incrementalLearner - Convert naive Bayes classification model to incremental learner - MATLAB (original) (raw)

Convert naive Bayes classification model to incremental learner

Since R2021a

Syntax

Description

[IncrementalMdl](#mw%5Fc3ae089d-221b-445d-a4f4-2994a9231a75) = incrementalLearner([Mdl](#mw%5Fcc61bc07-2701-4215-b2bd-6c540d606104)) returns a naive Bayes classification model for incremental learning,IncrementalMdl, using the hyperparameters of the traditionally trained naive Bayes classification model Mdl. Because its property values reflect the knowledge gained from Mdl,IncrementalMdl can predict labels given new observations, and it is_warm_, meaning that its predictive performance is tracked.

example

[IncrementalMdl](#mw%5Fc3ae089d-221b-445d-a4f4-2994a9231a75) = incrementalLearner([Mdl](#mw%5Fcc61bc07-2701-4215-b2bd-6c540d606104),[Name,Value](#namevaluepairarguments)) uses additional options specified by one or more name-value arguments. Some options require you to train IncrementalMdl before its predictive performance is tracked. For example,'MetricsWarmupPeriod',50,'MetricsWindowSize',100 specifies a preliminary incremental training period of 50 observations before performance metrics are tracked, and specifies processing 100 observations before updating the window performance metrics.

example

Examples

collapse all

Train a naive Bayes model by using fitcnb, and then convert it to an incremental learner.

Load and Preprocess Data

Load the human activity data set.

For details on the data set, enter Description at the command line.

Train Naive Bayes Model

Fit a naive Bayes classification model to the entire data set.

TTMdl = fitcnb(feat,actid);

TTMdl is a ClassificationNaiveBayes model object representing a traditionally trained naive Bayes classification model.

Convert Trained Model

Convert the traditionally trained naive Bayes classification model to one suitable for incremental learning.

IncrementalMdl = incrementalLearner(TTMdl)

IncrementalMdl = incrementalClassificationNaiveBayes

                IsWarm: 1
               Metrics: [1×2 table]
            ClassNames: [1 2 3 4 5]
        ScoreTransform: 'none'
     DistributionNames: {1×60 cell}
DistributionParameters: {5×60 cell}

Properties, Methods

IncrementalMdl is an incrementalClassificationNaiveBayes model object prepared for incremental learning using naive Bayes classification.

• The incrementalLearner function initializes the incremental learner by passing learned conditional predictor distribution parameters to it, along with other information TTMdl extracts from the training data.
• IncrementalMdl is warm (IsWarm is 1), which means that incremental learning functions can track performance metrics and make predictions.

Predict Responses

An incremental learner created from converting a traditionally trained model can generate predictions without further processing.

Predict classification scores (class posterior probabilities) for all observations using both models.

[,ttscores] = predict(TTMdl,feat); [,ilcores] = predict(IncrementalMdl,feat); compareScores = norm(ttscores - ilcores)

The difference between the scores generated by the models is 0.

Use a trained naive Bayes model to initialize an incremental learner. Prepare the incremental learner by specifying a metrics warm-up period, during which the updateMetricsAndFit function only fits the model. Specify a metrics window size of 500 observations.

Load the human activity data set.

For details on the data set, enter Description at the command line.

Randomly split the data in half: the first half for training a model traditionally, and the second half for incremental learning.

n = numel(actid);

rng(1) % For reproducibility cvp = cvpartition(n,'Holdout',0.5); idxtt = training(cvp); idxil = test(cvp);

% First half of data Xtt = feat(idxtt,:); Ytt = actid(idxtt);

% Second half of data Xil = feat(idxil,:); Yil = actid(idxil);

Fit a naive Bayes model to the first half of the data. Suppose you want to double the penalty to the classifier when it mistakenly classifies class 2.

C = ones(5) - eye(5); C(2,[1 3 4 5]) = 2; TTMdl = fitcnb(Xtt,Ytt,'Cost',C);

Convert the traditionally trained naive Bayes model to a naive Bayes classification model for incremental learning. Specify the following:

• A performance metrics warm-up period of 2000 observations.
• A metrics window size of 500 observations.
• Use of classification error and minimal cost to measure the performance of the model. You do not have to specify "mincost" for Metrics because incrementalClassificationNaiveBayes always tracks this metric.

IncrementalMdl = incrementalLearner(TTMdl,'MetricsWarmupPeriod',2000,'MetricsWindowSize',500,... 'Metrics','classiferror');

Fit the incremental model to the second half of the data by using the updateMetricsAndFit function. At each iteration:

• Simulate a data stream by processing 20 observations at a time.
• Overwrite the previous incremental model with a new one fitted to the incoming observations.
• Store the mean of the second predictor within the first class μ12, the cumulative metrics, and the window metrics to see how they evolve during incremental learning.

% Preallocation nil = numel(Yil); numObsPerChunk = 20; nchunk = ceil(nil/numObsPerChunk); ce = array2table(zeros(nchunk,2),'VariableNames',["Cumulative" "Window"]); mc = array2table(zeros(nchunk,2),'VariableNames',["Cumulative" "Window"]); mu12 = [IncrementalMdl.DistributionParameters{1,2}(1); zeros(nchunk,1)];

% Incremental fitting for j = 1:nchunk ibegin = min(nil,numObsPerChunk*(j-1) + 1); iend = min(nil,numObsPerChunk*j); idx = ibegin:iend;
IncrementalMdl = updateMetricsAndFit(IncrementalMdl,Xil(idx,:),Yil(idx)); ce{j,:} = IncrementalMdl.Metrics{"ClassificationError",:}; mc{j,:} = IncrementalMdl.Metrics{"MinimalCost",:}; mu12(j + 1) = IncrementalMdl.DistributionParameters{1,2}(1); end

IncrementalMdl is an incrementalClassificationNaiveBayes model object trained on all the data in the stream. During incremental learning and after the model is warmed up, updateMetricsAndFit checks the performance of the model on the incoming observations, and then fits the model to those observations.

