Accuracy of different algorithms on item and user rating Dataset
library(caret) library(data.table) ratings<-fread("ratings.csv") ratings[,N:=.N,.(user_id,book_id)] ratings<-ratings[N==1] ratings[,N:=.N,.(user_id)] rated<-ratings[1:15000,] rated<-rated[,1:3] full<-setNames(with(rated,expand.grid(sort(unique(book_id)),sort(unique(user_id)))), c("book_id","user_id")) rated<-merge(full,rated,all=TRUE) rated[is.na(rated)]<-0 rated$rating<-as.factor(rated$rating) seprate<-createDataPartition(rated$rating,p=0.8,list=FALSE) trainset<-rated[separate,] testset<-rated[-separate,] control<-trainControl(method="cv",number=10) fit.knn<-train(rating~.,trainset,method="knn",metric="Accuracy",trControl=control) print(fit.knn) prediction<-predict(fit.knn,testset) confusionMatrix(factor(prediction,levels=0:5),factor(testset$rating,levels=0:5)) change "method "and get "result" place ratings file in pro...