Now I want to seperate the dataset into two parts: one is with high level ozone which the targetsTrain is “h”, another one is with low level of ozone , the targetsTrain is “l”. Then build two regression models based on these two data sets.

## 
## > library(doParallel)

## Loading required package: foreach
## Loading required package: iterators
## Loading required package: parallel

## 
## > library(survival)

## Loading required package: splines

## 
## > library(splines)
## 
## > library(lattice)
## 
## > library(gbm)

## Loaded gbm 2.1

## 
## > library(methods)
## 
## > library(kernlab)
## 
## > library(MASS)
## 
## > library(caret)

## Loading required package: ggplot2
## 
## Attaching package: 'caret'
## 
## The following object is masked from 'package:survival':
## 
##     cluster

## 
## > library(ggplot2)
## 
## > library(corrplot)
## 
## > library(pbapply)
## 
## > library(testthat)
## 
## > library(devtools)
## 
## > library(caretEnsemble)

## Loading required package: caTools

## 
## > library(doMC)
## 
## > library(foreach)
## 
## > registerDoMC(cores = 5)
## 
## > denormalized <- function(y, output) {
## +     ((y - 0.1) * (max(output) - min(output))/0.8) + min(output)
## + }
## 
## > modelErrors <- function(predicted, actual) {
## +     sal <- vector(mode = "numeric", length = 3)
## +     names(sal) <- c("MAE", "RMSE", "RELE")
## +     me .... [TRUNCATED] 
## 
## > regression_Training <- function(inputsTrain, targetsTrain, 
## +     dataset) {
## +     resultList = list()
## +     cvcontrol <- trainControl(method = "cv" .... [TRUNCATED]

## Loading required package: nnet
## Loading required package: rpart
## Loading required package: randomForest
## randomForest 4.6-10
## Type rfNews() to see new features/changes/bug fixes.
## Loading required package: plyr
## Loading required package: ada
## Loading required package: ipred

##                 linear_pred
## targetsTestClass   h   l
##                h 464  93
##                l 135 235

Firstly we used the regression training model predict all the test data set.

## Predictions being made only for cases with complete data

##        lmFit nnetFit   rfFit rpartFit  svmFit bagTreeFit linearFit
## MAE  0.07380 0.07123 0.07290   0.0829 0.06994    0.07545   0.07011
## RMSE 0.09519 0.09257 0.09543   0.1064 0.09204    0.09833   0.09182
## RELE 0.24320 0.23055 0.24029   0.2810 0.21980    0.24961   0.22727
##      greedyFit gbm_ntrees_ 1 gbm_ntrees_ 2 gbm_ntrees_ 3 gbm_ntrees_ 4
## MAE    0.06996       0.08984       0.08506       0.08193       0.07991
## RMSE   0.09176       0.11253       0.10708       0.10371       0.10175
## RELE   0.22543       0.30752       0.29012       0.27804       0.27041
##      gbm_ntrees_ 5
## MAE        0.07811
## RMSE       0.10012
## RELE       0.26338

use high level regresion model to predict the test dataset which was predicted as high level

## Predictions being made only for cases with complete data

##        lmFit nnetFit  rfFit rpartFit  svmFit bagTreeFit linearFit
## MAE  0.08758 0.08803 0.0882  0.09169 0.08289    0.08682   0.08688
## RMSE 0.10955 0.11017 0.1105  0.11407 0.10483    0.10875   0.10870
## RELE 0.27455 0.27657 0.2780  0.28532 0.25362    0.27313   0.27341
##      greedyFit gbm_ntrees_ 1 gbm_ntrees_ 2 gbm_ntrees_ 3 gbm_ntrees_ 4
## MAE    0.08668       0.09468       0.09241       0.09136       0.09026
## RMSE   0.10846       0.11608       0.11361       0.11268       0.11163
## RELE   0.27200       0.29376       0.28717       0.28522       0.28218
##      gbm_ntrees_ 5
## MAE        0.09031
## RMSE       0.11162
## RELE       0.28254

use LOW level regression model to predict the test dataset which was predicted as low level

## Predictions being made only for cases with complete data

##        lmFit nnetFit   rfFit rpartFit  svmFit bagTreeFit linearFit
## MAE  0.06538 0.06348 0.06423  0.06800 0.06429    0.06445   0.06382
## RMSE 0.09372 0.09152 0.09255  0.09503 0.09388    0.09298   0.09228
## RELE 0.22139 0.21337 0.21714  0.23778 0.21453    0.21933   0.21401
##      greedyFit gbm_ntrees_ 1 gbm_ntrees_ 2 gbm_ntrees_ 3 gbm_ntrees_ 4
## MAE    0.06396       0.07094       0.06953       0.06833       0.06786
## RMSE   0.09231       0.09472       0.09428       0.09365       0.09335
## RELE   0.21579       0.25741       0.24962       0.24261       0.24019
##      gbm_ntrees_ 5
## MAE        0.06747
## RMSE       0.09340
## RELE       0.23796