automation

R/functions.R

@@ -16,7 +16,7 @@
 #' covariates\strong{:}
 #' matrix with \eqn{n} rows (samples) and \eqn{p} columns (variables)
 #' 
-#' @param nfold
+#' @param nfolds
 #' number of folds
 #' 
 #' @param alpha
@@ -30,12 +30,12 @@
 #' #y[1] <- 0.5
 #' #a <- glmnet::glmnet(y=y,x=x,family="binomial")
 #' #b <- stats::glm(y~x,family="binomial")
-colasso <- function(y,X,nfold=10,alpha=1){
+colasso <- function(y,X,nfold=10,alpha=1,nfolds=10){
     
     # properties
     n <- nrow(X); p <- ncol(X)
     if(length(y)!=n){stop("sample size")}
-    foldid <- sample(x=rep(x=seq_len(nfold),length.out=n))
+    foldid <- sample(x=rep(x=seq_len(nfolds),length.out=n))
     pi <- seq(from=0,to=0.5,by=0.1) # adapt this
 
     # model fitting

docs/articles/vignette.html

@@ -179,16 +179,16 @@ https://en.wikipedia.org/wiki/List_of_datasets_for_machine_learning_research#Mic
 <a class="sourceLine" id="cb2-22" data-line-number="22">    <span class="kw">cat</span>(<span class="st">"| j ="</span>,j,<span class="st">"|</span><span class="ch">\n</span><span class="st">"</span>)</a>
 <a class="sourceLine" id="cb2-23" data-line-number="23">    y &lt;-<span class="st"> </span>Y[,j]</a>
 <a class="sourceLine" id="cb2-24" data-line-number="24">    <span class="cf">if</span>(<span class="kw">sd</span>(y,<span class="dt">na.rm=</span><span class="ot">TRUE</span>)<span class="op">==</span><span class="dv">0</span>){<span class="cf">next</span>}</a>
-<a class="sourceLine" id="cb2-25" data-line-number="25">    <span class="co">#if(TRUE){</span></a>
+<a class="sourceLine" id="cb2-25" data-line-number="25">    <span class="cf">if</span>(<span class="ot">TRUE</span>){</a>
 <a class="sourceLine" id="cb2-26" data-line-number="26">    <span class="co">#    psel &lt;- sample(seq_len(56515),size=2000)</span></a>
-<a class="sourceLine" id="cb2-27" data-line-number="27">    <span class="co">#    nsel &lt;- sample(seq_len(2003),size=500)</span></a>
-<a class="sourceLine" id="cb2-28" data-line-number="28">    <span class="co">#    y &lt;- y[nsel]</span></a>
-<a class="sourceLine" id="cb2-29" data-line-number="29">    <span class="co">#    x &lt;- X[nsel,psel]</span></a>
-<a class="sourceLine" id="cb2-30" data-line-number="30">    <span class="co">#}</span></a>
+<a class="sourceLine" id="cb2-27" data-line-number="27">        nsel &lt;-<span class="st"> </span><span class="kw">sample</span>(<span class="kw">seq_len</span>(<span class="dv">2003</span>),<span class="dt">size=</span><span class="dv">500</span>)</a>
+<a class="sourceLine" id="cb2-28" data-line-number="28">        y &lt;-<span class="st"> </span>y[nsel]</a>
+<a class="sourceLine" id="cb2-29" data-line-number="29">        x &lt;-<span class="st"> </span>X[nsel,] <span class="co"># psel</span></a>
+<a class="sourceLine" id="cb2-30" data-line-number="30">    }</a>
 <a class="sourceLine" id="cb2-31" data-line-number="31">    cond &lt;-<span class="st"> </span><span class="op">!</span><span class="kw">is.na</span>(y)</a>
 <a class="sourceLine" id="cb2-32" data-line-number="32">    y &lt;-<span class="st"> </span><span class="kw">scale</span>(y[cond])</a>
-<a class="sourceLine" id="cb2-33" data-line-number="33">    x &lt;-<span class="st"> </span>X[cond,]</a>
-<a class="sourceLine" id="cb2-34" data-line-number="34">    loss &lt;-<span class="st"> </span><span class="kw">rbind</span>(loss,colasso<span class="op">::</span><span class="kw"><a href="http://www.rdocumentation.org/packages/colasso/topics/colasso_compare">colasso_compare</a></span>(<span class="dt">y=</span>y,<span class="dt">X=</span>x))</a>
+<a class="sourceLine" id="cb2-33" data-line-number="33">    x &lt;-<span class="st"> </span>x[cond,]</a>
+<a class="sourceLine" id="cb2-34" data-line-number="34">    loss &lt;-<span class="st"> </span><span class="kw">rbind</span>(loss,colasso<span class="op">::</span><span class="kw"><a href="http://www.rdocumentation.org/packages/colasso/topics/colasso_compare">colasso_compare</a></span>(<span class="dt">y=</span>y,<span class="dt">X=</span>x,<span class="dt">nfolds=</span><span class="dv">5</span>))</a>
 <a class="sourceLine" id="cb2-35" data-line-number="35">}</a></code></pre></div>
 <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" data-line-number="1">n &lt;-<span class="st"> </span><span class="dv">100</span>; p &lt;-<span class="st"> </span><span class="dv">10</span></a>
 <a class="sourceLine" id="cb3-2" data-line-number="2">x &lt;-<span class="st"> </span><span class="kw">matrix</span>(<span class="kw">rnorm</span>(n<span class="op">*</span>p),<span class="dt">nrow=</span>n,<span class="dt">ncol=</span>p)</a>

