In ModelOriented/forester: Quick and Simple Tools for Training and Testing of Tree-Based Models

<<<<<<< HEAD

title: "Ablation study of forester: Datasets Information" author: "Hubert Ruczyński" date: "r Sys.Date()" output: html_document: toc: yes toc_float: yes toc_collapsed: yes theme: lumen toc_depth: 3 number_sections: yes latex_engine: xelatex

---

```{css, echo=FALSE} body .main-container { max-width: 1820px !important; width: 1820px !important; } body { max-width: 1820px !important; width: 1820px !important; font-family: Helvetica !important; font-size: 16pt !important; } h1,h2,h3,h4,h5,h6{ font-size: 24pt !important; }

# Downloads

The necessary downloads required for the forester package to work properly, if downloaded, the user can skip this part.

```r
install.packages("devtools")
devtools::install_github("ModelOriented/forester")
devtools::install_github('catboost/catboost', subdir = 'catboost/R-package')
devtools::install_github('ricardo-bion/ggradar', dependencies = TRUE)
install.packages('tinytex')
tinytex::install_tinytex()

Imports

Importing the necessary libraries.

library(forester)
library(farff)

Datasets analysis

In this section we will describe the datasets with the usage of data_check() function from the forester package.

Binary classification

binary_CC18 <- readRDS("binary_CC18.RData")
binary_CC18 <- binary_CC18[c(1, 2, 3, 4, 5, 19, 25, 26)]

Data Check

kr-vs-kp

s <- check_data(binary_CC18$`kr-vs-kp`, 'class')

breast-w

s <- check_data(binary_CC18$`breast-w`, 'Class')

credit-approval

s <- check_data(binary_CC18$`credit-approval`, 'class')

credit-g

s <- check_data(binary_CC18$`credit-g`, 'class')

diabetes

s <- check_data(binary_CC18$diabetes, 'class')

phoneme

s <- check_data(binary_CC18$phoneme, 'Class')

banknote-authentication

s <- check_data(binary_CC18$`banknote-authentication`, 'Class')

blood-transfusion-service-center

s <- check_data(binary_CC18$`blood-transfusion-service-center`, 'Class')

Regression

Loading widely used datasets from OpenML. If you are reproducing the paper step by step, skip this one, as we will load a specially prepared version in another cell.

wind              <- readARFF('regression_datasets/wind.arff') # Not regression task
communities_crime <- readARFF('regression_datasets/phpeZQVCe.arff') # ViolentCrimesPerPop
bank32nh          <- readARFF('regression_datasets/phpYYZ4Qc.arff') # Target: rej
wine_quality      <- readARFF('regression_datasets/wine_quality.arff') # Target: quality
Mercedes_Benz     <- readARFF('regression_datasets/dataset.arff') # Target: y (2nd col)
Mercedes_Benz_y   <- Mercedes_Benz$y
Mercedes_Benz     <- Mercedes_Benz[, -2]
Mercedes_Benz$y   <- Mercedes_Benz_y # the last one
kin8nm            <- readARFF('regression_datasets/dataset_2175_kin8nm.arff') # Target: y
pol               <- readARFF('regression_datasets/dataset_2187_pol.arff') # Target: foo (really streched)
planes2d          <- readARFF('regression_datasets/dataset_2201_2dplanes.arff') # Target: y
elevators         <- readARFF('regression_datasets/dataset_2202_elevators.arff') # Target: Goal
stock             <- readARFF('regression_datasets/dataset_2209_stock.arff') # Not regression task

regression_bench <- list()

regression_bench[[1]]  <- as.data.frame(wind)
regression_bench[[2]]  <- as.data.frame(communities_crime)
regression_bench[[3]]  <- as.data.frame(bank32nh)
regression_bench[[4]]  <- as.data.frame(wine_quality)
regression_bench[[5]]  <- as.data.frame(Mercedes_Benz)
regression_bench[[6]]  <- as.data.frame(kin8nm)
regression_bench[[7]]  <- as.data.frame(pol)
regression_bench[[8]]  <- as.data.frame(planes2d)
regression_bench[[9]]  <- as.data.frame(elevators)
regression_bench[[10]] <- as.data.frame(stock)

names(regression_bench) <- c('wind', 'us_crime', 'bank32nh', 'wine_quality', 
                             'Mercedes_Benz_Greener_Manufacturing', 'kin8nm', 'pol', 
                             '2dplanes', 'elevators', 'stock')

regression_bench <- regression_bench[3:9]

saveRDS(regression_bench, 'regression_bench.RData')

Data Check

regression_bench <- readRDS("regression_bench.RData")

bank32nh

s <- check_data(regression_bench$bank32nh, 'rej')

wine_quality

s <- check_data(regression_bench$wine_quality, 'quality')

Mercedes_Benz_Greener_Manufacturing

s <- check_data(regression_bench$Mercedes_Benz_Greener_Manufacturing, 'y')

kin8nm

s <- check_data(regression_bench$kin8nm, 'y')

pol

s <- check_data(regression_bench$pol, 'foo')

2dplanes

s <- check_data(regression_bench$'2dplanes', 'y')

elevators

s <- check_data(regression_bench$elevators, 'Goal')

Summary

The results of this summary were created manually mostly based on this script. As seen below they are saved in the file named data_issues_summary.csv .

data_summary <- read.csv('data_issues_summary.csv', sep = ';')
rmarkdown::paged_table(data_summary)

=======

title: "Ablation study of forester: Datasets Information" author: "Hubert Ruczyński" date: "r Sys.Date()" output: html_document: toc: yes toc_float: yes toc_collapsed: yes theme: lumen toc_depth: 3 number_sections: yes latex_engine: xelatex

---

```{css, echo=FALSE} body .main-container { max-width: 1820px !important; width: 1820px !important; } body { max-width: 1820px !important; width: 1820px !important; font-family: Helvetica !important; font-size: 16pt !important; } h1,h2,h3,h4,h5,h6{ font-size: 24pt !important; }

# Downloads

The necessary downloads required for the forester package to work properly, if downloaded, the user can skip this part.

```r
install.packages("devtools")
devtools::install_github("ModelOriented/forester")
devtools::install_github('catboost/catboost', subdir = 'catboost/R-package')
devtools::install_github('ricardo-bion/ggradar', dependencies = TRUE)
install.packages('tinytex')
tinytex::install_tinytex()

Imports

Importing the necessary libraries.

library(forester)
library(farff)

Datasets analysis

In this section we will describe the datasets with the usage of data_check() function from the forester package.

Binary classification

binary_CC18 <- readRDS("binary_CC18.RData")
binary_CC18 <- binary_CC18[c(1, 2, 3, 4, 5, 19, 25, 26)]

Data Check

kr-vs-kp

s <- check_data(binary_CC18$`kr-vs-kp`, 'class')

breast-w

s <- check_data(binary_CC18$`breast-w`, 'Class')

credit-approval

s <- check_data(binary_CC18$`credit-approval`, 'class')

credit-g

s <- check_data(binary_CC18$`credit-g`, 'class')

diabetes

s <- check_data(binary_CC18$diabetes, 'class')

phoneme

s <- check_data(binary_CC18$phoneme, 'Class')

banknote-authentication

s <- check_data(binary_CC18$`banknote-authentication`, 'Class')

blood-transfusion-service-center

s <- check_data(binary_CC18$`blood-transfusion-service-center`, 'Class')

Regression

Loading widely used datasets from OpenML. If you are reproducing the paper step by step, skip this one, as we will load a specially prepared version in another cell.

wind              <- readARFF('regression_datasets/wind.arff') # Not regression task
communities_crime <- readARFF('regression_datasets/phpeZQVCe.arff') # ViolentCrimesPerPop
bank32nh          <- readARFF('regression_datasets/phpYYZ4Qc.arff') # Target: rej
wine_quality      <- readARFF('regression_datasets/wine_quality.arff') # Target: quality
Mercedes_Benz     <- readARFF('regression_datasets/dataset.arff') # Target: y (2nd col)
Mercedes_Benz_y   <- Mercedes_Benz$y
Mercedes_Benz     <- Mercedes_Benz[, -2]
Mercedes_Benz$y   <- Mercedes_Benz_y # the last one
kin8nm            <- readARFF('regression_datasets/dataset_2175_kin8nm.arff') # Target: y
pol               <- readARFF('regression_datasets/dataset_2187_pol.arff') # Target: foo (really streched)
planes2d          <- readARFF('regression_datasets/dataset_2201_2dplanes.arff') # Target: y
elevators         <- readARFF('regression_datasets/dataset_2202_elevators.arff') # Target: Goal
stock             <- readARFF('regression_datasets/dataset_2209_stock.arff') # Not regression task

regression_bench <- list()

regression_bench[[1]]  <- as.data.frame(wind)
regression_bench[[2]]  <- as.data.frame(communities_crime)
regression_bench[[3]]  <- as.data.frame(bank32nh)
regression_bench[[4]]  <- as.data.frame(wine_quality)
regression_bench[[5]]  <- as.data.frame(Mercedes_Benz)
regression_bench[[6]]  <- as.data.frame(kin8nm)
regression_bench[[7]]  <- as.data.frame(pol)
regression_bench[[8]]  <- as.data.frame(planes2d)
regression_bench[[9]]  <- as.data.frame(elevators)
regression_bench[[10]] <- as.data.frame(stock)

names(regression_bench) <- c('wind', 'us_crime', 'bank32nh', 'wine_quality', 
                             'Mercedes_Benz_Greener_Manufacturing', 'kin8nm', 'pol', 
                             '2dplanes', 'elevators', 'stock')

regression_bench <- regression_bench[3:9]

saveRDS(regression_bench, 'regression_bench.RData')

Data Check

regression_bench <- readRDS("regression_bench.RData")

bank32nh

s <- check_data(regression_bench$bank32nh, 'rej')

wine_quality

s <- check_data(regression_bench$wine_quality, 'quality')

Mercedes_Benz_Greener_Manufacturing

s <- check_data(regression_bench$Mercedes_Benz_Greener_Manufacturing, 'y')

kin8nm

s <- check_data(regression_bench$kin8nm, 'y')

pol

s <- check_data(regression_bench$pol, 'foo')

2dplanes

s <- check_data(regression_bench$'2dplanes', 'y')

elevators

s <- check_data(regression_bench$elevators, 'Goal')

Summary

The results of this summary were created manually mostly based on this script. As seen below they are saved in the file named data_issues_summary.csv .

data_summary <- read.csv('data_issues_summary.csv', sep = ';')
rmarkdown::paged_table(data_summary)

b6c9e7735ce229d9a94dce9db6fcedec62936c73

ModelOriented/forester documentation built on June 6, 2024, 7:29 a.m.