def testJointLinearModel(self):
"""Tests that loss goes down with training."""
def input_fn():
return {
'age':
sparse_tensor.SparseTensor(
values=['1'], indices=[[0, 0]], dense_shape=[1, 1]),
'language':
sparse_tensor.SparseTensor(
values=['english'], indices=[[0, 0]], dense_shape=[1, 1])
}, constant_op.constant([[1]])
language = feature_column.sparse_column_with_hash_bucket('language', 100)
age = feature_column.sparse_column_with_hash_bucket('age', 2)
head = head_lib._multi_class_head(n_classes=2)
classifier = _joint_linear_estimator(head, feature_columns=[age, language])
classifier.fit(input_fn=input_fn, steps=1000)
loss1 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
classifier.fit(input_fn=input_fn, steps=2000)
loss2 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
self.assertLess(loss2, loss1)
self.assertLess(loss2, 0.01)
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]])
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 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 testCrossedColumnNameCreatesSortedNames(self):
a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
b = fc.sparse_column_with_hash_bucket("bbb", hash_bucket_size=100)
bucket = fc.bucketized_column(fc.real_valued_column("cost"), [0, 4])
crossed = fc.crossed_column(set([b, bucket, a]), hash_bucket_size=10000)
self.assertEqual("aaa_X_bbb_X_cost_bucketized", crossed.name,
"name should be generated by sorted column names")
self.assertEqual("aaa", crossed.columns[0].name)
self.assertEqual("bbb", crossed.columns[1].name)
self.assertEqual("cost_bucketized", crossed.columns[2].name)
def testSparseColumnWithHashBucket(self):
a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
self.assertEqual(a.name, "aaa")
self.assertEqual(a.dtype, dtypes.string)
a = fc.sparse_column_with_hash_bucket(
"aaa", hash_bucket_size=100, dtype=dtypes.int64)
self.assertEqual(a.name, "aaa")
self.assertEqual(a.dtype, dtypes.int64)
with self.assertRaisesRegexp(ValueError, "dtype must be string or integer"):
a = fc.sparse_column_with_hash_bucket(
"aaa", hash_bucket_size=100, dtype=dtypes.float32)
def testCreateSequenceFeatureSpec(self):
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = fc.embedding_column(
fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
sparse_id_col = fc.sparse_column_with_keys("id_column",
["marlo", "omar", "stringer"])
weighted_id_col = fc.weighted_sparse_column(sparse_id_col,
"id_weights_column")
real_valued_col1 = fc.real_valued_column("real_valued_column", dimension=2)
real_valued_col2 = fc.real_valued_column(
"real_valued_default_column", dimension=5, default_value=3.0)
real_valued_col3 = fc._real_valued_var_len_column(
"real_valued_var_len_column", default_value=3.0, is_sparse=True)
real_valued_col4 = fc._real_valued_var_len_column(
"real_valued_var_len_dense_column", default_value=4.0, is_sparse=False)
feature_columns = set([
sparse_col, embedding_col, weighted_id_col, real_valued_col1,
real_valued_col2, real_valued_col3, real_valued_col4
])
feature_spec = fc._create_sequence_feature_spec_for_parsing(feature_columns)
expected_feature_spec = {
"sparse_column":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_embedding":
parsing_ops.VarLenFeature(dtypes.string),
"id_column":
parsing_ops.VarLenFeature(dtypes.string),
"id_weights_column":
parsing_ops.VarLenFeature(dtypes.float32),
"real_valued_column":
parsing_ops.FixedLenSequenceFeature(
shape=[2], dtype=dtypes.float32, allow_missing=False),
"real_valued_default_column":
parsing_ops.FixedLenSequenceFeature(
shape=[5], dtype=dtypes.float32, allow_missing=True),
"real_valued_var_len_column":
parsing_ops.VarLenFeature(dtype=dtypes.float32),
"real_valued_var_len_dense_column":
parsing_ops.FixedLenSequenceFeature(
shape=[], dtype=dtypes.float32, allow_missing=True,
default_value=4.0),
}
self.assertDictEqual(expected_feature_spec, feature_spec)
def testRegression_TensorData(self):
"""Tests regression using tensor data as input."""
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant([[.8], [.15], [0.]]),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
['en', 'fr', 'zh'], num_epochs=num_epochs),
indices=[[0, 0], [0, 1], [2, 0]],
dense_shape=[3, 2])
}
return features, constant_op.constant([1., 0., 0.2], dtype=dtypes.float32)
language_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
feature_columns = [
feature_column.embedding_column(
language_column, dimension=1),
feature_column.real_valued_column('age')
]
regressor = dnn.DNNRegressor(
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
regressor.fit(input_fn=_input_fn, steps=200)
scores = regressor.evaluate(input_fn=_input_fn, steps=1)
self.assertIn('loss', scores)
def testExport(self):
"""Tests export model for servo."""
def input_fn():
return {
'age':
constant_op.constant([1]),
'language':
sparse_tensor.SparseTensor(
values=['english'], indices=[[0, 0]], dense_shape=[1, 1])
}, constant_op.constant([[1]])
language = feature_column.sparse_column_with_hash_bucket('language', 100)
feature_columns = [
feature_column.real_valued_column('age'),
feature_column.embedding_column(
language, dimension=1)
]
classifier = dnn.DNNClassifier(
feature_columns=feature_columns, hidden_units=[3, 3])
classifier.fit(input_fn=input_fn, steps=5)
export_dir = tempfile.mkdtemp()
classifier.export(export_dir)
def testCrossedColumnNotSupportRealValuedColumn(self):
b = fc.sparse_column_with_hash_bucket("bbb", hash_bucket_size=100)
with self.assertRaisesRegexp(
TypeError, "columns must be a set of _SparseColumn, _CrossedColumn, "
"or _BucketizedColumn instances"):
fc.crossed_column(
set([b, fc.real_valued_column("real")]), hash_bucket_size=10000)
def testMakePlaceHolderTensorsForBaseFeatures(self):
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
real_valued_col = fc.real_valued_column("real_valued_column", 5)
vlen_real_valued_col = fc.real_valued_column(
"vlen_real_valued_column", dimension=None)
bucketized_col = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization"), [0, 4])
feature_columns = set(
[sparse_col, real_valued_col, vlen_real_valued_col, bucketized_col])
placeholders = (
fc.make_place_holder_tensors_for_base_features(feature_columns))
self.assertEqual(4, len(placeholders))
self.assertTrue(
isinstance(placeholders["sparse_column"],
sparse_tensor_lib.SparseTensor))
self.assertTrue(
isinstance(placeholders["vlen_real_valued_column"],
sparse_tensor_lib.SparseTensor))
placeholder = placeholders["real_valued_column"]
self.assertGreaterEqual(
placeholder.name.find(u"Placeholder_real_valued_column"), 0)
self.assertEqual(dtypes.float32, placeholder.dtype)
self.assertEqual([None, 5], placeholder.get_shape().as_list())
placeholder = placeholders["real_valued_column_for_bucketization"]
self.assertGreaterEqual(
placeholder.name.find(
u"Placeholder_real_valued_column_for_bucketization"), 0)
self.assertEqual(dtypes.float32, placeholder.dtype)
self.assertEqual([None, 1], placeholder.get_shape().as_list())
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]])
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 testExport(self):
"""Tests export model for servo."""
def input_fn():
return {
'age':
constant_op.constant([1]),
'language':
sparse_tensor.SparseTensor(values=['english'],
indices=[[0, 0]],
dense_shape=[1, 1])
}, constant_op.constant([[1]])
language = feature_column.sparse_column_with_hash_bucket(
'language', 100)
feature_columns = [
feature_column.real_valued_column('age'),
feature_column.embedding_column(language, dimension=1)
]
classifier = debug.DebugClassifier(config=run_config.RunConfig(
tf_random_seed=1))
classifier.fit(input_fn=input_fn, steps=5)
def default_input_fn(unused_estimator, examples):
return feature_column_ops.parse_feature_columns_from_examples(
examples, feature_columns)
export_dir = tempfile.mkdtemp()
classifier.export(export_dir, input_fn=default_input_fn)
def testLinearModel(self):
"""Tests that loss goes down with training."""
def input_fn():
return {
'age':
constant_op.constant([1]),
'language':
sparse_tensor.SparseTensor(values=['english'],
indices=[[0, 0]],
dense_shape=[1, 1])
}, constant_op.constant([[1]])
language = feature_column.sparse_column_with_hash_bucket(
'language', 100)
age = feature_column.real_valued_column('age')
head = head_lib._multi_class_head(n_classes=2)
classifier = _linear_estimator(head, feature_columns=[age, language])
classifier.fit(input_fn=input_fn, steps=1000)
loss1 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
classifier.fit(input_fn=input_fn, steps=2000)
loss2 = classifier.evaluate(input_fn=input_fn, steps=1)['loss']
self.assertLess(loss2, loss1)
self.assertLess(loss2, 0.01)
def testSparseFeatures(self):
"""Tests SDCALogisticClassifier with sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([[0.4], [0.6], [0.3]]),
'country':
sparse_tensor.SparseTensor(
values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 3], [2, 1]],
dense_shape=[3, 5]),
'weights':
constant_op.constant([[1.0], [1.0], [1.0]])
}, constant_op.constant([[1], [0], [1]])
with self._single_threaded_test_session():
price = feature_column_lib.real_valued_column('price')
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[price, country],
weight_column_name='weights')
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testSparseFeatures(self):
"""Tests SVM classifier with (hashed) sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([[0.8], [0.6], [0.3]]),
'country':
sparse_tensor.SparseTensor(values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1]),
}, constant_op.constant([[0], [1], [1]])
price = feature_column.real_valued_column('price')
country = feature_column.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
svm_classifier = svm.SVM(feature_columns=[price, country],
example_id_column='example_id',
l1_regularization=0.0,
l2_regularization=1.0)
svm_classifier.fit(input_fn=input_fn, steps=30)
accuracy = svm_classifier.evaluate(input_fn=input_fn,
steps=1)['accuracy']
self.assertAlmostEqual(accuracy, 1.0, places=3)
def testEmbeddingColumn(self):
a = fc.sparse_column_with_hash_bucket(
"aaa", hash_bucket_size=100, combiner="sum")
b = fc.embedding_column(a, dimension=4, combiner="mean")
self.assertEqual(b.sparse_id_column.name, "aaa")
self.assertEqual(b.dimension, 4)
self.assertEqual(b.combiner, "mean")
def testExport(self):
"""Tests export model for servo."""
def input_fn():
return {
'age':
constant_op.constant([1]),
'language':
sparse_tensor.SparseTensor(
values=['english'], indices=[[0, 0]], dense_shape=[1, 1])
}, constant_op.constant([[1]])
language = feature_column.sparse_column_with_hash_bucket('language', 100)
feature_columns = [
feature_column.real_valued_column('age'),
feature_column.embedding_column(
language, dimension=1)
]
classifier = debug.DebugClassifier(config=run_config.RunConfig(
tf_random_seed=1))
classifier.fit(input_fn=input_fn, steps=5)
def default_input_fn(unused_estimator, examples):
return feature_column_ops.parse_feature_columns_from_examples(
examples, feature_columns)
export_dir = tempfile.mkdtemp()
classifier.export(export_dir, input_fn=default_input_fn)
def testSparseFeatures(self):
"""Tests SVM classifier with (hashed) sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([[0.8], [0.6], [0.3]]),
'country':
sparse_tensor.SparseTensor(
values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1]),
}, constant_op.constant([[0], [1], [1]])
price = feature_column.real_valued_column('price')
country = feature_column.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
svm_classifier = svm.SVM(feature_columns=[price, country],
example_id_column='example_id',
l1_regularization=0.0,
l2_regularization=1.0)
svm_classifier.fit(input_fn=input_fn, steps=30)
accuracy = svm_classifier.evaluate(input_fn=input_fn, steps=1)['accuracy']
self.assertAlmostEqual(accuracy, 1.0, places=3)
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]])
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 testMakePlaceHolderTensorsForBaseFeatures(self):
sparse_col = fc.sparse_column_with_hash_bucket("sparse_column",
hash_bucket_size=100)
real_valued_col = fc.real_valued_column("real_valued_column", 5)
vlen_real_valued_col = fc.real_valued_column("vlen_real_valued_column",
dimension=None)
bucketized_col = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization"),
[0, 4])
feature_columns = set([
sparse_col, real_valued_col, vlen_real_valued_col, bucketized_col
])
placeholders = (
fc.make_place_holder_tensors_for_base_features(feature_columns))
self.assertEqual(4, len(placeholders))
self.assertTrue(
isinstance(placeholders["sparse_column"],
sparse_tensor_lib.SparseTensor))
self.assertTrue(
isinstance(placeholders["vlen_real_valued_column"],
sparse_tensor_lib.SparseTensor))
placeholder = placeholders["real_valued_column"]
self.assertGreaterEqual(
placeholder.name.find(u"Placeholder_real_valued_column"), 0)
self.assertEqual(dtypes.float32, placeholder.dtype)
self.assertEqual([None, 5], placeholder.get_shape().as_list())
placeholder = placeholders["real_valued_column_for_bucketization"]
self.assertGreaterEqual(
placeholder.name.find(
u"Placeholder_real_valued_column_for_bucketization"), 0)
self.assertEqual(dtypes.float32, placeholder.dtype)
self.assertEqual([None, 1], placeholder.get_shape().as_list())
def testMixedFeatures(self):
"""Tests SDCALogisticClassifier with a mix of features."""
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]])
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')
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testSparseFeatures(self):
"""Tests SDCALogisticClassifier with sparse features."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([[0.4], [0.6], [0.3]]),
'country':
sparse_tensor.SparseTensor(
values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 3], [2, 1]],
dense_shape=[3, 5]),
'weights':
constant_op.constant([[1.0], [1.0], [1.0]])
}, constant_op.constant([[1], [0], [1]])
price = feature_column_lib.real_valued_column('price')
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
classifier = sdca_estimator.SDCALogisticClassifier(
example_id_column='example_id',
feature_columns=[price, country],
weight_column_name='weights')
classifier.fit(input_fn=input_fn, steps=50)
metrics = classifier.evaluate(input_fn=input_fn, steps=1)
self.assertGreater(metrics['accuracy'], 0.9)
def testSparseColumnWithHashBucket(self):
a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
self.assertEqual(a.name, "aaa")
self.assertEqual(a.dtype, dtypes.string)
a = fc.sparse_column_with_hash_bucket("aaa",
hash_bucket_size=100,
dtype=dtypes.int64)
self.assertEqual(a.name, "aaa")
self.assertEqual(a.dtype, dtypes.int64)
with self.assertRaisesRegexp(ValueError,
"dtype must be string or integer"):
a = fc.sparse_column_with_hash_bucket("aaa",
hash_bucket_size=100,
dtype=dtypes.float32)
def testEmbeddingColumn(self):
a = fc.sparse_column_with_hash_bucket("aaa",
hash_bucket_size=100,
combiner="sum")
b = fc.embedding_column(a, dimension=4, combiner="mean")
self.assertEqual(b.sparse_id_column.name, "aaa")
self.assertEqual(b.dimension, 4)
self.assertEqual(b.combiner, "mean")
def testCrossedColumnNotSupportRealValuedColumn(self):
b = fc.sparse_column_with_hash_bucket("bbb", hash_bucket_size=100)
with self.assertRaisesRegexp(
TypeError,
"columns must be a set of _SparseColumn, _CrossedColumn, "
"or _BucketizedColumn instances"):
fc.crossed_column(set([b, fc.real_valued_column("real")]),
hash_bucket_size=10000)
def testSparseColumnHashBucketDeepCopy(self):
"""Tests deepcopy of sparse_column_with_hash_bucket."""
column = fc.sparse_column_with_hash_bucket("a", 10)
self.assertEqual("a", column.name)
column_copy = copy.deepcopy(column)
self.assertEqual("a", column_copy.name)
self.assertEqual(10, column_copy.bucket_size)
self.assertFalse(column_copy.is_integerized)
def testSparseColumnHashBucketDeepCopy(self):
"""Tests deepcopy of sparse_column_with_hash_bucket."""
column = fc.sparse_column_with_hash_bucket("a", 10)
self.assertEqual("a", column.name)
column_copy = copy.deepcopy(column)
self.assertEqual("a", column_copy.name)
self.assertEqual(10, column_copy.bucket_size)
self.assertFalse(column_copy.is_integerized)
def testMultipliesGradient(self):
embedding_language = feature_column.embedding_column(
feature_column.sparse_column_with_hash_bucket('language', 10),
dimension=1,
initializer=init_ops.constant_initializer(0.1))
embedding_wire = feature_column.embedding_column(
feature_column.sparse_column_with_hash_bucket('wire', 10),
dimension=1,
initializer=init_ops.constant_initializer(0.1))
params = {
'feature_columns': [embedding_language, embedding_wire],
'head': head_lib._multi_class_head(2),
'hidden_units': [1],
# Set lr mult to 0. to keep embeddings constant.
'embedding_lr_multipliers': {
embedding_language: 0.0
},
}
features = {
'language':
sparse_tensor.SparseTensor(
values=['en', 'fr', 'zh'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1]),
'wire':
sparse_tensor.SparseTensor(
values=['omar', 'stringer', 'marlo'],
indices=[[0, 0], [1, 0], [2, 0]],
dense_shape=[3, 1]),
}
labels = constant_op.constant([[0], [0], [0]], dtype=dtypes.int32)
model_ops = dnn._dnn_model_fn(features, labels, model_fn.ModeKeys.TRAIN,
params)
with monitored_session.MonitoredSession() as sess:
language_var = dnn_linear_combined._get_embedding_variable(
embedding_language, 'dnn', 'dnn/input_from_feature_columns')
wire_var = dnn_linear_combined._get_embedding_variable(
embedding_wire, 'dnn', 'dnn/input_from_feature_columns')
for _ in range(2):
_, language_value, wire_value = sess.run(
[model_ops.train_op, language_var, wire_var])
initial_value = np.full_like(language_value, 0.1)
self.assertTrue(np.all(np.isclose(language_value, initial_value)))
self.assertFalse(np.all(np.isclose(wire_value, initial_value)))
def testEmbeddingColumnDeepCopy(self):
a = fc.sparse_column_with_hash_bucket(
"aaa", hash_bucket_size=100, combiner="sum")
column = fc.embedding_column(a, dimension=4, combiner="mean")
column_copy = copy.deepcopy(column)
self.assertEqual(column_copy.name, "aaa_embedding")
self.assertEqual(column_copy.sparse_id_column.name, "aaa")
self.assertEqual(column_copy.dimension, 4)
self.assertEqual(column_copy.combiner, "mean")
def test_make_parsing_export_strategy(self):
"""Only tests that an ExportStrategy instance is created."""
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = fc.embedding_column(
fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
real_valued_col1 = fc.real_valued_column("real_valued_column1")
bucketized_col1 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
feature_columns = [sparse_col, embedding_col, real_valued_col1,
bucketized_col1]
export_strategy = saved_model_export_utils.make_parsing_export_strategy(
feature_columns=feature_columns)
self.assertTrue(
isinstance(export_strategy, export_strategy_lib.ExportStrategy))
def testEmbeddingColumnDeepCopy(self):
a = fc.sparse_column_with_hash_bucket(
"aaa", hash_bucket_size=100, combiner="sum")
column = fc.embedding_column(a, dimension=4, combiner="mean")
column_copy = copy.deepcopy(column)
self.assertEqual(column_copy.name, "aaa_embedding")
self.assertEqual(column_copy.sparse_id_column.name, "aaa")
self.assertEqual(column_copy.dimension, 4)
self.assertEqual(column_copy.combiner, "mean")
def test_make_parsing_export_strategy(self):
"""Only tests that an ExportStrategy instance is created."""
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = fc.embedding_column(
fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
real_valued_col1 = fc.real_valued_column("real_valued_column1")
bucketized_col1 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
feature_columns = [sparse_col, embedding_col, real_valued_col1,
bucketized_col1]
export_strategy = saved_model_export_utils.make_parsing_export_strategy(
feature_columns=feature_columns)
self.assertTrue(
isinstance(export_strategy, export_strategy_lib.ExportStrategy))
def testInitEmbeddingColumnWeightsFromCkpt(self):
sparse_col = fc.sparse_column_with_hash_bucket(
column_name="object_in_image", hash_bucket_size=4)
# Create _EmbeddingColumn which randomly initializes embedding of size
# [4, 16].
embedding_col = fc.embedding_column(sparse_col, dimension=16)
# Creating a SparseTensor which has all the ids possible for the given
# vocab.
input_tensor = sparse_tensor_lib.SparseTensor(
indices=[[0, 0], [1, 1], [2, 2], [3, 3]],
values=[0, 1, 2, 3],
dense_shape=[4, 4])
# Invoking 'layers.input_from_feature_columns' will create the embedding
# variable. Creating under scope 'run_1' so as to prevent name conflicts
# when creating embedding variable for 'embedding_column_pretrained'.
with variable_scope.variable_scope("run_1"):
with variable_scope.variable_scope(embedding_col.name):
# This will return a [4, 16] tensor which is same as embedding variable.
embeddings = feature_column_ops.input_from_feature_columns({
embedding_col: input_tensor
}, [embedding_col])
save = saver.Saver()
ckpt_dir_prefix = os.path.join(self.get_temp_dir(),
"init_embedding_col_w_from_ckpt")
ckpt_dir = tempfile.mkdtemp(prefix=ckpt_dir_prefix)
checkpoint_path = os.path.join(ckpt_dir, "model.ckpt")
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
saved_embedding = embeddings.eval()
save.save(sess, checkpoint_path)
embedding_col_initialized = fc.embedding_column(
sparse_id_column=sparse_col,
dimension=16,
ckpt_to_load_from=checkpoint_path,
tensor_name_in_ckpt=("run_1/object_in_image_embedding/"
"input_from_feature_columns/object"
"_in_image_embedding/weights"))
with variable_scope.variable_scope("run_2"):
# This will initialize the embedding from provided checkpoint and return a
# [4, 16] tensor which is same as embedding variable. Since we didn't
# modify embeddings, this should be same as 'saved_embedding'.
pretrained_embeddings = feature_column_ops.input_from_feature_columns({
embedding_col_initialized: input_tensor
}, [embedding_col_initialized])
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
loaded_embedding = pretrained_embeddings.eval()
self.assertAllClose(saved_embedding, loaded_embedding)
def testInitEmbeddingColumnWeightsFromCkpt(self):
sparse_col = fc.sparse_column_with_hash_bucket(
column_name="object_in_image", hash_bucket_size=4)
# Create _EmbeddingColumn which randomly initializes embedding of size
# [4, 16].
embedding_col = fc.embedding_column(sparse_col, dimension=16)
# Creating a SparseTensor which has all the ids possible for the given
# vocab.
input_tensor = sparse_tensor_lib.SparseTensor(
indices=[[0, 0], [1, 1], [2, 2], [3, 3]],
values=[0, 1, 2, 3],
dense_shape=[4, 4])
# Invoking 'layers.input_from_feature_columns' will create the embedding
# variable. Creating under scope 'run_1' so as to prevent name conflicts
# when creating embedding variable for 'embedding_column_pretrained'.
with variable_scope.variable_scope("run_1"):
with variable_scope.variable_scope(embedding_col.name):
# This will return a [4, 16] tensor which is same as embedding variable.
embeddings = feature_column_ops.input_from_feature_columns({
embedding_col: input_tensor
}, [embedding_col])
save = saver.Saver()
ckpt_dir_prefix = os.path.join(self.get_temp_dir(),
"init_embedding_col_w_from_ckpt")
ckpt_dir = tempfile.mkdtemp(prefix=ckpt_dir_prefix)
checkpoint_path = os.path.join(ckpt_dir, "model.ckpt")
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
saved_embedding = embeddings.eval()
save.save(sess, checkpoint_path)
embedding_col_initialized = fc.embedding_column(
sparse_id_column=sparse_col,
dimension=16,
ckpt_to_load_from=checkpoint_path,
tensor_name_in_ckpt=("run_1/object_in_image_embedding/"
"input_from_feature_columns/object"
"_in_image_embedding/weights"))
with variable_scope.variable_scope("run_2"):
# This will initialize the embedding from provided checkpoint and return a
# [4, 16] tensor which is same as embedding variable. Since we didn't
# modify embeddings, this should be same as 'saved_embedding'.
pretrained_embeddings = feature_column_ops.input_from_feature_columns({
embedding_col_initialized: input_tensor
}, [embedding_col_initialized])
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
loaded_embedding = pretrained_embeddings.eval()
self.assertAllClose(saved_embedding, loaded_embedding)
def testOneHotColumn(self):
a = fc.sparse_column_with_keys("a", ["a", "b", "c", "d"])
onehot_a = fc.one_hot_column(a)
self.assertEqual(onehot_a.sparse_id_column.name, "a")
self.assertEqual(onehot_a.length, 4)
b = fc.sparse_column_with_hash_bucket(
"b", hash_bucket_size=100, combiner="sum")
onehot_b = fc.one_hot_column(b)
self.assertEqual(onehot_b.sparse_id_column.name, "b")
self.assertEqual(onehot_b.length, 100)
def testOneHotColumn(self):
a = fc.sparse_column_with_keys("a", ["a", "b", "c", "d"])
onehot_a = fc.one_hot_column(a)
self.assertEqual(onehot_a.sparse_id_column.name, "a")
self.assertEqual(onehot_a.length, 4)
b = fc.sparse_column_with_hash_bucket(
"b", hash_bucket_size=100, combiner="sum")
onehot_b = fc.one_hot_column(b)
self.assertEqual(onehot_b.sparse_id_column.name, "b")
self.assertEqual(onehot_b.length, 100)
def testEmbeddingMultiplier(self):
embedding_language = feature_column.embedding_column(
feature_column.sparse_column_with_hash_bucket('language', 10),
dimension=1,
initializer=init_ops.constant_initializer(0.1))
classifier = dnn.DNNClassifier(
feature_columns=[embedding_language],
hidden_units=[3, 3],
embedding_lr_multipliers={embedding_language: 0.8})
self.assertEqual({
embedding_language: 0.8
}, classifier._estimator.params['embedding_lr_multipliers'])
def testTrainWithPartitionedVariables(self):
"""Tests training with partitioned variables."""
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant([[.8], [.2], [.1]]),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
['en', 'fr', 'zh'], num_epochs=num_epochs),
indices=[[0, 0], [0, 1], [2, 0]],
dense_shape=[3, 2])
}
return features, constant_op.constant([[1], [0], [0]], dtype=dtypes.int32)
# The given hash_bucket_size results in variables larger than the
# default min_slice_size attribute, so the variables are partitioned.
sparse_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=2e7)
feature_columns = [
feature_column.embedding_column(
sparse_column, dimension=1)
]
tf_config = {
'cluster': {
run_config.TaskType.PS: ['fake_ps_0', 'fake_ps_1']
}
}
with test.mock.patch.dict('os.environ',
{'TF_CONFIG': json.dumps(tf_config)}):
config = run_config.RunConfig(tf_random_seed=1)
# Because we did not start a distributed cluster, we need to pass an
# empty ClusterSpec, otherwise the device_setter will look for
# distributed jobs, such as "/job:ps" which are not present.
config._cluster_spec = server_lib.ClusterSpec({})
classifier = dnn.DNNClassifier(
n_classes=3,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=config)
classifier.fit(input_fn=_input_fn, steps=5)
scores = classifier.evaluate(input_fn=_input_fn, steps=1)
self._assertInRange(0.0, 1.0, scores['accuracy'])
self.assertIn('loss', scores)
def testExtractFeaturesWithTransformation(self):
"""Tests feature extraction."""
with self.test_session():
features = {}
features["dense_float"] = array_ops.zeros([2, 1], dtypes.float32)
features["sparse_float"] = sparse_tensor.SparseTensor(
array_ops.zeros([2, 2], dtypes.int64),
array_ops.zeros([2], dtypes.float32),
array_ops.zeros([2], dtypes.int64))
features["sparse_categorical"] = sparse_tensor.SparseTensor(
array_ops.zeros([2, 2], dtypes.int64),
array_ops.zeros([2], dtypes.string),
array_ops.zeros([2], dtypes.int64))
feature_columns = set()
feature_columns.add(layers.real_valued_column("dense_float"))
feature_columns.add(
layers.feature_column._real_valued_var_len_column(
"sparse_float", is_sparse=True))
feature_columns.add(
feature_column_lib.sparse_column_with_hash_bucket(
"sparse_categorical", hash_bucket_size=1000000))
(fc_names, dense_floats, sparse_float_indices, sparse_float_values,
sparse_float_shapes, sparse_int_indices, sparse_int_values,
sparse_int_shapes) = (gbdt_batch.extract_features(
features, feature_columns))
self.assertEqual(len(fc_names), 3)
self.assertAllEqual(
fc_names,
["dense_float", "sparse_float", "sparse_categorical"])
self.assertEqual(len(dense_floats), 1)
self.assertEqual(len(sparse_float_indices), 1)
self.assertEqual(len(sparse_float_values), 1)
self.assertEqual(len(sparse_float_shapes), 1)
self.assertEqual(len(sparse_int_indices), 1)
self.assertEqual(len(sparse_int_values), 1)
self.assertEqual(len(sparse_int_shapes), 1)
self.assertAllEqual(dense_floats[0].eval(),
features["dense_float"].eval())
self.assertAllEqual(sparse_float_indices[0].eval(),
features["sparse_float"].indices.eval())
self.assertAllEqual(sparse_float_values[0].eval(),
features["sparse_float"].values.eval())
self.assertAllEqual(sparse_float_shapes[0].eval(),
features["sparse_float"].dense_shape.eval())
self.assertAllEqual(sparse_int_indices[0].eval(),
features["sparse_categorical"].indices.eval())
self.assertAllEqual(sparse_int_values[0].eval(), [397263, 397263])
self.assertAllEqual(
sparse_int_shapes[0].eval(),
features["sparse_categorical"].dense_shape.eval())
def benchmarkTensorData(self):
def _input_fn():
iris = test_data.prepare_iris_data_for_logistic_regression()
features = {}
for i in range(4):
# The following shows how to provide the Tensor data for
# RealValuedColumns.
features.update({
str(i):
array_ops.reshape(
constant_op.constant(
iris.data[:, i], dtype=dtypes.float32), (-1, 1))
})
# The following shows how to provide the SparseTensor data for
# a SparseColumn.
features['dummy_sparse_column'] = sparse_tensor.SparseTensor(
values=('en', 'fr', 'zh'),
indices=((0, 0), (0, 1), (60, 0)),
dense_shape=(len(iris.target), 2))
labels = array_ops.reshape(
constant_op.constant(
iris.target, dtype=dtypes.int32), (-1, 1))
return features, labels
iris = test_data.prepare_iris_data_for_logistic_regression()
cont_features = [
feature_column.real_valued_column(str(i)) for i in range(4)
]
linear_features = [
feature_column.bucketized_column(
cont_features[i],
test_data.get_quantile_based_buckets(iris.data[:, i], 10))
for i in range(4)
]
linear_features.append(
feature_column.sparse_column_with_hash_bucket(
'dummy_sparse_column', hash_bucket_size=100))
classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
model_dir=tempfile.mkdtemp(),
linear_feature_columns=linear_features,
dnn_feature_columns=cont_features,
dnn_hidden_units=(3, 3))
metrics = classifier.fit(input_fn=_input_fn, steps=_ITERS).evaluate(
input_fn=_input_fn, steps=100)
self._assertSingleClassMetrics(metrics)
def testExtractFeaturesWithTransformation(self):
"""Tests feature extraction."""
