Created
May 12, 2016 06:21
-
-
Save klauszhang/ba353bc0f5ca50c60996ff4605fb081d to your computer and use it in GitHub Desktop.
expedia hotel prediction
This file contains 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
# folked from https://www.kaggle.com/signochastic/expedia-hotel-recommendations/r-version-of-most-popular-local-hotel | |
## R version of most popular local hotels | |
library(data.table) | |
expedia_train <- fread('../input/train.csv', header=TRUE) | |
expedia_test <- fread('../input/test.csv', header=TRUE) | |
sum_and_count <- function(x){ | |
sum(x)*0.835 + length(x) *0.165 | |
} | |
dest_id_hotel_cluster_count <- expedia_train[,sum_and_count(is_booking),by=list(srch_destination_id, hotel_cluster)] | |
top_five <- function(hc,v1){ | |
hc_sorted <- hc[order(v1,decreasing=TRUE)] | |
n <- min(5,length(hc_sorted)) | |
paste(hc_sorted[1:n],collapse=" ") | |
} | |
dest_top_five <- dest_id_hotel_cluster_count[,top_five(hotel_cluster,V1),by=srch_destination_id] | |
dd <- merge(expedia_test,dest_top_five, by="srch_destination_id",all.x=TRUE)[order(id),list(id,V1)] | |
setnames(dd,c("id","hotel_cluster")) | |
write.csv(dd, file='submission_sum_and_count.csv', row.names=FALSE) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment