Learn R Programming

keras (version 2.7.0)

layer_hashing: A preprocessing layer which hashes and bins categorical features.

Description

A preprocessing layer which hashes and bins categorical features.

Usage

layer_hashing(object, num_bins, mask_value = NULL, salt = NULL, ...)

Arguments

object

What to call the new Layer instance with. Typically a keras Model, another Layer, or a tf.Tensor/KerasTensor. If object is missing, the Layer instance is returned, otherwise, layer(object) is returned.

num_bins

Number of hash bins. Note that this includes the mask_value bin, so the effective number of bins is (num_bins - 1) if mask_value is set.

mask_value

A value that represents masked inputs, which are mapped to index 0. Defaults to NULL, meaning no mask term will be added and the hashing will start at index 0.

salt

A single unsigned integer or NULL. If passed, the hash function used will be SipHash64, with these values used as an additional input (known as a "salt" in cryptography). These should be non-zero. Defaults to NULL (in that case, the FarmHash64 hash function is used). It also supports list of 2 unsigned integer numbers, see reference paper for details.

...

standard layer arguments.

Details

This layer transforms single or multiple categorical inputs to hashed output. It converts a sequence of int or string to a sequence of int. The stable hash function uses tensorflow::ops::Fingerprint to produce the same output consistently across all platforms.

This layer uses FarmHash64 by default, which provides a consistent hashed output across different platforms and is stable across invocations, regardless of device and context, by mixing the input bits thoroughly.

If you want to obfuscate the hashed output, you can also pass a random salt argument in the constructor. In that case, the layer will use the SipHash64 hash function, with the salt value serving as additional input to the hash function.

Example (FarmHash64)

layer <- layer_hashing(num_bins=3)
inp <- matrix(c('A', 'B', 'C', 'D', 'E'))
layer(inp)
# <tf.Tensor: shape=(5, 1), dtype=int64, numpy=
#   array([[1],
#          [0],
#          [1],
#          [1],
#          [2]])>

Example (FarmHash64) with a mask value

layer <- layer_hashing(num_bins=3, mask_value='')
inp <- matrix(c('A', 'B', 'C', 'D', 'E'))
layer(inp)
# <tf.Tensor: shape=(5, 1), dtype=int64, numpy=
#   array([[1],
#          [1],
#          [0],
#          [2],
#          [2]])>

Example (SipHash64)

layer <- layer_hashing(num_bins=3, salt=c(133, 137))
inp <- matrix(c('A', 'B', 'C', 'D', 'E'))
layer(inp)
# <tf.Tensor: shape=(5, 1), dtype=int64, numpy=
#   array([[1],
#          [2],
#          [1],
#          [0],
#          [2]])>

Example (Siphash64 with a single integer, same as salt=[133, 133])

layer <- layer_hashing(num_bins=3, salt=133)
inp <- matrix(c('A', 'B', 'C', 'D', 'E'))
layer(inp)
# <tf.Tensor: shape=(5, 1), dtype=int64, numpy=
#   array([[0],
#          [0],
#          [2],
#          [1],
#          [0]])>

See Also

Other categorical features preprocessing layers: layer_category_encoding(), layer_integer_lookup(), layer_string_lookup()

Other preprocessing layers: layer_category_encoding(), layer_center_crop(), layer_discretization(), layer_integer_lookup(), layer_normalization(), layer_random_contrast(), layer_random_crop(), layer_random_flip(), layer_random_height(), layer_random_rotation(), layer_random_translation(), layer_random_width(), layer_random_zoom(), layer_rescaling(), layer_resizing(), layer_string_lookup(), layer_text_vectorization()