with self.test_session():
features = {}
features["dense_float"] = array_ops.zeros([2, 1], dtypes.float32)
features["sparse_float"] = sparse_tensor.SparseTensor(
array_ops.zeros([2, 2], dtypes.int64),
array_ops.zeros([2], dtypes.float32),
array_ops.zeros([2], dtypes.int64))
features["sparse_categorical"] = sparse_tensor.SparseTensor(
array_ops.zeros([2, 2], dtypes.int64),
array_ops.zeros(
[2], dtypes.string), array_ops.zeros([2], dtypes.int64))
feature_columns = set()
feature_columns.add(layers.real_valued_column("dense_float"))
feature_columns.add(
layers.feature_column._real_valued_var_len_column(
"sparse_float", is_sparse=True))
feature_columns.add(
feature_column_lib.sparse_column_with_hash_bucket(
"sparse_categorical", hash_bucket_size=1000000))
(fc_names, dense_floats, sparse_float_indices, sparse_float_values,
sparse_float_shapes, sparse_int_indices, sparse_int_values,
sparse_int_shapes) = (gbdt_batch.extract_features(
features, feature_columns))
self.assertEqual(len(fc_names), 3)
self.assertAllEqual(fc_names,
["dense_float", "sparse_float", "sparse_categorical"])
self.assertEqual(len(dense_floats), 1)
self.assertEqual(len(sparse_float_indices), 1)
self.assertEqual(len(sparse_float_values), 1)
self.assertEqual(len(sparse_float_shapes), 1)
self.assertEqual(len(sparse_int_indices), 1)
self.assertEqual(len(sparse_int_values), 1)
self.assertEqual(len(sparse_int_shapes), 1)
self.assertAllEqual(dense_floats[0].eval(),
features["dense_float"].eval())
self.assertAllEqual(sparse_float_indices[0].eval(),
features["sparse_float"].indices.eval())
self.assertAllEqual(sparse_float_values[0].eval(),
features["sparse_float"].values.eval())
self.assertAllEqual(sparse_float_shapes[0].eval(),
features["sparse_float"].dense_shape.eval())
self.assertAllEqual(sparse_int_indices[0].eval(),
features["sparse_categorical"].indices.eval())
self.assertAllEqual(sparse_int_values[0].eval(), [397263, 397263])
self.assertAllEqual(sparse_int_shapes[0].eval(),
features["sparse_categorical"].dense_shape.eval())
def benchmarkTensorData(self):
def _input_fn():
iris = test_data.prepare_iris_data_for_logistic_regression()
features = {}
for i in range(4):
# The following shows how to provide the Tensor data for
# RealValuedColumns.
features.update({
str(i):
array_ops.reshape(
constant_op.constant(iris.data[:, i],
dtype=dtypes.float32), (-1, 1))
})
# The following shows how to provide the SparseTensor data for
# a SparseColumn.
features['dummy_sparse_column'] = sparse_tensor.SparseTensor(
values=('en', 'fr', 'zh'),
indices=((0, 0), (0, 1), (60, 0)),
dense_shape=(len(iris.target), 2))
labels = array_ops.reshape(
constant_op.constant(iris.target, dtype=dtypes.int32), (-1, 1))
return features, labels
iris = test_data.prepare_iris_data_for_logistic_regression()
cont_features = [
feature_column.real_valued_column(str(i)) for i in range(4)
]
linear_features = [
feature_column.bucketized_column(
cont_features[i],
test_data.get_quantile_based_buckets(iris.data[:, i], 10))
for i in range(4)
]
linear_features.append(
feature_column.sparse_column_with_hash_bucket(
'dummy_sparse_column', hash_bucket_size=100))
classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
model_dir=tempfile.mkdtemp(),
linear_feature_columns=linear_features,
dnn_feature_columns=cont_features,
dnn_hidden_units=(3, 3))
metrics = classifier.fit(input_fn=_input_fn,
steps=_ITERS).evaluate(input_fn=_input_fn,
steps=100)
self._assertSingleClassMetrics(metrics)
def testPredict_AsIterable(self):
"""Tests predict and predict_prob methods with as_iterable=True."""
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant([[.8], [.2], [.1]]),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
['en', 'fr', 'zh'], num_epochs=num_epochs),
indices=[[0, 0], [0, 1], [2, 0]],
dense_shape=[3, 2])
}
return features, constant_op.constant([[1], [0], [0]], dtype=dtypes.int32)
language_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
feature_columns = [
feature_column.embedding_column(
language_column, dimension=1),
feature_column.real_valued_column('age')
]
classifier = dnn.DNNClassifier(
n_classes=3,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
classifier.fit(input_fn=_input_fn, steps=200)
scores = classifier.evaluate(input_fn=_input_fn, steps=1)
self._assertInRange(0.0, 1.0, scores['accuracy'])
self.assertIn('loss', scores)
predict_input_fn = functools.partial(_input_fn, num_epochs=1)
predictions = list(
classifier.predict(
input_fn=predict_input_fn, as_iterable=True))
self.assertListEqual(predictions, [1, 0, 0])
predictions = list(
classifier.predict_proba(
input_fn=predict_input_fn, as_iterable=True))
self.assertAllClose(
predictions, [[0., 1., 0.], [1., 0., 0.], [1., 0., 0.]], atol=0.3)
def benchmarkLogisticFloatLabel(self):
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(constant_op.constant(
((50, ), (20, ), (10, ))),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(values=input_lib.limit_epochs(
('en', 'fr', 'zh'), num_epochs=num_epochs),
indices=((0, 0), (0, 1), (2, 0)),
dense_shape=(3, 2))
}
return features, constant_op.constant(((0.8, ), (0., ), (0.2, )),
dtype=dtypes.float32)
lang_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
n_classes = 2
classifier = dnn.DNNClassifier(
n_classes=n_classes,
feature_columns=(feature_column.embedding_column(lang_column,
dimension=1),
feature_column.real_valued_column('age')),
hidden_units=(3, 3),
config=run_config.RunConfig(tf_random_seed=1))
steps = 1000
metrics = classifier.fit(input_fn=_input_fn,
steps=steps).evaluate(input_fn=_input_fn,
steps=1)
estimator_test_utils.assert_in_range(steps, steps + 5, 'global_step',
metrics)
# Prediction probabilities mirror the labels column, which proves that the
# classifier learns from float input.
self._report_metrics(metrics)
self._report_predictions(
classifier=classifier,
input_fn=functools.partial(_input_fn, num_epochs=1),
iters=metrics['global_step'],
n_examples=3,
n_classes=n_classes,
expected_probabilities=((0.2, 0.8), (1., 0.), (0.8, 0.2)),
expected_classes=(1, 0, 0),
benchmark_name_override=(
'DNNClassifierBenchmark.benchmarkLogisticFloatLabel_predictions'
))
def benchmarkLogisticFloatLabel(self):
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant(((50,), (20,), (10,))),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
('en', 'fr', 'zh'), num_epochs=num_epochs),
indices=((0, 0), (0, 1), (2, 0)),
dense_shape=(3, 2))
}
return features, constant_op.constant(
((0.8,), (0.,), (0.2,)), dtype=dtypes.float32)
lang_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
n_classes = 2
classifier = dnn.DNNClassifier(
n_classes=n_classes,
feature_columns=(feature_column.embedding_column(
lang_column, dimension=1),
feature_column.real_valued_column('age')),
hidden_units=(3, 3),
config=run_config.RunConfig(tf_random_seed=1))
steps = 1000
metrics = classifier.fit(input_fn=_input_fn, steps=steps).evaluate(
input_fn=_input_fn, steps=1)
estimator_test_utils.assert_in_range(steps, steps + 5, 'global_step',
metrics)
# Prediction probabilities mirror the labels column, which proves that the
# classifier learns from float input.
self._report_metrics(metrics)
self._report_predictions(
classifier=classifier,
input_fn=functools.partial(_input_fn, num_epochs=1),
iters=metrics['global_step'],
n_examples=3,
n_classes=n_classes,
expected_probabilities=((0.2, 0.8), (1., 0.), (0.8, 0.2)),
expected_classes=(1, 0, 0),
benchmark_name_override=(
'DNNClassifierBenchmark.benchmarkLogisticFloatLabel_predictions'))
def testTrainSaveLoad(self):
"""Tests that insures you can save and reload a trained model."""
