nlptoolkit-classification 1.0.0

package/dist/Model/DecisionTree/DecisionTree.d.ts

@@ -0,0 +1,37 @@
+import { ValidatedModel } from "../ValidatedModel";
+import { DecisionNode } from "./DecisionNode";
+import { Instance } from "../../Instance/Instance";
+import { InstanceList } from "../../InstanceList/InstanceList";
+export declare class DecisionTree extends ValidatedModel {
+    private root;
+    /**
+     * Constructor that sets root node of the decision tree.
+     *
+     * @param root DecisionNode type input.
+     */
+    constructor(root: DecisionNode);
+    /**
+     * The predict method  performs prediction on the root node of given instance, and if it is null, it returns the possible class labels.
+     * Otherwise it returns the returned class labels.
+     *
+     * @param instance Instance make prediction.
+     * @return Possible class labels.
+     */
+    predict(instance: Instance): string;
+    predictProbability(instance: Instance): Map<string, number>;
+    /**
+     * The prune method takes a {@link DecisionNode} and an {@link InstanceList} as inputs. It checks the classification performance
+     * of given InstanceList before pruning, i.e making a node leaf, and after pruning. If the after performance is better than the
+     * before performance it prune the given InstanceList from the tree.
+     *
+     * @param node     DecisionNode that will be pruned if conditions hold.
+     * @param pruneSet Small subset of tree that will be removed from tree.
+     */
+    pruneNode(node: DecisionNode, pruneSet: InstanceList): void;
+    /**
+     * The prune method takes an {@link InstanceList} and  performs pruning to the root node.
+     *
+     * @param pruneSet {@link InstanceList} to perform pruning.
+     */
+    prune(pruneSet: InstanceList): void;
+}

package/dist/Model/DecisionTree/DecisionTree.js

@@ -0,0 +1,75 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports", "../ValidatedModel", "../../Instance/CompositeInstance"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.DecisionTree = void 0;
+    const ValidatedModel_1 = require("../ValidatedModel");
+    const CompositeInstance_1 = require("../../Instance/CompositeInstance");
+    class DecisionTree extends ValidatedModel_1.ValidatedModel {
+        /**
+         * Constructor that sets root node of the decision tree.
+         *
+         * @param root DecisionNode type input.
+         */
+        constructor(root) {
+            super();
+            this.root = root;
+        }
+        /**
+         * The predict method  performs prediction on the root node of given instance, and if it is null, it returns the possible class labels.
+         * Otherwise it returns the returned class labels.
+         *
+         * @param instance Instance make prediction.
+         * @return Possible class labels.
+         */
+        predict(instance) {
+            let predictedClass = this.root.predict(instance);
+            if ((predictedClass == null) && ((instance instanceof CompositeInstance_1.CompositeInstance))) {
+                predictedClass = instance.getPossibleClassLabels()[0];
+            }
+            return predictedClass;
+        }
+        predictProbability(instance) {
+            return this.root.predictProbabilityDistribution(instance);
+        }
+        /**
+         * The prune method takes a {@link DecisionNode} and an {@link InstanceList} as inputs. It checks the classification performance
+         * of given InstanceList before pruning, i.e making a node leaf, and after pruning. If the after performance is better than the
+         * before performance it prune the given InstanceList from the tree.
+         *
+         * @param node     DecisionNode that will be pruned if conditions hold.
+         * @param pruneSet Small subset of tree that will be removed from tree.
+         */
+        pruneNode(node, pruneSet) {
+            if (node.leaf) {
+                return;
+            }
+            let before = this.testClassifier(pruneSet);
+            node.leaf = true;
+            let after = this.testClassifier(pruneSet);
+            if (after.getAccuracy() < before.getAccuracy()) {
+                node.leaf = false;
+                for (let child of node.children) {
+                    this.pruneNode(child, pruneSet);
+                }
+            }
+        }
+        /**
+         * The prune method takes an {@link InstanceList} and  performs pruning to the root node.
+         *
+         * @param pruneSet {@link InstanceList} to perform pruning.
+         */
+        prune(pruneSet) {
+            this.pruneNode(this.root, pruneSet);
+        }
+    }
+    exports.DecisionTree = DecisionTree;
+});
+//# sourceMappingURL=DecisionTree.js.map

package/dist/Model/DecisionTree/DecisionTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"DecisionTree.js","sourceRoot":"","sources":["../../../source/Model/DecisionTree/DecisionTree.ts"],"names":[],"mappings":";;;;;;;;;;;;IAAA,sDAAiD;IAGjD,wEAAmE;IAGnE,MAAa,YAAa,SAAQ,+BAAc;QAI5C;;;;WAIG;QACH,YAAY,IAAkB;YAC1B,KAAK,EAAE,CAAC;YACR,IAAI,CAAC,IAAI,GAAG,IAAI,CAAA;QACpB,CAAC;QAED;;;;;;WAMG;QACH,OAAO,CAAC,QAAkB;YACtB,IAAI,cAAc,GAAG,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;YACjD,IAAI,CAAC,cAAc,IAAI,IAAI,CAAC,IAAI,CAAC,CAAC,QAAQ,YAAY,qCAAiB,CAAC,CAAC,EAAE;gBACvE,cAAc,GAAwB,QAAS,CAAC,sBAAsB,EAAE,CAAC,CAAC,CAAC,CAAC;aAC/E;YACD,OAAO,cAAc,CAAC;QAC1B,CAAC;QAED,kBAAkB,CAAC,QAAkB;YACjC,OAAO,IAAI,CAAC,IAAI,CAAC,8BAA8B,CAAC,QAAQ,CAAC,CAAA;QAC7D,CAAC;QAED;;;;;;;WAOG;QACH,SAAS,CAAC,IAAkB,EAAE,QAAsB;YAChD,IAAI,IAAI,CAAC,IAAI,EAAC;gBACV,OAAO;aACV;YACD,IAAI,MAAM,GAAG,IAAI,CAAC,cAAc,CAAC,QAAQ,CAAC,CAAC;YAC3C,IAAI,CAAC,IAAI,GAAG,IAAI,CAAC;YACjB,IAAI,KAAK,GAAG,IAAI,CAAC,cAAc,CAAC,QAAQ,CAAC,CAAC;YAC1C,IAAI,KAAK,CAAC,WAAW,EAAE,GAAG,MAAM,CAAC,WAAW,EAAE,EAAE;gBAC5C,IAAI,CAAC,IAAI,GAAG,KAAK,CAAC;gBAClB,KAAK,IAAI,KAAK,IAAI,IAAI,CAAC,QAAQ,EAAE;oBAC7B,IAAI,CAAC,SAAS,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC;iBACnC;aACJ;QACL,CAAC;QAED;;;;WAIG;QACH,KAAK,CAAC,QAAsB;YACxB,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;QACvC,CAAC;KACJ;IAhED,oCAgEC"}

package/dist/Model/DeepNetworkModel.d.ts

@@ -0,0 +1,42 @@
+import { NeuralNetworkModel } from "./NeuralNetworkModel";
+import { DeepNetworkParameter } from "../Parameter/DeepNetworkParameter";
+import { InstanceList } from "../InstanceList/InstanceList";
+export declare class DeepNetworkModel extends NeuralNetworkModel {
+    private weights;
+    private hiddenLayerSize;
+    private readonly activationFunction;
+    /**
+     * The allocateWeights method takes {@link DeepNetworkParameter}s as an input. First it adds random weights to the {@link Array}
+     * of {@link Matrix} weights' first layer. Then it loops through the layers and adds random weights till the last layer.
+     * At the end it adds random weights to the last layer and also sets the hiddenLayerSize value.
+     *
+     * @param parameters {@link DeepNetworkParameter} input.
+     */
+    private allocateWeights;
+    /**
+     * The setBestWeights method creates an {@link Array} of Matrix as bestWeights and clones the values of weights {@link Array}
+     * into this newly created {@link Array}.
+     *
+     * @return An {@link Array} clones from the weights ArrayList.
+     */
+    private setBestWeights;
+    /**
+     * Constructor that takes two {@link InstanceList} train set and validation set and {@link DeepNetworkParameter} as inputs.
+     * First it sets the class labels, their sizes as K and the size of the continuous attributes as d of given train set and
+     * allocates weights and sets the best weights. At each epoch, it shuffles the train set and loops through the each item of that train set,
+     * it multiplies the weights Matrix with input Vector than applies the sigmoid function and stores the result as hidden and add bias.
+     * Then updates weights and at the end it compares the performance of these weights with validation set. It updates the bestClassificationPerformance and
+     * bestWeights according to the current situation. At the end it updates the learning rate via etaDecrease value and finishes
+     * with clearing the weights.
+     *
+     * @param trainSet      {@link InstanceList} to be used as trainSet.
+     * @param validationSet {@link InstanceList} to be used as validationSet.
+     * @param parameters    {@link DeepNetworkParameter} input.
+     */
+    constructor(trainSet: InstanceList, validationSet: InstanceList, parameters: DeepNetworkParameter);
+    /**
+     * The calculateOutput method loops size of the weights times and calculate one hidden layer at a time and adds bias term.
+     * At the end it updates the output y value.
+     */
+    protected calculateOutput(): void;
+}

