kaggle bike sharing program R code tranlated from python code ranked 9th

Use Caret to do the feature selection for rf.

train_row <- read.csv('E:/kuaipan/Kaggle Project/Bike Sharing Demand/train.csv')
test_row <- read.csv('e:/kuaipan/Kaggle Project/Bike Sharing Demand/test.csv')

train_row$type = 'train'
test_row$type = 'test'

colnames(train_row)

test_row$casual=NA
test_row$registered=NA
test_row$count=NA

row_df = rbind(train_row, test_row)
row_df_backup = row_df

for(col in c('casual','registered','count'))
{
  newcol = paste(col,'_log',sep="")
  row_df[newcol] = log(row_df[col] + 1)
}

if(!require('lubridate'))
{
  install.packages(lubridate)
}

row_df$dt = ymd_hms(row_df$datetime)
row_df$day = day(row_df$dt)
row_df$month = month(row_df$dt)
row_df$year = year(row_df$dt)
row_df$hour = hour(row_df$dt)
row_df$weekday =wday(row_df$dt)
row_df$week = week(row_df$dt)

for(s in c(1,2,3,4))
{
  row_df[which(row_df$season==s & row_df$type=='train'),'season_count']=sum(row_df[which(row_df$season==s & row_df$type=='train'),'count'])
}

#head(row_df)

SetWorkingDay = function(year,month,day,value){
  row_df[which(row_df$year %in% year & row_df$month %in% month & row_df$day %in% day),'workingday'] = value
  if(value == 1){
    b = 0
  }else{
    b = 1
  }
  row_df[which(row_df$year %in% year & row_df$month %in% month & row_df$day %in% day),'holiday'] = b
    
}

SetWorkingDay(2011,4,15,1)
SetWorkingDay(2012,4,16,1)
SetWorkingDay(2011,11,25,0)
SetWorkingDay(2012,11,23,0)

row_df[which(row_df$year == 2011 &row_df$month ==11 & row_df$day ==25),'holiday']=1
row_df[which(row_df$year == 2012 &row_df$month ==11 & row_df$day ==23),'holiday']=1
row_df[which(row_df$year == 2012 &row_df$month ==5 & row_df$day ==21),'holiday']=1
row_df[which(row_df$year == 2012 &row_df$month ==6 & row_df$day ==1),'holiday']=1
row_df[which(row_df$year == 2012 &row_df$month ==10 & row_df$day ==30),'holiday']=1
row_df[which(row_df$month ==12 & row_df$day %in% c(24,26,31)),'holiday']=1
row_df[which(row_df$month ==12 & row_df$day %in% c(24,31)),'workingday']=1

row_df[which(row_df$workingday==1 & row_df$hour %in% c(8,17,18,12)),'peak']=1
row_df[which(row_df$workingday==0 & 10<=row_df$hour<=19),'peak']=1
row_df[which(is.na(row_df$peak)),'peak']=0

row_df[which(row_df$temp>27 & row_df$windspeed <30),'ideal']=1
row_df[which(is.na(row_df$ideal)),'ideal']=0

row_df[which(row_df$humidity>=60&row_df$workingday==1),'sticky']=1
row_df[which(is.na(row_df$sticky)),'sticky']=0

row_df.train = row_df[which(row_df$type == 'train'),]
row_df.test  = row_df[which(row_df$type == 'test'),]

library(Metrics)
get_rmsle =function(pred, actual){
  rs = rmsle(log(pred+1),log(actual+1))
  sqrt((exp(rs)))
}

library(caret)

#use ten-fold cross validation 
control=rfeControl(functions=rfFuncs, method="cv", number=10)
row_df.features = row_df.train[,-c(10,11,12,14,15,16,1,17,13)]
#Feature dataset and result dataset must be same dataset
#By default the rfe will add a subset contain all the features.
result=rfe(row_df.train[,-c(10,11,12,14,15,16,1,17,13)],row_df.train[,14],size=c(16:17),rfeControl = control) 
plot(result, type=c('p','l'))

#the final rf model is result$fit