run_generate_data: Function for generating datasets

Description Usage Details

View source: R/main.R

Description

In general the first function that should be executed when the package is loaded. Generates the two dataset data_train_numeric_clean_imputed and data_test_numeric_clean_imputed.

Usage

1

Details

First the function generates data views for e.g. distinguishing categorical and ordinal variables. Next the data is cleaned by removing unnecessary columns and rows. After that imputation takes place by manually and automatically(mice with pmm) substituting missing values.


MarcoNiemann/kaggle_house documentation built on May 7, 2019, 2:50 p.m.