preprocessing: Data preprocessing

In santiago1234/codonr: What The Package Does (one line, title case required)

Description

Preprocess the predictors matrix X (train_set) data for trainin/testing models The following preprocessing steps are implemented

1. Impute the 3' UTR length with median

2. Apply spatial sign transformation to codon composition

3. Normalize all numeric variables

4. Dummy transformation for catergorical variables: 'cell_type', 'specie', and 'datatype'

Usage

preprocessing(X_train)

Arguments

X_train

training_set predictors, the X_train output of prepare_train_and_test_sets

Value

trained Data Recipe

santiago1234/codonr documentation built on Dec. 9, 2019, 10:15 a.m.