build based on 61f12f9

dev/.documenter-siteinfo.json

@@ -1 +1 @@
-{"documenter":{"julia_version":"1.10.3","generation_timestamp":"2024-05-06T00:28:19","documenter_version":"1.4.1"}}
+{"documenter":{"julia_version":"1.10.3","generation_timestamp":"2024-05-20T09:15:13","documenter_version":"1.4.1"}}

dev/correcting_class_imbalance/index.html

@@ -20,4 +20,4 @@
 
 # now this behaves as a unified model that can be trained, validated, fine-tuned, etc.
 mach = machine(balanced_model, X, y)
-fit!(mach)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaAI/MLJBalancing.jl/blob/v0.1.4/src/balanced_model.jl#L72-L118">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../homogeneous_ensembles/">« Homogeneous Ensembles</a><a class="docs-footer-nextpage" href="../model_stacking/">Model Stacking »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.1 on <span class="colophon-date" title="Monday 6 May 2024 00:28">Monday 6 May 2024</span>. Using Julia version 1.10.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+fit!(mach)</code></pre></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaAI/MLJBalancing.jl/blob/v0.1.4/src/balanced_model.jl#L72-L118">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../homogeneous_ensembles/">« Homogeneous Ensembles</a><a class="docs-footer-nextpage" href="../model_stacking/">Model Stacking »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.1 on <span class="colophon-date" title="Monday 20 May 2024 09:15">Monday 20 May 2024</span>. Using Julia version 1.10.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>

