_dict[self.weights] = w_b feed_dict[self.task_weights[0]] = w_b flags = np.sign(np.array(X_b[:, :, 0])) feed_dict[self.atom_flags] = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) feed_dict[self.atom_numbers] = np.array(X_b[:, :, 0], dtype=int) feed_dict[self.atom_feats] = np.array(X_b[:, :, :], dtype=float) atom_feats, atom_numbers, atom_flags = self.compute_features_on_batch( X_b) feed_dict[self.atom_feats] = atom_feats feed_dict[self.atom_numbers] = atom_numbers feed_dict[self.atom_flags] = atom_flags yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = dict() for layer, column in zip(self.features, feature_columns): feature_col = tf.feature_column.input_layer(features, [column]) if feature_col.dtype != column.dtype: feature_col = tf.cast(feature_col, column.dtype) tensors[layer] = feature_col if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = labels return tensors def save_numpy(self): """ Save to a portable numpy file. Note that this relies on the names to be consistent Loading deepchem/models/tensorgraph/tests/test_estimators.py +151 −2 Original line number Diff line number Diff line Loading @@ -467,9 +467,11 @@ class TestEstimators(unittest.TestCase): input_file = os.path.join(current_dir, "example_DTNN.mat") dataset = loadmat(input_file) num_vals_to_use = 5 np.random.seed(123) X = dataset['X'] y = dataset['T'].astype(np.float32) X = dataset['X'][:num_vals_to_use] y = dataset['T'][:num_vals_to_use].astype(np.float32) w = np.ones_like(y) dataset = dc.data.NumpyDataset(X, y, w, ids=None) n_tasks = y.shape[1] Loading Loading @@ -527,3 +529,150 @@ class TestEstimators(unittest.TestCase): results = estimator.evaluate(input_fn=lambda: input_fn(n_samples, 1)) assert results['error'] < 0.1 def test_bpsymm_regression_model(self): """Test creating an estimator for BPSymmetry Regression model.""" tasks, dataset, transformers = dc.molnet.load_qm7_from_mat( featurizer='BPSymmetryFunction', move_mean=False) num_samples_to_use = 5 train, _, _ = dataset X = train.X[:num_samples_to_use] y = train.y[:num_samples_to_use] w = train.w[:num_samples_to_use] ids = train.ids[:num_samples_to_use] dataset = dc.data.NumpyDataset(X, y, w, ids) max_atoms = 23 batch_size = 16 layer_structures = [128, 128, 64] ANItransformer = dc.trans.ANITransformer( max_atoms=max_atoms, atomic_number_differentiated=False) dataset = ANItransformer.transform(dataset) n_feat = ANItransformer.get_num_feats() - 1 model = dc.models.BPSymmetryFunctionRegression( len(tasks), max_atoms, n_feat, layer_structures=layer_structures, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") metrics = {'error': tf.metrics.mean_absolute_error} def input_fn(epochs): X, y, w = dataset.make_iterator( batch_size=batch_size, epochs=epochs).get_next() atom_feats, atom_flags = tf.py_func( model.compute_features_on_batch, [X], Tout=[tf.float32, tf.float32]) atom_feats = tf.reshape( atom_feats, shape=(tf.shape(atom_feats)[0], model.max_atoms * model.n_feat)) atom_flags = tf.reshape( atom_flags, shape=(tf.shape(atom_flags)[0], model.max_atoms * model.max_atoms)) features = dict() features['atom_feats'] = atom_feats features['atom_flags'] = atom_flags features['weights'] = w return features, y atom_feats = tf.feature_column.numeric_column( 'atom_feats', shape=(max_atoms * n_feat,), dtype=tf.float32) atom_flags = tf.feature_column.numeric_column( 'atom_flags', shape=(max_atoms * max_atoms), dtype=tf.float32) weight_col = tf.feature_column.numeric_column( 'weights', shape=(len(tasks),), dtype=tf.float32) estimator = model.make_estimator( feature_columns=[atom_feats, atom_flags], weight_column=weight_col, metrics=metrics) estimator.train(input_fn=lambda: input_fn(100)) results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['error'] < 0.1 def test_ani_regression(self): """Test creating an estimator for ANI Regression.""" max_atoms = 4 X = np.array( [[ [1, 5.0, 3.2, 1.1], [6, 1.0, 3.4, -1.1], [1, 2.3, 3.4, 2.2], [0, 0, 0, 0], ], [ [8, 2.0, -1.4, -1.1], [7, 6.3, 2.4, 3.2], [0, 0, 0, 0], [0, 0, 0, 0], ]], dtype=np.float32) y = np.array([[2.0], [1.1]], dtype=np.float32) layer_structures = [128, 128, 64] atom_number_cases = [1, 6, 7, 8] kwargs = { "n_tasks": 1, "max_atoms": max_atoms, "layer_structures": layer_structures, "atom_number_cases": atom_number_cases, "batch_size": 2, "learning_rate": 0.001, "use_queue": False, "mode": "regression" } model = dc.models.ANIRegression(**kwargs) dataset = dc.data.NumpyDataset(X, y, n_tasks=1) metrics = {'error': tf.metrics.mean_absolute_error} def input_fn(epochs): X, y, w = dataset.make_iterator(batch_size=2, epochs=epochs).get_next() atom_feats, atom_numbers, atom_flags = tf.py_func( model.compute_features_on_batch, [X], Tout=[tf.float32, tf.int32, tf.float32]) atom_feats = tf.reshape( atom_feats, shape=(tf.shape(atom_feats)[0], model.max_atoms * 4)) atom_numbers = tf.reshape( atom_numbers, shape=(tf.shape(atom_numbers)[0], model.max_atoms)) atom_flags = tf.reshape( atom_flags, shape=(tf.shape(atom_flags)[0], model.max_atoms * model.max_atoms)) features = dict() features['atom_feats'] = atom_feats features['atom_numbers'] = atom_numbers features['atom_flags'] = atom_flags features['weights'] = w return features, y atom_feats = tf.feature_column.numeric_column( 'atom_feats', shape=(max_atoms * 4,), dtype=tf.float32) atom_numbers = tf.feature_column.numeric_column( 'atom_numbers', shape=(max_atoms,), dtype=tf.int32) atom_flags = tf.feature_column.numeric_column( 'atom_flags', shape=(max_atoms * max_atoms), dtype=tf.float32) weight_col = tf.feature_column.numeric_column( 'weights', shape=(kwargs["n_tasks"],), dtype=tf.float32) estimator = model.make_estimator( feature_columns=[atom_feats, atom_numbers, atom_flags], weight_column=weight_col, metrics=metrics) estimator.train(input_fn=lambda: input_fn(100)) results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['error'] < 0.1 Loading
deepchem/models/tensorgraph/models/symmetry_function_regression.py +110 −57 Original line number Diff line number Diff line Loading @@ -16,7 +16,7 @@ import tensorflow as tf import deepchem as dc from deepchem.models.tensorgraph.layers import Dense, Concat, WeightedError, Stack, Layer, ANIFeat, Exp from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature, Dropout, WeightDecay from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature, Dropout, WeightDecay, ReduceSum, Reshape from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.models.tensorgraph.graph_layers import DTNNEmbedding from deepchem.models.tensorgraph.symmetry_functions import DistanceMatrix, \ Loading Loading @@ -49,12 +49,18 @@ class BPSymmetryFunctionRegression(TensorGraph): super(BPSymmetryFunctionRegression, self).__init__(**kwargs) self.build_graph() self._build_graph() def build_graph(self): self.atom_flags = Feature(shape=(None, self.max_atoms, self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms, self.n_feat)) previous_layer = self.atom_feats def _build_graph(self): self.atom_flags = Feature(shape=(None, self.max_atoms * self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms * self.n_feat)) reshaped_atom_feats = Reshape( in_layers=[self.atom_feats], shape=(-1, self.max_atoms, self.n_feat)) reshaped_atom_flags = Reshape( in_layers=[self.atom_flags], shape=(-1, self.max_atoms, self.max_atoms)) previous_layer = reshaped_atom_feats