Man page - mlpack_preprocess_scale(1)

Packages contains this manual

Package:  mlpack-bin
apt-get install mlpack-bin

Manuals in package:
• mlpack_fastmks(1)
• mlpack_mean_shift(1)
• mlpack_hmm_generate(1)
• mlpack_local_coordinate_coding(1)
• mlpack_sparse_coding(1)
• mlpack_preprocess_scale(1)
• mlpack_kmeans(1)
• mlpack_linear_svm(1)
• mlpack_preprocess_split(1)
• mlpack_softmax_regression(1)
• mlpack_hmm_train(1)
• mlpack_nca(1)
• mlpack_range_search(1)
• mlpack_radical(1)
• mlpack_gmm_generate(1)
• mlpack_cf(1)
• mlpack_random_forest(1)
• mlpack_lmnn(1)
• mlpack_gmm_probability(1)
• mlpack_emst(1)
• mlpack_dbscan(1)
• mlpack_nbc(1)
• mlpack_preprocess_one_hot_encoding(1)
• mlpack_lsh(1)
• mlpack_knn(1)
• mlpack_kde(1)
• mlpack_hoeffding_tree(1)
• mlpack_adaboost(1)
• mlpack_hmm_loglik(1)
• mlpack_nmf(1)
• mlpack_pca(1)
• mlpack_bayesian_linear_regression(1)
• mlpack_hmm_viterbi(1)
• mlpack_preprocess_describe(1)
• mlpack_decision_tree(1)
• mlpack_krann(1)
• mlpack_det(1)
• mlpack_lars(1)
• mlpack_preprocess_binarize(1)
• mlpack_logistic_regression(1)
• mlpack_gmm_train(1)
• mlpack_perceptron(1)
• mlpack_preprocess_imputer(1)
• mlpack_kernel_pca(1)
• mlpack_kfn(1)
• mlpack_linear_regression(1)
• mlpack_approx_kfn(1)
Documentations in package:
• mlpack-bin

Manual

mlpack_preprocess_scale

NAME
SYNOPSIS
DESCRIPTION
REQUIRED INPUT OPTIONS
OPTIONAL INPUT OPTIONS
OPTIONAL OUTPUT OPTIONS
ADDITIONAL INFORMATION

---

NAME

mlpack_preprocess_scale - scale data

SYNOPSIS

mlpack_preprocess_scale -i unknown [ -r double ] [ -m unknown ] [ -f bool ] [ -e int ] [ -b int ] [ -a string ] [ -s int ] [ -V bool ] [ -o unknown ] [ -M unknown ] [ -h -v ]

DESCRIPTION

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_file ( -i )’ and a scaling method type which you can specify using ’ --scaler_method ( -a )’ parameter; the default is standard scaler, and outputs a matrix with scaled feature.

The output scaled feature matrix may be saved with the ’ --output_file ( -o )’ output parameters.

The model to scale features can be saved using ’ --output_model_file ( -M )’ and later can be loaded back using’ --input_model_file ( -m )’.

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

$ mlpack_preprocess_scale --input_file X.csv --output_file X_scaled.csv --scaler_method standard_scaler

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

$ mlpack_preprocess_scale --input_file X.csv --output_file X_scaled.csv --scaler_method pca_whitening --epsilon 0.01

You can also retransform the scaled dataset back using’ --inverse_scaling ( -f )’. An example to rescale : ’X_scaled.csv’ into ’X.csv’using the saved model ’ --input_model_file ( -m )’ is:

$ mlpack_preprocess_scale --input_file X_scaled.csv --output_file X.csv --inverse_scaling --input_model_file saved.bin

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

$ mlpack_preprocess_scale --input_file X.csv --output_file X_scaled.csv --scaler_method min_max_scaler --min_value 1 --max_value 3

REQUIRED INPUT OPTIONS

--input_file (-i) [ unknown ]

Matrix containing data.

OPTIONAL INPUT OPTIONS

--epsilon (-r) [ double ]

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

--help (-h) [ bool ]

Default help info.

--info [ string ]

Print help on a specific option. Default value ’’.

--input_model_file (-m) [ unknown ]

Input Scaling model.

--inverse_scaling (-f) [ bool ]

Inverse Scaling to get original dataset

--max_value (-e) [ int ]

Ending value of range for min_max_scaler. Default value 1.

--min_value (-b) [ int ]

Starting value of range for min_max_scaler. Default value 0.

--scaler_method (-a) [ string ]

method to use for scaling, the default is standard_scaler. Default value ’standard_scaler’.

--seed (-s) [ int ]

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

--verbose (-v) [ bool ]

Display informational messages and the full list of parameters and timers at the end of execution.

--version (-V) [ bool ]

Display the version of mlpack.

OPTIONAL OUTPUT OPTIONS

--output_file ( -o ) [ unknown ] Matrix to save scaled data to.
--output_model_file (-M) [ unknown ]

Output scaling model.

ADDITIONAL INFORMATION

For further information, including relevant papers, citations, and theory, consult the documentation found at http://www.mlpack.org or included with your distribution of mlpack.

---