\section{K\+DE$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$ Class Template Reference} \label{classmlpack_1_1kde_1_1KDE}\index{K\+D\+E$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$@{K\+D\+E$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$}} The \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} class is a template class for performing Kernel Density Estimations. \subsection*{Public Types} \begin{DoxyCompactItemize} \item typedef Tree\+Type$<$ Metric\+Type, \textbf{ kde\+::\+K\+D\+E\+Stat}, Mat\+Type $>$ \textbf{ Tree} \begin{DoxyCompactList}\small\item\em Convenience typedef. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ K\+DE} (const double rel\+Error=\textbf{ K\+D\+E\+Default\+Params\+::rel\+Error}, const double abs\+Error=\textbf{ K\+D\+E\+Default\+Params\+::abs\+Error}, Kernel\+Type kernel=Kernel\+Type(), const \textbf{ K\+D\+E\+Mode} mode=\textbf{ K\+D\+E\+Default\+Params\+::mode}, Metric\+Type metric=Metric\+Type(), const bool monte\+Carlo=\textbf{ K\+D\+E\+Default\+Params\+::monte\+Carlo}, const double mc\+Prob=\textbf{ K\+D\+E\+Default\+Params\+::mc\+Prob}, const size\+\_\+t initial\+Sample\+Size=\textbf{ K\+D\+E\+Default\+Params\+::initial\+Sample\+Size}, const double mc\+Entry\+Coef=\textbf{ K\+D\+E\+Default\+Params\+::mc\+Entry\+Coef}, const double mc\+Break\+Coef=\textbf{ K\+D\+E\+Default\+Params\+::mc\+Break\+Coef}) \begin{DoxyCompactList}\small\item\em Initialize \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object using custom instantiated Metric and Kernel objects. \end{DoxyCompactList}\item \textbf{ K\+DE} (const \textbf{ K\+DE} \&other) \begin{DoxyCompactList}\small\item\em Construct \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object as a copy of the given model. \end{DoxyCompactList}\item \textbf{ K\+DE} (\textbf{ K\+DE} \&\&other) \begin{DoxyCompactList}\small\item\em Construct \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object taking ownership of the given model. \end{DoxyCompactList}\item \textbf{ $\sim$\+K\+DE} () \begin{DoxyCompactList}\small\item\em Destroy the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object. \end{DoxyCompactList}\item double \textbf{ Absolute\+Error} () const \begin{DoxyCompactList}\small\item\em Get absolute error tolerance. \end{DoxyCompactList}\item void \textbf{ Absolute\+Error} (const double new\+Error) \begin{DoxyCompactList}\small\item\em Modify absolute error tolerance (0 $<$= new\+Error). \end{DoxyCompactList}\item void \textbf{ Evaluate} (Mat\+Type query\+Set, arma\+::vec \&estimations) \begin{DoxyCompactList}\small\item\em Estimate density of each point in the query set given the data of the reference set. \end{DoxyCompactList}\item void \textbf{ Evaluate} (\textbf{ Tree} $\ast$query\+Tree, const std\+::vector$<$ size\+\_\+t $>$ \&old\+From\+New\+Queries, arma\+::vec \&estimations) \begin{DoxyCompactList}\small\item\em Estimate density of each point in the query set given the data of an already created query tree. \end{DoxyCompactList}\item void \textbf{ Evaluate} (arma\+::vec \&estimations) \begin{DoxyCompactList}\small\item\em Estimate density of each point in the reference set given the data of the reference set. \end{DoxyCompactList}\item bool \textbf{ Is\+Trained} () const \begin{DoxyCompactList}\small\item\em Check whether \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model is trained or not. \end{DoxyCompactList}\item const Kernel\+Type \& \textbf{ Kernel} () const \begin{DoxyCompactList}\small\item\em Get the kernel. \end{DoxyCompactList}\item Kernel\+Type \& \textbf{ Kernel} () \begin{DoxyCompactList}\small\item\em Modify the kernel. \end{DoxyCompactList}\item double \textbf{ M\+C\+Break\+Coef} () const \begin{DoxyCompactList}\small\item\em Get Monte Carlo break coefficient. \end{DoxyCompactList}\item void \textbf{ M\+C\+Break\+Coef} (const double new\+Coef) \begin{DoxyCompactList}\small\item\em Modify Monte Carlo break coefficient. (0 $<$ new\+Coef $<$= 1). \end{DoxyCompactList}\item double \textbf{ M\+C\+Entry\+Coef} () const \begin{DoxyCompactList}\small\item\em Get Monte Carlo entry coefficient. \end{DoxyCompactList}\item void \textbf{ M\+C\+Entry\+Coef} (const double new\+Coef) \begin{DoxyCompactList}\small\item\em Modify Monte Carlo entry coefficient. (new\+Coef $>$= 1). \end{DoxyCompactList}\item size\+\_\+t \textbf{ M\+C\+Initial\+Sample\+Size} () const \begin{DoxyCompactList}\small\item\em Get Monte Carlo initial sample size. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ M\+C\+Initial\+Sample\+Size} () \begin{DoxyCompactList}\small\item\em Modify Monte Carlo initial sample size. \end{DoxyCompactList}\item double \textbf{ M\+C\+Prob} () const \begin{DoxyCompactList}\small\item\em Get Monte Carlo probability of error being bounded by relative error. \end{DoxyCompactList}\item void \textbf{ M\+C\+Prob} (const double new\+Prob) \begin{DoxyCompactList}\small\item\em Modify Monte Carlo probability of error being bounded by relative error. \end{DoxyCompactList}\item const Metric\+Type \& \textbf{ Metric} () const \begin{DoxyCompactList}\small\item\em Get the metric. \end{DoxyCompactList}\item Metric\+Type \& \textbf{ Metric} () \begin{DoxyCompactList}\small\item\em Modify the metric. \end{DoxyCompactList}\item \textbf{ K\+D\+E\+Mode} \textbf{ Mode} () const \begin{DoxyCompactList}\small\item\em Get the mode of \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE}. \end{DoxyCompactList}\item \textbf{ K\+D\+E\+Mode} \& \textbf{ Mode} () \begin{DoxyCompactList}\small\item\em Modify the mode of \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE}. \end{DoxyCompactList}\item bool \textbf{ Monte\+Carlo} () const \begin{DoxyCompactList}\small\item\em Get whether Monte Carlo estimations are being used or not. \end{DoxyCompactList}\item bool \& \textbf{ Monte\+Carlo} () \begin{DoxyCompactList}\small\item\em Modify whether Monte Carlo estimations are being used or not. \end{DoxyCompactList}\item \textbf{ K\+DE} \& \textbf{ operator=} (\textbf{ K\+DE} other) \begin{DoxyCompactList}\small\item\em Copy a \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. \end{DoxyCompactList}\item bool \textbf{ Owns\+Reference\+Tree} () const \begin{DoxyCompactList}\small\item\em Check whether reference tree is owned by the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. \end{DoxyCompactList}\item \textbf{ Tree} $\ast$ \textbf{ Reference\+Tree} () \begin{DoxyCompactList}\small\item\em Get the reference tree. \end{DoxyCompactList}\item double \textbf{ Relative\+Error} () const \begin{DoxyCompactList}\small\item\em Get relative error tolerance. \end{DoxyCompactList}\item void \textbf{ Relative\+Error} (const double new\+Error) \begin{DoxyCompactList}\small\item\em Modify relative error tolerance (0 $<$= new\+Error $<$= 1). \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int version) \begin{DoxyCompactList}\small\item\em Serialize the model. \end{DoxyCompactList}\item void \textbf{ Train} (Mat\+Type reference\+Set) \begin{DoxyCompactList}\small\item\em Trains the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. \end{DoxyCompactList}\item void \textbf{ Train} (\textbf{ Tree} $\ast$reference\+Tree, std\+::vector$<$ size\+\_\+t $>$ $\ast$old\+From\+New\+References) \begin{DoxyCompactList}\small\item\em Trains the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Kernel\+Type = kernel\+::\+Gaussian\+Kernel, typename Metric\+Type = mlpack\+::metric\+::\+Euclidean\+Distance, typename Mat\+Type = arma\+::mat, template$<$ typename Tree\+Metric\+Type, typename Tree\+Stat\+Type, typename Tree\+Mat\+Type $>$ class Tree\+Type = tree\+::\+K\+D\+Tree, template$<$ typename Rule\+Type $>$ class Dual\+Tree\+Traversal\+Type = Tree\+Type$<$\+Metric\+Type, kde\+::\+K\+D\+E\+Stat, Mat\+Type$>$\+::template Dual\+Tree\+Traverser, template$<$ typename Rule\+Type $>$ class Single\+Tree\+Traversal\+Type = Tree\+Type$<$\+Metric\+Type, kde\+::\+K\+D\+E\+Stat, Mat\+Type$>$\+::template Single\+Tree\+Traverser$>$\newline class mlpack\+::kde\+::\+K\+D\+E$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$} The \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} class is a template class for performing Kernel Density Estimations. In statistics, kernel density estimation is a way to estimate the probability density function of a variable in a non parametric way. This implementation performs this estimation using a tree-\/independent dual-\/tree algorithm. Details about this algorithm are available in \doxyref{K\+D\+E\+Rules}{p.}{classmlpack_1_1kde_1_1KDERules}. \begin{DoxyTemplParams}{Template Parameters} {\em Kernel\+Type} & Kernel function to use for \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} calculations. \\ \hline {\em Metric\+Type} & Metric to use for \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} calculations. \\ \hline {\em Mat\+Type} & Type of data to use. \\ \hline {\em Tree\+Type} & Type of tree to use; must satisfy the Tree\+Type policy A\+PI. \\ \hline {\em Dual\+Tree\+Traversal\+Type} & Type of dual-\/tree traversal to use. \\ \hline {\em Single\+Tree\+Traversal\+Type} & Type of single-\/tree traversal to use. \\ \hline \end{DoxyTemplParams} Definition at line 88 of file kde.