def DISABLED_testBinaryClassifierTrainInMemoryFloatColumns(self):
train_input_fn = _make_train_input_fn_dataset(is_classification=True)
predict_input_fn = numpy_io.numpy_input_fn(x=FEATURES_DICT,
y=None,
batch_size=1,
num_epochs=1,
shuffle=False)
est = boosted_trees.boosted_trees_classifier_train_in_memory(
train_input_fn=train_input_fn,
feature_columns=self._numeric_feature_columns,
n_trees=1,
max_depth=5,
quantile_sketch_epsilon=0.33)
# It will stop after 5 steps because of the max depth and num trees.
self._assert_checkpoint(est.model_dir,
global_step=5,
finalized_trees=1,
attempted_layers=5,
bucket_boundaries=[[-2.001, -1.999, 12.5],
[-3., 0.4995, 2.],
[-100., 20., 102.75]])
eval_res = est.evaluate(input_fn=train_input_fn, steps=1)
self.assertAllClose(eval_res['accuracy'], 1.0)
predictions = list(est.predict(input_fn=predict_input_fn))
self.assertAllClose([[0], [1], [1], [0], [0]],
[pred['class_ids'] for pred in predictions])
def testBinaryClassifierTrainInMemoryWithDataset(self):
train_input_fn = _make_train_input_fn_dataset(is_classification=True)
predict_input_fn = numpy_io.numpy_input_fn(x=FEATURES_DICT,
y=None,
batch_size=1,
num_epochs=1,
shuffle=False)
est = boosted_trees.boosted_trees_classifier_train_in_memory(
train_input_fn=train_input_fn,
feature_columns=self._feature_columns,
n_trees=1,
max_depth=5)
# It will stop after 5 steps because of the max depth and num trees.
self._assert_checkpoint(est.model_dir,
global_step=5,
finalized_trees=1,
attempted_layers=5)
# Check evaluate and predict.
eval_res = est.evaluate(input_fn=train_input_fn, steps=1)
self.assertAllClose(eval_res['accuracy'], 1.0)
predictions = list(est.predict(input_fn=predict_input_fn))
self.assertAllClose([[0], [1], [1], [0], [0]],
[pred['class_ids'] for pred in predictions])
def testV2(self):
with compat.forward_compatibility_horizon(2019, 8, 9):
control_flow_util.enable_control_flow_v2()
variable_scope.enable_resource_variables()
train_input_fn = _make_train_input_fn_dataset(
is_classification=True)
predict_input_fn = numpy_io.numpy_input_fn(x=FEATURES_DICT,
y=None,
batch_size=1,
num_epochs=1,
shuffle=False)
est = boosted_trees.boosted_trees_classifier_train_in_memory(
train_input_fn=train_input_fn,
feature_columns=self._numeric_feature_columns,
n_trees=1,
max_depth=5,
quantile_sketch_epsilon=0.33)
# It will stop after 5 steps because of the max depth and num trees.
self._assert_checkpoint(est.model_dir,
global_step=5,
finalized_trees=1,
attempted_layers=5,
bucket_boundaries=[[-2.001, -1.999, 12.5],
[-3., 0.4995, 2.],
[-100., 20., 102.75]])
eval_res = est.evaluate(input_fn=train_input_fn, steps=1)
self.assertAllClose(eval_res['accuracy'], 1.0)
predictions = list(est.predict(input_fn=predict_input_fn))
self.assertAllClose([[0], [1], [1], [0], [0]],
[pred['class_ids'] for pred in predictions])
def testBinaryClassifierTrainInMemoryAndEvalAndInferWithPrePruning(self):
train_input_fn = _make_train_input_fn(is_classification=True)
predict_input_fn = numpy_io.numpy_input_fn(x=FEATURES_DICT,
y=None,
batch_size=1,
num_epochs=1,
shuffle=False)
est = boosted_trees.boosted_trees_classifier_train_in_memory(
train_input_fn=train_input_fn,
feature_columns=self._feature_columns,
n_trees=1,
max_depth=5,
pruning_mode='pre',
tree_complexity=0.01)
# We stop actually after 2*depth*n_trees steps (via a hook) because we still
# could not grow 1 trees of depth 5 (due to pre-pruning).
self._assert_checkpoint(est.model_dir,
global_step=11,
finalized_trees=0,
attempted_layers=11)
# Check evaluate and predict.
eval_res = est.evaluate(input_fn=train_input_fn, steps=1)
self.assertAllClose(eval_res['accuracy'], 1.0)
# Validate predictions.
predictions = list(est.predict(input_fn=predict_input_fn))
self.assertAllClose([[0], [1], [1], [0], [0]],
[pred['class_ids'] for pred in predictions])
def testBinaryClassifierTrainInMemoryWithMixedColumns(self):
categorical = feature_column.categorical_column_with_vocabulary_list(
key='f_0', vocabulary_list=('bad', 'good', 'ok'))
indicator_col = feature_column.indicator_column(categorical)
bucketized_col = feature_column.bucketized_column(
feature_column.numeric_column('f_1', dtype=dtypes.float32),
BUCKET_BOUNDARIES)
numeric_col = feature_column.numeric_column('f_2', dtype=dtypes.float32)
labels = np.array([[0], [1], [1], [1], [1]], dtype=np.float32)
input_fn = numpy_io.numpy_input_fn(
x={
'f_0': np.array(['bad', 'good', 'good', 'ok', 'bad']),
'f_1': np.array([1, 1, 1, 1, 1]),
'f_2': np.array([12.5, 1.0, -2.001, -2.0001, -1.999]),
},
y=labels,
num_epochs=None,
batch_size=5,
shuffle=False)
feature_columns = [numeric_col, bucketized_col, indicator_col]
est = boosted_trees.boosted_trees_classifier_train_in_memory(
train_input_fn=input_fn,
feature_columns=feature_columns,
n_trees=1,
max_depth=5,
quantile_sketch_epsilon=0.33)
self._assert_checkpoint(
est.model_dir, global_step=5, finalized_trees=1, attempted_layers=5)
eval_res = est.evaluate(input_fn=input_fn, steps=1)
self.assertAllClose(eval_res['accuracy'], 1.0)
