ml-kernel - npm Package Compare versions

Comparing version 2.3.4 to 3.0.0

History.md

@@ -0,1 +1,5 @@
+# [3.0.0](https://github.com/mljs/kernel/compare/v2.3.4...v3.0.0) (2019-06-29)
+
+
+
 <a name="2.3.4"></a>
@@ -2,0 +6,0 @@ ## [2.3.4](https://github.com/mljs/kernel/compare/v2.3.3...v2.3.4) (2017-07-21)

package.json

 {
   "name": "ml-kernel",
-  "version": "2.3.4",
+  "version": "3.0.0",
   "description": "A factory for kernel functions",
@@ -12,4 +12,5 @@ "main": "./src/kernel.js",
     "eslint-fix": "npm run eslint -- --fix",
-    "test": "npm run test-mocha && npm run eslint",
-    "test-mocha": "mocha --require should --reporter mocha-better-spec-reporter"
+    "test": "npm run test-coverage && npm run eslint",
+    "test-only": "jest",
+    "test-coverage": "jest --coverage"
   },
@@ -40,16 +41,15 @@ "repository": {
   "devDependencies": {
-    "eslint": "^4.2.0",
-    "eslint-config-cheminfo": "^1.1.2",
-    "eslint-plugin-no-only-tests": "^2.0.0",
-    "mocha": "^3.0.0",
-    "mocha-better-spec-reporter": "^3.0.2",
-    "should": "^11.1.0"
+    "eslint": "^6.0.1",
+    "eslint-config-cheminfo": "^1.20.1",
+    "eslint-plugin-import": "^2.18.0",
+    "eslint-plugin-jest": "^22.7.1",
+    "jest": "^24.8.0"
   },
   "dependencies": {
-    "ml-distance-euclidean": "^1.0.0",
-    "ml-kernel-gaussian": "^2.0.1",
-    "ml-kernel-polynomial": "^2.0.0",
-    "ml-kernel-sigmoid": "^1.0.0",
-    "ml-matrix": "^5.0.0"
+    "ml-distance-euclidean": "^2.0.0",
+    "ml-kernel-gaussian": "^2.0.2",
+    "ml-kernel-polynomial": "^2.0.1",
+    "ml-kernel-sigmoid": "^1.0.1",
+    "ml-matrix": "^6.1.2"
   }
 }

README.md

 # ml-kernel
 
-  [![NPM version][npm-image]][npm-url]
-  [![build status][travis-image]][travis-url]
-  [![David deps][david-image]][david-url]
-  [![npm download][download-image]][download-url]
+[![NPM version][npm-image]][npm-url]
+[![build status][travis-image]][travis-url]
+[![npm download][download-image]][download-url]
 
-A factory for kernel functions
+A factory for kernel functions.
 
 ## Installation
 
-`$ npm install ml-kernel`
+`$ npm i ml-kernel`
 
@@ -18,18 +17,19 @@ ## Usage
 
-This function can be called with a matrix of input vectors
+This function can be called with a matrix of input vectors.
 and optional landmarks. If no landmark is provided, the input vectors will be used.
 
-__Available kernels__
-* `linear` - Linear kernel
-* `gaussian` or `rbf` - [Gaussian (radial basis function) kernel](https://github.com/mljs/kernel-gaussian)
-* `polynomial` or `poly` - [Polynomial kernel](https://github.com/mljs/kernel-polynomial)
-* `exponential` - [Exponential kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#exponential)
-* `laplacian` - [Laplacian kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#laplacian)
-* `anova` - [ANOVA kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#anova)
-* `rational` - [Rational Quadratic kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#rational)
-* `multiquadratic` - [Multiquadratic kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#multiquadric)
-* `cauchy` - [Cauchy kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#cauchy)
-* `histogram` or `min` - [Histogram Intersection kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#histogram)
-* `sigmoid` or `mlp' - [Sigmoid (hyperbolic tangent) kernel](https://github.com/mljs/kernel-sigmoid)
+**Available kernels**:
 
