def testCreateSequenceFeatureSpec(self):
sparse_col = tf.contrib.layers.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = tf.contrib.layers.embedding_column(
tf.contrib.layers.sparse_column_with_hash_bucket(
"sparse_column_for_embedding",
hash_bucket_size=10),
dimension=4)
sparse_id_col = tf.contrib.layers.sparse_column_with_keys(
"id_column", ["marlo", "omar", "stringer"])
weighted_id_col = tf.contrib.layers.weighted_sparse_column(
sparse_id_col, "id_weights_column")
real_valued_col1 = tf.contrib.layers.real_valued_column(
"real_valued_column", dimension=2)
real_valued_col2 = tf.contrib.layers.real_valued_column(
"real_valued_default_column", dimension=5, default_value=3.0)
feature_columns = set([sparse_col, embedding_col, weighted_id_col,
real_valued_col1, real_valued_col2])
feature_spec = fc._create_sequence_feature_spec_for_parsing(feature_columns)
expected_feature_spec = {
"sparse_column": tf.VarLenFeature(tf.string),
"sparse_column_for_embedding": tf.VarLenFeature(tf.string),
"id_column": tf.VarLenFeature(tf.string),
"id_weights_column": tf.VarLenFeature(tf.float32),
"real_valued_column": tf.FixedLenSequenceFeature(
shape=[2], dtype=tf.float32, allow_missing=False),
"real_valued_default_column": tf.FixedLenSequenceFeature(
shape=[5], dtype=tf.float32, allow_missing=True)}
self.assertDictEqual(expected_feature_spec, feature_spec)
def testCreateSequenceFeatureSpec(self):
sparse_col = tf.contrib.layers.sparse_column_with_hash_bucket(
"sparse_column", hash_bucket_size=100)
embedding_col = tf.contrib.layers.embedding_column(
tf.contrib.layers.sparse_column_with_hash_bucket(
"sparse_column_for_embedding",
hash_bucket_size=10),
dimension=4)
sparse_id_col = tf.contrib.layers.sparse_column_with_keys(
"id_column", ["marlo", "omar", "stringer"])
weighted_id_col = tf.contrib.layers.weighted_sparse_column(
sparse_id_col, "id_weights_column")
real_valued_col1 = tf.contrib.layers.real_valued_column(
"real_valued_column", dimension=2)
real_valued_col2 = tf.contrib.layers.real_valued_column(
"real_valued_default_column", dimension=5, default_value=3.0)
feature_columns = set([sparse_col, embedding_col, weighted_id_col,
real_valued_col1, real_valued_col2])
feature_spec = fc._create_sequence_feature_spec_for_parsing(feature_columns)
expected_feature_spec = {
"sparse_column": tf.VarLenFeature(tf.string),
"sparse_column_for_embedding": tf.VarLenFeature(tf.string),
"id_column": tf.VarLenFeature(tf.string),
"id_weights_column": tf.VarLenFeature(tf.float32),
"real_valued_column": tf.FixedLenSequenceFeature(
shape=[2], dtype=tf.float32, allow_missing=False),
"real_valued_default_column": tf.FixedLenSequenceFeature(
shape=[5], dtype=tf.float32, allow_missing=True)}
self.assertDictEqual(expected_feature_spec, feature_spec)
def parse_feature_columns_from_sequence_examples(
serialized,
context_feature_columns,
sequence_feature_columns,
name=None,
example_name=None):
"""Parses tf.SequenceExamples to extract tensors for given `FeatureColumn`s.
Args:
serialized: A scalar (0-D Tensor) of type string, a single serialized
`SequenceExample` proto.
context_feature_columns: An iterable containing the feature columns for
context features. All items should be instances of classes derived from
`_FeatureColumn`. Can be `None`.
sequence_feature_columns: An iterable containing the feature columns for
sequence features. All items should be instances of classes derived from
`_FeatureColumn`. Can be `None`.
name: A name for this operation (optional).
example_name: A scalar (0-D Tensor) of type string (optional), the names of
the serialized proto.
Returns:
A tuple consisting of (context_features, sequence_features)
* context_features: a dict mapping `FeatureColumns` from
`context_feature_columns` to their parsed `Tensors`/`SparseTensor`s.
* sequence_features: a dict mapping `FeatureColumns` from
`sequence_feature_columns` to their parsed `Tensors`/`SparseTensor`s.
"""
# Sequence example parsing requires a single (scalar) example.
try:
serialized = array_ops.reshape(serialized, [])
except ValueError as e:
raise ValueError(
'serialized must contain as single sequence example. Batching must be '
'done after parsing for sequence examples. Error: {}'.format(e))
if context_feature_columns is None:
context_feature_columns = []
if sequence_feature_columns is None:
sequence_feature_columns = []
check_feature_columns(context_feature_columns)
context_feature_spec = fc.create_feature_spec_for_parsing(
context_feature_columns)
check_feature_columns(sequence_feature_columns)
sequence_feature_spec = fc._create_sequence_feature_spec_for_parsing( # pylint: disable=protected-access
sequence_feature_columns, allow_missing_by_default=False)
return parsing_ops.parse_single_sequence_example(serialized,
context_feature_spec,
sequence_feature_spec,
example_name,
name)
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 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)
