ml-kmeans - npm Package Compare versions

Comparing version 0.0.0 to 0.1.0

package.json

 {
   "name": "ml-kmeans",
-  "version": "0.0.0",
+  "version": "0.1.0",
   "description": "K-means in Javascript",
@@ -5,0 +5,0 @@ "main": "src/index.js",

README.md

@@ -15,10 +15,16 @@ # clustering
 ## Methods
-### kmeans(data, centers, [maxIter], [tol])
-Returns an array of cluster indexes for the training dots.
+### kmeans(data, centers, [props])
+Returns an object containing the following:
 
+* `clusters`: array of [cluster indexes](https://en.wikipedia.org/wiki/K-means_clustering) for the training dots.
+* `centroids`: array of calculated centroids.
+* `iterations`: array of `clusters` and `centroids` calculated during each iteration. It's optional, only included when `withIter` is set to true (see below).
+
 __Arguments__
 * `data`: An array of the (x,y) points to cluster, represented also as an array.
 * `centers`: An array of the K centers in format (x,y), represented also as an array.
-* `maxIter`: Maximum number of iterations allowed. Its default is 100.
-* `tol`: The numerical error tolerance. Its default is 1e-6.
+* `props`: A property object that can be used to set some parameters:
+   * `maxIter`: Maximum number of iterations allowed. Its default is 100.
+   * `tol`: The numerical error tolerance. Its default is 1e-6.
+   * `withIter`: If `true` it adds an `iterations` property in the returned object. Its default is false.
 
@@ -25,0 +31,0 @@ ## Test

src/kmeans.js

@@ -110,9 +110,19 @@ 'use strict';
  * @param {Array <Array <number>>} centers - the K centers in format (x,y)
+ * @param {Object} props - properties
  * @param {number} maxIter - maximum of iterations allowed
  * @param {number} tol - the error tolerance
- * @returns {Array <number>} the cluster identifier for each data dot
+ * @param {boolean} withIter - store clusters and centroids for each iteration
+ * @returns {Object} the cluster identifier for each data dot and centroids
  */
-function kmeans(data, centers, maxIter, tol) {
-    maxIter = (typeof maxIter === "undefined") ? 100 : maxIter;
-    tol = (typeof tol === "undefined") ? 1e-6 : tol;
+function kmeans(data, centers, props) {
+    var maxIter, tol, withIter;
+    if (typeof props === "undefined") {
+        maxIter = 100;
+        tol = 1e-6;
+        withIter = false;
+    } else {
+        maxIter = (typeof props.maxIter === "undefined") ? 100 : props.maxIter;
+        tol = (typeof props.tol === "undefined") ? 1e-6 : props.tol;
+        withIter = (typeof props.withIter === "undefined") ? false : props.withIter;
+    }
 
@@ -135,2 +145,3 @@ var nData = data.length;
     var curDistance = 0;
+    var iterations = [];
     for (var iter = 0; iter < maxIter; iter++) {
@@ -140,9 +151,39 @@ clusterID = updateClusterID(data, centers);
         curDistance = computeSSE(data, centers, clusterID);
-        if ((lastDistance - curDistance < tol) || ((lastDistance - curDistance)/lastDistance < tol))
-            return clusterID;
+        if (withIter) {
+            iterations.push({
+                "clusters": clusterID,
+                "centroids": centers
+            });
+        }
+
+        if ((lastDistance - curDistance < tol) || ((lastDistance - curDistance)/lastDistance < tol)) {
+            if (withIter) {
+                return {
+                    "clusters": clusterID,
+                    "centroids": centers,
+                    "iterations": iterations
+                };
+            } else {
+                return {
+                    "clusters": clusterID,
+                    "centroids": centers
+                };
+            }
+        }
         lastDistance = curDistance;
     }
-    return clusterID;
+    if (withIter) {
+        return {
+            "clusters": clusterID,
+            "centroids": centers,
+            "iterations": iterations
+        };
+    } else {
+        return {
+            "clusters": clusterID,
+            "centroids": centers
+        };
+    }
 }
 
-module.exports = kmeans;
+module.exports = kmeans;

test/kmeans.js

@@ -6,11 +6,43 @@ var kmeans = require('..');
 var clusterID = [1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0];
+var expectedCentroids = [[-8.4199, -1.6654], [4.4661, 1.3475]];
 
-describe('K-means test', function () {
+describe('K-means', function () {
 
-    it('main test', function () {
-        var ans = kmeans(data, centers);
-        for (var i = 0, l = clusterID.length; i < l; i++) {
-            ans[i].should.equal(clusterID[i]);
-        }
+    describe('when passing data points and centroids', function () {
+
+        it('main test', function () {
+            var ans = kmeans(data, centers);
+            clusts = ans.clusters;
+            centrs = ans.centroids;
+
+            for (var i = 0, l = clusterID.length; i < l; i++) {
+                clusts[i].should.equal(clusterID[i]);
+            }
+            for (var i = 0, l = centers.length; i < l; i++) {
+                centrs[i][0].should.be.approximately(expectedCentroids[i][0], 0.1);
+                centrs[i][1].should.be.approximately(expectedCentroids[i][1], 0.1);
+            }
+        });
+
     });
-});
+
+    describe('when passing `withIter` property', function () {
+
+        it('should store iterations', function () {
+            var ans = kmeans(data, centers, {"withIter": true});
+            clusts = ans.clusters;
+            centrs = ans.centroids;
+            iters = ans.iterations;
+
+            for (var i = 0, l = clusterID.length; i < l; i++) {
+                clusts[i].should.equal(clusterID[i]);
+            }
+            for (var i = 0, l = centers.length; i < l; i++) {
+                centrs[i][0].should.be.approximately(expectedCentroids[i][0], 0.1);
+                centrs[i][1].should.be.approximately(expectedCentroids[i][1], 0.1);
+            }
+            iters.length.should.equal(12);
+        });
+
+    });
+});

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

18244

increased by18.59%

Lines of code

236

increased by39.64%

Number of lines in readme file

53

increased by12.77%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes