tf.contrib.feature_column.sequence_categorical_column_with_vocabulary_list(
key,
vocabulary_list,
dtype=None,
default_value=-1,
num_oov_buckets=0
)
Defined in tensorflow/contrib/feature_column/python/feature_column/sequence_feature_column.py
.
A sequence of categorical terms where ids use an in-memory list.
Pass this to embedding_column
or indicator_column
to convert sequence
categorical data into dense representation for input to sequence NN, such as
RNN.
Example:
colors = sequence_categorical_column_with_vocabulary_list(
key='colors', vocabulary_list=('R', 'G', 'B', 'Y'),
num_oov_buckets=2)
colors_embedding = embedding_column(colors, dimension=3)
columns = [colors_embedding]
features = tf.parse_example(..., features=make_parse_example_spec(columns))
input_layer, sequence_length = sequence_input_layer(features, columns)
rnn_cell = tf.nn.rnn_cell.BasicRNNCell(hidden_size)
outputs, state = tf.nn.dynamic_rnn(
rnn_cell, inputs=input_layer, sequence_length=sequence_length)
Args:
key
: A unique string identifying the input feature.vocabulary_list
: An ordered iterable defining the vocabulary. Each feature is mapped to the index of its value (if present) invocabulary_list
. Must be castable todtype
.dtype
: The type of features. Only string and integer types are supported. IfNone
, it will be inferred fromvocabulary_list
.default_value
: The integer ID value to return for out-of-vocabulary feature values, defaults to-1
. This can not be specified with a positivenum_oov_buckets
.num_oov_buckets
: Non-negative integer, the number of out-of-vocabulary buckets. All out-of-vocabulary inputs will be assigned IDs in the range[len(vocabulary_list), len(vocabulary_list)+num_oov_buckets)
based on a hash of the input value. A positivenum_oov_buckets
can not be specified withdefault_value
.
Returns:
A _SequenceCategoricalColumn
.
Raises:
ValueError
: ifvocabulary_list
is empty, or contains duplicate keys.ValueError
:num_oov_buckets
is a negative integer.ValueError
:num_oov_buckets
anddefault_value
are both specified.ValueError
: ifdtype
is not integer or string.