zachmayer · May 3, 2011 14:34
diff --git a/1. Install Packages.R b/1. Install Packages.R
 install.packages(c("caret","reshape2","plyr","caTools"),dependencies=c("Depends", "Imports", "LinkingTo", "Suggests", "Enhances"))
diff --git a/2. Setup.R b/2. Setup.R
 #Directory
 setwd('~/Kaggle/Overfitting')

 #Load Required Packages
 library('caret')
 library('glmnet')
 library('ipred')
 library('e1071')
 library('caTools')
diff --git a/3. Read Data.R b/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)]
diff --git a/4. Split.R b/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= "+")))
diff --git a/5. Review.R b/5. Review.R
 head(Data)
 tail(Data)
 head(trainset)
 head(testset)
 print(FL)
	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)]
	#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= "+")))