Chapter 7 Computing

Today, I finished reading the first four parts of Chapter 7 and completed the computing part of it.

Computing:
library(caret)
library(earth)
library(kernlab)
library(nnet)
#R has a number of packages and functions for creating neural networks such as nnet, neural and RSNNS.
#1. neural networks
nnetfit=nnet(predictors, outcome, size=5, decay=0.01, linout = TRUE, trace = FALSE,
             maxit = 500, MaxNWts = 5*(ncol(predictors)+1)+5+1)
#trace=F: reduce the amount of printed output
#maxit: number of iterations to find parameter estimates
#MaxNWts: number of parameters
#this creates a single model with 5 hidden units assuming that the data in predictors have been
#standardized to be on the same scale
nnetavg=avNNet(predictors, outcome, size=5, decay=0.01, repeats = 5, linout = TRUE,
               trace = FALSE, maxit=500, MaxNWts = 5*(ncol(predictors)+1)+5+1)
predict(nnetfit, newdata)
predict(nnetavg, newdata)
toohigh=findCorrelation(cor(solTrainXtrans), cutoff = 0.75)
trainxnnet=solTrainXtrans[,-toohigh]
testxnnet=solTestXtrans[,-toohigh]
#define the candidate models to test
nnetgrid=expand.grid(.decay=c(0, 0.01, 0.1), .size=c(1:10), .bag=FALSE)
set.seed(100)
nnettune=train(solTrainXtrans, solTrainY, method="avNNet", tuneGrid = nnetgrid, trControl = ctr1,
               preProcess = c("center", "scale"), linout = TRUE, trace = FALSE,
               MaxNWts = 10*(ncol(predictors)+1)+10+1, maxit=500)
#2. multivariate adaptive regression splines
marsfit=earth(solTrainXtrans, solTrainY)
marsfit
summary(marsfit)
marsgrid=expand.grid(.degree=1:2, .nprune=2:38)
set.seed(100)
marstuned=train(solTrainXtrans, solTrainY, method="earth", tuneGrid = marsgrid,
                trControl = trainControl(method = "cv"))
marstuned
marspredict=predict(marstuned, solTestXtrans)
head(marspredict)
#estimate the importance of each predictor in the MARS model
varImp(marstuned)
#3. Support Vector Machines
#in kernlab package, the ksvm function is available for regression models and a large number of kernel functions
#the radial basis function is the default kernel function
library(kernlab)
#if appropriate values o the cost and kernel parameters are known, the model can be fit as:
svmfit=ksvm(x=solTrainXtrans, y=solTrainY, kernel="polydot", kpar="automatic", C=1, epsilon=0.1)
#if the values are unknown, they can be estimated through resampling.
#in train, "svmRadial", "svmLinear" or "svmPoly" fit different kernels
svmrtuned=train(solTrainXtrans, solTrainY, method = "svmRadial", preProcess = c("center", "scale"),
                tuneLength = 14, trControl = trainControl(method = "cv"))
svmrtuned
svmrtuned$finalModel
#4. k-nearest neighbors
knndescr=solTrainXtrans[, -nearZeroVar(solTrainXtrans)]
set.seed(100)
knntune=train(knndescr, solTrainY, method = "knn", preProcess = c("center", "scale"),
              tuneGrid = data.frame(.k=1:20), trControl = trainControl(method = "cv"))
knntune

Tomorrow, I will do exercises on Chapter 7.