This lab explores popular R recombination system. After doing
research online, I saw that the recommenderlab was a
recommended package to use for R.
library(recommenderlab)## Loading required package: Matrix## Loading required package: arules##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, write## Loading required package: proxy##
## Attaching package: 'proxy'## The following object is masked from 'package:Matrix':
##
## as.matrix## The following objects are masked from 'package:stats':
##
## as.dist, dist## The following object is masked from 'package:base':
##
## as.matrix## Registered S3 methods overwritten by 'registry':
## method from
## print.registry_field proxy
## print.registry_entry proxyThe below data frame is the survey data I collected:
df <- data.frame(Id = c(1, 2, 3, 4, 5),
Barbie = c(5, 4, 4, 3, 4),
Oppenheimer = c(3, 2, 2, 3, 4),
TopGunMaverick = c(3, 3, 3, 5, 3),
AvatarTheWayOfWater = c(2, 5, 5, 4, 4),
Wicked = c(4, 3, 4, 3, 4),
GetOut = c(5, 5, 4, 4, 5))I then turned the data frame into a matrix:
movie_matrix <- as.matrix(df[, -which(names(df) == "Id")])
row.names(movie_matrix) = c("u1", "u2", "u3", "u4", "u5")
r <- as(movie_matrix, "realRatingMatrix")
r## 5 x 6 rating matrix of class 'realRatingMatrix' with 30 ratings.getRatingMatrix(r)## 5 x 6 sparse Matrix of class "dgCMatrix"
## Barbie Oppenheimer TopGunMaverick AvatarTheWayOfWater Wicked GetOut
## u1 5 3 3 2 4 5
## u2 4 2 3 5 3 5
## u3 4 2 3 5 4 4
## u4 3 3 5 4 3 4
## u5 4 4 3 4 4 5Create the evaluation scheme using the split method:
# eval_scheme <- evaluationScheme(r, method="cross", train=0.8,
# given=-1, goodRating=5)
eval_scheme <- evaluationScheme(r, method="split", train=0.9, k=3, given=-1, goodRating=5)
eval_scheme## Evaluation scheme using all-but-1 items
## Method: 'split' with 3 run(s).
## Training set proportion: 0.900
## Good ratings: >=5.000000
## Data set: 5 x 6 rating matrix of class 'realRatingMatrix' with 30 ratings.Evaluate several recommender algorithms using an evaluation scheme:
algorithms <- list("random items" = list(name="RANDOM", param=NULL),
"popular items" = list(name="POPULAR", param=NULL),
"user-based CF" = list(name="UBCF", param=list(nn=50)),
"item-based CF" = list(name="IBCF", param=list(k=50)),
"SVD approximation" = list(name="SVD", param=list(k = 3)))
results <- recommenderlab::evaluate(
eval_scheme,
algorithms,
type= "topNList",
n = 1:5)## RANDOM run fold/sample [model time/prediction time]
## 1 [0.004sec/0.012sec]
## 2 [0sec/0.011sec]
## 3 [0sec/0.001sec]
## POPULAR run fold/sample [model time/prediction time]
## 1 [0.001sec/0.012sec]
## 2 [0.001sec/0.006sec]
## 3 [0sec/0.001sec]
## UBCF run fold/sample [model time/prediction time]
## 1 [0.001sec/0.005sec]
## 2 [0sec/0.017sec]
## 3 [0.001sec/0.001sec]
## IBCF run fold/sample [model time/prediction time]
## 1 [0.002sec/0.002sec]
## 2 [0.001sec/0.001sec]
## 3 [0.001sec/0.001sec]
## SVD run fold/sample [model time/prediction time]
## 1## Warning in irlba::irlba(m, nv = p$k, maxit = p$maxiter): You're computing too
## large a percentage of total singular values, use a standard svd instead.## [0.002sec/0.001sec]
## 2## Warning in irlba::irlba(m, nv = p$k, maxit = p$maxiter): You're computing too
## large a percentage of total singular values, use a standard svd instead.## [0.001sec/0.001sec]
## 3## Warning in irlba::irlba(m, nv = p$k, maxit = p$maxiter): You're computing too
## large a percentage of total singular values, use a standard svd instead.## [0sec/0.002sec]results## List of evaluation results for 5 recommenders:
##
## $`random items`
## Evaluation results for 3 folds/samples using method 'RANDOM'.
##
## $`popular items`
## Evaluation results for 3 folds/samples using method 'POPULAR'.
##
## $`user-based CF`
## Evaluation results for 3 folds/samples using method 'UBCF'.
##
## $`item-based CF`
## Evaluation results for 3 folds/samples using method 'IBCF'.
##
## $`SVD approximation`
## Evaluation results for 3 folds/samples using method 'SVD'.getConfusionMatrix(results$`random items`)[[1]]## TP FP FN TN N precision recall TPR FPR n
## [1,] 1 0 0 2 3 1.0000000 1 1 0.0 1
## [2,] 1 1 0 1 3 0.5000000 1 1 0.5 2
## [3,] 1 2 0 0 3 0.3333333 1 1 1.0 3
## [4,] 1 2 0 0 3 0.3333333 1 1 1.0 4
## [5,] 1 2 0 0 3 0.3333333 1 1 1.0 5avg(results)## $`random items`
## TP FP FN TN N precision recall TPR FPR n
## [1,] 0.3333333 0.3333333 0 0.6666667 1.333333 NaN NaN NaN NaN 1
## [2,] 0.3333333 0.6666667 0 0.3333333 1.333333 NaN NaN NaN NaN 2
## [3,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 3
## [4,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 4
## [5,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 5
##
## $`popular items`
## TP FP FN TN N precision recall TPR FPR n
## [1,] 0.3333333 0.3333333 0 0.6666667 1.333333 NaN NaN NaN NaN 1
## [2,] 0.3333333 0.6666667 0 0.3333333 1.333333 NaN NaN NaN NaN 2
## [3,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 3
## [4,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 4
## [5,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 5
##
## $`user-based CF`
## TP FP FN TN N precision recall TPR FPR n
## [1,] 0.3333333 0.3333333 0 0.6666667 1.333333 NaN NaN NaN NaN 1
## [2,] 0.3333333 0.6666667 0 0.3333333 1.333333 NaN NaN NaN NaN 2
## [3,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 3
## [4,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 4
## [5,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 5
##
## $`item-based CF`
## TP FP FN TN N precision recall TPR FPR
## [1,] 0.0000000 0.6666667 0.3333333 0.3333333 1.333333 NaN NaN NaN NaN
## [2,] 0.3333333 0.6666667 0.0000000 0.3333333 1.333333 NaN NaN NaN NaN
## [3,] 0.3333333 1.0000000 0.0000000 0.0000000 1.333333 NaN NaN NaN NaN
## [4,] 0.3333333 1.0000000 0.0000000 0.0000000 1.333333 NaN NaN NaN NaN
## [5,] 0.3333333 1.0000000 0.0000000 0.0000000 1.333333 NaN NaN NaN NaN
## n
## [1,] 1
## [2,] 2
## [3,] 3
## [4,] 4
## [5,] 5
##
## $`SVD approximation`
## TP FP FN TN N precision recall TPR FPR n
## [1,] 0.3333333 0.3333333 0 0.6666667 1.333333 NaN NaN NaN NaN 1
## [2,] 0.3333333 0.6666667 0 0.3333333 1.333333 NaN NaN NaN NaN 2
## [3,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 3
## [4,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 4
## [5,] 0.3333333 1.0000000 0 0.0000000 1.333333 NaN NaN NaN NaN 5