clustering-tfjs
Version:
High-performance TypeScript clustering algorithms (K-Means, Spectral, Agglomerative) with TensorFlow.js acceleration and scikit-learn compatibility
73 lines (72 loc) • 3.19 kB
JavaScript
;
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.createComponentIndicators = createComponentIndicators;
const tf = __importStar(require("../tf-adapter"));
/**
* Creates component indicator features for disconnected graphs.
*
* For a graph with k connected components, this creates indicator features
* where each feature has a constant value for all nodes in that component.
* This mimics the behavior of sklearn's shift-invert eigenvectors.
*
* @param componentLabels - Array indicating which component each node belongs to
* @param numComponents - Total number of components detected
* @param maxIndicators - Maximum number of indicator vectors to create (usually nClusters)
* @returns Component indicator matrix (n_samples x min(numComponents, maxIndicators))
*/
function createComponentIndicators(componentLabels, numComponents, maxIndicators) {
return tf.tidy(() => {
const n = componentLabels.length;
const numIndicators = Math.min(numComponents, maxIndicators);
// Count nodes per component for normalization
const componentSizes = new Array(numComponents).fill(0);
for (let i = 0; i < n; i++) {
componentSizes[componentLabels[i]]++;
}
// Create indicator matrix
const indicators = new Float32Array(n * numIndicators);
// Fill indicators with normalized values
// Using 1/sqrt(component_size) normalization to match eigenvector normalization
for (let i = 0; i < n; i++) {
const comp = componentLabels[i];
if (comp < numIndicators) {
indicators[i * numIndicators + comp] =
1.0 / Math.sqrt(componentSizes[comp]);
}
}
return tf.tensor2d(indicators, [n, numIndicators], 'float32');
});
}