transbiozi / rmtl Goto Github PK

View Code? Open in Web Editor NEW

19.0 3.0 12.0 339 KB

Regularized Multi-task Learning in R

Home Page: https://CRAN.R-project.org/package=RMTL

R 100.00%

multi-task-learning sparse-coding low-rank-representaion regularization

rmtl's Introduction

RMTL

Regularized Multi-task Learning in R

Description

This package provides an efficient implementation of regularized multi-task learning comprising 10 algorithms applicable for regression, classification, joint feature selection, task clustering, low-rank learning, sparse learning and network incorporation. All algorithms are implemented basd on the accelerated gradient descent method and feature a complexity of O(1/k^2). Sparse model structure is induced by the solving the proximal operator. The package has been uploaded in the CRAN: https://CRAN.R-project.org/package=RMTL

Required Packages

Four packages have to be instaled in advanced to enable functions i.e. eigen-decomposition, 2D plotting: ‘MASS’, ‘psych’, ‘corpcor’ and ‘fields’. You can install them from the CRAN.

install.packages("MASS")
install.packages("psych")
install.packages("corpcor")
install.packages("fields")

Installation

You can choose any of the three ways to install RMTL.

Install from CRAN in R environment (Recommend)

install.packages("RMTL")
# in this way, the requirement for installation are automatically checked.

Install from github in R environment

install.packages("devtools")
library("devtools")
install_github("transbioZI/RMTL")

Install from the source code

git clone https://github.com/transbioZI/RMTL.git
R CMD build ./RMTL/
R CMD INSTALL RMTL*.tar.gz

Tutorial

The tutorial of multi-task learning using RMTL can be found here.

Manual

Please check "RMTL-manuel.pdf" for more details.

Reference

Cao, Han, Jiayu Zhou and Emanuel Schwarz. "RMTL: An R Library for Multi-Task Learning." Bioinformatics (2018).

Contact

If you have any question, please contact: [email protected]

rmtl's People

Contributors

Stargazers

Watchers

Forkers

hank9cao riverdarda haithamsghaier fyc0803 mosaddek-hossain yongchangliugit vishalbelsare ghaithcode jinjun-ama bluevale rnaimehaom imalenica

rmtl's Issues

My own datasets

Hello,
I like to use this package for the multi-task learning of classification problem. However, I don't know how to import my datasets ( three tasks) in this package.
Please help me in this regard

the error in seq.default(cv_idx, task_sample_size, by = cv_fold)

I used this package for the multi-task learning of regression problem. The dataset is (160row, 31 column), and the X is (160row, 28column), Y is (160row, 3 column).

The model and the parameter are that:

cvfitr1 <- cvMTL(X, Y, type="Regression", Regularization="L21",

            Lam1_seq=10^seq(1,-4, -1),  Lam2=0, opts=list(init=0,  tol=10^-6, maxIter=1500),

            nfolds= 10, stratify=F, parallel=F)

The error is that:
Error in seq.default(cv_idx, task_sample_size, by = cv_fold) :
wrong sign in 'by' argument.

Another model and parameter:

model <- MTL(X, Y, type = "Regression",Regularization="L21",

         Lam1=0.1, Lam2=0.1, opts=list(init=0, tol=10^-6, maxIter=500))

Error is that:
Error in Y[[x]] : 下标出界(the subscript out of size)

bugs in parallel

thank you for your works, but maybe there have bug in parallel functions,:
1 need add stopImplicitCluster() to stop cluster when compute finished, otherwise r background process will not close.
2 some times parallel cvMTL and single thread cvMTL got different result Lam1.min

set.seed(202000)
library(RMTL)
data <- Create_simulated_data(t=1,p=50,n=200000,
                              Regularization="Lasso",
                              type="Classification")

cvfit<-cvMTL(data$X, data$Y, type="Classification", 
                         Regularization="Lasso",nfolds = 10)

cvfit1<-cvMTL(data$X, data$Y, type="Classification", 
                         Regularization="Lasso",parallel = T,
                         ncores = 2,nfolds = 10)
cvfit$Lam1.min==cvfit1$Lam1.min

#run it 
> set.seed(202000)
> library(RMTL)
> data <- Create_simulated_data(t=1,p=50,n=200000,
+                               Regularization="Lasso",
+                               type="Classification")
> 
> cvfit<-cvMTL(data$X, data$Y, type="Classification", 
+                          Regularization="Lasso",nfolds = 10)
> 
> cvfit1<-cvMTL(data$X, data$Y, type="Classification", 
+                          Regularization="Lasso",parallel = T,
+                          ncores = 2,nfolds = 10)
> cvfit$Lam1.min==cvfit1$Lam1.min
[1] FALSE
> cvfit$Lam1.min
[1] 1e-04
> cvfit1$Lam1.min
[1] 0.001
> cvfit
$Lam1_seq
[1] 1e+01 1e+00 1e-01 1e-02 1e-03 1e-04

$Lam1.min
[1] 1e-04

$Lam2
[1] 0

$cvm
[1] 0.499590 0.499590 0.221030 0.041510 0.035485 0.035435

attr(,"class")
[1] "cvMTL"
> cvfit1
$Lam1_seq
[1] 1e+01 1e+00 1e-01 1e-02 1e-03 1e-04

$Lam1.min
[1] 0.001

$Lam2
[1] 0

$cvm
[1] 0.500890 0.500890 0.220945 0.041620 0.035445 0.035445

attr(,"class")
[1] "cvMTL"
> sessionInfo()
R version 3.5.3 (2019-03-11)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 17763)

Matrix products: default

locale:
[1] LC_COLLATE=Chinese (Simplified)_China.936 
[2] LC_CTYPE=Chinese (Simplified)_China.936   
[3] LC_MONETARY=Chinese (Simplified)_China.936
[4] LC_NUMERIC=C                              
[5] LC_TIME=Chinese (Simplified)_China.936    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] RMTL_0.9

loaded via a namespace (and not attached):
[1] compiler_3.5.3    parallel_3.5.3    tools_3.5.3       codetools_0.2-16 
[5] doParallel_1.0.14 iterators_1.0.10  foreach_1.4.4    
>