Updated implementation of LogTransformer with base case (f36b2a72) · Commits · 钟慕尧 / deepchem

deepchem/transformers/init.py

+38 −26

Original line number	Diff line number	Diff line
		@@ -188,8 +188,11 @@ class LogTransformer(Transformer):
		row = df.iloc[i]
		if self.transform_X:
		X = load_from_disk(os.path.join(data_dir, row['X-transformed']))
		end_feat=len(X[1,:])
		for j in xrange(end_feat):
		num_features=len(X[0])
		if self.features is None:
		X = np.log(X+1)
		else:
		for j in xrange(num_features):
		if j in self.features:
		X[:,j] = np.log(X[:,j]+1)
		else:
		@@ -198,8 +201,11 @@ class LogTransformer(Transformer):

		if self.transform_y:
		y = load_from_disk(os.path.join(data_dir, row['y-transformed']))
		end_task=len(y[1,:])
		for j in xrange(end_task):
		num_tasks=len(y[0])
		if self.tasks is None:
		y = np.log(y+1)
		else:
		for j in xrange(num_tasks):
		if j in self.tasks:
		y[:,j] = np.log(y[:,j]+1)
		else:
		@@ -211,16 +217,22 @@ class LogTransformer(Transformer):
		Undo transformation on provided data.
		"""
		if self.transform_X:
		end_feat=len(z[1,:])
		for j in xrange(end_feat):
		num_features=len(z[0])
		if self.features is None:
		return np.exp(z)-1
		else:
		for j in xrange(num_features):
		if j in self.features:
		z[:,j] = np.exp(z[:,j])-1
		else:
		z[:,j] = z[:,j]
		return z
		elif self.transform_y:
		end_task=len(z[1,:])
		for j in xrange(end_task):
		num_tasks=len(z[0])
		if self.tasks is None:
		return np.exp(z)-1
		else:
		for j in xrange(num_tasks):
		if j in self.tasks:
		z[:,j] = np.exp(z[:,j])-1
		else:

deepchem/transformers/tests/test_transformers.py

+6 −9

Original line number	Diff line number	Diff line
		@@ -20,9 +20,8 @@ from deepchem.datasets.tests import TestDatasetAPI
		class TestTransformerAPI(TestDatasetAPI):
		"""Test top-level API for transformer objects."""

		"""
		def test_y_log_transformer(self):
		# Tests logarithmic data transformer.
		"""Tests logarithmic data transformer."""
		solubility_dataset = self.load_solubility_data()
		log_transformer = LogTransformer(
		transform_y=True, dataset=solubility_dataset)
		@@ -42,10 +41,9 @@ class TestTransformerAPI(TestDatasetAPI):

		# Check that untransform does the right thing.
		np.testing.assert_allclose(log_transformer.untransform(y_t), y)
		"""
		"""

		def test_X_log_transformer(self):
		# Tests logarithmic data transformer.
		"""Tests logarithmic data transformer."""
		solubility_dataset = self.load_solubility_data()
		log_transformer = LogTransformer(
		transform_X=True, dataset=solubility_dataset)
		@@ -65,9 +63,8 @@ class TestTransformerAPI(TestDatasetAPI):

		# Check that untransform does the right thing.
		np.testing.assert_allclose(log_transformer.untransform(X_t), X)
		"""

		def test_y_log_transformer(self):
		def test_y_log_transformer_select(self):
		"""Tests logarithmic data transformer with selection."""
		multitask_dataset = self.load_feat_multitask_data()
		dfe = pd.read_csv("../../models/tests/feat_multitask_example.csv")
		@@ -98,7 +95,7 @@ class TestTransformerAPI(TestDatasetAPI):
		# Check that untransform does the right thing.
		np.testing.assert_allclose(log_transformer.untransform(y_t), y)

		def test_X_log_transformer(self):
		def test_X_log_transformer_select(self):
		#Tests logarithmic data transformer with selection.
		multitask_dataset = self.load_feat_multitask_data()
		dfe = pd.read_csv("../../models/tests/feat_multitask_example.csv")

Admin message