Create a scatter plot matrix in Scilab
Abstract
In this page, we present a function to create a scatter plot matrix in Scilab.
Introduction
According to NIST [1], "given a set of variables X1, X2, ... , Xk, the scatter plot matrix contains all the pairwise scatter plots of the variables on a single page in a matrix format. That is, if there are k variables, the scatter plot matrix will have k rows and k columns and the ith row and jth column of this matrix is a plot of Xi versus Xj."
This feature is available from the "plotmatrix" function in Stixbox, v2.2. To install it, please use
atomsInstall('stixbox')
and restart Scilab.
The scripts are also available in attachement :
Scatter plot matrix
The function scattermatrix creates a scatter plot matrix. It has the calling sequence:
scattermatrix(x)
where x is a n-by-ninput matrix of doubles. Here, ninput is the number of input parameters and n is the number of experiments.
Here is the simplest example of scattermatrix. We have a model with 3 inputs and 3 outputs. We are interested in the scatter plot matrix of the outputs y1, y2, y3.
m=1000; x1=grand(m,1,"def"); x2=grand(m,1,"def"); x3=grand(m,1,"def"); y1=2*x1.*x2+x3; y2=-3*x1+x2.^2-2*x3; y3=sin(x1)-3*x2+3*x3; y=[y1,y2,y3]; // ylabels=["Y1","Y2","Y3"]; // No labels scattermatrix(y);
It is straightforward to add labels:
// With labels scattermatrix(y,"xlabels",ylabels);
We can also replace the empty diagonal with an histogram.
// With the histogram scattermatrix(y,"histogram",%t);
Scatter matrix X vs Y
The function scattermatrixXY plots the dependencies between Y and X in a model.
The script:
m=1000; x1=grand(m,1,"def"); x2=grand(m,1,"def"); x3=grand(m,1,"def"); y1=2*x1.*x2+x3; y2=-3*x1+x2.^2-2*x3; y3=sin(x1)-3*x2+3*x3; x=[x1,x2,x3]; y=[y1,y2,y3]; // xlabels=["X1","X2","X3"]; ylabels=["Y1","Y2","Y3"]; // No labels scattermatrixXY(x,y);
produces:
This is perhaps clearer with labels.
// With labels scattermatrixXY(x,y,"xlabels",xlabels,"ylabels",ylabels);
We can customize various settings, including the labels, the dot symbol and the size of the point.
References
Author: Michaƫl Baudin, 2013