+- `linear` - Linear kernel
+- `gaussian` or `rbf` - [Gaussian (radial basis function) kernel](https://github.com/mljs/kernel-gaussian)
+- `polynomial` or `poly` - [Polynomial kernel](https://github.com/mljs/kernel-polynomial)
+- `exponential` - [Exponential kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#exponential)
+- `laplacian` - [Laplacian kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#laplacian)
+- `anova` - [ANOVA kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#anova)
+- `rational` - [Rational Quadratic kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#rational)
+- `multiquadratic` - [Multiquadratic kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#multiquadric)
+- `cauchy` - [Cauchy kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#cauchy)
+- `histogram` or `min` - [Histogram Intersection kernel](http://crsouza.com/2010/03/kernel-functions-for-machine-learning-applications/#histogram)
+- `sigmoid` or `mlp' - [Sigmoid (hyperbolic tangent) kernel](https://github.com/mljs/kernel-sigmoid)
+
 ### kernel.compute(inputs, landmarks)
@@ -43,3 +43,3 @@
 
-  [MIT](./LICENSE)
+[MIT](./LICENSE)
 
@@ -50,5 +50,3 @@ [npm-image]: https://img.shields.io/npm/v/ml-kernel.svg?style=flat-square
 [travis-url]: https://travis-ci.org/mljs/kernel
-[david-image]: https://img.shields.io/david/mljs/kernel.svg?style=flat-square
-[david-url]: https://david-dm.org/mljs/kernel
 [download-image]: https://img.shields.io/npm/dm/ml-kernel.svg?style=flat-square
 [download-url]: https://npmjs.org/package/ml-kernel

src/kernel.js

 'use strict';
 
-const Matrix = require('ml-matrix').Matrix;
-
+const { Matrix, MatrixTransposeView } = require('ml-matrix');
 const GaussianKernel = require('ml-kernel-gaussian');
 const PolynomialKernel = require('ml-kernel-polynomial');
+const SigmoidKernel = require('ml-kernel-sigmoid');
+
 const ANOVAKernel = require('./kernels/anova-kernel');
@@ -14,71 +15,82 @@ const CauchyKernel = require('./kernels/cauchy-kernel');
 const RationalKernel = require('./kernels/rational-quadratic-kernel');
-const SigmoidKernel = require('ml-kernel-sigmoid');
 
 const kernelType = {
-    gaussian: GaussianKernel,
-    rbf: GaussianKernel,
-    polynomial: PolynomialKernel,
-    poly: PolynomialKernel,
-    anova: ANOVAKernel,
-    cauchy: CauchyKernel,
-    exponential: ExponentialKernel,
-    histogram: HistogramKernel,
-    min: HistogramKernel,
-    laplacian: LaplacianKernel,
-    multiquadratic: MultiquadraticKernel,
-    rational: RationalKernel,
-    sigmoid: SigmoidKernel,
-    mlp: SigmoidKernel
+  gaussian: GaussianKernel,
+  rbf: GaussianKernel,
+  polynomial: PolynomialKernel,
+  poly: PolynomialKernel,
+  anova: ANOVAKernel,
+  cauchy: CauchyKernel,
+  exponential: ExponentialKernel,
+  histogram: HistogramKernel,
+  min: HistogramKernel,
+  laplacian: LaplacianKernel,
+  multiquadratic: MultiquadraticKernel,
+  rational: RationalKernel,
+  sigmoid: SigmoidKernel,
+  mlp: SigmoidKernel
 };
 
 class Kernel {
-    constructor(type, options) {
-        this.kernelType = type;
-        if (type === 'linear') return;
+  constructor(type, options) {
+    this.kernelType = type;
+    if (type === 'linear') return;
 
-        if (typeof type === 'string') {
-            type = type.toLowerCase();
+    if (typeof type === 'string') {
+      type = type.toLowerCase();
 
-            var KernelConstructor = kernelType[type];
-            if (KernelConstructor) {
-                this.kernelFunction = new KernelConstructor(options);
-            } else {
-                throw new Error('unsupported kernel type: ' + type);
-            }
-        } else if (typeof type === 'object' && typeof type.compute === 'function') {
-            this.kernelFunction = type;
-        } else {
-            throw new TypeError('first argument must be a valid kernel type or instance');
-        }
+      var KernelConstructor = kernelType[type];
+      if (KernelConstructor) {
+        this.kernelFunction = new KernelConstructor(options);
+      } else {
+        throw new Error(`unsupported kernel type: ${type}`);
+      }
+    } else if (typeof type === 'object' && typeof type.compute === 'function') {
+      this.kernelFunction = type;
+    } else {
+      throw new TypeError(
+        'first argument must be a valid kernel type or instance'
+      );
     }
+  }
 
