def _training_examples_and_variables():
"""Returns dictionaries for training examples and variables."""
batch_size = targets.get_shape()[0]
# Iterate over all feature columns and create appropriate lists for dense
# and sparse features as well as dense and sparse weights (variables) for
# SDCA.
# TODO(sibyl-vie3Poto): Reshape variables stored as values in column_to_variables
# dict as 1-dimensional tensors.
dense_features, sparse_features, sparse_feature_with_values = [], [], []
dense_feature_weights = []
sparse_feature_weights, sparse_feature_with_values_weights = [], []
for column in sorted(columns_to_variables.keys(), key=lambda x: x.key):
transformed_tensor = features[column]
if isinstance(column, layers.feature_column._RealValuedColumn): # pylint: disable=protected-access
# A real-valued column corresponds to a dense feature in SDCA. A
# transformed tensor corresponding to a RealValuedColumn has rank 2
# (its shape is typically [batch_size, column.dimension]) and so it
# can be passed to SDCA as is.
dense_features.append(transformed_tensor)
# For real valued columns, the variables list contains exactly one
# element.
dense_feature_weights.append(columns_to_variables[column][0])
elif isinstance(column, layers.feature_column._BucketizedColumn): # pylint: disable=protected-access
# A bucketized column corresponds to a sparse feature in SDCA. The
# bucketized feature is "sparsified" for SDCA by converting it to a
# SparseFeatureColumn respresenting the one-hot encoding of the
# bucketized feature.
#
# TODO(sibyl-vie3Poto): Explore whether it is more efficient to translate a
# bucketized feature column to a dense feature in SDCA. This will likely
# depend on the number of buckets.
dense_bucket_tensor = column._to_dnn_input_layer(
transformed_tensor) # pylint: disable=protected-access
sparse_feature_column = _dense_tensor_to_sparse_feature_column(
dense_bucket_tensor)
sparse_feature_with_values.append(sparse_feature_column)
# For bucketized columns, the variables list contains exactly one
# element.
sparse_feature_with_values_weights.append(
columns_to_variables[column][0])
elif isinstance(
column,
(
layers.feature_column._CrossedColumn, # pylint: disable=protected-access
layers.feature_column._SparseColumn)): # pylint: disable=protected-access
sparse_features.append(
SparseFeatureColumn(
array_ops.reshape(
array_ops.split(value=transformed_tensor.indices,
num_or_size_splits=2,
axis=1)[0], [-1]),
array_ops.reshape(transformed_tensor.values, [-1]),
None))
sparse_feature_weights.append(columns_to_variables[column][0])
elif isinstance(column,
layers.feature_column._WeightedSparseColumn): # pylint: disable=protected-access
id_tensor = column.id_tensor(transformed_tensor)
weight_tensor = column.weight_tensor(transformed_tensor)
sparse_feature_with_values.append(
SparseFeatureColumn(
array_ops.reshape(
array_ops.split(value=id_tensor.indices,
num_or_size_splits=2,
axis=1)[0], [-1]),
array_ops.reshape(id_tensor.values, [-1]),
array_ops.reshape(weight_tensor.values, [-1])))
sparse_feature_with_values_weights.append(
columns_to_variables[column][0])
else:
raise ValueError(
"SDCAOptimizer does not support column type {}".format(
type(column).__name__))
example_weights = array_ops.reshape(
features[weight_column_name],
shape=[-1]) if weight_column_name else array_ops.ones([batch_size])
example_ids = features[optimizer.example_id_column]
sparse_feature_with_values.extend(sparse_features)
sparse_feature_with_values_weights.extend(sparse_feature_weights)
examples = dict(sparse_features=sparse_feature_with_values,
dense_features=dense_features,
example_labels=math_ops.to_float(
array_ops.reshape(targets, shape=[-1])),
example_weights=example_weights,
example_ids=example_ids)
sdca_variables = dict(
sparse_features_weights=sparse_feature_with_values_weights,
dense_features_weights=dense_feature_weights)
return examples, sdca_variables
def _training_examples_and_variables():
"""Returns dictionaries for training examples and variables."""
batch_size = targets.get_shape()[0]
# Iterate over all feature columns and create appropriate lists for dense
# and sparse features as well as dense and sparse weights (variables) for
# SDCA.
# TODO(sibyl-vie3Poto): Reshape variables stored as values in column_to_variables
# dict as 1-dimensional tensors.
dense_features, sparse_features, sparse_feature_with_values = [], [], []
dense_feature_weights = []
sparse_feature_weights, sparse_feature_with_values_weights = [], []
for column in sorted(columns_to_variables.keys(),
key=lambda x: x.key):
transformed_tensor = features[column]
if isinstance(column, layers.feature_column._RealValuedColumn): # pylint: disable=protected-access
# A real-valued column corresponds to a dense feature in SDCA. A
# transformed tensor corresponding to a RealValuedColumn should have
# rank at most 2. In order to be passed to SDCA, its rank needs to be
# exactly 2 (i.e., its shape should be [batch_size, column.dim]).
check_rank_op = control_flow_ops.Assert(
math_ops.less_equal(array_ops.rank(transformed_tensor),
2),
['transformed_tensor should have rank at most 2.'])
