confusionchart

Create confusion matrix chart for classification problem

Syntax

confusionchart(trueLabels,predictedLabels)

confusionchart(m)

confusionchart(m,classLabels)

confusionchart(parent,___)

confusionchart(___,Name,Value)

cm = confusionchart(___)

Description

confusionchart(trueLabels,predictedLabels) creates a confusion matrix chart from true labels trueLabels and predicted labels predictedLabels and returns a ConfusionMatrixChart object. The rows of the confusion matrix correspond to the true class and the columns correspond to the predicted class. Diagonal and off-diagonal cells correspond to correctly and incorrectly classified observations, respectively. Use cm to modify the confusion matrix chart after it is created. For a list of properties, see ConfusionMatrixChart Properties.

confusionchart(m) creates a confusion matrix chart from the numeric confusion matrix m. Use this syntax if you already have a numeric confusion matrix in the workspace.

confusionchart(m,classLabels) specifies class labels that appear along the x-axis and y-axis. Use this syntax if you already have a numeric confusion matrix and class labels in the workspace.

confusionchart(parent,___) creates the confusion chart in the figure, panel, or tab specified by parent.

confusionchart(___,Name,Value) specifies additional ConfusionMatrixChart properties using one or more name-value pair arguments. Specify the properties after all other input arguments. For a list of properties, see ConfusionMatrixChart Properties.

cm = confusionchart(___) returns the ConfusionMatrixChart object. Use cm to modify properties of the chart after creating it. For a list of properties, see ConfusionMatrixChart Properties.

Examples

Create Confusion Matrix Chart

Load a sample of predicted and true labels for a classification problem. trueLabels is the true labels for an image classification problem and predictedLabels is the predictions of a convolutional neural network.

load('Cifar10Labels.mat','trueLabels','predictedLabels');

Create a confusion matrix chart.

figure
cm = confusionchart(trueLabels,predictedLabels);

Modify the appearance and behavior of the confusion matrix chart by changing property values. Add column and row summaries and a title. A column-normalized column summary displays the number of correctly and incorrectly classified observations for each predicted class as percentages of the number of observations of the corresponding predicted class. A row-normalized row summary displays the number of correctly and incorrectly classified observations for each true class as percentages of the number of observations of the corresponding true class.

cm.ColumnSummary = 'column-normalized';
cm.RowSummary = 'row-normalized';
cm.Title = 'CIFAR-10 Confusion Matrix';

Create Confusion Matrix Chart from Numeric Confusion Matrix

You can use confusionchart to create a confusion matrix chart from a numeric confusion matrix.

Load a sample confusion matrix m and the associated class labels classLabels.

load('Cifar10ConfusionMat.mat','m','classLabels');
m

m = 10×10

   923     4    21     8     4     1     5     5    23     6
     5   972     2     0     0     0     0     1     5    15
    26     2   892    30    13     8    17     5     4     3
    12     4    32   826    24    48    30    12     5     7
     5     1    28    24   898    13    14    14     2     1
     7     2    28   111    18   801    13    17     0     3
     5     0    16    27     3     4   943     1     1     0
     9     1    14    13    22    17     3   915     2     4
    37    10     4     4     0     1     2     1   931    10
    20    39     3     3     0     0     2     1     9   923

classLabels

classLabels = 10×1 categorical
     airplane 
     automobile 
     bird 
     cat 
     deer 
     dog 
     frog 
     horse 
     ship 
     truck 

Create a confusion matrix chart from the numeric confusion matrix and the class labels.

cm = confusionchart(m,classLabels);

Sort Classes by Precision or Recall

Load a sample of predicted and true labels for a classification problem. trueLabels are the true labels for an image classification problem and predictedLabels are the predictions of a convolutional neural network. Create a confusion matrix chart with column and row summaries.

load('Cifar10Labels.mat','trueLabels','predictedLabels');
figure
cm = confusionchart(trueLabels,predictedLabels, ...
    'ColumnSummary','column-normalized', ...
    'RowSummary','row-normalized');

To sort the classes of the confusion matrix by class-wise recall (true positive rate), normalize the cell values across each row, that is, by the number of observations that have the same true class. Sort the classes by the corresponding diagonal cell values and reset the normalization of the cell values. The classes are now sorted such that the percentages in the blue cells in the row summaries to the right are decreasing.

cm.Normalization = 'row-normalized';
sortClasses(cm,'descending-diagonal');
cm.Normalization = 'absolute';

To sort the classes by class-wise precision (positive predictive value), normalize the cell values across each column, that is, by the number of observations that have the same predicted class. Sort the classes by the corresponding diagonal cell values and reset the normalization of the cell values. The classes are now sorted such that the percentages in the blue cells in the column summaries at the bottom are decreasing.

cm.Normalization = 'column-normalized';
sortClasses(cm,'descending-diagonal');
cm.Normalization = 'absolute';

Input Arguments

trueLabels — True labels of classification problem

categorical vector | numeric vector | string vector | character array | cell array of character vectors | logical vector

True labels of classification problem, specified as a categorical vector, numeric vector, string vector, character array, cell array of character vectors, or logical vector. If trueLabels is a vector, then each element corresponds to one observation. If trueLabels is a character array, then it must be two-dimensional with each row corresponding to the label of one observation.

predictedLabels — Predicted labels of classification problem

categorical vector | numeric vector | string vector | character array | cell array of character vectors | logical vector

Predicted labels of classification problem, specified as a categorical vector, numeric vector, string vector, character array, cell array of character vectors, or logical vector. If predictedLabels is a vector, then each element corresponds to one observation. If predictedLabels is a character array, then it must be two-dimensional with each row corresponding to the label of one observation.

m — Confusion matrix

matrix

Confusion matrix, specified as a matrix. m must be square and its elements must be positive integers. The element m(i,j) is the number of times an observation of the ith true class was predicted to be of the jth class. Each colored cell of the confusion matrix chart corresponds to one element of the confusion matrix m.

classLabels — Class labels

categorical vector | numeric vector | string vector | character array | cell array of character vectors | logical vector

Class labels of the confusion matrix chart, specified as a categorical vector, numeric vector, string vector, character array, cell array of character vectors, or logical vector. If classLabels is a vector, then it must have the same number of elements as the confusion matrix has rows and columns. If classLabels is a character array, then it must be two-dimensional with each row corresponding to the label of one class.

parent — Parent container

Figure object | Panel object | Tab object | TiledChartLayout object | GridLayout object

Parent container, specified as a Figure, Panel, Tab, TiledChartLayout, or GridLayout object.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: cm = confusionchart(trueLabels,predictedLabels,'Title','My Title Text','ColumnSummary','column-normalized')

Note

The properties listed here are only a subset. For a complete list, see ConfusionMatrixChart Properties.

Title — Title

'' (default) | character vector | string scalar

Title of the confusion matrix chart, specified as a character vector or string scalar.

Example: cm = confusionchart(__,'Title','My Title Text')

Example: cm.Title = 'My Title Text'

ColumnSummary — Column summary

'off' (default) | 'absolute' | 'column-normalized' | 'total-normalized'

Column summary of the confusion matrix chart, specified as one of the following:

Option	Description
'off'	Do not display a column summary.
'absolute'	Display the total number of correctly and incorrectly classified observations for each predicted class.
'column-normalized'	Display the number of correctly and incorrectly classified observations for each predicted class as percentages of the number of observations of the corresponding predicted class. The percentages of correctly classified observations can be thought of as class-wise precisions (or positive predictive values).
'total-normalized'	Display the number of correctly and incorrectly classified observations for each predicted class as percentages of the total number of observations.

Example: cm = confusionchart(__,'ColumnSummary','column-normalized')

Example: cm.ColumnSummary = 'column-normalized'

RowSummary — Row summary

'off' (default) | 'absolute' | 'row-normalized' | 'total-normalized'

Row summary of the confusion matrix chart, specified as one of the following:

Option	Description
'off'	Do not display a row summary.
'absolute'	Display the total number of correctly and incorrectly classified observations for each true class.
'row-normalized'	Display the number of correctly and incorrectly classified observations for each true class as percentages of the number of observations of the corresponding true class. The percentages of correctly classified observations can be thought of as class-wise recalls (or true positive rates).
'total-normalized'	Display the number of correctly and incorrectly classified observations for each true class as percentages of the total number of observations.

Example: cm = confusionchart(__,'RowSummary','row-normalized')

Example: cm.RowSummary = 'row-normalized'

Normalization — Normalization of cell values

'absolute' (default) | 'column-normalized' | 'row-normalized' | 'total-normalized'

Normalization of cell values, specified as one of the following:

Option	Description
'absolute'	Display the total number of observations in each cell.
'column-normalized'	Normalize each cell value by the number of observations that has the same predicted class.
'row-normalized'	Normalize each cell value by the number of observations that has the same true class.
'total-normalized'	Normalize each cell value by the total number of observations.

Modifying the normalization of cell values also affects the colors of the cells.

Example: cm = confusionchart(__,'Normalization','total-normalized')

Example: cm.Normalization = 'total-normalized'

Output Arguments

cm — Confusion matrix chart object

ConfusionMatrixChart object

ConfusionMatrixChart object, which is a standalone visualization. Use cm to set properties of the confusion matrix chart after creating it.

Limitations

• MATLAB^® code generation is not supported for ConfusionMatrixChart objects.

More About

Standalone Visualization

A standalone visualization is a chart designed for a special purpose that works independently from other charts. Unlike other charts such as plot and surf, a standalone visualization has a preconfigured axes object built into it, and some customizations are not available. A standalone visualization also has these characteristics:

• It cannot be combined with other graphics elements, such as lines, patches, or surfaces. Thus, the hold command is not supported.

• The gca function can return the chart object as the current axes.

• You can pass the chart object to many MATLAB functions that accept an axes object as an input argument. For example, you can pass the chart object to the title function.

Tips

• If you have one-hot (one-of-N) data, use onehotdecode to prepare your data for use with confusionchart. For example, suppose you have true labels targets and predicted labels outputs, with observations in columns. You can create a confusion matrix chart using

  numClasses = size(targets,1);
  trueLabels = onehotdecode(targets,1:numClasses,1);
  predictedLabels = onehotdecode(outputs,1:numClasses,1);
  confusionchart(trueLabels,predictedLabels)

• If you have Statistics and Machine Learning Toolbox™, you can create a confusion matrix chart for tall arrays. For details, see confusionchart (Statistics and Machine Learning Toolbox) and Confusion Matrix for Classification Using Tall Arrays (Statistics and Machine Learning Toolbox).

Version History

Introduced in R2018b

R2025a: Customize confusion chart display

You can now customize the titles and labels of ConfusionMatrixChart objects:

• Specify labels for the row (y-axis) and column (x-axis) values using the RowDisplayLabels and ColumnDisplayLabels properties.

• Interpret text labels, such as titles and axis labels, with TeX markup, LaTeX markup, or no markup using the Interpreter property.

  Before R2025a: All confusion charts have the interpreter set to 'tex' for title and axis labels and 'none' for tick labels.

• Display labels for the true positive rate (TPR), false negative rate (FNR), positive predictive value (PPV), and false discovery rate (FDR) on the row and column summaries using the SummaryLabelsVisible property.