def sum(x): # pylint: disable=redefined-builtin
"""Computes the sum of a `Column`.
Args:
x: An input `Column' wrapping a `Tensor`.
Returns:
A `Statistic`.
"""
if not isinstance(x.tensor, tf.Tensor):
raise TypeError('Expected a Tensor, but got %r' % x.tensor)
# pylint: disable=protected-access
return api._AnalyzerOutput(tf.placeholder(x.tensor.dtype, ()),
api.CanonicalAnalyzers.SUM, [x], {})
def uniques(x, top_k=None, frequency_threshold=None):
"""Returns the unique values of the input tensor.
Computes The unique values taken by the input column `x`, which can be backed
by a `Tensor` or `SparseTensor` of any size. The unique values will be
aggregated over all dimensions of `x` and all instances.
The unique values are sorted by decreasing frequency and then decreasing
value.
Args:
x: An input `Column` wrapping a `Tensor` or `SparseTensor`.
top_k: Limit the generated vocabulary to the first `top_k` elements. If set
to None, the full vocabulary is generated.
frequency_threshold: Limit the generated vocabulary only to elements whose
frequency is >= to the supplied threshold. If set to None, the full
vocabulary is generated.
Returns:
The unique values of `x`.
Raises:
ValueError: If `top_k` or `frequency_threshold` is negative.
"""
if top_k is not None:
top_k = long(top_k)
if top_k < 0:
raise ValueError('top_k must be non-negative, but got: %r' % top_k)
if frequency_threshold is not None:
frequency_threshold = long(frequency_threshold)
if frequency_threshold < 0:
raise ValueError(
'frequency_threshold must be non-negative, but got: %r' %
frequency_threshold)
if isinstance(x.tensor, tf.SparseTensor):
values = x.tensor.values
else:
values = x.tensor
arg_dict = {'top_k': top_k, 'frequency_threshold': frequency_threshold}
# Create output placeholder whose shape is a 1-d tensor of unkown size.
# pylint: disable=protected-access
return api._AnalyzerOutput(tf.placeholder(values.dtype, (None, )),
api.CanonicalAnalyzers.UNIQUES, [x], arg_dict)
def sum(x, reduce_instance_dims=True): # pylint: disable=redefined-builtin
"""Computes the sum of a `Column`.
Args:
x: An input `Column' wrapping a `Tensor`.
reduce_instance_dims: By default collapses the batch and instance dimensions
to arrive at a single scalar output. If False, only collapses the batch
dimension and outputs a vector of the same shape as the output.
Returns:
A `Statistic`.
"""
if not isinstance(x.tensor, tf.Tensor):
raise TypeError('Expected a Tensor, but got %r' % x.tensor)
arg_dict = {'reduce_instance_dims': reduce_instance_dims}
# pylint: disable=protected-access
return api._AnalyzerOutput(
tf.placeholder(x.tensor.dtype,
_get_output_shape(x, reduce_instance_dims)),
api.CanonicalAnalyzers.SUM, [x], arg_dict)
