#title Decision Tree
[[TableOfContents]]


https://rolkra.github.io/lets-grow-trees/
https://cambiotraining.github.io/intro-machine-learning/decision-trees.html


{{{
library(dplyr)
library(explore)
library(palmerpenguins)
library(visNetwork)
library(caret)

mydata %>% 
  explain_tree(target = val, out = "model") %>% 
  visTree()


library(rpart)
library(visNetwork)
fit <- rpart(y ~ x1 + x2 + x3, data = mydata, control = rpart.control(maxdepth=15, cp = 0.01))
visTree(fit, height = "600px", width = "1024px")

tree_plot <- visTree(fit, data = mydata, nodesPopSize = TRUE, minNodeSize = 10, maxNodeSize = 30, height = "800px", width = "2048px")
visSave(tree_plot, file = "C:\\R\\Plot\\tree.html")
}}}


==== 예제 ====
{{{
library(rpart)
library("rpart.utils")
library("rpart.plot")

fit<-rpart(Reliability~.,data=car.test.frame)
rpart.subrules.table(fit)

plotcp(fit)
rpart.plot(fit, type=4)

}}}
==== 예제 ====
{{{
library(rpart)
model <- rpart(factor(is_out)~., data=training, method="class")

plot(model, uniform=TRUE)
text(model, use.n=T)

library(rattle)
fancyRpartPlot(model)
}}}

==== 예제 ====
{{{
#install.packages("tree")
library(tree)
ir.tr <- tree(Species ~., iris)
ir.tr
ir.tr1 <- snip.tree(ir.tr, nodes = c(12, 7))
summary(ir.tr1)
par(pty = "s")
plot(iris[, 3],iris[, 4], type="n",
     xlab="petal length", ylab="petal width")
text(iris[, 3], iris[, 4], c("s", "c", "v")[iris[, 5]])
partition.tree(ir.tr1, add = TRUE, cex = 1.5)

# 1D example
ir.tr <- tree(Petal.Width ~ Petal.Length, iris)
plot(iris[,3], iris[,4], type="n", xlab="Length", ylab="Width")
partition.tree(ir.tr, add = TRUE, cex = 1.5)
}}}
partition.tree()를 사용하면 아래와 같은 그림을 볼 수 있다. 
attachment:DecisionTree/partition_tree.png

==== Boosting Tree ====
{{{
library(xgboost)
}}}
--참고: http://freesearch.pe.kr/archives/4405
==== 참고자료 ====
 * http://www.di.fc.ul.pt/~jpn/r/tree/tree.html --> Classification & Regression Trees, 좋네요.
 * attachment:DecisionTree/DTreesO.pdf ([http://onepager.togaware.com/DTreesO.pdf 원본])--> R 예제가 잘 되어 있다.