Use this when your inputs are integers in the range [0, num_buckets), and
you want to use the input value itself as the categorical ID. Values outside
this range will result in default_value if specified, otherwise it will
fail.
column_categorical_with_identity(..., num_buckets, default_value = NULL)Expression(s) identifying input feature(s). Used as the column name and the dictionary key for feature parsing configs, feature tensors, and feature columns.
Number of unique values.
If NULL, this column's graph operations will fail for
out-of-range inputs. Otherwise, this value must be in the range [0, num_buckets), and will replace inputs in that range.
A categorical column that returns identity values.
ValueError: if num_buckets is less than one.
ValueError: if default_value is not in range [0, num_buckets).
Typically, this is used for contiguous ranges of integer indexes, but it
doesn't have to be. This might be inefficient, however, if many of IDs are
unused. Consider column_categorical_with_hash_bucket() in that case.
For input dictionary features, features$key is either tensor or sparse
tensor object. If it's tensor object, missing values can be represented by -1 for
int and '' for string. Note that these values are independent of the
default_value argument.
Other feature column constructors:
column_bucketized(),
column_categorical_weighted(),
column_categorical_with_hash_bucket(),
column_categorical_with_vocabulary_file(),
column_categorical_with_vocabulary_list(),
column_crossed(),
column_embedding(),
column_numeric(),
input_layer()