Check OK

Initialized github

Author: jlaria

NAMESPACE

@@ -6,7 +6,8 @@ exportPattern(s2net,
               s2Fista,
               s2netR,
               simulate_extra,
-              simulate_groups)
+              simulate_groups,
+              transform_ExtJT)
 
 S3method(print, s2Data)
 S3method(print, s2Fista)

README.Rmd

@@ -19,7 +19,7 @@ knitr::opts_chunk$set(
 
 R package `s2net`
 
- + Our method extends the supervised elastic-net problem, and thus it is an ideal solution to the problem of feature selection in semi-supervised contexts.
+ + Our method extends the supervised elastic-net problem, and thus it is a practical solution to the problem of feature selection in semi-supervised contexts.
  + Its mathematical formulation is presented from a general perspective, covering a wide range of models. 
  + We develop a flexible and fast implementation for `s2net` in `R`, written in `C++` using `RcppArmadillo` and integrated into `R` via `Rcpp` modules.
 

README.md

@@ -8,7 +8,7 @@
 R package `s2net`
 
   - Our method extends the supervised elastic-net problem, and thus it
-    is an ideal solution to the problem of feature selection in
+    is a practical solution to the problem of feature selection in
     semi-supervised contexts.
   - Its mathematical formulation is presented from a general
     perspective, covering a wide range of models.

man/figures/s2net.png

@@ -6,7 +6,6 @@
 #define TYPE_TRANSFORM_ExtJT 1
 
 
-
 arma::mat transform_ExtJT(const arma::mat & X, double gamma2, double gamma3){
     int n = X.n_rows;
     int p = X.n_cols;

src/transformations.h

@@ -7,7 +7,7 @@ lm_test = function(train){
   lm_fit = lm.fit(x = train$xL, y = train$yL)
   true_beta = unname(lm_fit$coefficients)
   found_beta = as.vector(obj$beta)
-  expect_equal(found_beta, true_beta, tolerance = .001)
+  expect_equal(found_beta, true_beta, tolerance = .01)
 
   lm_error = mean((train$xL%*%lm_fit$coefficients - train$yL)^2)
   error = mean((obj$intercept + train$xL%*%obj$beta - train$yL)^2)

tests/testthat/test.optimization.R

@@ -1,8 +1,8 @@
 ---
-title: "The supervised `nExtJT`"
+title: "The supervised `s2net`"
 output: rmarkdown::html_vignette
 vignette: >
-  %\VignetteIndexEntry{The supervised `nExtJT`}
+  %\VignetteIndexEntry{The supervised `s2net`}
   %\VignetteEngine{knitr::rmarkdown}
   %\VignetteEncoding{UTF-8}
 ---
@@ -17,18 +17,18 @@ knitr::opts_chunk$set(
 )
 ```
 
-`nExtJT` can be used as a supervised method (without unlabeled data) and it is equialent to elastic net. 
+`s2net` can be used as a supervised method (without unlabeled data) and it is equialent to elastic net. 
 
 ## Data
 
-The `auto_mpg` dataset is available when `nExtJT` is installed. 
+The `auto_mpg` dataset is available when `s2net` is installed. 
 
 ```{r}
-library(nExtJT)
+library(s2net)
 data("auto_mpg")
 
-# Preprocess the data using the nExtData function
-train = nExtData(auto_mpg$P1$xL, auto_mpg$P1$yL, preprocess = TRUE)
+# Preprocess the data using the s2Data function
+train = s2Data(auto_mpg$P1$xL, auto_mpg$P1$yL, preprocess = TRUE)
 ```
 
 ## Ordinary least squares
@@ -39,10 +39,10 @@ To fit an OLS model, we will use the `lm` function (without intercept).
 lm.fit = lm( y~ 0 + ., data = data.frame(train$xL, y = train$yL))
 ```
 
-To obtain the estimations from `nExtJT` we use
+To obtain the estimations from `s2net` we use
 
 ```{r}
-obj = nExtJTR(train, nExtParams(0))
+obj = s2netR(train, s2Params(0))
 # We set all the hyper-parameters to 0
 ```
 
@@ -56,11 +56,11 @@ print("OLS error:")
 mse(ypred, train$yL)
 
 ypred = predict(obj, train$xL)
-print("nExtJT error:")
+print("s2net error:")
 mse(ypred, train$yL)
 
 #Estimations
-data.frame(mle = lm.fit$coefficients, nExtJT = obj$beta)
+data.frame(mle = lm.fit$coefficients, s2net = obj$beta)
 ```
 
 ## Lasso
@@ -74,13 +74,13 @@ ypred = predict(lasso.fit, train$xL)
 print("Lasso error:")
 mse(ypred, train$yL)
 
-obj = nExtJTR(train, nExtParams(lambda1 = 0.01))
+obj = s2netR(train, s2Params(lambda1 = 0.01))
 ypred = predict(obj, train$xL)
-print("nExtJT error")
+print("s2net error")
 mse(ypred, train$yL)
 
 print("Coefficients")
-data.frame(lasso = as.numeric(lasso.fit$beta), nExtJT = obj$beta)
+data.frame(lasso = as.numeric(lasso.fit$beta), s2net = obj$beta)
 ```
 
 ## Elastic net
@@ -92,11 +92,11 @@ ypred = predict(enet.fit, train$xL)
 print("glmnet error")
 mse(ypred, train$yL)
 
-obj = nExtJTR(train, nExtParams(lambda1 = 0.01, lambda2 = 0.01))
+obj = s2netR(train, s2Params(lambda1 = 0.01, lambda2 = 0.01))
 ypred = predict(obj, train$xL)
-print("nExtJT error")
+print("s2net error")
 mse(ypred, train$yL)
 
 print("Coefficients")
-data.frame(enet = as.matrix(enet.fit$beta), nExtJT = obj$beta)
+data.frame(enet = as.matrix(enet.fit$beta), s2net = obj$beta)
 ```