4

please help me out to draw this type of mindmap in latex. I have done learning forest but i did not get my output.

mind map]

i have found buble type output. i am using miktex with texlipse.

9

I got the output which I wanted finally - almost there. By the way, thank you all of you for your help.

Output

enter image description here

\documentclass[border=10pt,multi,tikz]{standalone}
\usetikzlibrary{shapes.geometric}
\begin{document}

\tikzset{
treenode/.style = {draw,ellipse, align=left,
                 top color=white, bottom color=blue!20},
root/.style     = {treenode, font=\large, bottom color=white},
env/.style      = {treenode, font=\ttfamily\normalsize},
dummy/.style    = {circle,draw}
}
\begin{tikzpicture}
[  
 level 1/.style={ edge from parent path={
        (\tikzparentnode) to[out=0, in=180] (\tikzchildnode)
        -- (\tikzchildnode)
    },},
level 2/.style={minimum width=200pt, edge from parent path={
        (\tikzparentnode.east) to[out=0, in=180] (\tikzchildnode.south west)
        -- (\tikzchildnode.south east)
    },
    sibling distance=0.6cm},
level 1/.append style={level distance=4.5cm},
level 2/.append style={level distance=6.5cm},
%edge from parent/.style = {draw, -latex},
%every node/.style       = {font=\footnotesize},
sloped,
     ]

 \node [root] {Algorithm}
[grow=right]
  child [sibling distance=4.0cm] { node{Clustering} 
            child { node  {k-Means}}
            child { node  {k-Medians}}
            child { node  {Expectation Maximisation (EM)}}
            child { node  {Hierarchical Clustering}}
           }
child [sibling distance=4.5cm] { node {Bayesian}
            child { node  {Naive Bayes}}
            child { node  {Gaussian Naive Bayes}}
            child { node  {Multinomial Naive Bayes}}
            child { node  {Averaged One-Depen. Esti. (AODE)}}
            child { node  {Bayesian Belief Network (BBN)}}
            child { node  {Bayesian Network (BN)}}
           }
 child [sibling distance=0.5cm] { node {Decision Tree}
            child { node  {Classification and Regression Tree (CART)}}
            child { node  {Iterative Dichotomiser 3 (ID3)}}
            child { node  {C4.5 and C5.0}} 
            child { node  {Chi-squared Auto.Inte. Det. (CHAID)}}
            child { node  {Decision Stump}}
            child { node  {M5}}
            child { node  {Conditional Decision Trees}}
           } 
 child [sibling distance=5.5cm]{ node {Dimesionality Reduction}
            child { node  {[Principal Component Analysis (PCA)}}
            child { node  {Principal Component Regression (PCR)}}
            child { node  {Partial Least Squares Regression\\(PLSR)}}
            child { node  {Sammon Mapping}}
            child { node  {Multidimensional Scaling (MDS)}}
            child { node  {Projection Pursuit}}
            child { node  {Linear Discriminant Analysis (LDA)}}
            child { node  {Mixture Discriminant Analysis (MDA)}}
            child { node  {Quadratic Discriminant Analysis (QDA)}}
            child { node  {Flexible Discriminant Analysis (FDA)}}
           }               
 child [sibling distance=5.cm] { node  {Regularisation}
            child { node  {Ridge Regression}}
            child { node  {Least Abs. Shr. and Sel. Ope. (LASSO)}}
            child { node  {Elastic Net}}
            child { node  {Least-Angle Regression (LARS)}}
           };               
\tikzset{
level 1/.style={ edge from parent path={
        (\tikzparentnode) to[out=180, in=0] (\tikzchildnode)
        -- (\tikzchildnode)
    }},
level 2/.style={minimum width=200pt,align=left, edge from parent path={
        (\tikzparentnode) to[out=180, in=0] (\tikzchildnode.south east)
        -- (\tikzchildnode.south west)
    },
    sibling distance=0.6cm},
level 1/.append style={level distance=4.5cm},
level 2/.append style={level distance=5.5cm},
%edge from parent/.style = {draw, -latex},
%every node/.style       = {font=\footnotesize},
sloped,
     }
  \node [root]{Algorithm}
 [grow=left]
 child [sibling distance=3.1cm]{ node{Deep Learning} 
            child { node  {Deep Boltzmann Machine (DBM)}}
            child { node  {Deep Belief Network (DBN)}}
            child { node  {Convolutional Neural Network (CNN)}}
            child { node  {Stacked Auto-Encoders}}
           }
   child [sibling distance=2.8cm]{ node {Ensamble}
            child { node  {Boosting}}
            child { node  {Bootstrapped Aggregation (Bagging)}}
            child { node  {AdaBoost}}
            child { node  {Stacked Generalization (blending)}}
            child { node  {Gradient Boosting Machines (GBM)}}
            child { node  {Gradient Boosted Regr. Trees (GBRT)}}
            child { node  {Random Forest}}
           }
    child { node{Neural Networks} 
            child { node  {Perceptron}}
            child { node  {Back-Propagation}}
            child { node  {Hopfield Network}}
            child { node  {Radial Basis Function Net. (RBFN)}}
           }
   child[sibling distance=3.9cm] { node {Insatnce Based}
           child { node  {k-Nearest Neighbour(KNN)}}
           child { node  {Learning vector quantization(LVQ)}}             
           child { node  {self-organised map}}
           child { node  {Locally Weighted Learning(LWL)}}
           }
  child[sibling distance=3.2cm] { node {Rule system}
           child { node  {Cubist}}
           child { node  {One Rule (OneR)}}             
           child { node  {Zero Rule (ZeroR)}}
           child { node  {Rep.Inc.Pr2pro. Err. Red. (RIPPER)}}
           }                            
  child [sibling distance=3.3cm]{ node  {Regression}
            child { node  {Linear}}
            child { node  {Ordinary Least Squares}}
            child { node  {Logistic}}
            child { node  {Stepwise}}
            child { node  {Locally Esti.Scatt. Smoo.(LOESS)}}
            child { node  {Multi. Ada. Reg.Splines (MARS)}} 
            };
 \end{tikzpicture}
\end{document}

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.