dev/homogeneous_ensembles/index.html

@@ -5,4 +5,4 @@
               n=100,
               rng=GLOBAL_RNG,
               acceleration=CPU1(),
-              out_of_bag_measure=[])</code></pre><p>Create a model for training an ensemble of <code>n</code> clones of <code>model</code>, with optional bagging. Ensembling is useful if <code>fit!(machine(atom, data...))</code> does not create identical models on repeated calls (ie, is a stochastic model, such as a decision tree with randomized node selection criteria), or if <code>bagging_fraction</code> is set to a value less than 1.0, or both.</p><p>Here the atomic <code>model</code> must support targets with scitype <code>AbstractVector{&lt;:Finite}</code> (single-target classifiers) or <code>AbstractVector{&lt;:Continuous}</code> (single-target regressors).</p><p>If <code>rng</code> is an integer, then <code>MersenneTwister(rng)</code> is the random number generator used for bagging. Otherwise some <code>AbstractRNG</code> object is expected.</p><p>The atomic predictions are optionally weighted according to the vector <code>atomic_weights</code> (to allow for external optimization) except in the case that <code>model</code> is a <code>Deterministic</code> classifier, in which case <code>atomic_weights</code> are ignored.</p><p>The ensemble model is <code>Deterministic</code> or <code>Probabilistic</code>, according to the corresponding supertype of <code>atom</code>. In the case of deterministic classifiers (<code>target_scitype(atom) &lt;: Abstract{&lt;:Finite}</code>), the predictions are majority votes, and for regressors (<code>target_scitype(atom)&lt;: AbstractVector{&lt;:Continuous}</code>) they are ordinary averages.  Probabilistic predictions are obtained by averaging the atomic probability distribution/mass functions; in particular, for regressors, the ensemble prediction on each input pattern has the type <code>MixtureModel{VF,VS,D}</code> from the Distributions.jl package, where <code>D</code> is the type of predicted distribution for <code>atom</code>.</p><p>Specify <code>acceleration=CPUProcesses()</code> for distributed computing, or <code>CPUThreads()</code> for multithreading.</p><p>If a single measure or non-empty vector of measures is specified by <code>out_of_bag_measure</code>, then out-of-bag estimates of performance are written to the training report (call <code>report</code> on the trained machine wrapping the ensemble model).</p><p><em>Important:</em> If per-observation or class weights <code>w</code> (not to be confused with atomic weights) are specified when constructing a machine for the ensemble model, as in <code>mach = machine(ensemble_model, X, y, w)</code>, then <code>w</code> is used by any measures specified in <code>out_of_bag_measure</code> that support them.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaAI/MLJEnsembles.jl/blob/v0.4.1/src/ensembles.jl#L276-L329">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../target_transformations/">« Target Transformations</a><a class="docs-footer-nextpage" href="../correcting_class_imbalance/">Correcting Class Imbalance »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.1 on <span class="colophon-date" title="Monday 6 May 2024 00:28">Monday 6 May 2024</span>. Using Julia version 1.10.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>
+              out_of_bag_measure=[])</code></pre><p>Create a model for training an ensemble of <code>n</code> clones of <code>model</code>, with optional bagging. Ensembling is useful if <code>fit!(machine(atom, data...))</code> does not create identical models on repeated calls (ie, is a stochastic model, such as a decision tree with randomized node selection criteria), or if <code>bagging_fraction</code> is set to a value less than 1.0, or both.</p><p>Here the atomic <code>model</code> must support targets with scitype <code>AbstractVector{&lt;:Finite}</code> (single-target classifiers) or <code>AbstractVector{&lt;:Continuous}</code> (single-target regressors).</p><p>If <code>rng</code> is an integer, then <code>MersenneTwister(rng)</code> is the random number generator used for bagging. Otherwise some <code>AbstractRNG</code> object is expected.</p><p>The atomic predictions are optionally weighted according to the vector <code>atomic_weights</code> (to allow for external optimization) except in the case that <code>model</code> is a <code>Deterministic</code> classifier, in which case <code>atomic_weights</code> are ignored.</p><p>The ensemble model is <code>Deterministic</code> or <code>Probabilistic</code>, according to the corresponding supertype of <code>atom</code>. In the case of deterministic classifiers (<code>target_scitype(atom) &lt;: Abstract{&lt;:Finite}</code>), the predictions are majority votes, and for regressors (<code>target_scitype(atom)&lt;: AbstractVector{&lt;:Continuous}</code>) they are ordinary averages.  Probabilistic predictions are obtained by averaging the atomic probability distribution/mass functions; in particular, for regressors, the ensemble prediction on each input pattern has the type <code>MixtureModel{VF,VS,D}</code> from the Distributions.jl package, where <code>D</code> is the type of predicted distribution for <code>atom</code>.</p><p>Specify <code>acceleration=CPUProcesses()</code> for distributed computing, or <code>CPUThreads()</code> for multithreading.</p><p>If a single measure or non-empty vector of measures is specified by <code>out_of_bag_measure</code>, then out-of-bag estimates of performance are written to the training report (call <code>report</code> on the trained machine wrapping the ensemble model).</p><p><em>Important:</em> If per-observation or class weights <code>w</code> (not to be confused with atomic weights) are specified when constructing a machine for the ensemble model, as in <code>mach = machine(ensemble_model, X, y, w)</code>, then <code>w</code> is used by any measures specified in <code>out_of_bag_measure</code> that support them.</p></div><a class="docs-sourcelink" target="_blank" href="https://github.com/JuliaAI/MLJEnsembles.jl/blob/v0.4.2/src/ensembles.jl#L276-L329">source</a></section></article></article><nav class="docs-footer"><a class="docs-footer-prevpage" href="../target_transformations/">« Target Transformations</a><a class="docs-footer-nextpage" href="../correcting_class_imbalance/">Correcting Class Imbalance »</a><div class="flexbox-break"></div><p class="footer-message">Powered by <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> and the <a href="https://julialang.org/">Julia Programming Language</a>.</p></nav></div><div class="modal" id="documenter-settings"><div class="modal-background"></div><div class="modal-card"><header class="modal-card-head"><p class="modal-card-title">Settings</p><button class="delete"></button></header><section class="modal-card-body"><p><label class="label">Theme</label><div class="select"><select id="documenter-themepicker"><option value="auto">Automatic (OS)</option><option value="documenter-light">documenter-light</option><option value="documenter-dark">documenter-dark</option></select></div></p><hr/><p>This document was generated with <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a> version 1.4.1 on <span class="colophon-date" title="Monday 20 May 2024 09:15">Monday 20 May 2024</span>. Using Julia version 1.10.3.</p></section><footer class="modal-card-foot"></footer></div></div></div></body></html>