Represents Sparse Feature where IDs are set by Hashing
Use this when your sparse features are in string or integer format, and you
want to distribute your inputs into a finite number of buckets by hashing.
output_id = Hash(input_feature_string)
features$key$ is either tensor or sparse tensor object. If it's
tensor object, missing values can be represented by
-1 for int and
string. Note that these values are independent of the
column_categorical_with_hash_bucket(..., hash_bucket_size, dtype = tf$string)
Expression(s) identifying input feature(s). Used as the column name and the dictionary key for feature parsing configs, feature tensors, and feature columns.
An int > 1. The number of buckets.
The type of features. Only string and integer types are supported.
hash_bucket_sizeis not greater than 1.
dtypeis neither string nor integer.