Added smiles_to_seq conversion to input_fn and corresponding changes in text_cnn (04fadd9f) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/models/text_cnn.py

+17 −2

Original line number	Diff line number	Diff line
		@@ -205,6 +205,22 @@ class TextCNNModel(TensorGraph):
		weighted_loss = WeightedError(in_layers=[loss, weights])
		self.set_loss(weighted_loss)

		@staticmethod
		def convert_bytes_to_char(s):
		s = ''.join(chr(b) for b in s)
		return s

		def smiles_to_seq_batch(self, ids_b):
		"""Converts SMILES strings to np.array sequence.

		A tf.py_func wrapper is written around this when creating the input_fn for make_estimator
		"""
		if isinstance(ids_b[0], bytes):
		ids_b = [TextCNNModel.convert_bytes_to_char(smiles) for smiles in ids_b]
		smiles_seqs = [self.smiles_to_seq(smiles) for smiles in ids_b]
		smiles_seqs = np.vstack(smiles_seqs)
		return smiles_seqs

		def default_generator(self,
		dataset,
		epochs=1,
		@@ -230,8 +246,7 @@ class TextCNNModel(TensorGraph):
		feed_dict[self.task_weights[0]] = w_b

		# Transform SMILES sequence to integers
		smiles_seqs = [self.smiles_to_seq(smiles) for smiles in ids_b]
		feed_dict[self.smiles_seqs] = np.vstack(smiles_seqs)
		feed_dict[self.smiles_seqs] = self.smiles_to_seq_batch(ids_b)
		yield feed_dict

		def create_estimator_inputs(self, feature_columns, weight_column, features,

deepchem/models/tensorgraph/tests/test_estimators.py

+8 −5

Original line number	Diff line number	Diff line
		@@ -296,7 +296,7 @@ class TestEstimators(unittest.TestCase):

		np.random.seed(123)
		smile_ids = ["CCCCC", "CCC(=O)O", "CCC", "CC(=O)O", "O=C=O"]
		X = [model.smiles_to_seq(smile) for smile in smile_ids]
		X = smile_ids
		y = np.zeros((n_samples, n_tasks))
		w = np.ones((n_samples, n_tasks))
		dataset = NumpyDataset(X, y, w, smile_ids)
		@@ -307,7 +307,8 @@ class TestEstimators(unittest.TestCase):
		def input_fn(epochs):
		x, y, weights = dataset.make_iterator(
		batch_size=n_samples, epochs=epochs).get_next()
		return {'x': x, 'weights': weights}, y
		smiles_seq = tf.py_func(model.smiles_to_seq_batch, inp=[x], Tout=tf.int32)
		return {'x': smiles_seq, 'weights': weights}, y

		# Create an estimator from it.
		x_col = tf.feature_column.numeric_column(
		@@ -342,7 +343,7 @@ class TestEstimators(unittest.TestCase):

		np.random.seed(123)
		smile_ids = ["CCCCC", "CCC(=O)O", "CCC", "CC(=O)O", "O=C=O"]
		X = [model.smiles_to_seq(smile) for smile in smile_ids]
		X = smile_ids
		y = np.zeros((n_samples, n_tasks, 1), dtype=np.float32)
		w = np.ones((n_samples, n_tasks))
		dataset = NumpyDataset(X, y, w, smile_ids)
		@@ -350,10 +351,12 @@ class TestEstimators(unittest.TestCase):
		def input_fn(epochs):
		x, y, weights = dataset.make_iterator(
		batch_size=n_samples, epochs=epochs).get_next()
		return {'x': x, 'weights': weights}, y
		smiles_seq = tf.py_func(model.smiles_to_seq_batch, inp=[x], Tout=tf.int32)
		return {'x': smiles_seq, 'weights': weights}, y

		# Create an estimator from it.
		x_col = tf.feature_column.numeric_column('x', shape=(seq_length,))
		x_col = tf.feature_column.numeric_column(
		'x', shape=(seq_length,), dtype=tf.int32)
		weight_col = tf.feature_column.numeric_column('weights', shape=(n_tasks,))
		metrics = {'error': tf.metrics.mean_absolute_error}
		estimator = model.make_estimator(

Admin message