predict

Predict labels using classification XGBoost model

Since R2026a

Syntax

labels = predict(mdl,X)

labels = predict(mdl,X,UseParallel=UseParallel)

[labels,scores] = predict(___)

Description

labels = predict(mdl,X) returns a vector of predicted class labels for the predictor data in the table or matrix X, based on the pretrained XGBoost classification model mdl.

labels = predict(mdl,X,UseParallel=UseParallel) specifies whether to perform computations in parallel.

[labels,scores] = predict(___) also returns a matrix of classification scores indicating the likelihood that a label comes from a particular class, using any of the input argument combinations in the previous syntaxes. For each observation in X, the predicted class label corresponds to the maximum score among all classes.

Examples

Predict Multiclass Labels Using XGBoost Model

Import a pretrained XGBoost multiclass classification model trained using the NLP dataset with 13 classes. The pretrained model is provided with this example.

The model was trained in Python and saved as a json file using model.save_model('trainedMulticlassXGBoostModel.json').

load nlpdata
modelfile = "trainedMulticlassXGBoostModel.json";
Mdl = importModelFromXGBoost(modelfile)

Mdl = 
  CompactClassificationXGBoost
               ResponseName: 'Y'
                 ClassNames: [0 1 2 3 4 5 6 7 8 9 10 11 12]
             ScoreTransform: 'softmax'
                 NumTrained: 390
    ImportedModelParameters: [1×1 struct]


  Properties, Methods

The model is imported as a CompactClassificationXGBoost model object.

Use the dot notation to view the imported model parameters.

Mdl.ImportedModelParameters

ans = struct with fields:
            BaseScore: 0.5000
            Objective: 'multi:softmax'
              Booster: 'Tree'
    NumBoostingRounds: 30
     HasParallelTrees: 1
           NumClasses: 13
             IsBinary: 0

The parameters indicate it is a multiclass classification model trained using the 'Tree' booster. Convert the response data Y to an encoded array to match the imported model and the predictor matrix X to a full matrix.

labels = categories(Y);

% Create mapping with 0-based indexing
labelMap = containers.Map(labels,0:length(labels)-1);

% Encode Y
Y = cellstr(Y);
encodedY = zeros(size(Y));
for i = 1:length(Y)
    encodedY(i) = labelMap(Y{i});
end

fullX = full(X);

Use the predict function to evaluate the class for the ninth sample.

predict(Mdl,fullX(9,:))

ans = 
0

Input Arguments

mdl — Compact classification XGBoost model

CompactClassificationXGBoost model object

Compact classification XGBoost model, specified as a CompactClassificationXGBoost model object created with importModelFromXGBoost.

X — Predictor data

numeric matrix | table

Predictor data to be classified, specified as a numeric matrix or a table.

Each row of X corresponds to one observation, and each column corresponds to one variable. If there are missing values in a row, the software uses the learned branch direction from the pretrained model. The predictor data cannot include categorical predictors (logical, categorical, char, string, or cell).

For a numeric matrix, the variables that make up the columns of X must have the same order as the predictor variables used to train mdl.

For a table:

• predict does not support multicolumn variables or cell arrays other than cell arrays of character vectors.

• All predictor variables in X must have the same variable names and data types as those stored in mdl.PredictorNames. X can contain additional variables, such as response variables and observation weights, but predict ignores them.

UseParallel — Flag to run in parallel

false or 0 (default) | true or 1

Flag to run in parallel, specified as a numeric or logical 1 (true) or 0 (false). If you specify UseParallel=true, the predict function executes for-loop iterations by using parfor. The loop runs in parallel when you have Parallel Computing Toolbox™.

Example: UseParallel=true

Data Types: logical

Output Arguments

labels — Predicted class labels

numeric array

Predicted class labels, returned as a numeric array.

The predict function classifies an observation into the class yielding the highest score.

scores — Class scores

numeric matrix

Class scores, returned as a numeric matrix with one row per observation and one column per class. For each observation and each class, the score represents the confidence that the observation originates from that class. A higher score indicates a higher confidence.

Extended Capabilities

Tall Arrays

Calculate with arrays that have more rows than fit in memory.

Usage notes and limitations:

• You cannot use the UseParallel name-value argument with tall arrays.

For more information, see Tall Arrays.

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

• Use saveLearnerForCoder, loadLearnerForCoder, and codegen (MATLAB Coder) to generate code for the predict function. Save a trained model by using saveLearnerForCoder. Define an entry-point function that loads the saved model by using loadLearnerForCoder and calls the predict function. Then use codegen to generate code for the entry-point function.

• Only single-precision C/C++ code is supported.

• Fixed-point code generation is not supported.

• This table contains notes about the arguments of predict. Arguments not included in this table are fully supported.

  Argument	Notes and Limitations
  X	For general code generation, X must be a single-precision matrix. The number of rows, or observations, in X can be a variable size, but the number of columns in X must be fixed.

For more information, see Introduction to Code Generation for Statistics and Machine Learning Functions.

Automatic Parallel Support

Accelerate code by automatically running computation in parallel using Parallel Computing Toolbox™.

To run in parallel, set the UseParallel name-value argument to true in the call to this function.

For more general information about parallel computing, see Run MATLAB Functions with Automatic Parallel Support (Parallel Computing Toolbox).

You cannot use UseParallel with tall or GPU arrays or in code generation.

GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

Usage notes and limitations:

• You cannot use UseParallel with GPU arrays.

For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

Version History

Introduced in R2026a