top_cols {slimrec}

top_cols

Description

Find the column numbers corresponding the largest values in a particular row of a matrix

Usage

top_cols(mat, row, k = 5, ignore)

Arguments

mat

(Sparse matrix of class 'dgCmatrix' or a integer/numeric matrix or 'big.matrix') Rating matrix.

row

(positive integer) Row number in which top columns are to be selected.

k

(positive integer) Number of column numbers to be recommended. This might not be strictly adhered to, see Details.

ignore

(integer vector) Column numbers to be ignored.

Details

To find top-n recommendations of a ratings matrix given an item (or a user). Although k recommendations are expected to be returned, the function might sometimes return more or less than k recommendations.

• Less: This happens when it is not possible to recommend k elements. For example, k is larger than the number of elements.

• More: This happens when a few elements have same rating. The function returns the index corresponding to all the elements which have the same rating. If ratings were 3,2,2,2,3:

  • k = 3: returns 1, 5, 2, 3, 4

  • k = 2: returns 1, 5

  • k = 1: returns 1, 5

Examples

## Not run: 
temp <- slim(mat           = ft_implicit # input sparse ratings matrix
             , alpha       = 0.5         # 0 for ridge, 1 for lasso
             #, lambda                   # suggested not to set lambda
             #, nlambda                  # using default nlambda = 100
             , nonNegCoeff = TRUE        # better accuracy, lower interpretability
             , directory   = td          # dir where output matrices are stored
             , coeffMat    = TRUE        # helpful in 'predict'ing later
             , returnMat   = TRUE        # return matrices in memory
             , computeRMSE = TRUE        # RMSE over rated items
             , nproc       = 2L          # number of concurrent processes
             , progress    = TRUE        # show a progressbar
             , check       = TRUE        # do basic checks on input params
             , cleanup     = FALSE       # keep output matrices on disk
             )
str(temp)
# output ratings matrix would be comparatively denser
predMat <- temp[["ratingMat"]] != 0
sum(predMat)/((dim(predMat)[1])*(dim(predMat)[2]))
# recommend top 5 items for a user 10
top_cols(temp[["ratingMat"]]
         , row = 10
         , k   = 5
         )
# if you intend to avoid recommending 10, 215 and 3
top_cols(temp[["ratingMat"]]
         , row = 10
         , k   = 5
         , ignore = c(10, 215, 3)
         )

## End(Not run)