To see how the performance metrics and μ12 evolve during training, plot them on separate tiles.

t = tiledlayout(3,1); nexttile plot(mu12) ylabel('\mu_{12}') xlim([0 nchunk]); xline(IncrementalMdl.MetricsWarmupPeriod/numObsPerChunk,'r-.'); nexttile h = plot(ce.Variables); xlim([0 nchunk]); ylabel('Classification Error') xline(IncrementalMdl.MetricsWarmupPeriod/numObsPerChunk,'r-.'); legend(h,ce.Properties.VariableNames,'Location','northwest') nexttile h = plot(mc.Variables); xlim([0 nchunk]); ylabel('Minimal Cost') xline(IncrementalMdl.MetricsWarmupPeriod/numObsPerChunk,'r-.'); legend(h,mc.Properties.VariableNames,'Location','northwest') xlabel(t,'Iteration')

The plots indicate that updateMetricsAndFit performs the following actions:

• Fit μ12 during all incremental learning iterations.
• Compute the performance metrics after the metrics warm-up period (red vertical line) only.
• Compute the cumulative metrics during each iteration.
• Compute the window metrics after processing 500 observations (25 iterations).

Because the data is ordered by activity, the mean and performance metrics periodically change abruptly.

Input Arguments

collapse all

Traditionally trained naive Bayes model for multiclass classification, specified as a ClassificationNaiveBayes model object returned by fitcnb. The conditional distribution of each predictor variable, as stored in Mdl.DistributionNames, cannot be a kernel distribution.

Name-Value Arguments

collapse all

Specify optional pairs of arguments asName1=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: 'Metrics',["classiferror" "mincost"],'MetricsWindowSize',100 specifies tracking the misclassification rate and minimal cost, and specifies processing 100 observations before updating the window performance metrics.

Data Types: char | string | struct | cell | function_handle

Data Types: single | double

Data Types: single | double

Output Arguments

collapse all

Naive Bayes classification model for incremental learning, returned as an incrementalClassificationNaiveBayes model object. IncrementalMdl is also configured to generate predictions given new data (see predict).

incrementalLearner initializes IncrementalMdl for incremental learning using the model information in Mdl. The following table shows the Mdl properties thatincrementalLearner passes to corresponding properties ofIncrementalMdl. The function also uses other model properties required to initialize IncrementalMdl, such as Y (class labels) and W (observation weights).

More About

collapse all

Incremental learning, or online learning, is a branch of machine learning concerned with processing incoming data from a data stream, possibly given little to no knowledge of the distribution of the predictor variables, aspects of the prediction or objective function (including tuning parameter values), or whether the observations are labeled. Incremental learning differs from traditional machine learning, where enough labeled data is available to fit to a model, perform cross-validation to tune hyperparameters, and infer the predictor distribution.

Given incoming observations, an incremental learning model processes data in any of the following ways, but usually in this order:

• Predict labels.
• Measure the predictive performance.
• Check for structural breaks or drift in the model.
• Fit the model to the incoming observations.

For more details, see Incremental Learning Overview.

Algorithms

collapse all

• The updateMetrics andupdateMetricsAndFit functions track model performance metrics (Metrics) from new data only when the incremental model is warm (IsWarm property is true).
  • If you create an incremental model by usingincrementalLearner andMetricsWarmupPeriod is 0 (default forincrementalLearner), the model is warm at creation.
  • Otherwise, an incremental model becomes warm afterfit or updateMetricsAndFit performs both of these actions:
    * Fit the incremental model to MetricsWarmupPeriod observations, which is the metrics warm-up period.
    * Fit the incremental model to all expected classes (see theMaxNumClasses and ClassNames arguments ofincrementalClassificationNaiveBayes).
• The Metrics property of the incremental model stores two forms of each performance metric as variables (columns) of a table, Cumulative and Window, with individual metrics in rows. When the incremental model is warm, updateMetrics and updateMetricsAndFit update the metrics at the following frequencies:
  • Cumulative — The functions compute cumulative metrics since the start of model performance tracking. The functions update metrics every time you call the functions and base the calculation on the entire supplied data set.
  • Window — The functions compute metrics based on all observations within a window determined by the MetricsWindowSize name-value argument.MetricsWindowSize also determines the frequency at which the software updates Window metrics. For example, if MetricsWindowSize is 20, the functions compute metrics based on the last 20 observations in the supplied data (X((end – 20 + 1):end,:) and Y((end – 20 + 1):end)).
    Incremental functions that track performance metrics within a window use the following process:
    1. Store a buffer of lengthMetricsWindowSize for each specified metric, and store a buffer of observation weights.
    2. Populate elements of the metrics buffer with the model performance based on batches of incoming observations, and store corresponding observation weights in the weights buffer.
    3. When the buffer is full, overwriteMdl.Metrics.Window with the weighted average performance in the metrics window. If the buffer overfills when the function processes a batch of observations, the latest incomingMetricsWindowSize observations enter the buffer, and the earliest observations are removed from the buffer. For example, supposeMetricsWindowSize is 20, the metrics buffer has 10 values from a previously processed batch, and 15 values are incoming. To compose the length 20 window, the functions use the measurements from the 15 incoming observations and the latest 5 measurements from the previous batch.
• The software omits an observation with a NaN score when computing the Cumulative and Window performance metric values.

Version History

Introduced in R2021a