def analyzer_fn(inputs):
key_vocab, q_b, scale_factor_per_key, shift_per_key, num_buckets = (
analyzers._quantiles_per_key(
inputs['x'], inputs['key'], num_buckets=3, epsilon=0.00001))
return {
'key_vocab': key_vocab,
'q_b': q_b,
'scale_factor_per_key': scale_factor_per_key,
'shift_per_key': shift_per_key,
'num_buckets': num_buckets,
}
def bucketize_per_key(x, key, num_buckets, epsilon=None, name=None):
"""Returns a bucketized column, with a bucket index assigned to each input.
Args:
x: A numeric input `Tensor` or `SparseTensor` with rank 1, whose values
should be mapped to buckets. `SparseTensor`s will have their non-missing
values mapped and missing values left as missing.
key: A Tensor with the same shape as `x` and dtype tf.string. If `x` is
a `SparseTensor`, `key` must exactly match `x` in everything except
values, i.e. indices and dense_shape must be identical.
num_buckets: Values in the input `x` are divided into approximately
equal-sized buckets, where the number of buckets is num_buckets.
epsilon: (Optional) see `bucketize`
name: (Optional) A name for this operation.
Returns:
A `Tensor` of the same shape as `x`, with each element in the
returned tensor representing the bucketized value. Bucketized value is
in the range [0, actual_num_buckets).
Raises:
ValueError: If value of num_buckets is not > 1.
"""
with tf.name_scope(name, 'bucketize_per_key'):
if not isinstance(num_buckets, int):
raise TypeError('num_buckets must be an int, got {}'.format(
type(num_buckets)))
if num_buckets < 1:
raise ValueError('Invalid num_buckets {}'.format(num_buckets))
if epsilon is None:
# See explanation in args documentation for epsilon.
epsilon = min(1.0 / num_buckets, 0.01)
key_vocab, bucket_boundaries = analyzers._quantiles_per_key( # pylint: disable=protected-access
x.values if isinstance(x, tf.SparseTensor) else x,
key.values if isinstance(key, tf.SparseTensor) else key,
num_buckets, epsilon)
return _apply_buckets_with_keys(x, key, key_vocab, bucket_boundaries)