Ensemble.Rmd

---
title: "Ensemble"
author: "Rodolfo Viana"
date: "06-09-2015"
output: html_document
---



```{r}
train <- read.csv("~/Projetos/Hackathon3.x/data/new_train.csv")
test <- read.csv("~/Projetos/Hackathon3.x/new_test.csv")

# Step 2 : Specify basic metrics like number of bags/iterations, number of learners/models

num_models <- 24
itertions <- 1000

# Step 3 : Load the library needed for the performance metric (optional)

library(Metrics)

# Step 4 : Calculating individual performance of models for establishing benchmarks

rmsle_mat <- matrix(0,num_models,2)
rmsle_mat[,2] <- 1:num_models
for(i in 1:num_models){
rmsle_mat[i,1] <- rmsle(train[,i],train[,num_models+1])
print(rmsle(train[,i],train[,num_models+1]))
}
best_model_no <- rmsle_mat[rmsle_mat[,1] == min(rmsle_mat[,1]),2]
rmsle(train[,best_model_no],train[,num_models+1])

# Step 5 : Using all the metrics specified apply forward selection with replacement in 1000 bags

x <- matrix(0,1000,itertions)
prediction_test <- matrix(0,nrow(test),1)
prediction_train <- matrix(0,nrow(train),1)
for (j in 1:itertions){
rmsle_in <- 1
rmsle_new <- matrix(0,num_models,2)
rmsle_new[,2] <- 1:num_models
print(j)
t = 1
set.seed(j*121)
train1 <- train[sample(1:nrow(train), 10000,replace=FALSE),]
for(i in 1:num_models){
rmsle_mat[i,1] <- rmsle(train1[,i],train1[,num_models+1])
}
best_model_no <- rmsle_mat[rmsle_mat[,1] == min(rmsle_mat[,1]),2]
prediction <- train1[,best_model_no]
prediction_1 <- test[,best_model_no]
prediction_2 <- train[,best_model_no]
x[t,j] <- best_model_no
while(-1 < 0) {
t <- t + 1
prediction1 <- prediction
for (i in 1:num_models){
prediction1 <- ((t*prediction) + train1[,i])/(t+1)
rmsle_new[i,1] <- rmsle(prediction1,train1[,num_models+1])
}
rmsle_min <- min(rmsle_new[,1])
model_no <- rmsle_new[rmsle_new[,1] == min(rmsle_new[,1]),2]
if(rmsle_in < rmsle_min) {break} else {
rmsle_in <- rmsle_min
prediction <- (((t-1)*prediction) + train1[,model_no])/t
prediction_1 <- (((t-1)*prediction_1) + test[,model_no])/t
prediction_2 <- (((t-1)*prediction_2) + train[,model_no])/t
x[t,j] <- model_no
print(rmsle_in)
}
}
prediction_test <- cbind(prediction_test,prediction_1)
prediction_train <- cbind(prediction_train,prediction_2)
}

```

You can also embed plots, for example:

```{r, echo=FALSE}
plot(cars)
```

Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.