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant([[.8], [.2], [.1]]),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
['en', 'fr', 'zh'], num_epochs=num_epochs),
indices=[[0, 0], [0, 1], [2, 0]],
dense_shape=[3, 2])
}
return features, constant_op.constant([[1], [0], [0]], dtype=dtypes.int32)
sparse_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
feature_columns = [
feature_column.embedding_column(
sparse_column, dimension=1)
]
model_dir = tempfile.mkdtemp()
classifier = dnn.DNNClassifier(
model_dir=model_dir,
n_classes=3,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
classifier.fit(input_fn=_input_fn, steps=5)
predict_input_fn = functools.partial(_input_fn, num_epochs=1)
predictions1 = classifier.predict(input_fn=predict_input_fn)
del classifier
classifier2 = dnn.DNNClassifier(
model_dir=model_dir,
n_classes=3,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
predictions2 = classifier2.predict(input_fn=predict_input_fn)
self.assertEqual(list(predictions1), list(predictions2))
def testTrainSaveLoad(self):
"""Tests that insures you can save and reload a trained model."""
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(
constant_op.constant([[0.8], [0.15], [0.]]),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(
values=input_lib.limit_epochs(
['en', 'fr', 'zh'], num_epochs=num_epochs),
indices=[[0, 0], [0, 1], [2, 0]],
dense_shape=[3, 2])
}
return features, constant_op.constant([1., 0., 0.2], dtype=dtypes.float32)
sparse_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
feature_columns = [
feature_column.embedding_column(
sparse_column, dimension=1),
feature_column.real_valued_column('age')
]
model_dir = tempfile.mkdtemp()
regressor = dnn.DNNRegressor(
model_dir=model_dir,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
regressor.fit(input_fn=_input_fn, steps=5)
predict_input_fn = functools.partial(_input_fn, num_epochs=1)
predictions = list(regressor.predict(input_fn=predict_input_fn))
del regressor
regressor2 = dnn.DNNRegressor(
model_dir=model_dir,
feature_columns=feature_columns,
hidden_units=[3, 3],
config=run_config.RunConfig(tf_random_seed=1))
predictions2 = list(regressor2.predict(input_fn=predict_input_fn))
self.assertAllClose(predictions, predictions2)
def benchmarkLogisticTensorData(self):
def _input_fn(num_epochs=None):
features = {
'age':
input_lib.limit_epochs(constant_op.constant(
((.8, ), (0.2, ), (.1, ))),
num_epochs=num_epochs),
'language':
sparse_tensor.SparseTensor(values=input_lib.limit_epochs(
('en', 'fr', 'zh'), num_epochs=num_epochs),
indices=((0, 0), (0, 1), (2, 0)),
dense_shape=(3, 2))
}
return features, constant_op.constant(((1, ), (0, ), (0, )),
dtype=dtypes.int32)
lang_column = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=20)
classifier = dnn.DNNClassifier(
feature_columns=(feature_column.embedding_column(lang_column,
dimension=1),
feature_column.real_valued_column('age')),
hidden_units=(3, 3),
config=run_config.RunConfig(tf_random_seed=1))
steps = 100
metrics = classifier.fit(input_fn=_input_fn,
steps=steps).evaluate(input_fn=_input_fn,
steps=1)
estimator_test_utils.assert_in_range(steps, steps + 5, 'global_step',
metrics)
estimator_test_utils.assert_in_range(0.9, 1.0, 'accuracy', metrics)
estimator_test_utils.assert_in_range(0.0, 0.3, 'loss', metrics)
self._report_metrics(metrics)
self._report_predictions(
classifier=classifier,
input_fn=functools.partial(_input_fn, num_epochs=1),
iters=metrics['global_step'],
n_examples=3,
n_classes=2,
expected_classes=(1, 0, 0),
benchmark_name_override=(
'DNNClassifierBenchmark.benchmarkLogisticTensorData_predictions'
))
def benchmarkPartitionedVariables(self):
def _input_fn():
features = {
'language':
sparse_tensor.SparseTensor(values=('en', 'fr', 'zh'),
indices=((0, 0), (0, 1), (2, 0)),
dense_shape=(3, 2))
}
labels = constant_op.constant(((1, ), (0, ), (0, )))
return features, labels
# The given hash_bucket_size results in variables larger than the
# default min_slice_size attribute, so the variables are partitioned.
sparse_feature = feature_column.sparse_column_with_hash_bucket(
'language', hash_bucket_size=2e7)
embedding_feature = feature_column.embedding_column(sparse_feature,
dimension=1)
tf_config = {
'cluster': {
run_config.TaskType.PS: ['fake_ps_0', 'fake_ps_1']
}
}
with test.mock.patch.dict('os.environ',
{'TF_CONFIG': json.dumps(tf_config)}):
config = run_config.RunConfig()
# Because we did not start a distributed cluster, we need to pass an
# empty ClusterSpec, otherwise the device_setter will look for
# distributed jobs, such as "/job:ps" which are not present.
config._cluster_spec = server_lib.ClusterSpec({})
classifier = dnn_linear_combined.DNNLinearCombinedClassifier(
linear_feature_columns=(sparse_feature, ),
dnn_feature_columns=(embedding_feature, ),
dnn_hidden_units=(3, 3),
config=config)
metrics = classifier.fit(input_fn=_input_fn,
steps=_ITERS).evaluate(input_fn=_input_fn,
steps=100)
self._assertCommonMetrics(metrics)
def testMixedFeaturesArbitraryWeightsPartitioned(self):
"""Tests SDCALinearRegressor works 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], [5.0], [7.0]])
}, constant_op.constant([[1.55], [-1.25], [-3.0]])
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)
regressor = sdca_estimator.SDCALinearRegressor(
example_id_column='example_id',
feature_columns=[
price, sq_footage_bucket, country, sq_footage_country
],
l2_regularization=1.0,
weight_column_name='weights',
partitioner=partitioned_variables.fixed_size_partitioner(
num_shards=2, axis=0))
regressor.fit(input_fn=input_fn, steps=20)
loss = regressor.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 testMixedFeatures(self):
"""Tests SVM classifier with a mix of features."""
