@thi.ng/text-analysis 0.2.0 → 0.3.0

package/CHANGELOG.md

@@ -1,6 +1,6 @@
 # Change Log
 
-- **Last updated**: 2025-06-14T20:56:27Z
+- **Last updated**: 2025-06-15T12:37:24Z
 - **Generator**: [thi.ng/monopub](https://thi.ng/monopub)
 
 All notable changes to this project will be documented in this file.
@@ -11,6 +11,13 @@ See [Conventional Commits](https://conventionalcommits.org/) for commit guidelin
 **Note:** Unlisted _patch_ versions only involve non-code or otherwise excluded changes
 and/or version bumps of transitive dependencies.
 
+## [0.3.0](https://github.com/thi-ng/umbrella/tree/@thi.ng/text-analysis@0.3.0) (2025-06-15)
+
+#### 🚀 Features
+
+- update kmeansDense ([d35b6bd](https://github.com/thi-ng/umbrella/commit/d35b6bd))
+  - update results to include original `docs` for each cluster
+
 ## [0.2.0](https://github.com/thi-ng/umbrella/tree/@thi.ng/text-analysis@0.2.0) (2025-06-14)
 
 #### 🚀 Features

package/cluster.d.ts

@@ -18,7 +18,12 @@ export declare const JACCARD_DIST_DENSE: Untransformed<ReadonlyVec>;
  * @param docs
  * @param opts
  */
-export declare const kmeansDense: (k: number, docs: ReadonlyVec[], opts?: Partial<KMeansOpts>) => import("@thi.ng/k-means").Cluster[];
+export declare const kmeansDense: (k: number, docs: ReadonlyVec[], opts?: Partial<KMeansOpts>) => {
+    docs: ReadonlyVec[];
+    id: number;
+    centroid: ReadonlyVec;
+    items: number[];
+}[];
 /**
  * k-means clustering for sparse multi-hot vectors. First converts vectors into
  * dense versions (using {@link toDense}), then calls {@link kmeansDense} to
@@ -34,7 +39,12 @@ export declare const kmeansDense: (k: number, docs: ReadonlyVec[], opts?: Partia
  */
 export declare const kmeansSparse: (k: number, docs: ReadonlyVec[], opts: Partial<KMeansOpts> & {
     dim: number;
-}) => import("@thi.ng/k-means").Cluster[];
+}) => {
+    docs: ReadonlyVec[];
+    id: number;
+    centroid: ReadonlyVec;
+    items: number[];
+}[];
 export declare function clusterBounds(docs: ReadonlyVec[]): {
     centroid: ReadonlyVec;
     radius: number;

package/cluster.js

@@ -11,7 +11,10 @@ import { distSq } from "@thi.ng/vectors/distsq";
 import { mean } from "@thi.ng/vectors/mean";
 import { toDense } from "./vec.js";
 const JACCARD_DIST_DENSE = new Untransformed(distJaccard);
-const kmeansDense = (k, docs, opts) => kmeans(k, docs, { maxIter: 100, ...opts });
+const kmeansDense = (k, docs, opts) => kmeans(k, docs, { maxIter: 100, ...opts }).map((cluster) => ({
+  ...cluster,
+  docs: lookup(docs, cluster.items)
+}));
 const kmeansSparse = (k, docs, opts) => kmeansDense(
   k,
   docs.map((x) => toDense(opts.dim, x)),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@thi.ng/text-analysis",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Text tokenization, transformation & analysis transducers, utilities, stop words, porter stemming, vector encodings, similarities",
   "type": "module",
   "module": "./index.js",
@@ -141,5 +141,5 @@
     "status": "alpha",
     "year": 2021
   },
-  "gitHead": "14e994e531d32053e948768998324d443436a542\n"
+  "gitHead": "4635a24acc2623894887ca31189fdffda87ff9d3\n"
 }