Built-in Datasets

1import {2  loadBreastCancer,3  loadConcentricRings,4  loadCropYield,5  loadCustomerSegments,6  loadDiabetes,7  loadDigits,8  loadEnergyEfficiency,9  loadFitnessScores,10  loadFlowersExtended,11  loadFruitQuality,12  loadGaussianIslands,13  loadHousingMini,14  loadIris,15  loadLeafShapes,16  loadLinnerud,17  loadMoonsMulti,18  loadPerfectlySeparable,19  loadPlantGrowth,20  loadSeedMorphology,21  loadSensorStates,22  loadSpiralArms,23  loadStudentPerformance,24  loadTrafficConditions,25  loadWeatherOutcomes,26  makeBlobs,27  makeCircles,28  makeClassification,29  makeGaussianQuantiles,30  makeMoons,31  makeRegression,32} from "deepbox/datasets";3334console.log("=== Built-in Datasets ===\n");3536// ─── Classic Reference Datasets ─────────────────────────────────────────────3738console.log("--- Classic Reference Datasets ---\n");3940console.log("1. Iris Dataset:");41console.log("-".repeat(50));42const iris = loadIris();43console.log(`Samples: ${iris.data.shape[0]}`);44console.log(`Features: ${iris.data.shape[1]}`);45console.log(`Classes: ${iris.targetNames?.join(", ") || "N/A"}`);46console.log(`Features: ${iris.featureNames?.join(", ") || "N/A"}\n`);4748console.log("2. Digits Dataset:");49console.log("-".repeat(50));50const digits = loadDigits();51console.log(`Samples: ${digits.data.shape[0]}`);52console.log(`Features: ${digits.data.shape[1]} (8x8 images flattened)`);53console.log(`Classes: 10 (digits 0-9)\n`);5455console.log("3. Breast Cancer Dataset:");56console.log("-".repeat(50));57const cancer = loadBreastCancer();58console.log(`Samples: ${cancer.data.shape[0]}`);59console.log(`Features: ${cancer.data.shape[1]}`);60console.log(`Classes: ${cancer.targetNames?.join(", ") || "N/A"}\n`);6162console.log("4. Diabetes Dataset (Regression):");63console.log("-".repeat(50));64const diabetes = loadDiabetes();65console.log(`Samples: ${diabetes.data.shape[0]}`);66console.log(`Features: ${diabetes.data.shape[1]}`);67console.log(`Task: Regression (predict disease progression)\n`);6869console.log("5. Linnerud Dataset (Multi-Output):");70console.log("-".repeat(50));71const linnerud = loadLinnerud();72console.log(`Samples: ${linnerud.data.shape[0]}`);73console.log(`Features: ${linnerud.data.shape[1]}`);74console.log(`Targets: ${linnerud.target.shape[1]} (multi-output regression)\n`);7576// ─── Tabular Classification ─────────────────────────────────────────────────7778console.log("--- Tabular Classification Datasets ---\n");7980console.log("6. Flowers Extended (4-class Iris variant):");81console.log("-".repeat(50));82const flowers = loadFlowersExtended();83console.log(`Samples: ${flowers.data.shape[0]}, Features: ${flowers.data.shape[1]}`);84console.log(`Classes: ${flowers.targetNames?.join(", ") || "N/A"}\n`);8586console.log("7. Leaf Shapes (5-class morphology):");87console.log("-".repeat(50));88const leaves = loadLeafShapes();89console.log(`Samples: ${leaves.data.shape[0]}, Features: ${leaves.data.shape[1]}`);90console.log(`Classes: ${leaves.targetNames?.join(", ") || "N/A"}\n`);9192console.log("8. Fruit Quality:");93console.log("-".repeat(50));94const fruit = loadFruitQuality();95console.log(`Samples: ${fruit.data.shape[0]}, Features: ${fruit.data.shape[1]}`);96console.log(`Classes: ${fruit.targetNames?.join(", ") || "N/A"}\n`);9798console.log("9. Seed Morphology:");99console.log("-".repeat(50));100const seeds = loadSeedMorphology();101console.log(`Samples: ${seeds.data.shape[0]}, Features: ${seeds.data.shape[1]}`);102console.log(`Classes: ${seeds.targetNames?.join(", ") || "N/A"}\n`);103104// ─── Non-Linear Classification ──────────────────────────────────────────────105106console.log("--- Non-Linear Classification Datasets ---\n");107108console.log("10. Moons-Multi (3 interleaving crescents):");109console.log("-".repeat(50));110const moons = loadMoonsMulti();111console.log(`Samples: ${moons.data.shape[0]}, Features: ${moons.data.shape[1]}\n`);112113console.log("11. Concentric Rings:");114console.log("-".repeat(50));115const rings = loadConcentricRings();116console.log(`Samples: ${rings.data.shape[0]}, Features: ${rings.data.shape[1]}\n`);117118console.log("12. Spiral Arms:");119console.log("-".repeat(50));120const spirals = loadSpiralArms();121console.log(`Samples: ${spirals.data.shape[0]}, Features: ${spirals.data.shape[1]}\n`);122123console.log("13. Gaussian Islands (3D clusters):");124console.log("-".repeat(50));125const islands = loadGaussianIslands();126console.log(`Samples: ${islands.data.shape[0]}, Features: ${islands.data.shape[1]}\n`);127128// ─── Regression Datasets ────────────────────────────────────────────────────129130console.log("--- Regression Datasets ---\n");131132console.log("14. Plant Growth:");133console.log("-".repeat(50));134const plant = loadPlantGrowth();135console.log(`Samples: ${plant.data.shape[0]}, Features: ${plant.data.shape[1]}`);136console.log(`Features: ${plant.featureNames.join(", ")}\n`);137138console.log("15. Housing-Mini:");139console.log("-".repeat(50));140const housing = loadHousingMini();141console.log(`Samples: ${housing.data.shape[0]}, Features: ${housing.data.shape[1]}`);142console.log(`Features: ${housing.featureNames.join(", ")}\n`);143144console.log("16. Energy Efficiency:");145console.log("-".repeat(50));146const energy = loadEnergyEfficiency();147console.log(`Samples: ${energy.data.shape[0]}, Features: ${energy.data.shape[1]}\n`);148149console.log("17. Crop Yield:");150console.log("-".repeat(50));151const crop = loadCropYield();152console.log(`Samples: ${crop.data.shape[0]}, Features: ${crop.data.shape[1]}\n`);153154// ─── Clustering Datasets ────────────────────────────────────────────────────155156console.log("--- Clustering Datasets ---\n");157158console.log("18. Customer Segments:");159console.log("-".repeat(50));160const customers = loadCustomerSegments();161console.log(`Samples: ${customers.data.shape[0]}, Features: ${customers.data.shape[1]}`);162console.log(`Clusters: ${customers.targetNames?.join(", ") || "N/A"}\n`);163164console.log("19. Sensor States:");165console.log("-".repeat(50));166const sensors = loadSensorStates();167console.log(`Samples: ${sensors.data.shape[0]}, Features: ${sensors.data.shape[1]}`);168console.log(`Modes: ${sensors.targetNames?.join(", ") || "N/A"}\n`);169170// ─── Integer-Heavy Datasets ─────────────────────────────────────────────────171172console.log("--- Integer-Heavy Datasets ---\n");173174console.log("20. Student Performance:");175console.log("-".repeat(50));176const students = loadStudentPerformance();177console.log(`Samples: ${students.data.shape[0]}, Features: ${students.data.shape[1]}\n`);178179console.log("21. Traffic Conditions:");180console.log("-".repeat(50));181const traffic = loadTrafficConditions();182console.log(`Samples: ${traffic.data.shape[0]}, Features: ${traffic.data.shape[1]}\n`);183184// ─── Multi-Output Datasets ──────────────────────────────────────────────────185186console.log("--- Multi-Output Datasets ---\n");187188console.log("22. Fitness Scores (3 targets):");189console.log("-".repeat(50));190const fitness = loadFitnessScores();191console.log(`Samples: ${fitness.data.shape[0]}, Features: ${fitness.data.shape[1]}`);192console.log(`Targets: ${fitness.target.shape[1]} (${fitness.targetNames?.join(", ") || "N/A"})\n`);193194console.log("23. Weather Outcomes (2 targets):");195console.log("-".repeat(50));196const weather = loadWeatherOutcomes();197console.log(`Samples: ${weather.data.shape[0]}, Features: ${weather.data.shape[1]}`);198console.log(`Targets: ${weather.target.shape[1]} (${weather.targetNames?.join(", ") || "N/A"})\n`);199200// ─── Benchmark / Sanity-Check ───────────────────────────────────────────────201202console.log("--- Benchmark / Sanity-Check ---\n");203204console.log("24. Perfectly Separable:");205console.log("-".repeat(50));206const perfect = loadPerfectlySeparable();207console.log(`Samples: ${perfect.data.shape[0]}, Features: ${perfect.data.shape[1]}`);208console.log(`Classes: ${perfect.targetNames?.join(", ") || "N/A"}\n`);209210// ─── Synthetic Dataset Generators ───────────────────────────────────────────211212console.log("=== Synthetic Dataset Generators ===\n");213214console.log("25. Make Classification:");215console.log("-".repeat(50));216const classData = makeClassification({217  nSamples: 100,218  nFeatures: 4,219  nClasses: 2,220  randomState: 42,221});222const X_class = classData[0];223console.log(`Generated ${X_class.shape[0]} samples with ${X_class.shape[1]} features\n`);224225console.log("26. Make Regression:");226console.log("-".repeat(50));227const regData = makeRegression({228  nSamples: 100,229  nFeatures: 3,230  noise: 0.1,231  randomState: 42,232});233const X_reg = regData[0];234console.log(`Generated ${X_reg.shape[0]} samples with ${X_reg.shape[1]} features\n`);235236console.log("27. Make Blobs:");237console.log("-".repeat(50));238const blobsData = makeBlobs({239  nSamples: 150,240  nFeatures: 2,241  centers: 3,242  randomState: 42,243});244const X_blobs = blobsData[0];245console.log(`Generated ${X_blobs.shape[0]} samples in ${3} clusters\n`);246247console.log("28. Make Moons:");248console.log("-".repeat(50));249const moonsData = makeMoons({250  nSamples: 100,251  noise: 0.1,252  randomState: 42,253});254const X_moons = moonsData[0];255console.log(`Generated ${X_moons.shape[0]} samples (2 interleaving half circles)\n`);256257console.log("29. Make Circles:");258console.log("-".repeat(50));259const circlesData = makeCircles({260  nSamples: 100,261  noise: 0.05,262  randomState: 42,263});264const X_circles = circlesData[0];265console.log(`Generated ${X_circles.shape[0]} samples (concentric circles)\n`);266267console.log("30. Make Gaussian Quantiles:");268console.log("-".repeat(50));269const gaussData = makeGaussianQuantiles({270  nSamples: 100,271  nFeatures: 2,272  nClasses: 3,273  randomState: 42,274});275const X_gauss = gaussData[0];276console.log(`Generated ${X_gauss.shape[0]} samples in ${3} quantile-based classes\n`);277278console.log("✓ All 24 built-in datasets + 6 synthetic generators explored!");