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]])
price = feature_column.real_valued_column('price')
sq_footage_bucket = feature_column.bucketized_column(
feature_column.real_valued_column('sq_footage'),
boundaries=[650.0, 800.0])
country = feature_column.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
sq_footage_country = feature_column.crossed_column(
[sq_footage_bucket, country], hash_bucket_size=10)
svm_classifier = svm.SVM(feature_columns=[
price, sq_footage_bucket, country, sq_footage_country
],
example_id_column='example_id',
weight_column_name='weights',
l1_regularization=0.1,
l2_regularization=1.0)
svm_classifier.fit(input_fn=input_fn, steps=30)
accuracy = svm_classifier.evaluate(input_fn=input_fn,
steps=1)['accuracy']
self.assertAlmostEqual(accuracy, 1.0, places=3)
def testInitCrossedColumnWeightsFromCkpt(self):
sparse_col_1 = fc.sparse_column_with_hash_bucket(column_name="col_1",
hash_bucket_size=4)
sparse_col_2 = fc.sparse_column_with_hash_bucket(column_name="col_2",
hash_bucket_size=4)
crossed_col = fc.crossed_column(columns=[sparse_col_1, sparse_col_2],
hash_bucket_size=4)
input_tensor = sparse_tensor_lib.SparseTensor(indices=[[0, 0], [1, 1],
[2, 2], [3, 3]],
values=[0, 1, 2, 3],
dense_shape=[4, 4])
# Invoking 'weighted_sum_from_feature_columns' will create the crossed
# column weights variable.
with variable_scope.variable_scope("run_1"):
with variable_scope.variable_scope(crossed_col.name):
# Returns looked up column weights which is same as crossed column
# weights as well as actual references to weights variables.
_, col_weights, _ = (
feature_column_ops.weighted_sum_from_feature_columns(
{
sparse_col_1.name: input_tensor,
sparse_col_2.name: input_tensor
}, [crossed_col], 1))
# Update the weights since default initializer initializes all weights
# to 0.0.
for weight in col_weights.values():
assign_op = state_ops.assign(weight[0], weight[0] + 0.5)
save = saver.Saver()
ckpt_dir_prefix = os.path.join(self.get_temp_dir(),
"init_crossed_col_w_from_ckpt")
ckpt_dir = tempfile.mkdtemp(prefix=ckpt_dir_prefix)
checkpoint_path = os.path.join(ckpt_dir, "model.ckpt")
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
sess.run(assign_op)
saved_col_weights = col_weights[crossed_col][0].eval()
save.save(sess, checkpoint_path)
crossed_col_initialized = fc.crossed_column(
columns=[sparse_col_1, sparse_col_2],
hash_bucket_size=4,
ckpt_to_load_from=checkpoint_path,
tensor_name_in_ckpt=("run_1/col_1_X_col_2/"
"weighted_sum_from_feature_columns/"
"col_1_X_col_2/weights"))
with variable_scope.variable_scope("run_2"):
# This will initialize the crossed column weights from provided checkpoint
# and return a [4, 1] tensor which is same as weights variable. Since we
# won't modify weights, this should be same as 'saved_col_weights'.
_, col_weights, _ = (
feature_column_ops.weighted_sum_from_feature_columns(
{
sparse_col_1.name: input_tensor,
sparse_col_2.name: input_tensor
}, [crossed_col_initialized], 1))
col_weights_from_ckpt = col_weights[crossed_col_initialized][0]
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
loaded_col_weights = col_weights_from_ckpt.eval()
self.assertAllClose(saved_col_weights, loaded_col_weights)
def testImmutability(self):
a = fc.sparse_column_with_hash_bucket("aaa", hash_bucket_size=100)
with self.assertRaises(AttributeError):
a.column_name = "bbb"
def testCreateFeatureSpec(self):
sparse_col = fc.sparse_column_with_hash_bucket("sparse_column",
hash_bucket_size=100)
embedding_col = fc.embedding_column(fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
sparse_id_col = fc.sparse_column_with_keys(
"id_column", ["marlo", "omar", "stringer"])
weighted_id_col = fc.weighted_sparse_column(sparse_id_col,
"id_weights_column")
real_valued_col1 = fc.real_valued_column("real_valued_column1")
real_valued_col2 = fc.real_valued_column("real_valued_column2", 5)
real_valued_col3 = fc.real_valued_column("real_valued_column3",
dimension=None)
bucketized_col1 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization1"),
[0, 4])
bucketized_col2 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization2", 4),
[0, 4])
a = fc.sparse_column_with_hash_bucket("cross_aaa",
hash_bucket_size=100)
b = fc.sparse_column_with_hash_bucket("cross_bbb",
hash_bucket_size=100)
cross_col = fc.crossed_column(set([a, b]), hash_bucket_size=10000)
feature_columns = set([
sparse_col, embedding_col, weighted_id_col, real_valued_col1,
real_valued_col2, real_valued_col3, bucketized_col1,
bucketized_col2, cross_col
])
expected_config = {
"sparse_column":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_embedding":
parsing_ops.VarLenFeature(dtypes.string),
"id_column":
parsing_ops.VarLenFeature(dtypes.string),
"id_weights_column":
parsing_ops.VarLenFeature(dtypes.float32),
"real_valued_column1":
parsing_ops.FixedLenFeature([1], dtype=dtypes.float32),
"real_valued_column2":
parsing_ops.FixedLenFeature([5], dtype=dtypes.float32),
"real_valued_column3":
parsing_ops.VarLenFeature(dtype=dtypes.float32),
"real_valued_column_for_bucketization1":
parsing_ops.FixedLenFeature([1], dtype=dtypes.float32),
"real_valued_column_for_bucketization2":
parsing_ops.FixedLenFeature([4], dtype=dtypes.float32),
"cross_aaa":
parsing_ops.VarLenFeature(dtypes.string),
"cross_bbb":
parsing_ops.VarLenFeature(dtypes.string)
}
config = fc.create_feature_spec_for_parsing(feature_columns)
self.assertDictEqual(expected_config, config)
# Test that the same config is parsed out if we pass a dictionary.
feature_columns_dict = {
str(i): val
for i, val in enumerate(feature_columns)
}
config = fc.create_feature_spec_for_parsing(feature_columns_dict)
self.assertDictEqual(expected_config, config)
def testCreateFeatureSpec(self):
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = fc.embedding_column(
fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
str_sparse_id_col = fc.sparse_column_with_keys(
"str_id_column", ["marlo", "omar", "stringer"])
int32_sparse_id_col = fc.sparse_column_with_keys(
"int32_id_column", [42, 1, -1000], dtype=dtypes.int32)
int64_sparse_id_col = fc.sparse_column_with_keys(
"int64_id_column", [42, 1, -1000], dtype=dtypes.int64)
weighted_id_col = fc.weighted_sparse_column(str_sparse_id_col,
"str_id_weights_column")
real_valued_col1 = fc.real_valued_column("real_valued_column1")
real_valued_col2 = fc.real_valued_column("real_valued_column2", 5)
real_valued_col3 = fc._real_valued_var_len_column(
"real_valued_column3", is_sparse=True)
real_valued_col4 = fc._real_valued_var_len_column(
"real_valued_column4", dtype=dtypes.int64, default_value=0,
is_sparse=False)
bucketized_col1 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
bucketized_col2 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization2", 4),
[0, 4])
a = fc.sparse_column_with_hash_bucket("cross_aaa", hash_bucket_size=100)
b = fc.sparse_column_with_hash_bucket("cross_bbb", hash_bucket_size=100)
cross_col = fc.crossed_column(set([a, b]), hash_bucket_size=10000)
one_hot_col = fc.one_hot_column(fc.sparse_column_with_hash_bucket(
"sparse_column_for_one_hot", hash_bucket_size=100))
scattered_embedding_col = fc.scattered_embedding_column(
"scattered_embedding_column", size=100, dimension=10, hash_key=1)
feature_columns = set([
sparse_col, embedding_col, weighted_id_col, int32_sparse_id_col,
int64_sparse_id_col, real_valued_col1, real_valued_col2,
real_valued_col3, real_valued_col4, bucketized_col1, bucketized_col2,
cross_col, one_hot_col, scattered_embedding_col
])
expected_config = {
"sparse_column":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_embedding":
parsing_ops.VarLenFeature(dtypes.string),
"str_id_column":
parsing_ops.VarLenFeature(dtypes.string),
"int32_id_column":
parsing_ops.VarLenFeature(dtypes.int32),
"int64_id_column":
parsing_ops.VarLenFeature(dtypes.int64),
"str_id_weights_column":
parsing_ops.VarLenFeature(dtypes.float32),
"real_valued_column1":
parsing_ops.FixedLenFeature(
[1], dtype=dtypes.float32),
"real_valued_column2":
parsing_ops.FixedLenFeature(
[5], dtype=dtypes.float32),
"real_valued_column3":
parsing_ops.VarLenFeature(dtype=dtypes.float32),
"real_valued_column4":
parsing_ops.FixedLenSequenceFeature(
[], dtype=dtypes.int64, allow_missing=True, default_value=0),
"real_valued_column_for_bucketization1":
parsing_ops.FixedLenFeature(
[1], dtype=dtypes.float32),
"real_valued_column_for_bucketization2":
parsing_ops.FixedLenFeature(
[4], dtype=dtypes.float32),
"cross_aaa":
parsing_ops.VarLenFeature(dtypes.string),
"cross_bbb":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_one_hot":
parsing_ops.VarLenFeature(dtypes.string),
"scattered_embedding_column":
parsing_ops.VarLenFeature(dtypes.string),
}
config = fc.create_feature_spec_for_parsing(feature_columns)
self.assertDictEqual(expected_config, config)