docs/reference/colasso.html

@@ -120,7 +120,7 @@
     
     </div>
 
-    <pre class="usage"><span class='fu'>colasso</span>(<span class='no'>y</span>, <span class='no'>X</span>, <span class='kw'>nfold</span> <span class='kw'>=</span> <span class='fl'>10</span>, <span class='kw'>alpha</span> <span class='kw'>=</span> <span class='fl'>1</span>)</pre>
+    <pre class="usage"><span class='fu'>colasso</span>(<span class='no'>y</span>, <span class='no'>X</span>, <span class='kw'>nfold</span> <span class='kw'>=</span> <span class='fl'>10</span>, <span class='kw'>alpha</span> <span class='kw'>=</span> <span class='fl'>1</span>, <span class='kw'>nfolds</span> <span class='kw'>=</span> <span class='fl'>10</span>)</pre>
     
     <h2 class="hasAnchor" id="arguments"><a class="anchor" href="#arguments"></a>Arguments</h2>
     <table class="ref-arguments">
@@ -135,14 +135,14 @@ vector of length \(n\)</p></td>
       <td><p>covariates<strong>:</strong>
 matrix with \(n\) rows (samples) and \(p\) columns (variables)</p></td>
     </tr>
-    <tr>
-      <th>nfold</th>
-      <td><p>number of folds</p></td>
-    </tr>
     <tr>
       <th>alpha</th>
       <td><p>elastic net parameter</p></td>
     </tr>
+    <tr>
+      <th>nfolds</th>
+      <td><p>number of folds</p></td>
+    </tr>
     </table>
     
 

man/colasso.Rd

@@ -5,7 +5,7 @@
 \alias{colasso-package}
 \title{colasso}
 \usage{
-colasso(y, X, nfold = 10, alpha = 1)
+colasso(y, X, nfold = 10, alpha = 1, nfolds = 10)
 }
 \arguments{
 \item{y}{response\strong{:}
@@ -14,9 +14,9 @@ vector of length \eqn{n}}
 \item{X}{covariates\strong{:}
 matrix with \eqn{n} rows (samples) and \eqn{p} columns (variables)}
 
-\item{nfold}{number of folds}
-
 \item{alpha}{elastic net parameter}
+
+\item{nfolds}{number of folds}
 }
 \description{
 This function ...

vignettes/vignette.Rmd

@@ -104,16 +104,16 @@ for(j in seq_len(ncol(Y))){
     cat("| j =",j,"|\n")
     y <- Y[,j]
     if(sd(y,na.rm=TRUE)==0){next}
-    #if(TRUE){
+    if(TRUE){
     #    psel <- sample(seq_len(56515),size=2000)
-    #    nsel <- sample(seq_len(2003),size=500)
-    #    y <- y[nsel]
-    #    x <- X[nsel,psel]
-    #}
+        nsel <- sample(seq_len(2003),size=500)
+        y <- y[nsel]
+        x <- X[nsel,] # psel
+    }
     cond <- !is.na(y)
     y <- scale(y[cond])
-    x <- X[cond,]
-    loss <- rbind(loss,colasso::colasso_compare(y=y,X=x))
+    x <- x[cond,]
+    loss <- rbind(loss,colasso::colasso_compare(y=y,X=x,nfolds=5))
 }