Kaggle introduction

1. Install Packages.R

install.packages(c("caret","reshape2","plyr","caTools"),dependencies=c("Depends", "Imports", "LinkingTo", "Suggests", "Enhances"))

2. Setup.R

#Directory
setwd('~/Kaggle/Overfitting')

#Load Required Packages
library('caret')
library('glmnet')
library('ipred')
library('e1071')
library('caTools')

3. Read Data.R

Data <- read.csv("overfitting.csv", header=TRUE)

#Choose Target
Data$Target <- as.factor(ifelse(Data$Target_Practice==1,'X1','X0'))
Data$Target_Evaluate = NULL
Data$Target_Leaderboard = NULL
Data$Target_Practice = NULL

#Order
xnames <- setdiff(names(Data),c('Target','case_id','train'))
Data <- Data[,c('Target','case_id','train',xnames)]

4. Split.R

#Split to train and test
trainset = Data[Data$train == 1,]
testset = Data[Data$train == 0,]

#Remove unwanted columns
trainset$case_id = NULL
trainset$train = NULL

#Define Formula
FL <- as.formula(paste("Target ~ ", paste(xnames, collapse= "+")))

5. Review.R

head(Data)
tail(Data)
head(trainset)
head(testset)
print(FL)