# Reshape to [batch_size, dense_column_dimension].
with ops.control_dependencies([check_rank_op]):
transformed_tensor = array_ops.reshape(
transformed_tensor,
[array_ops.shape(transformed_tensor)[0], -1])
dense_features.append(transformed_tensor)
# For real valued columns, the variables list contains exactly one
# element.
dense_feature_weights.append(
columns_to_variables[column][0])
elif isinstance(column,
layers.feature_column._BucketizedColumn): # pylint: disable=protected-access
# A bucketized column corresponds to a sparse feature in SDCA. The
# bucketized feature is "sparsified" for SDCA by converting it to a
# SparseFeatureColumn representing the one-hot encoding of the
# bucketized feature.
#
# TODO(sibyl-vie3Poto): Explore whether it is more efficient to translate a
# bucketized feature column to a dense feature in SDCA. This will
# likely depend on the number of buckets.
dense_bucket_tensor = column._to_dnn_input_layer(
transformed_tensor) # pylint: disable=protected-access
sparse_feature_column = _dense_tensor_to_sparse_feature_column(
dense_bucket_tensor)
sparse_feature_with_values.append(sparse_feature_column)
# If a partitioner was used during variable creation, we will have a
# list of Variables here larger than 1.
vars_to_append = columns_to_variables[column][0]
if len(columns_to_variables[column]) > 1:
vars_to_append = columns_to_variables[column]
sparse_feature_with_values_weights.append(vars_to_append)
elif isinstance(
column,
(
layers.feature_column._WeightedSparseColumn, # pylint: disable=protected-access
layers.feature_column._CrossedColumn, # pylint: disable=protected-access
layers.feature_column._SparseColumn)): # pylint: disable=protected-access
if isinstance(column,
layers.feature_column._WeightedSparseColumn): # pylint: disable=protected-access
id_tensor = column.id_tensor(transformed_tensor)
weight_tensor = array_ops.reshape(
column.weight_tensor(transformed_tensor).values,
[-1])
else:
id_tensor = transformed_tensor
weight_tensor = array_ops.ones(
[array_ops.shape(id_tensor.indices)[0]],
dtypes.float32)
example_ids = array_ops.reshape(id_tensor.indices[:, 0],
[-1])
flat_ids = array_ops.reshape(id_tensor.values, [-1])
# Prune invalid IDs (< 0) from the flat_ids, example_ids, and
# weight_tensor. These can come from looking up an OOV entry in the
# vocabulary (default value being -1).
is_id_valid = math_ops.greater_equal(flat_ids, 0)
flat_ids = array_ops.boolean_mask(flat_ids, is_id_valid)
example_ids = array_ops.boolean_mask(
example_ids, is_id_valid)
weight_tensor = array_ops.boolean_mask(
weight_tensor, is_id_valid)
projection_length = math_ops.reduce_max(flat_ids) + 1
# project ids based on example ids so that we can dedup ids that
# occur multiple times for a single example.
projected_ids = projection_length * example_ids + flat_ids
# Remove any redundant ids.
ids, idx = array_ops.unique(projected_ids)
# Keep only one example id per duplicated ids.
example_ids_filtered = math_ops.unsorted_segment_min(
example_ids, idx,
array_ops.shape(ids)[0])
# reproject ids back feature id space.
reproject_ids = (ids -
projection_length * example_ids_filtered)
weights = array_ops.reshape(
math_ops.unsorted_segment_sum(weight_tensor, idx,
array_ops.shape(ids)[0]),
[-1])
sparse_feature_with_values.append(
SparseFeatureColumn(example_ids_filtered,
reproject_ids, weights))
# If a partitioner was used during variable creation, we will have a
# list of Variables here larger than 1.
vars_to_append = columns_to_variables[column][0]
if len(columns_to_variables[column]) > 1:
vars_to_append = columns_to_variables[column]
sparse_feature_with_values_weights.append(vars_to_append)
else:
raise ValueError(
'SDCAOptimizer does not support column type %s.' %
type(column).__name__)
example_weights = array_ops.reshape(
features[weight_column_name], shape=[
-1
]) if weight_column_name else array_ops.ones([batch_size])
example_ids = features[self._example_id_column]
sparse_feature_with_values.extend(sparse_features)
sparse_feature_with_values_weights.extend(sparse_feature_weights)
examples = dict(sparse_features=sparse_feature_with_values,
dense_features=dense_features,
example_labels=math_ops.cast(
array_ops.reshape(targets, shape=[-1]),
dtypes.float32),
example_weights=example_weights,
example_ids=example_ids)
sdca_variables = dict(
sparse_features_weights=sparse_feature_with_values_weights,
dense_features_weights=dense_feature_weights)
return examples, sdca_variables
def _training_examples_and_variables():
"""Returns dictionaries for training examples and variables."""