-    compute(inputs, landmarks) {
-        if (landmarks === undefined) {
-            landmarks = inputs;
-        }
+  compute(inputs, landmarks) {
+    inputs = Matrix.checkMatrix(inputs);
+    if (landmarks === undefined) {
+      landmarks = inputs;
+    } else {
+      landmarks = Matrix.checkMatrix(landmarks);
+    }
+    if (this.kernelType === 'linear') {
+      return inputs.mmul(new MatrixTransposeView(landmarks));
+    }
 
-        if (this.kernelType === 'linear') {
-            var matrix = new Matrix(inputs);
-            return matrix.mmul(new Matrix(landmarks).transposeView());
+    const kernelMatrix = new Matrix(inputs.rows, landmarks.rows);
+    if (inputs === landmarks) {
+      // fast path, matrix is symmetric
+      for (let i = 0; i < inputs.rows; i++) {
+        for (let j = i; j < inputs.rows; j++) {
+          const value = this.kernelFunction.compute(
+            inputs.getRow(i),
+            inputs.getRow(j)
+          );
+          kernelMatrix.set(i, j, value);
+          kernelMatrix.set(j, i, value);
         }
-
-        const kernelMatrix = new Matrix(inputs.length, landmarks.length);
-        var i, j;
-        if (inputs === landmarks) { // fast path, matrix is symmetric
-            for (i = 0; i < inputs.length; i++) {
-                for (j = i; j < inputs.length; j++) {
-                    kernelMatrix[i][j] = kernelMatrix[j][i] = this.kernelFunction.compute(inputs[i], inputs[j]);
-                }
-            }
-        } else {
-            for (i = 0; i < inputs.length; i++) {
-                for (j = 0; j < landmarks.length; j++) {
-                    kernelMatrix[i][j] = this.kernelFunction.compute(inputs[i], landmarks[j]);
-                }
-            }
+      }
+    } else {
+      for (let i = 0; i < inputs.rows; i++) {
+        for (let j = 0; j < landmarks.rows; j++) {
+          kernelMatrix.set(
+            i,
+            j,
+            this.kernelFunction.compute(inputs.getRow(i), landmarks.getRow(j))
+          );
         }
-        return kernelMatrix;
+      }
     }
+    return kernelMatrix;
+  }
 }
 
 module.exports = Kernel;

src/kernels/anova-kernel.js

 'use strict';
 
 const defaultOptions = {
-    sigma: 1,
-    degree: 1
+  sigma: 1,
+  degree: 1
 };
 
 class ANOVAKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.sigma = options.sigma;
-        this.degree = options.degree;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.sigma = options.sigma;
+    this.degree = options.degree;
+  }
 
-    compute(x, y) {
-        var sum = 0;
-        var len = Math.min(x.length, y.length);
-        for (var i = 1; i <= len; ++i) {
-            sum += Math.pow(Math.exp(-this.sigma * Math.pow(Math.pow(x[i - 1], i) -
-                    Math.pow(y[i - 1], i), 2)), this.degree);
-        }
-        return sum;
+  compute(x, y) {
+    var sum = 0;
+    var len = Math.min(x.length, y.length);
+    for (var i = 1; i <= len; ++i) {
+      sum += Math.pow(
+        Math.exp(
+          -this.sigma *
+            Math.pow(Math.pow(x[i - 1], i) - Math.pow(y[i - 1], i), 2)
+        ),
+        this.degree
+      );
     }
+    return sum;
+  }
 }
 
 module.exports = ANOVAKernel;

src/kernels/cauchy-kernel.js

 'use strict';
 
-const squaredEuclidean = require('ml-distance-euclidean').squared;
+const { squaredEuclidean } = require('ml-distance-euclidean');
 
 const defaultOptions = {
-    sigma: 1
+  sigma: 1
 };
 
 class CauchyKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.sigma = options.sigma;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.sigma = options.sigma;
+  }
 
-    compute(x, y) {
-        return 1 / (1 + squaredEuclidean(x, y) / (this.sigma * this.sigma));
-    }
+  compute(x, y) {
+    return 1 / (1 + squaredEuclidean(x, y) / (this.sigma * this.sigma));
+  }
 }
 
 module.exports = CauchyKernel;

src/kernels/exponential-kernel.js

 'use strict';
 
-const euclidean = require('ml-distance-euclidean');
+const { euclidean } = require('ml-distance-euclidean');
 
 const defaultOptions = {
-    sigma: 1
+  sigma: 1
 };
 
 class ExponentialKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.sigma = options.sigma;
-        this.divisor = 2 * options.sigma * options.sigma;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.sigma = options.sigma;
+    this.divisor = 2 * options.sigma * options.sigma;
+  }
 
-    compute(x, y) {
-        const distance = euclidean(x, y);
-        return Math.exp(-distance / this.divisor);
-    }
+  compute(x, y) {
+    const distance = euclidean(x, y);
+    return Math.exp(-distance / this.divisor);
+  }
 }
 
 module.exports = ExponentialKernel;

src/kernels/histogram-intersection-kernel.js

 'use strict';
 
 class HistogramIntersectionKernel {
-    compute(x, y) {
-        var min = Math.min(x.length, y.length);
-        var sum = 0;
-        for (var i = 0; i < min; ++i) {
-            sum += Math.min(x[i], y[i]);
-        }
+  compute(x, y) {
+    var min = Math.min(x.length, y.length);
+    var sum = 0;
+    for (var i = 0; i < min; ++i) {
+      sum += Math.min(x[i], y[i]);
+    }
 
-        return sum;
-    }
+    return sum;
+  }
 }
 
 module.exports = HistogramIntersectionKernel;

src/kernels/laplacian-kernel.js

 'use strict';
 
-const euclidean = require('ml-distance-euclidean');
+const { euclidean } = require('ml-distance-euclidean');
 
 const defaultOptions = {
-    sigma: 1
+  sigma: 1
 };
 
 class LaplacianKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.sigma = options.sigma;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.sigma = options.sigma;
+  }
 
-    compute(x, y) {
-        const distance = euclidean(x, y);
-        return Math.exp(-distance / this.sigma);
-    }
+  compute(x, y) {
+    const distance = euclidean(x, y);
+    return Math.exp(-distance / this.sigma);
+  }
 }
 
 module.exports = LaplacianKernel;

src/kernels/multiquadratic-kernel.js

 'use strict';
 
-const squaredEuclidean = require('ml-distance-euclidean').squared;
+const { squaredEuclidean } = require('ml-distance-euclidean');
 
 const defaultOptions = {
-    constant: 1
+  constant: 1
 };
 
 class MultiquadraticKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.constant = options.constant;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.constant = options.constant;
+  }
 
-    compute(x, y) {
-        return Math.sqrt(squaredEuclidean(x, y) + this.constant * this.constant);
-    }
+  compute(x, y) {
+    return Math.sqrt(squaredEuclidean(x, y) + this.constant * this.constant);
+  }
 }
 
 module.exports = MultiquadraticKernel;

src/kernels/rational-quadratic-kernel.js

 'use strict';
 
-const squaredEuclidean = require('ml-distance-euclidean').squared;
+const { squaredEuclidean } = require('ml-distance-euclidean');
 
 const defaultOptions = {
-    constant: 1
+  constant: 1
 };
 
 class RationalQuadraticKernel {
-    constructor(options) {
-        options = Object.assign({}, defaultOptions, options);
-        this.constant = options.constant;
-    }
+  constructor(options) {
+    options = Object.assign({}, defaultOptions, options);
+    this.constant = options.constant;
+  }
 
-    compute(x, y) {
-        const distance = squaredEuclidean(x, y);
-        return 1 - (distance / (distance + this.constant));
-    }
+  compute(x, y) {
+    const distance = squaredEuclidean(x, y);
+    return 1 - distance / (distance + this.constant);
+  }
 }
 
 module.exports = RationalQuadraticKernel;

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

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

Dev dependency count

5

decreased by-16.67%

Lines of code

204

increased by9.68%

Worsened metrics

Total package byte prevSize

11779

decreased by-2.6%

Number of lines in readme file

50

decreased by-3.85%

Dependency changes

• + Addedml-matrix@6.12.0(transitive)

• - Removedml-distance-euclidean@1.0.0(transitive)

• - Removedml-matrix@5.3.0(transitive)

• Updatedml-distance-euclidean@^2.0.0

• Updatedml-kernel-gaussian@^2.0.2

• Updatedml-kernel-polynomial@^2.0.1

• Updatedml-kernel-sigmoid@^1.0.1

• Updatedml-matrix@^6.1.2