判别分析

正则化线性判别分析和二次判别分析

要以交互方式训练判别分析模型，可以使用分类学习器。为了获得更大的灵活性，可以在命令行界面中使用 fitcdiscr 来训练判别分析模型。训练模型后，可将模型和预测变量数据传递给 predict，以预测标签或估计后验概率。

App

分类学习器

使用有监督的机器学习训练模型以对数据进行分类

模块

ClassificationDiscriminant Predict

Classify observations using discriminant analysis model (自 R2024a 起)

函数

全部展开

创建判别分析模型

`fitcdiscr`	Fit discriminant analysis classifier
`makecdiscr`	Construct discriminant analysis classifier from parameters
`compact`	Reduce size of discriminant analysis classifier

改进判别分析模型

cvshrink Cross-validate regularization of linear discriminant

解释判别分析模型

`lime`	Local interpretable model-agnostic explanations (LIME) (自 R2020b 起)
`partialDependence`	Compute partial dependence (自 R2020b 起)
`permutationImportance`	Predictor importance by permutation (自 R2024a 起)
`plotPartialDependence`	Create partial dependence plot (PDP) and individual conditional expectation (ICE) plots
`shapley`	Shapley values (自 R2021a 起)

交叉验证

`crossval`	Cross-validate machine learning model
`kfoldEdge`	Classification edge for cross-validated classification model
`kfoldLoss`	Classification loss for cross-validated classification model
`kfoldfun`	Cross-validate function for classification
`kfoldMargin`	Classification margins for cross-validated classification model
`kfoldPredict`	Classify observations in cross-validated classification model

测量性能

`loss`	Classification loss for discriminant analysis classifier
`resubLoss`	Resubstitution classification loss for discriminant analysis classifier
`logp`	Log unconditional probability density for discriminant analysis classifier
`mahal`	Mahalanobis distance to class means of discriminant analysis classifier
`nLinearCoeffs`	Number of nonzero linear coefficients in discriminant analysis classifier
`compareHoldout`	Compare accuracies of two classification models using new data
`edge`	Classification edge for discriminant analysis classifier
`margin`	Classification margins for discriminant analysis classifier
`resubEdge`	Resubstitution classification edge for discriminant analysis classifier
`resubMargin`	Resubstitution classification margins for discriminant analysis classifier
`testckfold`	Compare accuracies of two classification models by repeated cross-validation

为观测值分类

`predict`	Predict labels using discriminant analysis classifier
`resubPredict`	Classify observations in discriminant analysis classifier by resubstitution
`classify`	Classify observations using discriminant analysis

对象

`ClassificationDiscriminant`	Discriminant analysis classification
`CompactClassificationDiscriminant`	Compact discriminant analysis classification
`ClassificationPartitionedModel`	Cross-validated classification model

主题

Train Discriminant Analysis Classifiers Using Classification Learner App
Create and compare discriminant analysis classifiers, and export trained models to make predictions for new data.
Supervised Learning Workflow and Algorithms
Understand the steps for supervised learning and the characteristics of nonparametric classification and regression functions.
Parametric Classification
Learn about parametric classification methods.
Discriminant Analysis Classification
Understand the discriminant analysis algorithm and how to fit a discriminant analysis model to data.
Creating Discriminant Analysis Model
Understand the algorithm used to construct discriminant analysis classifiers.
Create and Visualize Discriminant Analysis Classifier
Perform linear and quadratic classification of Fisher iris data.
Improving Discriminant Analysis Models
Examine and improve discriminant analysis model performance.
Regularize Discriminant Analysis Classifier
Make a more robust and simpler model by removing predictors without compromising the predictive power of the model.
Examine the Gaussian Mixture Assumption
Discriminant analysis assumes that the data comes from a Gaussian mixture model. Understand how to examine this assumption.
Prediction Using Discriminant Analysis Models
Understand how predict classifies observations using a discriminant analysis model.
Visualize Decision Surfaces of Different Classifiers
This example shows how to visualize the decision surface for different classification algorithms.