Package: softImpute 1.4-1

softImpute: Matrix Completion via Iterative Soft-Thresholded SVD

Iterative methods for matrix completion that use nuclear-norm regularization. There are two main approaches.The one approach uses iterative soft-thresholded svds to impute the missing values. The second approach uses alternating least squares. Both have an 'EM' flavor, in that at each iteration the matrix is completed with the current estimate. For large matrices there is a special sparse-matrix class named "Incomplete" that efficiently handles all computations. The package includes procedures for centering and scaling rows, columns or both, and for computing low-rank SVDs on large sparse centered matrices (i.e. principal components).

Authors:Trevor Hastie <[email protected]> and Rahul Mazumder <[email protected]>

softImpute_1.4-1.tar.gz
softImpute_1.4-1.zip(r-4.5)softImpute_1.4-1.zip(r-4.4)softImpute_1.4-1.zip(r-4.3)
softImpute_1.4-1.tgz(r-4.4-x86_64)softImpute_1.4-1.tgz(r-4.4-arm64)softImpute_1.4-1.tgz(r-4.3-x86_64)softImpute_1.4-1.tgz(r-4.3-arm64)
softImpute_1.4-1.tar.gz(r-4.5-noble)softImpute_1.4-1.tar.gz(r-4.4-noble)
softImpute_1.4-1.tgz(r-4.4-emscripten)softImpute_1.4-1.tgz(r-4.3-emscripten)
softImpute.pdf |softImpute.html
softImpute/json (API)

# Install 'softImpute' in R:
install.packages('softImpute', repos = c('https://trevorhastie.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

7.48 score 10 stars 23 packages 235 scripts 1.8k downloads 12 mentions 24 exports 2 dependencies

Last updated 4 years agofrom:b497771bee. Checks:OK: 7 NOTE: 2. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 06 2024
R-4.5-win-x86_64NOTENov 06 2024
R-4.5-linux-x86_64NOTENov 06 2024
R-4.4-win-x86_64OKNov 06 2024
R-4.4-mac-x86_64OKNov 06 2024
R-4.4-mac-aarch64OKNov 06 2024
R-4.3-win-x86_64OKNov 06 2024
R-4.3-mac-x86_64OKNov 06 2024
R-4.3-mac-aarch64OKNov 06 2024

Exports:as.matrixbiScaleclean.warm.startcoercecolMeanscolSumscompletedeBiasimputeIncompletelambda0normrowMeansrowSumssimpute.alssimpute.svdsoftImputesoftImpute.x.IncompletesoftImpute.x.matrixsplrSsimpute.alsSsimpute.svdSsvd.alssvd.als

Dependencies:latticeMatrix

An Introduction to softImpute

Rendered fromsoftImpute.Rmdusingknitr::knitron Nov 06 2024.

Last update: 2021-05-09
Started: 2015-02-13

Readme and manuals

Help Manual

Help pageTopics
standardize a matrix to have optionally row means zero and variances one, and/or column means zero and variances one.biScale
make predictions from an svd objectcomplete complete,Incomplete-method complete,matrix-method impute
Recompute the '$d' component of a '"softImpute"' object through regression.deBias
create a matrix of class 'Incomplete'coerce,matrix-method Incomplete
Class '"Incomplete"'as.matrix,Incomplete-method coerce,matrix,Incomplete-method coerce,sparseMatrix,Incomplete-method Incomplete-class
compute the smallest value for 'lambda' such that 'softImpute(x,lambda)' returns the zero solution.lambda0 lambda0,Incomplete-method lambda0,sparseMatrix-method lambda0,SparseplusLowRank-method
impute missing values for a matrix via nuclear-norm regularization.softImpute
Class '"SparseplusLowRank"'%*%,ANY,SparseplusLowRank-method %*%,Matrix,SparseplusLowRank-method %*%,SparseplusLowRank,ANY-method %*%,SparseplusLowRank,Matrix-method as.matrix,SparseplusLowRank-method colMeans,SparseplusLowRank-method colSums,SparseplusLowRank-method dim,SparseplusLowRank-method norm,SparseplusLowRank,character-method rowMeans,SparseplusLowRank-method rowSums,SparseplusLowRank-method SparseplusLowRank-class
create a 'SparseplusLowRank' objectsplr
compute a low rank soft-thresholded svd by alternating orthogonal ridge regressionsvd.als svd.als,sparseMatrix-method svd.als,SparseplusLowRank-method