Skip to content

matlab/matlab-agentic-toolkit / skills-catalog/ai-and-statistics/matlab-engineer-tabular-features

matlab-engineer-tabular-features

Unverified

Use when engineering or selecting the best features for single-response classification or regression in MATLAB, whatever the data's modality — for non-tabular data it routes extraction to a domain skill, then selects, assesses, and delivers on the resulting table. Not for multi-response problems, model training, or raw data acquisition.

FileKindSize
SKILL.mdskill md18.9 KB
manifest.yamlconfig570 B
references/assess.mdmarkdown16.7 KB
references/deliver.mdmarkdown13.0 KB
references/domain-routing.mdmarkdown18.1 KB
references/feature-pool.mdmarkdown10.9 KB
references/intake.mdmarkdown16.9 KB
references/internal-helpers.mdmarkdown12.2 KB
references/provider-protocol.mdmarkdown12.3 KB
references/report.mdmarkdown9.7 KB
references/reproduce-pool.mdmarkdown7.1 KB
references/select.mdmarkdown7.1 KB
scripts/BordaVoter.mother2.3 KB
scripts/ConsensusVoter.mother2.5 KB
scripts/MajorityVoter.mother2.0 KB
scripts/RRFVoter.mother1.9 KB
scripts/assessGenerationStability.mother11.9 KB
scripts/assessKFold.mother20.6 KB
scripts/assessSelectionStability.mother9.8 KB
scripts/baselineComparison.mother18.9 KB
scripts/buildRecipe.mother8.2 KB
scripts/chooseNumBins.mother5.0 KB
scripts/chooseStandardization.mother4.5 KB
scripts/computeNSelect.mother2.9 KB
scripts/createConsensusVoter.mother2.2 KB
scripts/describeFeatures.mother5.1 KB
scripts/expandBlockMap.pbinary440 B
scripts/featureSetQuality.mother12.3 KB
scripts/generateFeatureReport.mother67.2 KB
scripts/generateFeatureReportPdf.mother64.9 KB
scripts/generateFeatures.mother14.6 KB
scripts/hasReportGenerator.mother630 B
scripts/isDomainRecipe.mother1.4 KB
scripts/isStringEmpty.mother577 B
scripts/lambdaSequence.pbinary637 B
scripts/lassoFeatureRanking.pbinary971 B
scripts/macroF1Score.mother931 B
scripts/mrmrFeatureRanking.pbinary239 B
scripts/mutualInformationPanel.pbinary1.1 KB
scripts/ncaFeatureRanking.pbinary464 B
scripts/nogueiraStability.mother3.8 KB
scripts/oobFeatureRanking.pbinary414 B
scripts/plotSelectionConsensus.mother2.7 KB
scripts/plotSelectionDecision.mother6.3 KB
scripts/plotSelectionStability.mother10.2 KB
scripts/plotValidationBaseline.mother6.1 KB
scripts/printSummary.mother18.3 KB
scripts/profileForSplit.mother6.2 KB
scripts/rankAgreement.mother1.3 KB
scripts/rankFeatures.mother6.2 KB
scripts/reserveHoldoutForUser.mother5.5 KB
scripts/runConsensusSelection.mother9.4 KB
scripts/sampleSkewness.mother600 B
scripts/saveResults.mother2.1 KB
scripts/scoreFeaturePanel.pbinary1.6 KB
scripts/screenPredictors.mother13.3 KB
scripts/selectFeatures.mother2.3 KB
scripts/splitStrategy.mother5.4 KB
scripts/stratifiedDownsampleRows.mother2.2 KB
scripts/stratifiedSubsampleIndices.mother3.4 KB
scripts/transformFeatures.mother6.1 KB
scripts/validateRecipe.mother12.3 KB
scripts/writeInferenceScript.mother10.5 KB

scripts/rankFeatures.m

View on GitHub
function [RankedIdx, Scores] = rankFeatures(TrainX, TrainY, Method, Options)
%rankFeatures Unified supervised feature ranking via SMLT methods.
%   Accepts table input (with mixed numeric/categorical columns) for methods
%   that support it natively (fscmrmr, fscnca, fsrnca, permutation,
%   predictorImportance, sequentialfs). Methods requiring numeric-only input
%   (lasso, relieff, chi2, ftest, stepwiselm, stepwiseglm) extract numeric
%   columns automatically.

% Copyright 2026 The MathWorks, Inc.
    arguments
        TrainX
        TrainY (:,1)
        Method (1,1) string {mustBeMember(Method, ...
            ["fscmrmr","fsrmrmr","relieff","fscnca","fsrnca","lasso", ...
             "chi2","ftest","sequentialfs","permutation", ...
             "predictorImportance","stepwiselm","stepwiseglm"])}
        Options.ProblemType (1,1) string {mustBeMember(Options.ProblemType, ...
            ["classification","regression"])} = "classification"
        Options.MethodOptions (1,1) struct = struct()
    end

    ProblemType = Options.ProblemType;
    NVPairs = namedargs2cell(Options.MethodOptions);

