View source on GitHub |
A sequence of categorical terms where ids use a vocabulary file.
tf.feature_column.sequence_categorical_column_with_vocabulary_file(
key,
vocabulary_file,
vocabulary_size=None,
num_oov_buckets=0,
default_value=None,
dtype=tf.dtypes.string
)
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:
states = sequence_categorical_column_with_vocabulary_file(
key='states', vocabulary_file='/us/states.txt', vocabulary_size=50,
num_oov_buckets=5)
states_embedding = embedding_column(states, dimension=10)
columns = [states_embedding]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
sequence_feature_layer = SequenceFeatures(columns)
sequence_input, sequence_length = sequence_feature_layer(features)
sequence_length_mask = tf.sequence_mask(sequence_length)
rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size)
rnn_layer = tf.keras.layers.RNN(rnn_cell)
outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask)
Returns | |
---|---|
A SequenceCategoricalColumn .
|