tf.feature_column.categorical_column_with_vocabulary_file

A CategoricalColumn with a vocabulary file.

Used in the notebooks

Used in the tutorials

Use this when your inputs are in string or integer format, and you have a vocabulary file that maps each value to an integer ID. By default, out-of-vocabulary values are ignored. Use either (but not both) of num_oov_buckets and default_value to specify how to include out-of-vocabulary values.

For input dictionary features, features[key] is either Tensor or SparseTensor. If Tensor, missing values can be represented by -1 for int and '' for string, which will be dropped by this feature column.

Example with num_oov_buckets: File '/us/states.txt' contains 50 lines, each with a 2-character U.S. state abbreviation. All inputs with values in that file are assigned an ID 0-49, corresponding to its line number. All other values are hashed and assigned an ID 50-54.

states = categorical_column_with_vocabulary_file(
    key='states', vocabulary_file='/us/states.txt', vocabulary_size=50,
    num_oov_buckets=5)
columns = [states, ...]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
linear_prediction = linear_model(features, columns)

Example with default_value: File '/us/states.txt' contains 51 lines - the first line is 'XX', and the other 50 each have a 2-character U.S. state abbreviation. Both a literal 'XX' in input, and other values missing from the file, will be assigned ID 0. All others are assigned the corresponding line number 1-50.

states = categorical_column_with_vocabulary_file(
    key='states', vocabulary_file='/us/states.txt', vocabulary_size=51,
    default_value=0)
columns = [states, ...]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
linear_prediction, _, _ = linear_model(features, columns)

And to make an embedding with either:

columns = [embedding_column(states, 3),...]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
dense_tensor = input_layer(features, columns)

key A unique string identifying the input feature. It is used as the column name and the dictionary key for feature parsing configs, feature Tensor objects, and feature columns.
vocabulary_file The vocabulary file name.
vocabulary_size Number of the elements in the vocabulary. This must be no greater than length of vocabulary_file, if less than length, later values are ignored. If None, it is set to the length of vocabulary_file.
dtype The type of features. Only string and integer types are supported.
default_value The integer ID value to return for out-of-vocabulary f