Created
January 12, 2014 15:23
-
-
Save mwacc/8385950 to your computer and use it in GitHub Desktop.
sample of using random forest to predict future :)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# read dataset from local file | |
data <- read.csv("/Users/kostya/Downloads/abalone.data.csv", header=F) | |
# set names for dataframe columns | |
colnames(data) <- c('Sex', 'Length', 'Diameter', 'Height', 'WholeWeight', 'ShuckedWeight', | |
'VisceraWeight', 'ShellWeight', 'Rings') | |
# split dataset into train and test seta | |
train.size <- floor(0.9 * nrow(data)) | |
train <- data[1:train.size, ] | |
test <- data[(train.size+1):nrow(data), ] | |
# get the names of the columns | |
props <- names(data[,-length(names(data))]) | |
props <- props[! props %in% 'Rings'] | |
n <- length(props) | |
# construct all possible combinations | |
id <- unlist( | |
lapply(1:n, | |
function(i) combn(1:n,i,simplify=F) | |
) | |
,recursive=F) | |
# and paste them to formula | |
Formulas <- sapply(id, function(i) | |
paste("Rings~",paste(props[i],collapse="+")) | |
) | |
# evaluate all formulas | |
rf <- lapply(Formulas, function(i) | |
randomForest(as.formula(i), data=train, ntree=70)) | |
# pick up the formula based on the best prediction | |
bestRF <- rf[[1]] | |
bestRsq <- bestRF$rsq[ length(bestRF$rsq) ] | |
for(i in 2:length(rf)) { | |
if( rf[[i]]$rsq[ length(rf[[i]]$rsq) ] > bestRsq ) { | |
bestRF <- rf[[i]] | |
bestRsq <- bestRF$rsq[ length(bestRF$rsq) ] | |
} | |
} | |
# predict | |
head( predict(bestRF, newdata=test) ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment