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/chooseStandardization.m

View on GitHub
function [Mode, Reasoning] = chooseStandardization(RawTbl, Response, TargetModel)
%chooseStandardization Recommend a TransformedDataStandardization mode.
%
%   [Mode, Reasoning] = chooseStandardization(RawTbl, Response, TargetModel)
%   inspects the numeric predictors and the declared model family to recommend
%   how genc/genrfeatures should standardize their engineered features. The
%   returned Mode is one of "none", "zscore", "mad", "range" (never "auto" —
%   this utility resolves "auto" into a concrete choice) and is passed as the
%   TransformedDataStandardization name-value argument to the generator.
%
%   Decision logic (each auto-choice matches the generator's own default for the
%   family, so the only deliberate deviation is the data-driven mad case):
%     tree_ensemble                    -> "none"   (trees are scale-invariant;
%                                                    matches the bag default)
%     heavy-skew predictors dominate   -> "mad"    (robust center/scale resists
%       (fraction with |skew| >= 2 over            the outliers/heavy tails a
%        half of numeric predictors)               z-score would let dominate)
%     linear / kernel_distance /       -> "zscore" (the generator's own default
%       agnostic (low skew)                         for scale-sensitive learners;
%                                                    agnostic generates as linear)
%
%   "range" is never auto-selected: it is correct only for bounded/proportion or
%   non-negative data the skew read cannot detect, so reach it via the explicit
%   Standardization override rather than inferring it here.
%
%   Inputs:
%     RawTbl      - table of raw predictors + response
%     Response    - (1,1) string, response variable name (excluded from stats)
%     TargetModel - (1,1) string, "agnostic" | "tree_ensemble" | "linear" |
%                   "kernel_distance"
%
%   Outputs:
%     Mode      - (1,1) string, chosen standardization mode
%     Reasoning - (1,1) string, human-readable justification citing the measured
%                 skew fraction and family

% Copyright 2026 The MathWorks, Inc.

    arguments
        RawTbl table
        Response (1,1) string
        TargetModel (1,1) string {mustBeMember(TargetModel, ...
            ["agnostic","tree_ensemble","linear","kernel_distance"])}
    end

    if TargetModel == "tree_ensemble"
        Mode = "none";
        Reasoning = "tree_ensemble: trees are scale-invariant, no standardization needed";
        return;
    end

    [HeavySkewFrac, NumNumeric] = heavySkewFraction(RawTbl, Response);

    if NumNumeric == 0
        % No numeric predictors to profile (all categorical). Standardization
        % applies to the numeric engineered features the generator still emits;
        % default to z-score for the scale-sensitive families.
        Mode = "zscore";
        Reasoning = sprintf(...
            "%s: no numeric raw predictors to profile; default z-score for engineered numerics", ...
            TargetModel);
        return;
    end

    if HeavySkewFrac > 0.5
        Mode = "mad";
        Reasoning = sprintf(...
            "%.0f%% of %d numeric predictors are heavy-skewed (|skew| >= 2); MAD scaling resists outliers", ...
            100 * HeavySkewFrac, NumNumeric);
    else
        % linear / kernel_distance / agnostic, low skew: z-score matches the
        % generator's own default for these scale-sensitive learners.
        Mode = "zscore";
        Reasoning = sprintf(...
            "%s with low skew (%.0f%% heavy of %d); z-score is standard for symmetric data", ...
            TargetModel, 100 * HeavySkewFrac, NumNumeric);
    end
end


function [Frac, NumNumeric] = heavySkewFraction(RawTbl, Response)
%heavySkewFraction Fraction of numeric predictors with |skewness| >= 2.
%   Excludes the response column and any non-numeric predictors. Returns 0 for
%   the fraction when there are no numeric predictors.

    HeavyThreshold = 2;   % |skew| >= 2 flags a heavy-tailed / strongly skewed column
    Vars = string(RawTbl.Properties.VariableNames);
    Vars = Vars(Vars ~= Response);

    NumNumeric = 0;
    NumHeavy = 0;
    for v = Vars
        Col = RawTbl.(v);
        if ~isnumeric(Col)
            continue;
        end
        Col = double(Col(~isnan(Col)));
        if numel(Col) < 3
            continue;
        end
        NumNumeric = NumNumeric + 1;
        if abs(sampleSkewness(Col)) >= HeavyThreshold
            NumHeavy = NumHeavy + 1;
        end
    end

    if NumNumeric == 0
        Frac = 0;
    else
        Frac = NumHeavy / NumNumeric;
    end
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