<p>In <a href="https://github.com/mlpack/mlpack/pull/694#discussion_r70637214">src/mlpack/core/data/imputation_methods/listwise_deletion.hpp</a>:</p>
<pre style='color:#555'>&gt; +              const T&amp; mappedValue,
&gt; +              const size_t dimension,
&gt; +              const bool transpose = true)
&gt; +  {
&gt; +    // initiate output
&gt; +    output = input;
&gt; +    size_t count = 0;
&gt; +
&gt; +    if (transpose)
&gt; +    {
&gt; +      for (size_t i = 0; i &lt; input.n_cols; ++i)
&gt; +      {
&gt; +         if (input(dimension, i) == mappedValue ||
&gt; +             std::isnan(input(dimension, i)))
&gt; +         {
&gt; +           output.shed_col(i - count);
</pre>
<p>I think that the speedup should be much more dramatic if you use larger datasets, too.  It's probably a good idea to test with matrices that are something like 100k+ points in a variety of dimensions.  If you want, I can provide some typical datasets that I like to use for testing.</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/694/files/a8818316a04506530e2269a2e0a32ba2f6a1c83b#r70637214">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe/AJ4bFMiBCKazKUw3SozmZfDjR_EXW7Z_ks5qVPfzgaJpZM4I07W-">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFJCd9U2CcdVZY5uIroFyHdwQC1x-ks5qVPfzgaJpZM4I07W-.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
  <link itemprop="url" href="https://github.com/mlpack/mlpack/pull/694/files/a8818316a04506530e2269a2e0a32ba2f6a1c83b#r70637214"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>