\+hpp. \subsection{Member Typedef Documentation} \mbox{\label{classmlpack_1_1kde_1_1KDE_a7ec73720d052fdfc84bb673625973f6c}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Tree@{Tree}} \index{Tree@{Tree}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Tree} {\footnotesize\ttfamily typedef Tree\+Type$<$Metric\+Type, \textbf{ kde\+::\+K\+D\+E\+Stat}, Mat\+Type$>$ \textbf{ Tree}} Convenience typedef. Definition at line 92 of file kde.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1kde_1_1KDE_a3b15ef11109a15007464af153c5cc27c}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!K\+DE@{K\+DE}} \index{K\+DE@{K\+DE}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{K\+D\+E()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily \textbf{ K\+DE} (\begin{DoxyParamCaption}\item[{const double}]{rel\+Error = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::rel\+Error}}, }\item[{const double}]{abs\+Error = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::abs\+Error}}, }\item[{Kernel\+Type}]{kernel = {\ttfamily KernelType()}, }\item[{const \textbf{ K\+D\+E\+Mode}}]{mode = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::mode}}, }\item[{Metric\+Type}]{metric = {\ttfamily MetricType()}, }\item[{const bool}]{monte\+Carlo = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::monte\+Carlo}}, }\item[{const double}]{mc\+Prob = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::mc\+Prob}}, }\item[{const size\+\_\+t}]{initial\+Sample\+Size = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::initial\+Sample\+Size}}, }\item[{const double}]{mc\+Entry\+Coef = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::mc\+Entry\+Coef}}, }\item[{const double}]{mc\+Break\+Coef = {\ttfamily \textbf{ K\+D\+E\+Default\+Params\+::mc\+Break\+Coef}} }\end{DoxyParamCaption})} Initialize \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object using custom instantiated Metric and Kernel objects. \begin{DoxyParams}{Parameters} {\em rel\+Error} & Relative error tolerance of the model. \\ \hline {\em abs\+Error} & Absolute error tolerance of the model. \\ \hline {\em kernel} & Instantiated kernel object. \\ \hline {\em mode} & Mode for the algorithm. \\ \hline {\em metric} & Instantiated metric object. \\ \hline {\em monte\+Carlo} & Whether to use Monte Carlo estimations when possible. \\ \hline {\em mc\+Prob} & Probability of a Monte Carlo estimation to be bounded by relative error tolerance. \\ \hline {\em initial\+Sample\+Size} & Initial sample size for Monte Carlo estimations. \\ \hline {\em mc\+Entry\+Coef} & Coefficient to control how much larger does the amount of node descendants has to be compared to the initial sample size in order for it to be a candidate for Monte Carlo estimations. \\ \hline {\em mc\+Break\+Coef} & Coefficient to control what fraction of the node\textquotesingle{}s descendants evaluated is the limit before Monte Carlo estimation recurses. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_a0c58cd0cc7015dd56f5a2fff80045d53}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!K\+DE@{K\+DE}} \index{K\+DE@{K\+DE}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{K\+D\+E()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily \textbf{ K\+DE} (\begin{DoxyParamCaption}\item[{const \textbf{ K\+DE}$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$ \&}]{other }\end{DoxyParamCaption})} Construct \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object as a copy of the given model. This may be computationally intensive! \begin{DoxyParams}{Parameters} {\em other} & \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object to copy. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_ad7c0a5538d2f6c9f71caf0eec9f5b217}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!K\+DE@{K\+DE}} \index{K\+DE@{K\+DE}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{K\+D\+E()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily \textbf{ K\+DE} (\begin{DoxyParamCaption}\item[{\textbf{ K\+DE}$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$ \&\&}]{other }\end{DoxyParamCaption})} Construct \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object taking ownership of the given model. \begin{DoxyParams}{Parameters} {\em other} & \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object to take ownership of. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_a5415f52db7dc45d65e7536750b5197bb}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!````~K\+DE@{$\sim$\+K\+DE}} \index{````~K\+DE@{$\sim$\+K\+DE}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{$\sim$\+K\+D\+E()} {\footnotesize\ttfamily $\sim$\textbf{ K\+DE} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Destroy the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} object. If this object created any trees, they will be deleted. If you created the trees then you have to delete them yourself. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1kde_1_1KDE_aca74512f13027b15d913461e55df3da2}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Absolute\+Error@{Absolute\+Error}} \index{Absolute\+Error@{Absolute\+Error}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Absolute\+Error()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Absolute\+Error (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get absolute error tolerance. Definition at line 245 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::abs\+Error. \mbox{\label{classmlpack_1_1kde_1_1KDE_acc3d1ceb7d9a4ad69d29438ab2cce83c}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Absolute\+Error@{Absolute\+Error}} \index{Absolute\+Error@{Absolute\+Error}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Absolute\+Error()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void Absolute\+Error (\begin{DoxyParamCaption}\item[{const double}]{new\+Error }\end{DoxyParamCaption})} Modify absolute error tolerance (0 $<$= new\+Error). \mbox{\label{classmlpack_1_1kde_1_1KDE_aa5b23d22f7d3de88a0de5eb74a0053b8}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily void Evaluate (\begin{DoxyParamCaption}\item[{Mat\+Type}]{query\+Set, }\item[{arma\+::vec \&}]{estimations }\end{DoxyParamCaption})} Estimate density of each point in the query set given the data of the reference set. The result is stored in an estimations vector. Estimations might not be normalized. \begin{DoxyItemize} \item Dimension of each point in the query set must match the dimension of each point in the reference set. \item Use std\+::move if the query set is no longer needed. \end{DoxyItemize} \begin{DoxyPrecond}{Precondition} The model has to be previously trained. \end{DoxyPrecond} \begin{DoxyParams}{Parameters} {\em query\+Set} & Set of query points to get the density of. \\ \hline {\em estimations} & Object which will hold the density of each query point. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_ac9b3a488ac370ad0a985098caa235e83}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily void Evaluate (\begin{DoxyParamCaption}\item[{\textbf{ Tree} $\ast$}]{query\+Tree, }\item[{const std\+::vector$<$ size\+\_\+t $>$ \&}]{old\+From\+New\+Queries, }\item[{arma\+::vec \&}]{estimations }\end{DoxyParamCaption})} Estimate density of each point in the query set given the data of an already created query tree. The result is stored in an estimations vector. Estimations might not be normalized. \begin{DoxyItemize} \item Dimension of each point in the query\+Tree dataset must match the dimension of each point in the reference set. \item Use std\+::move if the query tree is no longer needed. \end{DoxyItemize} \begin{DoxyPrecond}{Precondition} The model has to be previously trained and mode has to be dual-\/tree. \end{DoxyPrecond} \begin{DoxyParams}{Parameters} {\em query\+Tree} & Tree of query points to get the density of. \\ \hline {\em old\+From\+New\+Queries} & Mappings of query points to the tree dataset. \\ \hline {\em estimations} & Object which will hold the density of each query point. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_a995ae5cd93b97b9b96f4fb9b87c427c9}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily void Evaluate (\begin{DoxyParamCaption}\item[{arma\+::vec \&}]{estimations }\end{DoxyParamCaption})} Estimate density of each point in the reference set given the data of the reference set. It does not compute the estimation of a point with itself. The result is stored in an estimations vector. Estimations might not be normalized. \begin{DoxyPrecond}{Precondition} The model has to be previously trained. \end{DoxyPrecond} \begin{DoxyParams}{Parameters} {\em estimations} & Object which will hold the density of each reference point. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_a5270a78c5fedacf75d68a66d4d3f5ef8}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Is\+Trained@{Is\+Trained}} \index{Is\+Trained@{Is\+Trained}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Is\+Trained()} {\footnotesize\ttfamily bool Is\+Trained (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Check whether \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model is trained or not. Definition at line 254 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_a917492b75cc17298bc58c3d28e2944fb}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Kernel@{Kernel}} \index{Kernel@{Kernel}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Kernel()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const Kernel\+Type\& Kernel (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the kernel. Definition at line 224 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_ab8d1bedeac8344d80e50d819790a117a}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Kernel@{Kernel}} \index{Kernel@{Kernel}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Kernel()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Kernel\+Type\& Kernel (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the kernel. Definition at line 227 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_a383c3b24cdfe09c445bbac92c8f9d22a}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Break\+Coef@{M\+C\+Break\+Coef}} \index{M\+C\+Break\+Coef@{M\+C\+Break\+Coef}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Break\+Coef()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double M\+C\+Break\+Coef (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get Monte Carlo break coefficient. Definition at line 288 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::abs\+Error, K\+D\+E\+Default\+Params\+::initial\+Sample\+Size, K\+D\+E\+Default\+Params\+::mc\+Break\+Coef, K\+D\+E\+Default\+Params\+::mc\+Entry\+Coef, K\+D\+E\+Default\+Params\+::mc\+Prob, K\+D\+E\+Default\+Params\+::mode, K\+D\+E\+Default\+Params\+::monte\+Carlo, and K\+D\+E\+Default\+Params\+::rel\+Error. \mbox{\label{classmlpack_1_1kde_1_1KDE_af2cbea78691c295425eea5dd8b1a833e}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Break\+Coef@{M\+C\+Break\+Coef}} \index{M\+C\+Break\+Coef@{M\+C\+Break\+Coef}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Break\+Coef()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void M\+C\+Break\+Coef (\begin{DoxyParamCaption}\item[{const double}]{new\+Coef }\end{DoxyParamCaption})} Modify Monte Carlo break coefficient. (0 $<$ new\+Coef $<$= 1). \mbox{\label{classmlpack_1_1kde_1_1KDE_a1b5eaa65ee1fb8956638afd7df76d32d}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Entry\+Coef@{M\+C\+Entry\+Coef}} \index{M\+C\+Entry\+Coef@{M\+C\+Entry\+Coef}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Entry\+Coef()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double M\+C\+Entry\+Coef (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get Monte Carlo entry coefficient. Definition at line 282 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::mc\+Entry\+Coef. \mbox{\label{classmlpack_1_1kde_1_1KDE_aaf327103b86180c1982ca8ef79aefee5}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Entry\+Coef@{M\+C\+Entry\+Coef}} \index{M\+C\+Entry\+Coef@{M\+C\+Entry\+Coef}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Entry\+Coef()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void M\+C\+Entry\+Coef (\begin{DoxyParamCaption}\item[{const double}]{new\+Coef }\end{DoxyParamCaption})} Modify Monte Carlo entry coefficient. (new\+Coef $>$= 1). \mbox{\label{classmlpack_1_1kde_1_1KDE_a9c03312f8ff7dec25f32ba59dac70881}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Initial\+Sample\+Size@{M\+C\+Initial\+Sample\+Size}} \index{M\+C\+Initial\+Sample\+Size@{M\+C\+Initial\+Sample\+Size}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Initial\+Sample\+Size()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t M\+C\+Initial\+Sample\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get Monte Carlo initial sample size. Definition at line 276 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::initial\+Sample\+Size. \mbox{\label{classmlpack_1_1kde_1_1KDE_a2b8c45e6258f5219a2a956d656674d9c}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Initial\+Sample\+Size@{M\+C\+Initial\+Sample\+Size}} \index{M\+C\+Initial\+Sample\+Size@{M\+C\+Initial\+Sample\+Size}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Initial\+Sample\+Size()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& M\+C\+Initial\+Sample\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify