tf.feature_column.categorical_column_with_vocabulary_list

A CategoricalColumn with in-memory vocabulary.

Used in the notebooks

Used in the guide Used in the tutorials

Use this when your inputs are in string or integer format, and you have an in-memory vocabulary mapping 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: In the following example, each input in vocabulary_list is assigned an ID 0-3 corresponding to its index (e.g., input 'B' produces output 2). All other inputs are hashed and assigned an ID 4-5.

colors = categorical_column_with_vocabulary_list(
    key='colors', vocabulary_list=('R', 'G', 'B', 'Y'),
    num_oov_buckets=2)
columns = [colors, ...]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
linear_prediction, _, _ = linear_model(features, columns)

Example with default_value: In the following example, each input in vocabulary_list is assigned an ID 0-4 corresponding to its index (e.g., input 'B' produces output 3). All other inputs are assigned default_value 0.

colors = categorical_column_with_vocabulary_list(
    key='colors', vocabulary_list=('X', 'R', 'G', 'B', 'Y'), default_value=0)
columns = [colors, ...]
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(colors, 3),...]
features = tf.io.parse_example(..., features=make_parse_example_spec(columns))
dense_tensor = input_layer(features, columns)

key A unique string identi