package/dist/Model/DeepNetworkModel.js

@@ -0,0 +1,163 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports", "./NeuralNetworkModel", "nlptoolkit-math/dist/Matrix", "../Parameter/ActivationFunction", "nlptoolkit-math/dist/Vector", "../Performance/ClassificationPerformance"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.DeepNetworkModel = void 0;
+    const NeuralNetworkModel_1 = require("./NeuralNetworkModel");
+    const Matrix_1 = require("nlptoolkit-math/dist/Matrix");
+    const ActivationFunction_1 = require("../Parameter/ActivationFunction");
+    const Vector_1 = require("nlptoolkit-math/dist/Vector");
+    const ClassificationPerformance_1 = require("../Performance/ClassificationPerformance");
+    class DeepNetworkModel extends NeuralNetworkModel_1.NeuralNetworkModel {
+        /**
+         * Constructor that takes two {@link InstanceList} train set and validation set and {@link DeepNetworkParameter} as inputs.
+         * First it sets the class labels, their sizes as K and the size of the continuous attributes as d of given train set and
+         * allocates weights and sets the best weights. At each epoch, it shuffles the train set and loops through the each item of that train set,
+         * it multiplies the weights Matrix with input Vector than applies the sigmoid function and stores the result as hidden and add bias.
+         * Then updates weights and at the end it compares the performance of these weights with validation set. It updates the bestClassificationPerformance and
+         * bestWeights according to the current situation. At the end it updates the learning rate via etaDecrease value and finishes
+         * with clearing the weights.
+         *
+         * @param trainSet      {@link InstanceList} to be used as trainSet.
+         * @param validationSet {@link InstanceList} to be used as validationSet.
+         * @param parameters    {@link DeepNetworkParameter} input.
+         */
+        constructor(trainSet, validationSet, parameters) {
+            super(trainSet);
+            let tmpHidden = new Vector_1.Vector(0, 0);
+            let deltaWeights = new Array();
+            let hidden = new Array();
+            let hiddenBiased = new Array();
+            this.activationFunction = parameters.getActivationFunction();
+            this.allocateWeights(parameters);
+            let bestWeights = this.setBestWeights();
+            let bestClassificationPerformance = new ClassificationPerformance_1.ClassificationPerformance(0.0);
+            let epoch = parameters.getEpoch();
+            let learningRate = parameters.getLearningRate();
+            for (let i = 0; i < epoch; i++) {
+                trainSet.shuffle(parameters.getSeed());
+                for (let j = 0; j < trainSet.size(); j++) {
+                    this.createInputVector(trainSet.get(j));
+                    hidden = new Array();
+                    hiddenBiased = new Array();
+                    deltaWeights = new Array();
+                    for (let k = 0; k < this.hiddenLayerSize; k++) {
+                        if (k == 0) {
+                            hidden.push(this.calculateHidden(this.x, this.weights[k], this.activationFunction));
+                        }
+                        else {
+                            hidden.push(this.calculateHidden(hiddenBiased[k - 1], this.weights[k], this.activationFunction));
+                        }
+                        hiddenBiased.push(hidden[k].biased());
+                    }
+                    let rMinusY = this.calculateRMinusY(trainSet.get(j), hiddenBiased[this.hiddenLayerSize - 1], this.weights[this.weights.length - 1]);
+                    deltaWeights.splice(0, 0, new Matrix_1.Matrix(rMinusY, hiddenBiased[this.hiddenLayerSize - 1]));
+                    for (let k = this.weights.length - 2; k >= 0; k--) {
+                        let tmph;
+                        if (k == this.weights.length - 2) {
+                            tmph = this.weights[k + 1].multiplyWithVectorFromLeft(rMinusY);
+                        }
+                        else {
+                            tmph = this.weights[k + 1].multiplyWithVectorFromLeft(tmpHidden);
+                        }
+                        tmph.remove(0);
+                        let activationDerivative;
+                        switch (this.activationFunction) {
+                            case ActivationFunction_1.ActivationFunction.SIGMOID:
+                            default:
+                                let oneMinusHidden = this.calculateOneMinusHidden(hidden[k]);
+                                activationDerivative = oneMinusHidden.elementProduct(hidden[k]);
+                                break;
+                            case ActivationFunction_1.ActivationFunction.TANH:
+                                let one = new Vector_1.Vector(hidden.length, 1.0);
+                                hidden[k].tanh();
+                                activationDerivative = one.difference(hidden[k].elementProduct(hidden[k]));
+                                break;
+                            case ActivationFunction_1.ActivationFunction.RELU:
+                                hidden[k].reluDerivative();
+                                activationDerivative = hidden[k];
+                                break;
+                        }
+                        tmpHidden = tmph.elementProduct(activationDerivative);
+                        if (k == 0) {
+                            deltaWeights.splice(0, 0, new Matrix_1.Matrix(tmpHidden, this.x));
+                        }
+                        else {
+                            deltaWeights.splice(0, 0, new Matrix_1.Matrix(tmpHidden, hiddenBiased[k - 1]));
+                        }
+                    }
+                    for (let k = 0; k < this.weights.length; k++) {
+                        deltaWeights[k].multiplyWithConstant(learningRate);
+                        this.weights[k].add(deltaWeights[k]);
+                    }
+                }
+                let currentClassificationPerformance = this.testClassifier(validationSet);
+                if (currentClassificationPerformance.getAccuracy() > bestClassificationPerformance.getAccuracy()) {
+                    bestClassificationPerformance = currentClassificationPerformance;
+                    bestWeights = this.setBestWeights();
+                }
+                learningRate *= parameters.getEtaDecrease();
+            }
+            this.weights = new Array();
+            for (let m of bestWeights) {
+                this.weights.push(m);
+            }
+        }
+        /**
+         * The allocateWeights method takes {@link DeepNetworkParameter}s as an input. First it adds random weights to the {@link Array}
+         * of {@link Matrix} weights' first layer. Then it loops through the layers and adds random weights till the last layer.
+         * At the end it adds random weights to the last layer and also sets the hiddenLayerSize value.
+         *
+         * @param parameters {@link DeepNetworkParameter} input.
+         */
+        allocateWeights(parameters) {
+            this.weights = new Array();
+            this.weights.push(this.allocateLayerWeights(parameters.getHiddenNodes(0), this.d + 1));
+            for (let i = 0; i < parameters.layerSize() - 1; i++) {
+                this.weights.push(this.allocateLayerWeights(parameters.getHiddenNodes(i + 1), parameters.getHiddenNodes(i) + 1));
+            }
+            this.weights.push(this.allocateLayerWeights(this.K, parameters.getHiddenNodes(parameters.layerSize() - 1) + 1));
+            this.hiddenLayerSize = parameters.layerSize();
+        }
+        /**
+         * The setBestWeights method creates an {@link Array} of Matrix as bestWeights and clones the values of weights {@link Array}
+         * into this newly created {@link Array}.
+         *
+         * @return An {@link Array} clones from the weights ArrayList.
+         */
+        setBestWeights() {
+            let bestWeights = new Array();
+            for (let m of this.weights) {
+                bestWeights.push(m.clone());
+            }
+            return bestWeights;
+        }
+        /**
+         * The calculateOutput method loops size of the weights times and calculate one hidden layer at a time and adds bias term.
+         * At the end it updates the output y value.
+         */
+        calculateOutput() {
+            let hiddenBiased;
+            for (let i = 0; i < this.weights.length - 1; i++) {
+                let hidden;
+                if (i == 0) {
+                    hidden = this.calculateHidden(this.x, this.weights[i], this.activationFunction);
+                }
+                else {
+                    hidden = this.calculateHidden(hiddenBiased, this.weights[i], this.activationFunction);
+                }
+                hiddenBiased = hidden.biased();
+            }
+            this.y = this.weights[this.weights.length - 1].multiplyWithVectorFromRight(hiddenBiased);
+        }
+    }
+    exports.DeepNetworkModel = DeepNetworkModel;
+});
+//# sourceMappingURL=DeepNetworkModel.js.map

package/dist/Model/DeepNetworkModel.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"DeepNetworkModel.js","sourceRoot":"","sources":["../../source/Model/DeepNetworkModel.ts"],"names":[],"mappings":";;;;;;;;;;;;IAAA,6DAAwD;IACxD,wDAAmD;IACnD,wEAAmE;IAGnE,wDAAmD;IACnD,wFAAmF;IAEnF,MAAa,gBAAiB,SAAQ,uCAAkB;QAqCpD;;;;;;;;;;;;WAYG;QACH,YAAY,QAAsB,EAAE,aAA2B,EAAE,UAAgC;YAC7F,KAAK,CAAC,QAAQ,CAAC,CAAC;YAChB,IAAI,SAAS,GAAG,IAAI,eAAM,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;YACjC,IAAI,YAAY,GAAG,IAAI,KAAK,EAAU,CAAC;YACvC,IAAI,MAAM,GAAG,IAAI,KAAK,EAAU,CAAC;YACjC,IAAI,YAAY,GAAG,IAAI,KAAK,EAAU,CAAC;YACvC,IAAI,CAAC,kBAAkB,GAAG,UAAU,CAAC,qBAAqB,EAAE,CAAC;YAC7D,IAAI,CAAC,eAAe,CAAC,UAAU,CAAC,CAAC;YACjC,IAAI,WAAW,GAAG,IAAI,CAAC,cAAc,EAAE,CAAC;YACxC,IAAI,6BAA6B,GAAG,IAAI,qDAAyB,CAAC,GAAG,CAAC,CAAC;YACvE,IAAI,KAAK,GAAG,UAAU,CAAC,QAAQ,EAAE,CAAC;YAClC,IAAI,YAAY,GAAG,UAAU,CAAC,eAAe,EAAE,CAAC;YAChD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE;gBAC5B,QAAQ,CAAC,OAAO,CAAC,UAAU,CAAC,OAAO,EAAE,CAAC,CAAC;gBACvC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE;oBACtC,IAAI,CAAC,iBAAiB,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;oBACxC,MAAM,GAAG,IAAI,KAAK,EAAU,CAAC;oBAC7B,YAAY,GAAG,IAAI,KAAK,EAAU,CAAC;oBACnC,YAAY,GAAG,IAAI,KAAK,EAAU,CAAC;oBACnC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,eAAe,EAAE,CAAC,EAAE,EAAE;wBAC3C,IAAI,CAAC,IAAI,CAAC,EAAE;4BACR,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,kBAAkB,CAAC,CAAC,CAAC;yBACvF;6BAAM;4BACH,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,eAAe,CAAC,YAAY,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,kBAAkB,CAAC,CAAC,CAAC;yBACpG;wBACD,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC;qBACzC;oBACD,IAAI,OAAO,GAAG,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,YAAY,CAAC,IAAI,CAAC,eAAe,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC;oBACpI,YAAY,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,EAAE,IAAI,eAAM,CAAC,OAAO,EAAE,YAAY,CAAC,IAAI,CAAC,eAAe,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;oBACvF,KAAK,IAAI,CAAC,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,EAAE;wBAC/C,IAAI,IAAI,CAAA;wBACR,IAAI,CAAC,IAAI,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAC;4BAC7B,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,0BAA0B,CAAC,OAAO,CAAC,CAAC;yBAClE;6BAAM;4BACH,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,0BAA0B,CAAC,SAAS,CAAC,CAAC;yBACpE;wBACD,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC;wBACf,IAAI,oBAAoB,CAAA;wBACxB,QAAQ,IAAI,CAAC,kBAAkB,EAAC;4BAC5B,KAAK,uCAAkB,CAAC,OAAO,CAAC;4BAChC;gCACI,IAAI,cAAc,GAAG,IAAI,CAAC,uBAAuB,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;gCAC7D,oBAAoB,GAAG,cAAc,CAAC,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC;gCAChE,MAAM;4BACV,KAAK,uCAAkB,CAAC,IAAI;gCACxB,IAAI,GAAG,GAAG,IAAI,eAAM,CAAC,MAAM,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;gCACzC,MAAM,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;gCACjB,oBAAoB,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gCAC3E,MAAM;4BACV,KAAK,uCAAkB,CAAC,IAAI;gCACxB,MAAM,CAAC,CAAC,CAAC,CAAC,cAAc,EAAE,CAAC;gCAC3B,oBAAoB,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC;gCACjC,MAAM;yBACb;wBACD,SAAS,GAAG,IAAI,CAAC,cAAc,CAAC,oBAAoB,CAAC,CAAC;wBACtD,IAAI,CAAC,IAAI,CAAC,EAAE;4BACR,YAAY,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,EAAE,IAAI,eAAM,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC;yBAC5D;6BAAM;4BACH,YAAY,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,EAAE,IAAI,eAAM,CAAC,SAAS,EAAE,YAAY,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;yBACzE;qBACJ;oBACD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;wBAC1C,YAAY,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,YAAY,CAAC,CAAC;wBACnD,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,CAAC;qBACxC;iBACJ;gBACD,IAAI,gCAAgC,GAAG,IAAI,CAAC,cAAc,CAAC,aAAa,CAAC,CAAC;gBAC1E,IAAI,gCAAgC,CAAC,WAAW,EAAE,GAAG,6BAA6B,CAAC,WAAW,EAAE,EAAE;oBAC9F,6BAA6B,GAAG,gCAAgC,CAAC;oBACjE,WAAW,GAAG,IAAI,CAAC,cAAc,EAAE,CAAC;iBACvC;gBACD,YAAY,IAAI,UAAU,CAAC,cAAc,EAAE,CAAC;aAC/C;YACD,IAAI,CAAC,OAAO,GAAG,IAAI,KAAK,EAAU,CAAC;YACnC,KAAK,IAAI,CAAC,IAAI,WAAW,EAAE;gBACvB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;aACxB;QACL,CAAC;QAzHD;;;;;;WAMG;QACK,eAAe,CAAC,UAAgC;YACpD,IAAI,CAAC,OAAO,GAAG,IAAI,KAAK,EAAU,CAAC;YACnC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,oBAAoB,CAAC,UAAU,CAAC,cAAc,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YACvF,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,UAAU,CAAC,SAAS,EAAE,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE;gBACjD,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,oBAAoB,CAAC,UAAU,CAAC,cAAc,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,UAAU,CAAC,cAAc,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;aACpH;YACD,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,CAAC,EAAE,UAAU,CAAC,cAAc,CAAC,UAAU,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;YAChH,IAAI,CAAC,eAAe,GAAG,UAAU,CAAC,SAAS,EAAE,CAAC;QAClD,CAAC;QAED;;;;;WAKG;QACK,cAAc;YAClB,IAAI,WAAW,GAAG,IAAI,KAAK,EAAU,CAAC;YACtC,KAAK,IAAI,CAAC,IAAI,IAAI,CAAC,OAAO,EAAE;gBACxB,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,EAAE,CAAC,CAAC;aAC/B;YACD,OAAO,WAAW,CAAC;QACvB,CAAC;QA8FD;;;WAGG;QACO,eAAe;YACrB,IAAI,YAAY,CAAA;YAChB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE;gBAC9C,IAAI,MAAM,CAAA;gBACV,IAAI,CAAC,IAAI,CAAC,EAAE;oBACR,MAAM,GAAG,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,kBAAkB,CAAC,CAAC;iBACnF;qBAAM;oBACH,MAAM,GAAG,IAAI,CAAC,eAAe,CAAC,YAAY,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,kBAAkB,CAAC,CAAC;iBACzF;gBACD,YAAY,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC;aAClC;YACD,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,2BAA2B,CAAC,YAAY,CAAC,CAAC;QAC7F,CAAC;KAEJ;IAnJD,4CAmJC"}