batch_size = targets.get_shape()[0]
# Iterate over all feature columns and create appropriate lists for dense
# and sparse features as well as dense and sparse weights (variables) for
# SDCA.
# TODO (sibyl-vie3Poto): Reshape variables stored as values in column_to_variables id:814 gh:815
# dict as 1-dimensional tensors.
dense_features, sparse_features, sparse_feature_with_values = [], [], []
dense_feature_weights = []
sparse_feature_weights, sparse_feature_with_values_weights = [], []
for column in sorted(columns_to_variables.keys(),
key=lambda x: x.key):
transformed_tensor = features[column]
if isinstance(column, layers.feature_column._RealValuedColumn): # pylint: disable=protected-access
# A real-valued column corresponds to a dense feature in SDCA. A
# transformed tensor corresponding to a RealValuedColumn should have
# rank at most 2. In order to be passed to SDCA, its rank needs to be
# exactly 2 (i.e., its shape should be [batch_size, column.dim]).
check_rank_op = control_flow_ops.Assert(
math_ops.less_equal(array_ops.rank(transformed_tensor),
2),
['transformed_tensor shouls have rank at most 2.'])
# Reshape to [batch_size, dense_column_dimension].
with ops.control_dependencies([check_rank_op]):
transformed_tensor = array_ops.reshape(
transformed_tensor,
[array_ops.shape(transformed_tensor)[0], -1])
dense_features.append(transformed_tensor)
# For real valued columns, the variables list contains exactly one
# element.
dense_feature_weights.append(
columns_to_variables[column][0])
elif isinstance(column,
layers.feature_column._BucketizedColumn): # pylint: disable=protected-access
# A bucketized column corresponds to a sparse feature in SDCA. The
# bucketized feature is "sparsified" for SDCA by converting it to a
# SparseFeatureColumn respresenting the one-hot encoding of the
# bucketized feature.
#
# TODO (sibyl-vie3Poto): Explore whether it is more efficient to translate a id:755 gh:756
# bucketized feature column to a dense feature in SDCA. This will
# likely depend on the number of buckets.
dense_bucket_tensor = column._to_dnn_input_layer(
transformed_tensor) # pylint: disable=protected-access
sparse_feature_column = _dense_tensor_to_sparse_feature_column(
dense_bucket_tensor)
sparse_feature_with_values.append(sparse_feature_column)
# For bucketized columns, the variables list contains exactly one
# element.
sparse_feature_with_values_weights.append(
columns_to_variables[column][0])
elif isinstance(
column,
(
layers.feature_column._CrossedColumn, # pylint: disable=protected-access
layers.feature_column._SparseColumn)): # pylint: disable=protected-access
sparse_features.append(
SparseFeatureColumn(
array_ops.reshape(
array_ops.split(
value=transformed_tensor.indices,
num_or_size_splits=2,
axis=1)[0], [-1]),
array_ops.reshape(transformed_tensor.values, [-1]),
None))
sparse_feature_weights.append(
columns_to_variables[column][0])
elif isinstance(column,
layers.feature_column._WeightedSparseColumn): # pylint: disable=protected-access
id_tensor = column.id_tensor(transformed_tensor)
weight_tensor = column.weight_tensor(transformed_tensor)
sparse_feature_with_values.append(
SparseFeatureColumn(
array_ops.reshape(
array_ops.split(value=id_tensor.indices,
num_or_size_splits=2,
axis=1)[0], [-1]),
array_ops.reshape(id_tensor.values, [-1]),
array_ops.reshape(weight_tensor.values, [-1])))
sparse_feature_with_values_weights.append(
columns_to_variables[column][0])
else:
raise ValueError(
'SDCAOptimizer does not support column type %s.' %
type(column).__name__)
example_weights = array_ops.reshape(
features[weight_column_name], shape=[
-1
]) if weight_column_name else array_ops.ones([batch_size])
example_ids = features[self._example_id_column]
sparse_feature_with_values.extend(sparse_features)
sparse_feature_with_values_weights.extend(sparse_feature_weights)
examples = dict(sparse_features=sparse_feature_with_values,
dense_features=dense_features,
example_labels=math_ops.to_float(
array_ops.reshape(targets, shape=[-1])),
example_weights=example_weights,
example_ids=example_ids)
sdca_variables = dict(
sparse_features_weights=sparse_feature_with_values_weights,
dense_features_weights=dense_feature_weights)
return examples, sdca_variables
