def testCrossedFeatures(self):
"""Tests SDCALogisticClassifier with crossed features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'language':
sparse_tensor.SparseTensor(
values=['english', 'italian', 'spanish'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1]),
'country':
sparse_tensor.SparseTensor(
values=['US', 'IT', 'MX'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1])
}, constant_op.constant([[0], [0], [1]])
with self._single_threaded_test_session():
language = feature_column_lib.sparse_column_with_hash_bucket(
'language', hash_bucket_size=5)
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
country_language = feature_column_lib.crossed_column(
[language, country], hash_bucket_size=10)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id', feature_columns=[country_language])
classifier.fit(input_fn=input_fn, steps=10)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testBucketizedFeatures(self):
"""Tests SDCALogisticClassifier with bucketized features."""
def input_fn():
return {
'example_id': constant_op.constant(['1', '2', '3']),
'price': constant_op.constant([600.0, 1000.0, 400.0]),
'sq_footage': constant_op.constant([[1000.0], [600.0], [700.0]]),
'weights': constant_op.constant([[1.0], [1.0], [1.0]])
}, constant_op.constant([[1], [0], [1]])
with self._single_threaded_test_session():
price_bucket = feature_column_lib.bucketized_column(
feature_column_lib.real_valued_column('price'),
boundaries=[500.0, 700.0])
sq_footage_bucket = feature_column_lib.bucketized_column(
feature_column_lib.real_valued_column('sq_footage'),
boundaries=[650.0])
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[price_bucket, sq_footage_bucket],
weight_column_name='weights',
l2_regularization=1.0)
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testSparseFeaturesWithDuplicates(self):
"""Tests SDCALogisticClassifier with duplicated sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2']),
'age':
sparse_tensor.SparseTensor(
values=['20-29'] * 5 + ['31-40'] * 5,
indices=[[0, 0], [0, 0], [0, 0], [0, 0], [0, 0], [1, 0],
[1, 0], [1, 0], [1, 0], [1, 0]],
dense_shape=[2, 1]),
'gender':
sparse_tensor.SparseTensor(
values=['m'] * 5 + ['f'] * 5,
indices=[[0, 0], [0, 0], [0, 0], [0, 0], [0, 0], [1, 0],
[1, 0], [1, 0], [1, 0], [1, 0]],
dense_shape=[2, 1]),
}, constant_op.constant([[1], [0]])
with self._single_threaded_test_session():
age = feature_column_lib.sparse_column_with_hash_bucket(
'age', hash_bucket_size=10)
gender = feature_column_lib.sparse_column_with_hash_bucket(
'gender', hash_bucket_size=10)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id', feature_columns=[age, gender])
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertLess(metrics['loss'], 0.060)
def testWeightedSparseFeatures(self):
"""Tests SDCALogisticClassifier with weighted sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
sparse_tensor.SparseTensor(
values=[2., 3., 1.],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 5]),
'country':
sparse_tensor.SparseTensor(
values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 5])
}, constant_op.constant([[1], [0], [1]])
with self._single_threaded_test_session():
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
country_weighted_by_price = feature_column_lib.weighted_sparse_column(
country, 'price')
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[country_weighted_by_price])
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testRealValuedFeatureWithHigherDimension(self):
"""Tests SDCALogisticClassifier with high-dimension real valued features."""
# input_fn is identical to the one in testRealValuedFeatures where 2
# 1-dimensional dense features are replaced by a 2-dimensional feature.
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2']),
'dense_feature':
constant_op.constant([[500.0, 800.0], [200.0, 600.0]])
}, constant_op.constant([[0], [1]])
with self._single_threaded_test_session():
dense_feature = feature_column_lib.real_valued_column(
'dense_feature', dimension=2)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id', feature_columns=[dense_feature])
classifier.fit(input_fn=input_fn, steps=100)
loss = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
self.assertLess(loss, 0.05)
def testPartitionedMixedFeatures(self):
"""Tests SDCALogisticClassifier with a mix of features (partitioned)."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([[0.6], [0.8], [0.3]]),
'sq_footage':
constant_op.constant([900.0, 700.0, 600.0]),
'country':
sparse_tensor.SparseTensor(
values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 3], [2, 1]],
dense_shape=[3, 5]),
'weights':
constant_op.constant([[3.0], [1.0], [1.0]])
}, constant_op.constant([[1], [0], [1]])
with self._single_threaded_test_session():
price = feature_column_lib.real_valued_column('price')
sq_footage_bucket = feature_column_lib.bucketized_column(
feature_column_lib.real_valued_column('sq_footage'),
boundaries=[650.0, 800.0])
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
sq_footage_country = feature_column_lib.crossed_column(
[sq_footage_bucket, country], hash_bucket_size=10)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[
price, sq_footage_bucket, country, sq_footage_country
],
weight_column_name='weights',
partitioner=partitioned_variables.fixed_size_partitioner(
num_shards=2, axis=0))
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testRealValuedFeatures(self):
"""Tests SDCALogisticClassifier works with real valued features."""
def input_fn():
return {
'example_id': constant_op.constant(['1', '2']),
'maintenance_cost': constant_op.constant([500.0, 200.0]),
'sq_footage': constant_op.constant([[800.0], [600.0]]),
'weights': constant_op.constant([[1.0], [1.0]])
}, constant_op.constant([[0], [1]])
with self._single_threaded_test_session():
maintenance_cost = feature_column_lib.real_valued_column(
'maintenance_cost')
sq_footage = feature_column_lib.real_valued_column('sq_footage')
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[maintenance_cost, sq_footage],
weight_column_name='weights')
classifier.fit(input_fn=input_fn, steps=100)
loss = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
self.assertLess(loss, 0.05)