package/dist/Model/DummyModel.d.ts

@@ -0,0 +1,20 @@
+import { Model } from "./Model";
+import { Instance } from "../Instance/Instance";
+import { InstanceList } from "../InstanceList/InstanceList";
+export declare class DummyModel extends Model {
+    private distribution;
+    /**
+     * Constructor which sets the distribution using the given {@link InstanceList}.
+     *
+     * @param trainSet {@link InstanceList} which is used to get the class distribution.
+     */
+    constructor(trainSet: InstanceList);
+    /**
+     * The predict method takes an Instance as an input and returns the entry of distribution which has the maximum value.
+     *
+     * @param instance Instance to make prediction.
+     * @return The entry of distribution which has the maximum value.
+     */
+    predict(instance: Instance): string;
+    predictProbability(instance: Instance): Map<string, number>;
+}

package/dist/Model/DummyModel.js

@@ -0,0 +1,46 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports", "./Model", "../Instance/CompositeInstance"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.DummyModel = void 0;
+    const Model_1 = require("./Model");
+    const CompositeInstance_1 = require("../Instance/CompositeInstance");
+    class DummyModel extends Model_1.Model {
+        /**
+         * Constructor which sets the distribution using the given {@link InstanceList}.
+         *
+         * @param trainSet {@link InstanceList} which is used to get the class distribution.
+         */
+        constructor(trainSet) {
+            super();
+            this.distribution = trainSet.classDistribution();
+        }
+        /**
+         * The predict method takes an Instance as an input and returns the entry of distribution which has the maximum value.
+         *
+         * @param instance Instance to make prediction.
+         * @return The entry of distribution which has the maximum value.
+         */
+        predict(instance) {
+            if ((instance instanceof CompositeInstance_1.CompositeInstance)) {
+                let possibleClassLabels = instance.getPossibleClassLabels();
+                return this.distribution.getMaxItem(possibleClassLabels);
+            }
+            else {
+                return this.distribution.getMaxItem();
+            }
+        }
+        predictProbability(instance) {
+            return this.distribution.getProbabilityDistribution();
+        }
+    }
+    exports.DummyModel = DummyModel;
+});
+//# sourceMappingURL=DummyModel.js.map

package/dist/Model/DummyModel.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"DummyModel.js","sourceRoot":"","sources":["../../source/Model/DummyModel.ts"],"names":[],"mappings":";;;;;;;;;;;;IAAA,mCAA8B;IAI9B,qEAAgE;IAEhE,MAAa,UAAW,SAAQ,aAAK;QAIjC;;;;WAIG;QACH,YAAY,QAAsB;YAC9B,KAAK,EAAE,CAAC;YACR,IAAI,CAAC,YAAY,GAAG,QAAQ,CAAC,iBAAiB,EAAE,CAAC;QACrD,CAAC;QAED;;;;;WAKG;QACH,OAAO,CAAC,QAAkB;YACtB,IAAI,CAAC,QAAQ,YAAY,qCAAiB,CAAC,EAAE;gBACzC,IAAI,mBAAmB,GAAwB,QAAS,CAAC,sBAAsB,EAAE,CAAC;gBAClF,OAAO,IAAI,CAAC,YAAY,CAAC,UAAU,CAAC,mBAAmB,CAAC,CAAC;aAC5D;iBAAM;gBACH,OAAO,IAAI,CAAC,YAAY,CAAC,UAAU,EAAE,CAAC;aACzC;QACL,CAAC;QAED,kBAAkB,CAAC,QAAkB;YACjC,OAAO,IAAI,CAAC,YAAY,CAAC,0BAA0B,EAAE,CAAC;QAC1D,CAAC;KAEJ;IAjCD,gCAiCC"}

package/dist/Model/GaussianModel.d.ts

@@ -0,0 +1,24 @@
+import { DiscreteDistribution } from "nlptoolkit-math/dist/DiscreteDistribution";
+import { Instance } from "../Instance/Instance";
+import { ValidatedModel } from "./ValidatedModel";
+export declare abstract class GaussianModel extends ValidatedModel {
+    protected priorDistribution: DiscreteDistribution;
+    /**
+     * Abstract method calculateMetric takes an {@link Instance} and a String as inputs.
+     *
+     * @param instance {@link Instance} input.
+     * @param Ci       String input.
+     * @return A double value as metric.
+     */
+    abstract calculateMetric(instance: Instance, Ci: string): number;
+    /**
+     * The predict method takes an Instance as an input. First it gets the size of prior distribution and loops this size times.
+     * Then it gets the possible class labels and and calculates metric value. At the end, it returns the class which has the
+     * maximum value of metric.
+     *
+     * @param instance {@link Instance} to predict.
+     * @return The class which has the maximum value of metric.
+     */
+    predict(instance: Instance): string;
+    predictProbability(instance: Instance): Map<string, number>;
+}