# Test that the same config is parsed out if we pass a dictionary.
feature_columns_dict = {
str(i): val
for i, val in enumerate(feature_columns)
}
config = fc.create_feature_spec_for_parsing(feature_columns_dict)
self.assertDictEqual(expected_config, config)
def testCreateFeatureSpec(self):
sparse_col = fc.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = fc.embedding_column(
fc.sparse_column_with_hash_bucket(
"sparse_column_for_embedding", hash_bucket_size=10),
dimension=4)
str_sparse_id_col = fc.sparse_column_with_keys(
"str_id_column", ["marlo", "omar", "stringer"])
int32_sparse_id_col = fc.sparse_column_with_keys(
"int32_id_column", [42, 1, -1000], dtype=dtypes.int32)
int64_sparse_id_col = fc.sparse_column_with_keys(
"int64_id_column", [42, 1, -1000], dtype=dtypes.int64)
weighted_id_col = fc.weighted_sparse_column(str_sparse_id_col,
"str_id_weights_column")
real_valued_col1 = fc.real_valued_column("real_valued_column1")
real_valued_col2 = fc.real_valued_column("real_valued_column2", 5)
bucketized_col1 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization1"), [0, 4])
bucketized_col2 = fc.bucketized_column(
fc.real_valued_column("real_valued_column_for_bucketization2", 4),
[0, 4])
a = fc.sparse_column_with_hash_bucket("cross_aaa", hash_bucket_size=100)
b = fc.sparse_column_with_hash_bucket("cross_bbb", hash_bucket_size=100)
cross_col = fc.crossed_column(set([a, b]), hash_bucket_size=10000)
one_hot_col = fc.one_hot_column(fc.sparse_column_with_hash_bucket(
"sparse_column_for_one_hot", hash_bucket_size=100))
scattered_embedding_col = fc.scattered_embedding_column(
"scattered_embedding_column", size=100, dimension=10, hash_key=1)
feature_columns = set([
sparse_col, embedding_col, weighted_id_col, int32_sparse_id_col,
int64_sparse_id_col, real_valued_col1, real_valued_col2,
bucketized_col1, bucketized_col2, cross_col, one_hot_col,
scattered_embedding_col
])
expected_config = {
"sparse_column":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_embedding":
parsing_ops.VarLenFeature(dtypes.string),
"str_id_column":
parsing_ops.VarLenFeature(dtypes.string),
"int32_id_column":
parsing_ops.VarLenFeature(dtypes.int32),
"int64_id_column":
parsing_ops.VarLenFeature(dtypes.int64),
"str_id_weights_column":
parsing_ops.VarLenFeature(dtypes.float32),
"real_valued_column1":
parsing_ops.FixedLenFeature(
[1], dtype=dtypes.float32),
"real_valued_column2":
parsing_ops.FixedLenFeature(
[5], dtype=dtypes.float32),
"real_valued_column_for_bucketization1":
parsing_ops.FixedLenFeature(
[1], dtype=dtypes.float32),
"real_valued_column_for_bucketization2":
parsing_ops.FixedLenFeature(
[4], dtype=dtypes.float32),
"cross_aaa":
parsing_ops.VarLenFeature(dtypes.string),
"cross_bbb":
parsing_ops.VarLenFeature(dtypes.string),
"sparse_column_for_one_hot":
parsing_ops.VarLenFeature(dtypes.string),
"scattered_embedding_column":
parsing_ops.VarLenFeature(dtypes.string),
}
config = fc.create_feature_spec_for_parsing(feature_columns)
self.assertDictEqual(expected_config, config)
# Tests that contrib feature columns work with core library:
config_core = fc_core.make_parse_example_spec(feature_columns)
self.assertDictEqual(expected_config, config_core)
# Test that the same config is parsed out if we pass a dictionary.
feature_columns_dict = {
str(i): val
for i, val in enumerate(feature_columns)
}
config = fc.create_feature_spec_for_parsing(feature_columns_dict)
self.assertDictEqual(expected_config, config)
def testSdcaOptimizerSparseFeaturesWithL1Reg(self):
"""SDCALinearRegressor works with sparse features and L1 regularization."""
def input_fn():
return {
'example_id':
constant_op.constant(['1', '2', '3']),
'price':
constant_op.constant([0.4, 0.6, 0.3]),
'country':
sparse_tensor.SparseTensor(values=['IT', 'US', 'GB'],
indices=[[0, 0], [1, 3], [2, 1]],
dense_shape=[3, 5]),
'weights':
constant_op.constant([[10.0], [10.0], [10.0]])
}, constant_op.constant([[1.4], [-0.8], [2.6]])
with self._single_threaded_test_session():
price = feature_column_lib.real_valued_column('price')
country = feature_column_lib.sparse_column_with_hash_bucket(
'country', hash_bucket_size=5)
# Regressor with no L1 regularization.
regressor = sdca_estimator.SDCALinearRegressor(
example_id_column='example_id',
feature_columns=[price, country],
weight_column_name='weights')
regressor.fit(input_fn=input_fn, steps=20)
no_l1_reg_loss = regressor.evaluate(input_fn=input_fn,
steps=1)['loss']
variable_names = regressor.get_variable_names()
self.assertIn('linear/price/weight', variable_names)
self.assertIn('linear/country/weights', variable_names)
no_l1_reg_weights = {
'linear/price/weight':
regressor.get_variable_value('linear/price/weight'),
'linear/country/weights':
regressor.get_variable_value('linear/country/weights'),
}
# Regressor with L1 regularization.
regressor = sdca_estimator.SDCALinearRegressor(
example_id_column='example_id',
feature_columns=[price, country],
l1_regularization=1.0,
weight_column_name='weights')
regressor.fit(input_fn=input_fn, steps=20)
l1_reg_loss = regressor.evaluate(input_fn=input_fn,
steps=1)['loss']
l1_reg_weights = {
'linear/price/weight':
regressor.get_variable_value('linear/price/weight'),
'linear/country/weights':
regressor.get_variable_value('linear/country/weights'),
}
# Unregularized loss is lower when there is no L1 regularization.
self.assertLess(no_l1_reg_loss, l1_reg_loss)
self.assertLess(no_l1_reg_loss, 0.05)
# But weights returned by the regressor with L1 regularization have
# smaller L1 norm.
l1_reg_weights_norm, no_l1_reg_weights_norm = 0.0, 0.0
for var_name in sorted(l1_reg_weights):
l1_reg_weights_norm += sum(
np.absolute(l1_reg_weights[var_name].flatten()))
no_l1_reg_weights_norm += sum(
np.absolute(no_l1_reg_weights[var_name].flatten()))
print('Var name: %s, value: %s' %
(var_name, no_l1_reg_weights[var_name].flatten()))
self.assertLess(l1_reg_weights_norm, no_l1_reg_weights_norm)