    NeedsNumeric = ismember(Method, ["relieff","lasso","chi2","ftest","stepwiselm","stepwiseglm","fsrmrmr"]);
    if NeedsNumeric && istable(TrainX)
        TrainX = TrainX(:, vartype("numeric"));
    end

    if istable(TrainX)
        p = width(TrainX);
    else
        p = size(TrainX, 2);
    end

    switch Method
        case "fscmrmr"
            [Idx, Scores] = fscmrmr(TrainX, TrainY);
            RankedIdx = Idx;

        case "fsrmrmr"
            [Idx, Scores] = fsrmrmr(TrainX, TrainY);
            RankedIdx = Idx;

        case "relieff"
            K = 10;
            if isfield(Options.MethodOptions, 'NumNeighbors')
                K = Options.MethodOptions.NumNeighbors;
            end
            [RankedIdx, Weights] = relieff(TrainX, TrainY, K);
            Scores = zeros(1, p);
            Scores(RankedIdx) = Weights;

        case "fscnca"
            Mdl = fscnca(TrainX, TrainY, NVPairs{:}, Verbose=0);
            Scores = Mdl.FeatureWeights';
            [~, RankedIdx] = sort(Scores, 'descend');

        case "fsrnca"
            Mdl = fsrnca(TrainX, TrainY, NVPairs{:}, Verbose=0);
            Scores = Mdl.FeatureWeights';
            [~, RankedIdx] = sort(Scores, 'descend');

        case "lasso"
            if ProblemType == "classification"
                Classes = categories(categorical(TrainY));
                nClasses = numel(Classes);
                ClassScores = zeros(nClasses, p);
                for k = 1:nClasses
                    Yk = categorical(TrainY) == Classes{k};
                    [B, FitInfo] = lassoglm(TrainX, Yk, 'binomial', NVPairs{:}, CV=5);
                    ClassScores(k, :) = abs(B(:, FitInfo.Index1SE))';
                end
                Scores = max(ClassScores, [], 1);
            else
                [B, FitInfo] = lasso(TrainX, double(TrainY), NVPairs{:}, CV=5);
                Scores = abs(B(:, FitInfo.Index1SE))';
            end
            [~, RankedIdx] = sort(Scores, 'descend');

        case "chi2"
            [Idx, Scores] = fscchi2(TrainX, TrainY);
            RankedIdx = Idx;

        case "ftest"
            [Idx, Scores] = fsrftest(TrainX, TrainY);
            RankedIdx = Idx;

        case "sequentialfs"
            if ProblemType == "classification"
                Criterion = @(XTr, YTr, XTe, YTe) ...
                    loss(fitcensemble(XTr, YTr, Method="Bag", NumLearningCycles=30), XTe, YTe);
            else
                Criterion = @(XTr, YTr, XTe, YTe) ...
                    loss(fitrensemble(XTr, YTr, Method="Bag", NumLearningCycles=30), XTe, YTe);
            end
            Selected = sequentialfs(Criterion, TrainX, TrainY, NVPairs{:});
            Scores = scoreSelectedSubset(TrainX, TrainY, Selected, ProblemType, p);
            [~, RankedIdx] = sort(Scores, 'descend');

        case "permutation"
            if ProblemType == "classification"
                Mdl = fitcensemble(TrainX, TrainY, NVPairs{:}, Method="Bag");
            else
                Mdl = fitrensemble(TrainX, TrainY, NVPairs{:}, Method="Bag");
            end
            Imp = oobPermutedPredictorImportance(Mdl);
            Scores = Imp;
            [~, RankedIdx] = sort(Scores, 'descend');

        case "predictorImportance"
            if ProblemType == "classification"
                Tree = fitctree(TrainX, TrainY, NVPairs{:});
            else
                Tree = fitrtree(TrainX, TrainY, NVPairs{:});
            end
            Scores = predictorImportance(Tree);
            [~, RankedIdx] = sort(Scores, 'descend');

        case "stepwiselm"
            Mdl = stepwiselm(TrainX, double(TrainY), NVPairs{:}, Verbose=0);
            Selected = Mdl.VariableInfo.InModel';
            Scores = scoreSelectedSubset(TrainX, TrainY, Selected, ProblemType, p);
            [~, RankedIdx] = sort(Scores, 'descend');

        case "stepwiseglm"
            if ProblemType == "classification"
                Classes = categories(categorical(TrainY));
                nClasses = numel(Classes);
                Selected = false(1, p);
                for k = 1:nClasses
                    Yk = double(categorical(TrainY) == Classes{k});
                    Mdl = stepwiseglm(TrainX, Yk, NVPairs{:}, ...
                        Distribution="binomial", Verbose=0);
                    InModel = Mdl.VariableInfo.InModel;
                    Selected = Selected | InModel(1:p)';
                end
            else
                Mdl = stepwiseglm(TrainX, double(TrainY), NVPairs{:}, Verbose=0);
                InModel = Mdl.VariableInfo.InModel;
                Selected = InModel(1:p)';
            end
            Scores = scoreSelectedSubset(TrainX, TrainY, Selected, ProblemType, p);
            [~, RankedIdx] = sort(Scores, 'descend');
    end

    RankedIdx = RankedIdx(:)';
    Scores = Scores(:)';
end


function Scores = scoreSelectedSubset(TrainX, TrainY, Selected, ProblemType, p)
    SelIdx = find(Selected);
    SelX = TrainX(:, SelIdx);

    if ProblemType == "regression"
        [~, SubScores] = fsrftest(SelX, TrainY);
    else
        [~, SubScores] = fscchi2(SelX, TrainY);
    end

    Scores = zeros(1, p);
    Scores(SelIdx) = SubScores;
end
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall