def testAdditionalOutputs(self):
"""Tests multi-class classification using matrix data as input."""
hparams = tensor_forest.ForestHParams(num_trees=1,
max_nodes=100,
num_classes=3,
num_features=4,
split_after_samples=20,
inference_tree_paths=True)
classifier = random_forest.CoreTensorForestEstimator(
hparams.fill(), keys_column='keys', include_all_in_serving=True)
iris = base.load_iris()
data = iris.data.astype(np.float32)
labels = iris.target.astype(np.int32)
input_fn = numpy_io.numpy_input_fn(x={
'x':
data,
'keys':
np.arange(len(iris.data)).reshape(150, 1)
},
y=labels,
batch_size=10,
num_epochs=1,
shuffle=False)
classifier.train(input_fn=input_fn, steps=100)
predictions = list(classifier.predict(input_fn=input_fn))
# Check that there is a key column, tree paths and var.
for pred in predictions:
self.assertTrue('keys' in pred)
self.assertTrue('tree_paths' in pred)
self.assertTrue('prediction_variance' in pred)
def testWithFeatureColumns(self):
head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
n_classes=3,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(num_trees=3,
max_nodes=1000,
num_classes=3,
num_features=4,
split_after_samples=20,
inference_tree_paths=True)
est = random_forest.CoreTensorForestEstimator(
hparams.fill(),
head=head_fn,
feature_columns=[core_feature_column.numeric_column('x')])
iris = base.load_iris()
data = {'x': iris.data.astype(np.float32)}
labels = iris.target.astype(np.int32)
input_fn = numpy_io.numpy_input_fn(x=data,
y=labels,
batch_size=150,
num_epochs=None,
shuffle=False)
est.train(input_fn=input_fn, steps=100)
res = est.evaluate(input_fn=input_fn, steps=1)
self.assertEqual(1.0, res['accuracy'])
self.assertAllClose(0.55144483, res['loss'])
def testRegression(self):
"""Tests regression using matrix data as input."""
head_fn = head_lib._regression_head(
label_dimension=1,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(num_trees=5,
max_nodes=1000,
num_classes=1,
num_features=13,
regression=True,
split_after_samples=20)
regressor = random_forest.CoreTensorForestEstimator(hparams.fill(),
head=head_fn)
input_fn, predict_input_fn = _get_regression_input_fns()
regressor.train(input_fn=input_fn, steps=100)
res = regressor.evaluate(input_fn=input_fn, steps=10)
self.assertGreaterEqual(0.1, res['loss'])
predictions = list(regressor.predict(input_fn=predict_input_fn))
self.assertAllClose([[24.]],
[pred['predictions'] for pred in predictions],
atol=1)
def testTrainEvaluateInferDoesNotThrowErrorForClassifier(self):
head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
n_classes=3,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(num_trees=3,
max_nodes=1000,
num_classes=3,
num_features=4,
split_after_samples=20,
inference_tree_paths=True)
est = random_forest.CoreTensorForestEstimator(hparams.fill(),
head=head_fn)
input_fn, predict_input_fn = _get_classification_input_fns()
est.train(input_fn=input_fn, steps=100)
res = est.evaluate(input_fn=input_fn, steps=1)
self.assertEqual(1.0, res['accuracy'])
self.assertAllClose(0.55144483, res['loss'])
predictions = list(est.predict(input_fn=predict_input_fn))
self.assertAllClose([[0.576117, 0.211942, 0.211942]],
[pred['probabilities'] for pred in predictions])
def testAutofillsClassificationHead(self):
hparams = tensor_forest.ForestHParams(num_trees=3,
max_nodes=1000,
num_classes=3,
num_features=4,
split_after_samples=20,
inference_tree_paths=True)
est = random_forest.CoreTensorForestEstimator(hparams.fill())
input_fn, _ = _get_classification_input_fns()
est.train(input_fn=input_fn, steps=100)
res = est.evaluate(input_fn=input_fn, steps=1)
self.assertEqual(1.0, res['accuracy'])
self.assertAllClose(0.55144483, res['loss'])
def testAutofillsRegressionHead(self):
hparams = tensor_forest.ForestHParams(num_trees=5,
max_nodes=1000,
num_classes=1,
num_features=13,
regression=True,
split_after_samples=20)
regressor = random_forest.CoreTensorForestEstimator(hparams.fill())
input_fn, predict_input_fn = _get_regression_input_fns()
regressor.train(input_fn=input_fn, steps=100)
res = regressor.evaluate(input_fn=input_fn, steps=10)
self.assertGreaterEqual(0.1, res['loss'])
predictions = list(regressor.predict(input_fn=predict_input_fn))
self.assertAllClose([[24.]],
[pred['predictions'] for pred in predictions],
atol=1)
def testEarlyStopping(self):
head_fn = head_lib._multi_class_head_with_softmax_cross_entropy_loss(
n_classes=3,
loss_reduction=losses.Reduction.SUM_OVER_NONZERO_WEIGHTS)
hparams = tensor_forest.ForestHParams(num_trees=3,
max_nodes=1000,
num_classes=3,
num_features=4,
split_after_samples=20,
inference_tree_paths=True)
est = random_forest.CoreTensorForestEstimator(
hparams.fill(),
head=head_fn,
# Set a crazy threshold - 30% loss change.
early_stopping_loss_threshold=0.3,
early_stopping_rounds=2)
input_fn, _ = _get_classification_input_fns()
est.train(input_fn=input_fn, steps=100)
# We stopped early.
self._assert_checkpoint(est.model_dir, global_step=8)