Monte Carlo initial sample size. Definition at line 279 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::initial\+Sample\+Size. \mbox{\label{classmlpack_1_1kde_1_1KDE_a43aaa23d2540a3ea399bec8731b7417b}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Prob@{M\+C\+Prob}} \index{M\+C\+Prob@{M\+C\+Prob}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Prob()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double M\+C\+Prob (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get Monte Carlo probability of error being bounded by relative error. Definition at line 269 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::mc\+Prob. \mbox{\label{classmlpack_1_1kde_1_1KDE_a1f0423027203dc7cfec12ce5da60becd}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!M\+C\+Prob@{M\+C\+Prob}} \index{M\+C\+Prob@{M\+C\+Prob}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{M\+C\+Prob()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void M\+C\+Prob (\begin{DoxyParamCaption}\item[{const double}]{new\+Prob }\end{DoxyParamCaption})} Modify Monte Carlo probability of error being bounded by relative error. (0 $<$= new\+Prob $<$ 1). \mbox{\label{classmlpack_1_1kde_1_1KDE_aac4d643c62af7d9cc2a072aea10d2b32}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Metric@{Metric}} \index{Metric@{Metric}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Metric()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const Metric\+Type\& Metric (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the metric. Definition at line 230 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_acc71d930ed90e73b2bc0c360835c5371}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Metric@{Metric}} \index{Metric@{Metric}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Metric()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Metric\+Type\& Metric (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the metric. Definition at line 233 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_a6f3cb532b850ad02807a209193ff2289}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Mode@{Mode}} \index{Mode@{Mode}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Mode()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily \textbf{ K\+D\+E\+Mode} Mode (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the mode of \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE}. Definition at line 257 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::mode. \mbox{\label{classmlpack_1_1kde_1_1KDE_a94b40037a0d33cbb55823d5c36d677a7}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Mode@{Mode}} \index{Mode@{Mode}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Mode()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily \textbf{ K\+D\+E\+Mode}\& Mode (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the mode of \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE}. Definition at line 260 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::mode. \mbox{\label{classmlpack_1_1kde_1_1KDE_aa7ca7b5a3a96b5603461debdc82f3c3e}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Monte\+Carlo@{Monte\+Carlo}} \index{Monte\+Carlo@{Monte\+Carlo}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Monte\+Carlo()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Monte\+Carlo (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get whether Monte Carlo estimations are being used or not. Definition at line 263 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::monte\+Carlo. \mbox{\label{classmlpack_1_1kde_1_1KDE_ab9f78566bfa14c2a766ef00c898a55d4}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Monte\+Carlo@{Monte\+Carlo}} \index{Monte\+Carlo@{Monte\+Carlo}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Monte\+Carlo()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Monte\+Carlo (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify whether Monte Carlo estimations are being used or not. Definition at line 266 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::monte\+Carlo. \mbox{\label{classmlpack_1_1kde_1_1KDE_a05e5342f7a11707643392ffdc0c268f6}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!operator=@{operator=}} \index{operator=@{operator=}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{operator=()} {\footnotesize\ttfamily \textbf{ K\+DE}\& operator= (\begin{DoxyParamCaption}\item[{\textbf{ K\+DE}$<$ Kernel\+Type, Metric\+Type, Mat\+Type, Tree\+Type, Dual\+Tree\+Traversal\+Type, Single\+Tree\+Traversal\+Type $>$}]{other }\end{DoxyParamCaption})} Copy a \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. Use std\+::move if the object to copy is no longer needed. \begin{DoxyParams}{Parameters} {\em other} & \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model to copy. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_a4c5662e0d098ea1e60da85efa93ad561}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Owns\+Reference\+Tree@{Owns\+Reference\+Tree}} \index{Owns\+Reference\+Tree@{Owns\+Reference\+Tree}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Owns\+Reference\+Tree()} {\footnotesize\ttfamily bool Owns\+Reference\+Tree (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Check whether reference tree is owned by the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. Definition at line 251 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_a92cb2297c084f56afea6f37e3c894f52}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Reference\+Tree@{Reference\+Tree}} \index{Reference\+Tree@{Reference\+Tree}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Reference\+Tree()} {\footnotesize\ttfamily \textbf{ Tree}$\ast$ Reference\+Tree (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get the reference tree. Definition at line 236 of file kde.\+hpp. \mbox{\label{classmlpack_1_1kde_1_1KDE_a2cd3d49a6dcafe980d0734421d296828}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Relative\+Error@{Relative\+Error}} \index{Relative\+Error@{Relative\+Error}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Relative\+Error()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Relative\+Error (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get relative error tolerance. Definition at line 239 of file kde.\+hpp. References K\+D\+E\+Default\+Params\+::rel\+Error. \mbox{\label{classmlpack_1_1kde_1_1KDE_a3f0da520dc2a015ceb086eb09e5c3bc2}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Relative\+Error@{Relative\+Error}} \index{Relative\+Error@{Relative\+Error}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Relative\+Error()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void Relative\+Error (\begin{DoxyParamCaption}\item[{const double}]{new\+Error }\end{DoxyParamCaption})} Modify relative error tolerance (0 $<$= new\+Error $<$= 1). \mbox{\label{classmlpack_1_1kde_1_1KDE_a68e832cb064e3b7ca978d8e5911cf700}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned int}]{version }\end{DoxyParamCaption})} Serialize the model. \mbox{\label{classmlpack_1_1kde_1_1KDE_a27ba39af83e3cb01f2e6fbec159adf0e}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Train@{Train}} \index{Train@{Train}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Train()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily void Train (\begin{DoxyParamCaption}\item[{Mat\+Type}]{reference\+Set }\end{DoxyParamCaption})} Trains the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. It builds a tree using a reference set. Use std\+::move if the reference set is no longer needed. \begin{DoxyParams}{Parameters} {\em reference\+Set} & Set of reference data. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1kde_1_1KDE_af96057bbfd77c3ba7bcdf9ebcd70d7d4}} \index{mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}!Train@{Train}} \index{Train@{Train}!mlpack\+::kde\+::\+K\+DE@{mlpack\+::kde\+::\+K\+DE}} \subsubsection{Train()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void Train (\begin{DoxyParamCaption}\item[{\textbf{ Tree} $\ast$}]{reference\+Tree, }\item[{std\+::vector$<$ size\+\_\+t $>$ $\ast$}]{old\+From\+New\+References }\end{DoxyParamCaption})} Trains the \doxyref{K\+DE}{p.}{classmlpack_1_1kde_1_1KDE} model. Sets the reference tree to an already created tree. \begin{DoxyItemize} \item If Tree\+Traits$<$\+Tree\+Type$>$\+::\+Rearranges\+Dataset is false then it is possible to use an empty old\+From\+New\+References vector. \end{DoxyItemize} \begin{DoxyParams}{Parameters} {\em reference\+Tree} & Built reference tree. \\ \hline {\em old\+From\+New\+References} & Permutations of reference points obtained during tree generation. \\ \hline \end{DoxyParams} The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/git/src/mlpack/methods/kde/\textbf{ kde.\+hpp}\end{DoxyCompactItemize}