clustering-tfjs/dist/datasets/synthetic.js

High-performance TypeScript clustering algorithms (K-Means, Spectral, Agglomerative) with TensorFlow.js acceleration and scikit-learn compatibility

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
Object.defineProperty(exports, "__esModule", { value: true });
exports.makeBlobs = makeBlobs;
const tf = __importStar(require("../tf-adapter"));
function makeBlobs(options) {
    const { nSamples, nFeatures, centers, clusterStd = 1.0, randomState, } = options;
    // Set random seed if provided
    if (randomState !== undefined) {
        tf.randomUniform([1], 0, 1, 'float32', randomState);
    }
    let centersTensor;
    let nCenters;
    if (typeof centers === 'number') {
        nCenters = centers;
        // Generate random centers
        centersTensor = tf.randomUniform([centers, nFeatures], -10, 10);
    }
    else {
        centersTensor = centers;
        nCenters = centersTensor.shape[0];
    }
    // Generate samples
    const samplesPerCluster = Math.floor(nSamples / nCenters);
    const extraSamples = nSamples % nCenters;
    const samples = [];
    const labels = [];
    for (let i = 0; i < nCenters; i++) {
        const nSamplesCluster = samplesPerCluster + (i < extraSamples ? 1 : 0);
        // Get center for this cluster
        const center = centersTensor.slice([i, 0], [1, nFeatures]);
        // Generate samples around this center
        const noise = tf.randomNormal([nSamplesCluster, nFeatures], 0, clusterStd);
        const clusterSamples = tf.add(noise, center);
        samples.push(clusterSamples);
        labels.push(...new Array(nSamplesCluster).fill(i));
    }
    // Concatenate all samples
    const X = tf.concat(samples, 0);
    // Clean up
    if (typeof centers === 'number') {
        centersTensor.dispose();
    }
    samples.forEach((s) => s.dispose());
    return { X, y: labels };
}