a <- runif(100, 1, 100)
b <- runif(100, 1, 100)
c <- 1:100 + rnorm(100, mean = 0, sd = 5)
y <- 1:100 + rnorm(100, mean = 0, sd = 5)
par(mfrow = c(2,2))
plot(y ~ a); plot(y ~ b); plot(y ~ c)
Data <- data.frame(matrix(c(y, a, b, c), ncol = 4))
names(Data) <- c("y", "a", "b", "c")
library(gbm)
gbm.gaus <- gbm(y ~ a + b + c, data = Data, distribution = "gaussian")
par(mfrow = c(2,2))
plot(gbm.gaus, i.var = 1)
plot(gbm.gaus, i.var = 2)
plot(gbm.gaus, i.var = 3)

a <- runif(100, 1, 100)
b <- runif(100, 1, 100)
c <- 1:100 + rnorm(100, mean = 0, sd = 5)
y <- 1:100 + rnorm(100, mean = 0, sd = 5)
par(mfrow = c(2,2))
plot(y ~ a); plot(y ~ b); plot(y ~ c)
Data <- data.frame(matrix(c(y, a, b, c), ncol = 4))
names(Data) <- c("y", "a", "b", "c")

library(gbm)
gbm.gaus <- gbm(y ~ a + b + c, data = Data, distribution = "gaussian")

library(randomForest)
rf.model <- randomForest(y ~ a + b + c, data = Data)

x11(height = 8, width = 5)
par(mfrow = c(3,2))
par(oma = c(1,1,4,1))
plot(gbm.gaus, i.var = 1)
partialPlot(rf.model, Data[,2:4], x.var = "a")
plot(gbm.gaus, i.var = 2)
partialPlot(rf.model, Data[,2:4], x.var = "b")
plot(gbm.gaus, i.var = 3)
partialPlot(rf.model, Data[,2:4], x.var = "c")
title(main = "Boosted regression tree", outer = TRUE, adj = 0.15)
title(main = "Random forest", outer = TRUE, adj = 0.85)

#more observations are created...
a <- runif(5000, 1, 100)
b <- runif(5000, 1, 100)
c <- (1:5000)/50 + rnorm(100, mean = 0, sd = 0.1)
y <- (1:5000)/50 + rnorm(100, mean = 0, sd = 0.1)
par(mfrow = c(1,3))
plot(y ~ a); plot(y ~ b); plot(y ~ c)
Data <- data.frame(matrix(c(y, a, b, c), ncol = 4))
names(Data) <- c("y", "a", "b", "c")
library(randomForest)
#smaller nodesize "not as important" when there number of observartion is increased
#more tress can smooth flattening so boundery regions have best possible signal to             noise, data specific how many needed

plot.partial = function() {
partialPlot(rf.model, Data[,2:4], x.var = "a",xlim=c(1,100),ylim=c(1,100))
partialPlot(rf.model, Data[,2:4], x.var = "b",xlim=c(1,100),ylim=c(1,100))
partialPlot(rf.model, Data[,2:4], x.var = "c",xlim=c(1,100),ylim=c(1,100))
}

#worst case! : with 100 samples from Data and nodesize=30
rf.model <- randomForest(y ~ a + b + c, data = Data[sample(5000,100),],nodesize=30)
plot.partial()

#reasonble settings for least partial flattening by few observations: 100 samples and nodesize=3 and ntrees=2000
#more tress can smooth flattening so boundery regions have best possiblefidelity
rf.model <- randomForest(y ~ a + b + c, data = Data[sample(5000,100),],nodesize=5,ntress=2000)
plot.partial()

#more observations is great!
rf.model <- randomForest(y ~ a + b + c,
 data = Data[sample(5000,5000),],
 nodesize=5,ntress=2000)
plot.partial()

gbm.gaus <- gbm(y~., data = Data, dist = "gaussian")
library(plotmo)   # for the plotres function
plotres(gbm.gaus) # plot the error per ntrees and the residuals

gbm.gaus1 <- gbm(y~., data = Data, dist = "gaussian",
                 n.trees=5000, interact=3)
plotres(gbm.gaus1)

library(plotmo)
plotmo(gbm.gaus1, pmethod="partdep", all1=TRUE, all2=TRUE)
plotmo(rf.model,  pmethod="partdep", all1=TRUE, all2=TRUE)