Hiddens = [] for n_hidden in self.layer_structures: Loading @@ -65,23 +71,27 @@ class BPSymmetryFunctionRegression(TensorGraph): Hiddens.append(Hidden) previous_layer = Hiddens[-1] costs = [] self.labels_fd = [] for task in range(self.n_tasks): regression = Dense( out_channels=1, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather(self.max_atoms, in_layers=[regression, self.atom_flags]) out_channels=1 * self.n_tasks, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather( self.max_atoms, in_layers=[regression, reshaped_atom_flags]) self.add_output(output) label = Label(shape=(None, 1)) self.labels_fd.append(label) cost = L2Loss(in_layers=[label, output]) costs.append(cost) label = Label(shape=(None, self.n_tasks, 1)) loss = ReduceSum(L2Loss(in_layers=[label, output])) weights = Weights(shape=(None, self.n_tasks)) weighted_loss = WeightedError(in_layers=[loss, weights]) self.set_loss(weighted_loss) all_cost = Stack(in_layers=costs, axis=1) self.weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[all_cost, self.weights]) self.set_loss(loss) def compute_features_on_batch(self, X_b): flags = np.sign(np.array(X_b[:, :, 0])) atom_flags = np.stack([flags] * self.max_atoms, axis=2) * \ np.stack([flags] * self.max_atoms, axis=1) atom_feats = np.array(X_b[:, :, 1:], dtype=np.float32) return [atom_feats, atom_flags] def default_generator(self, dataset, Loading @@ -99,17 +109,33 @@ class BPSymmetryFunctionRegression(TensorGraph): feed_dict = dict() if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] feed_dict[self.labels[0]] = y_b if w_b is not None and not predict: feed_dict[self.weights] = w_b feed_dict[self.task_weights[0]] = w_b atom_feats, atom_flags = self.compute_features_on_batch(X_b) feed_dict[self.atom_feats] = atom_feats feed_dict[self.atom_flags] = atom_flags flags = np.sign(np.array(X_b[:, :, 0])) feed_dict[self.atom_flags] = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) feed_dict[self.atom_feats] = np.array(X_b[:, :, 1:], dtype=float) yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = dict() for layer, column in zip(self.features, feature_columns): feature_col = tf.feature_column.input_layer(features, [column]) if feature_col.dtype != column.dtype: feature_col = tf.cast(feature_col, column.dtype) tensors[layer] = feature_col if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = labels return tensors class ANIRegression(TensorGraph): Loading Loading @@ -304,11 +330,16 @@ class ANIRegression(TensorGraph): def build_graph(self): self.atom_numbers = Feature(shape=(None, self.max_atoms), dtype=tf.int32) self.atom_flags = Feature(shape=(None, self.max_atoms, self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms, 4)) self.atom_flags = Feature(shape=(None, self.max_atoms * self.max_atoms)) self.atom_feats = Feature(shape=(None, self.max_atoms * 4)) reshaped_atom_flags = Reshape( in_layers=[self.atom_flags], shape=(-1, self.max_atoms, self.max_atoms)) reshaped_atom_feats = Reshape( in_layers=[self.atom_feats], shape=(-1, self.max_atoms, 4)) previous_layer = ANIFeat( in_layers=self.atom_feats, max_atoms=self.max_atoms) in_layers=reshaped_atom_feats, max_atoms=self.max_atoms) self.featurized = previous_layer Loading @@ -323,25 +354,31 @@ class ANIRegression(TensorGraph): Hiddens.append(Hidden) previous_layer = Hiddens[-1] costs = [] self.labels_fd = [] for task in range(self.n_tasks): regression = Dense( out_channels=1, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather(self.max_atoms, in_layers=[regression, self.atom_flags]) out_channels=1 * self.n_tasks, activation_fn=None, in_layers=[Hiddens[-1]]) output = BPGather( self.max_atoms, in_layers=[regression, reshaped_atom_flags]) self.add_output(output) label = Label(shape=(None, 1)) self.labels_fd.append(label) cost = L2Loss(in_layers=[label, output]) costs.append(cost) label = Label(shape=(None, self.n_tasks, 1)) loss = ReduceSum(L2Loss(in_layers=[label, output])) weights = Weights(shape=(None, self.n_tasks)) all_cost = Stack(in_layers=costs, axis=1) self.weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[all_cost, self.weights]) weighted_loss = WeightedError(in_layers=[loss, weights]) if self.exp_loss: loss = Exp(in_layers=[loss]) self.set_loss(loss) weighted_loss = Exp(in_layers=[weighted_loss]) self.set_loss(weighted_loss) def compute_features_on_batch(self, X_b): flags = np.sign(np.array(X_b[:, :, 0])) atom_flags = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) atom_numbers = np.array(X_b[:, :, 0], dtype=np.int32) atom_feats = np.array(X_b[:, :, :], dtype=np.float32) return [atom_feats, atom_numbers, atom_flags] def default_generator(self, dataset, Loading @@ -359,18 +396,34 @@ class ANIRegression(TensorGraph): feed_dict = dict() if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] feed_dict[self.labels[0]] = y_b if w_b is not None and not predict: feed_dict[self.weights] = w_b feed_dict[self.task_weights[0]] = w_b flags = np.sign(np.array(X_b[:, :, 0])) feed_dict[self.atom_flags] = np.stack([flags]*self.max_atoms, axis=2)*\ np.stack([flags]*self.max_atoms, axis=1) feed_dict[self.atom_numbers] = np.array(X_b[:, :, 0], dtype=int) feed_dict[self.atom_feats] = np.array(X_b[:, :, :], dtype=float) atom_feats, atom_numbers, atom_flags = self.compute_features_on_batch( X_b) feed_dict[self.atom_feats] = atom_feats feed_dict[self.atom_numbers] = atom_numbers feed_dict[self.atom_flags] = atom_flags yield feed_dict def create_estimator_inputs(self, feature_columns, weight_column, features, labels, mode): tensors = dict() for layer, column in zip(self.features, feature_columns): feature_col = tf.feature_column.input_layer(features, [column]) if feature_col.dtype != column.dtype: feature_col = tf.cast(feature_col, column.dtype) tensors[layer] = feature_col if weight_column is not None: tensors[self.task_weights[0]] = tf.feature_column.input_layer( features, [weight_column]) if labels is not None: tensors[self.labels[0]] = labels return tensors def save_numpy(self): """ Save to a portable numpy file. Note that this relies on the names to be consistent Loading
deepchem/models/tensorgraph/tests/test_estimators.py +151 −2 Original line number Diff line number Diff line Loading @@ -467,9 +467,11 @@ class TestEstimators(unittest.TestCase): input_file = os.path.join(current_dir, "example_DTNN.mat") dataset = loadmat(input_file) num_vals_to_use = 5 np.random.seed(123) X = dataset['X'] y = dataset['T'].astype(np.float32) X = dataset['X'][:num_vals_to_use] y = dataset['T'][:num_vals_to_use].astype(np.float32) w = np.ones_like(y) dataset = dc.data.NumpyDataset(X, y, w, ids=None) n_tasks = y.shape[1] Loading Loading @@ -527,3 +529,150 @@ class TestEstimators(unittest.TestCase): results = estimator.evaluate(input_fn=lambda: input_fn(n_samples, 1)) assert results['error'] < 0.1 def test_bpsymm_regression_model(self): """Test creating an estimator for BPSymmetry Regression model.""" tasks, dataset, transformers = dc.molnet.load_qm7_from_mat( featurizer='BPSymmetryFunction', move_mean=False) num_samples_to_use = 5 train, _, _ = dataset X = train.X[:num_samples_to_use] y = train.y[:num_samples_to_use] w = train.w[:num_samples_to_use] ids = train.ids[:num_samples_to_use] dataset = dc.data.NumpyDataset(X, y, w, ids) max_atoms = 23 batch_size = 16 layer_structures = [128, 128, 64] ANItransformer = dc.trans.ANITransformer( max_atoms=max_atoms, atomic_number_differentiated=False) dataset = ANItransformer.transform(dataset) n_feat = ANItransformer.get_num_feats() - 1 model = dc.models.BPSymmetryFunctionRegression( len(tasks), max_atoms, n_feat, layer_structures=layer_structures, batch_size=batch_size, learning_rate=0.001, use_queue=False, mode="regression") metrics = {'error': tf.metrics.mean_absolute_error} def input_fn(epochs): X, y, w = dataset.make_iterator( batch_size=batch_size, epochs=epochs).get_next() atom_feats, atom_flags = tf.py_func( model.compute_features_on_batch, [X], Tout=[tf.float32, tf.float32]) atom_feats = tf.reshape( atom_feats, shape=(tf.shape(atom_feats)[0], model.max_atoms * model.n_feat)) atom_flags = tf.reshape( atom_flags, shape=(tf.shape(atom_flags)[0], model.max_atoms * model.max_atoms)) features = dict() features['atom_feats'] = atom_feats features['atom_flags'] = atom_flags features['weights'] = w return features, y atom_feats = tf.feature_column.numeric_column( 'atom_feats', shape=(max_atoms * n_feat,), dtype=tf.float32) atom_flags = tf.feature_column.numeric_column( 'atom_flags', shape=(max_atoms * max_atoms), dtype=tf.float32) weight_col = tf.feature_column.numeric_column( 'weights', shape=(len(tasks),), dtype=tf.float32) estimator = model.make_estimator( feature_columns=[atom_feats, atom_flags], weight_column=weight_col, metrics=metrics) estimator.train(input_fn=lambda: input_fn(100)) results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['error'] < 0.1 def test_ani_regression(self): """Test creating an estimator for ANI Regression.""" max_atoms = 4 X = np.array( [[ [1, 5.0, 3.2, 1.1], [6, 1.0, 3.4, -1.1], [1, 2.3, 3.4, 2.2], [0, 0, 0, 0], ], [ [8, 2.0, -1.4, -1.1], [7, 6.3, 2.4, 3.2], [0, 0, 0, 0], [0, 0, 0, 0], ]], dtype=np.float32) y = np.array([[2.0], [1.1]], dtype=np.float32) layer_structures = [128, 128, 64] atom_number_cases = [1, 6, 7, 8] kwargs = { "n_tasks": 1, "max_atoms": max_atoms, "layer_structures": layer_structures, "atom_number_cases": atom_number_cases, "batch_size": 2, "learning_rate": 0.001, "use_queue": False, "mode": "regression" } model = dc.models.ANIRegression(**kwargs) dataset = dc.data.NumpyDataset(X, y, n_tasks=1) metrics = {'error': tf.metrics.mean_absolute_error} def input_fn(epochs): X, y, w = dataset.make_iterator(batch_size=2, epochs=epochs).get_next() atom_feats, atom_numbers, atom_flags = tf.py_func( model.compute_features_on_batch, [X], Tout=[tf.float32, tf.int32, tf.float32]) atom_feats = tf.reshape( atom_feats, shape=(tf.shape(atom_feats)[0], model.max_atoms * 4)) atom_numbers = tf.reshape( atom_numbers, shape=(tf.shape(atom_numbers)[0], model.max_atoms)) atom_flags = tf.reshape( atom_flags, shape=(tf.shape(atom_flags)[0], model.max_atoms * model.max_atoms)) features = dict() features['atom_feats'] = atom_feats features['atom_numbers'] = atom_numbers features['atom_flags'] = atom_flags features['weights'] = w return features, y atom_feats = tf.feature_column.numeric_column( 'atom_feats', shape=(max_atoms * 4,), dtype=tf.float32) atom_numbers = tf.feature_column.numeric_column( 'atom_numbers', shape=(max_atoms,), dtype=tf.int32) atom_flags = tf.feature_column.numeric_column( 'atom_flags', shape=(max_atoms * max_atoms), dtype=tf.float32) weight_col = tf.feature_column.numeric_column( 'weights', shape=(kwargs["n_tasks"],), dtype=tf.float32) estimator = model.make_estimator( feature_columns=[atom_feats, atom_numbers, atom_flags], weight_column=weight_col, metrics=metrics) estimator.train(input_fn=lambda: input_fn(100)) results = estimator.evaluate(input_fn=lambda: input_fn(1)) assert results['error'] < 0.1
