Create a biplot of the first three principal component coefficients, the observations, and the observed variables for the carsmall data set.

Load the sample data.

load carsmall

Create a matrix consisting of the variables Acceleration, Displacement, Horsepower, MPG, and Weight. Delete rows in the matrix that have missing values.

X = [Acceleration Displacement Horsepower MPG Weight];
X = rmmissing(X);

Standardize X and perform a principal component analysis.

Z = zscore(X); % Standardized data
[coefs,score] = pca(Z);

The 5-by-5 matrix coefs contains the principal component coefficients (one column for each principal component). The matrix score contains the principal component scores (the observations).

Create a biplot of the first three principal component coefficients. The axes of the biplot represent the columns of coefs, and the vectors in the biplot represent the rows of coefs.

biplot(coefs(:,1:3))

Create a more detailed biplot by labeling each variable and plotting the observations in the space of the first three principal components.

vbls = {'Accel','Disp','HP','MPG','Wgt'}; % Labels for the variables
biplot(coefs(:,1:3),'Scores',score(:,1:3),'VarLabels',vbls);

Load the fisheriris data set, standardize the flower measurements in meas, and perform a principal component analysis.

load fisheriris
Z = zscore(meas);
[coefs,scores] = pca(Z);

Create a figure with two subplots and return the Axes objects as ax1 and ax2. Create a biplot in each set of axes by referring to the corresponding Axes object. In the top subplot, display a biplot using the first two principal components. In the bottom subplot, display a biplot using the third and fourth principal components. Specify the x-axis and y-axis limits by passing the corresponding Axes objects to the xlim and ylim functions. Change the x-axis and y-axis labels in the bottom plot by passing ax2 to xlabel and ylabel.

figure('Units','normalized','Position',[0.3 0.3 0.3 0.5])
variables = {'SepalLength','SepalWidth','PetalLength','PetalWidth'};
ax1 = subplot(2,1,1); % Top subplot
biplot(ax1,coefs(:,1:2),'Scores',scores(:,1:2),'VarLabels',variables);
xlim(ax1,[-1 1])
ylim(ax1,[-1 1])

ax2 = subplot(2,1,2); % Bottom subplot
biplot(ax2,coefs(:,3:4),'Scores',scores(:,3:4),'VarLabels',variables);
xlim(ax2,[-1 1])
ylim(ax2,[-1 1])
xlabel(ax2,'Component 3')
ylabel(ax2,'Component 4')

Control the appearance of a biplot by specifying supported line property names and values, and by using handles to the graphics objects created by biplot.

Load the sample data.

load carsmall

Create a matrix consisting of the variables Acceleration, Displacement, and MPG. Delete rows in the matrix that have missing values.

X = [Acceleration Displacement MPG];
X = rmmissing(X);

Standardize X and perform a principal component analysis.

Z = zscore(X); % Standardized data
[coefs,score] = pca(Z);

The 3-by-3 matrix coefs contains the principal component coefficients (one column for each principal component). The matrix score contains the principal component scores (the observations).

Create a biplot of the observations in the space of the first two principal components. Use the default properties for the biplot.

h = biplot(coefs(:,1:2),'Scores',score(:,1:2));

h is a vector of handles to graphics objects. You can modify the properties of the line objects returned by biplot.

Label the three variables for easy identification. Specify circles as the marker symbol and blue as the line color for all line objects.

vbls = {'Accel','Disp','MPG'}; % Array of variable labels
h1 = biplot(coefs(:,1:2),'Scores',score(:,1:2),...
    'Color','b','Marker','o','VarLabels',vbls);

h1 is a vector of handles to graphics objects. View the first few elements of h1.

h1(1:10) % First ten object handles

ans = 
  10x1 graphics array:

  Line    (varline)
  Line    (varline)
  Line    (varline)
  Line    (varmarker)
  Line    (varmarker)
  Line    (varmarker)
  Text    (varlabel)
  Text    (varlabel)
  Text    (varlabel)
  Line    (obsmarker)

The handles for the variable labels (h1(7:9)) are text. Therefore, the settings specified for the line properties do not affect these labels.

Create another biplot of the observations in the space of the first two principal components, and label the three variables for easy identification.

h2 = biplot(coefs(:,1:2),'Scores',score(:,1:2),'VarLabels',vbls);

h2 is a vector of handles to graphics objects. View the first few elements of h2.

h2(1:10) % First ten object handles

ans = 
  10x1 graphics array:

  Line    (varline)
  Line    (varline)
  Line    (varline)
  Line    (varmarker)
  Line    (varmarker)
  Line    (varmarker)
  Text    (varlabel)
  Text    (varlabel)
  Text    (varlabel)
  Line    (obsmarker)

h2 contains 104 object handles.

Modify specific properties of the biplot by using handles to the graphics objects.

Change the line color of the variables (vectors).

for k = 1:3
    h2(k).Color = 'r'; % Specify red as the line color
end

Modify the font of the variable labels.

for k = 7:9
    h2(k).FontWeight = 'bold';  % Specify bold font
end

Change the color of the observation markers.

for k = 10:103
    h2(k).MarkerEdgeColor = 'k';  % Specify black color for the observations
end