DL1_H2o.R

path = "~/mydata/deeplearning"
setwd(path)

#load libraries
library(data.table)
library(mlr)
#set variable names
setcol <- c("age",
           "workclass",
           "fnlwgt",
           "education",
           "education-num",
           "marital-status",
           "occupation",
           "relationship",
           "race",
           "sex",
           "capital-gain",
           "capital-loss",
           "hours-per-week",
           "native-country",
           "target")

#load data
train <- read.table("adultdata.txt",header = F,sep = ",",col.names = setcol,na.strings = c(" ?"),stringsAsFactors = F)
test <- read.table("adulttest.txt",header = F,sep = ",",col.names = setcol,skip = 1, na.strings = c(" ?"),stringsAsFactors = F)

setDT(train)
setDT(test)

#Data Sanity
dim(train) #32561 X 15
dim(test) #16281 X 15
str(train)
str(test)

#check missing values
table(is.na(train))
sapply(train, function(x) sum(is.na(x))/length(x))*100
table(is.na(test))
sapply(test, function(x) sum(is.na(x))/length(x))*100

#check target variable
#binary in nature check if data is imbalanced
train[,.N/nrow(train),target]
test[,.N/nrow(test),target]

#remove extra characters
test[,target := substr(target,start = 1,stop = nchar(target)-1)]

#remove leading whitespace
library(stringr)
char_col <- colnames(train)[sapply(test,is.character)]

for(i in char_col)
 set(train,j=i,value = str_trim(train[[i]],side = "left"))

#set all character variables as factor
fact_col <- colnames(train)[sapply(train,is.character)]

for(i in fact_col)
 set(train,j=i,value = factor(train[[i]]))

for(i in fact_col)
 set(test,j=i,value = factor(test[[i]]))
#impute missing values
imp1 <- impute(data = train,target = "target",classes = list(integer = imputeMedian(), factor = imputeMode()))
imp2 <- impute(data = test,target = "target",classes = list(integer = imputeMedian(), factor = imputeMode()))

train <- setDT(imp1$data)
test <- setDT(imp2$data)