mlpack (version 4.6.0)

preprocess_scale: Scale Data

Description

A utility to perform feature scaling on datasets using one of sixtechniques. Both scaling and inverse scaling are supported, andscalers can be saved and then applied to other datasets.

Usage

preprocess_scale(
  input,
  epsilon = NA,
  input_model = NA,
  inverse_scaling = FALSE,
  max_value = NA,
  min_value = NA,
  scaler_method = NA,
  seed = NA,
  verbose = getOption("mlpack.verbose", FALSE)
)

Value

A list with several components:

output

Matrix to save scaled data to (numeric matrix).

output_model

Output scaling model (ScalingModel).

Arguments

input

Matrix containing data (numeric matrix).

epsilon

regularization Parameter for pcawhitening, or zcawhitening, should be between -1 to 1. Default value "1e-06" (numeric).

input_model

Input Scaling model (ScalingModel).

inverse_scaling

Inverse Scaling to get original datase. Default value "FALSE" (logical).

max_value

Ending value of range for min_max_scaler. Default value "1" (integer).

min_value

Starting value of range for min_max_scaler. Default value "0" (integer).

scaler_method

method to use for scaling, the default is standard_scaler. Default value "standard_scaler" (character).

seed

Random seed (0 for std::time(NULL)). Default value "0" (integer).

verbose

Display informational messages and the full list of parameters and timers at the end of execution. Default value "getOption("mlpack.verbose", FALSE)" (logical).

Author

mlpack developers

Details

This utility takes a dataset and performs feature scaling using one of the six scaler methods namely: 'max_abs_scaler', 'mean_normalization', 'min_max_scaler' ,'standard_scaler', 'pca_whitening' and 'zca_whitening'. The function takes a matrix as "input" and a scaling method type which you can specify using "scaler_method" parameter; the default is standard scaler, and outputs a matrix with scaled feature.

The output scaled feature matrix may be saved with the "output" output parameters.

The model to scale features can be saved using "output_model" and later can be loaded back using"input_model".

Examples

# So, a simple example where we want to scale the dataset "X" into "X_scaled"
# with  standard_scaler as scaler_method, we could run 

if (FALSE) {
output <- preprocess_scale(input=X, scaler_method="standard_scaler")
X_scaled <- output$output
}

# A simple example where we want to whiten the dataset "X" into "X_whitened"
# with  PCA as whitening_method and use 0.01 as regularization parameter, we
# could run 

if (FALSE) {
output <- preprocess_scale(input=X, scaler_method="pca_whitening",
  epsilon=0.01)
X_scaled <- output$output
}

# You can also retransform the scaled dataset back using"inverse_scaling". An
# example to rescale : "X_scaled" into "X"using the saved model "input_model"
# is:

if (FALSE) {
output <- preprocess_scale(input=X_scaled, inverse_scaling=TRUE,
  input_model=saved)
X <- output$output
}

# Another simple example where we want to scale the dataset "X" into
# "X_scaled" with  min_max_scaler as scaler method, where scaling range is 1
# to 3 instead of default 0 to 1. We could run 

if (FALSE) {
output <- preprocess_scale(input=X, scaler_method="min_max_scaler",
  min_value=1, max_value=3)
X_scaled <- output$output
}