package/dist/Model/GaussianModel.js

@@ -0,0 +1,59 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports", "./ValidatedModel", "../Instance/CompositeInstance"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.GaussianModel = void 0;
+    const ValidatedModel_1 = require("./ValidatedModel");
+    const CompositeInstance_1 = require("../Instance/CompositeInstance");
+    class GaussianModel extends ValidatedModel_1.ValidatedModel {
+        /**
+         * The predict method takes an Instance as an input. First it gets the size of prior distribution and loops this size times.
+         * Then it gets the possible class labels and and calculates metric value. At the end, it returns the class which has the
+         * maximum value of metric.
+         *
+         * @param instance {@link Instance} to predict.
+         * @return The class which has the maximum value of metric.
+         */
+        predict(instance) {
+            let maxMetric = Number.NEGATIVE_INFINITY;
+            let predictedClass, size;
+            if (instance instanceof CompositeInstance_1.CompositeInstance) {
+                predictedClass = instance.getPossibleClassLabels()[0];
+                size = instance.getPossibleClassLabels().length;
+            }
+            else {
+                predictedClass = this.priorDistribution.getMaxItem();
+                size = this.priorDistribution.size;
+            }
+            for (let i = 0; i < size; i++) {
+                let Ci;
+                if (instance instanceof CompositeInstance_1.CompositeInstance) {
+                    Ci = instance.getPossibleClassLabels()[i];
+                }
+                else {
+                    Ci = this.priorDistribution.getItem(i);
+                }
+                if (this.priorDistribution.containsItem(Ci)) {
+                    let metric = this.calculateMetric(instance, Ci);
+                    if (metric > maxMetric) {
+                        maxMetric = metric;
+                        predictedClass = Ci;
+                    }
+                }
+            }
+            return predictedClass;
+        }
+        predictProbability(instance) {
+            return undefined;
+        }
+    }
+    exports.GaussianModel = GaussianModel;
+});
+//# sourceMappingURL=GaussianModel.js.map

package/dist/Model/GaussianModel.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"GaussianModel.js","sourceRoot":"","sources":["../../source/Model/GaussianModel.ts"],"names":[],"mappings":";;;;;;;;;;;;IAEA,qDAAgD;IAChD,qEAAgE;IAEhE,MAAsB,aAAc,SAAQ,+BAAc;QAatD;;;;;;;WAOG;QACH,OAAO,CAAC,QAAkB;YACtB,IAAI,SAAS,GAAG,MAAM,CAAC,iBAAiB,CAAC;YACzC,IAAI,cAAc,EAAE,IAAI,CAAA;YACxB,IAAI,QAAQ,YAAY,qCAAiB,EAAE;gBACvC,cAAc,GAAwB,QAAS,CAAC,sBAAsB,EAAE,CAAC,CAAC,CAAC,CAAC;gBAC5E,IAAI,GAAwB,QAAS,CAAC,sBAAsB,EAAE,CAAC,MAAM,CAAC;aACzE;iBAAM;gBACH,cAAc,GAAG,IAAI,CAAC,iBAAiB,CAAC,UAAU,EAAE,CAAC;gBACrD,IAAI,GAAG,IAAI,CAAC,iBAAiB,CAAC,IAAI,CAAC;aACtC;YACD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,EAAE,CAAC,EAAE,EAAE;gBAC3B,IAAI,EAAE,CAAA;gBACN,IAAI,QAAQ,YAAY,qCAAiB,EAAE;oBACvC,EAAE,GAAwB,QAAS,CAAC,sBAAsB,EAAE,CAAC,CAAC,CAAC,CAAC;iBACnE;qBAAM;oBACH,EAAE,GAAG,IAAI,CAAC,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;iBAC1C;gBACD,IAAI,IAAI,CAAC,iBAAiB,CAAC,YAAY,CAAC,EAAE,CAAC,EAAE;oBACzC,IAAI,MAAM,GAAG,IAAI,CAAC,eAAe,CAAC,QAAQ,EAAE,EAAE,CAAC,CAAC;oBAChD,IAAI,MAAM,GAAG,SAAS,EAAE;wBACpB,SAAS,GAAG,MAAM,CAAC;wBACnB,cAAc,GAAG,EAAE,CAAC;qBACvB;iBACJ;aACJ;YACD,OAAO,cAAc,CAAC;QAC1B,CAAC;QAED,kBAAkB,CAAC,QAAkB;YACjC,OAAO,SAAS,CAAC;QACrB,CAAC;KACJ;IApDD,sCAoDC"}

package/dist/Model/KMeansModel.d.ts

@@ -0,0 +1,27 @@
+import { GaussianModel } from "./GaussianModel";
+import { InstanceList } from "../InstanceList/InstanceList";
+import { DistanceMetric } from "../DistanceMetric/DistanceMetric";
+import { Instance } from "../Instance/Instance";
+import { DiscreteDistribution } from "nlptoolkit-math/dist/DiscreteDistribution";
+export declare class KMeansModel extends GaussianModel {
+    private classMeans;
+    private distanceMetric;
+    /**
+     * The constructor that sets the classMeans, priorDistribution and distanceMetric according to given inputs.
+     *
+     * @param priorDistribution {@link DiscreteDistribution} input.
+     * @param classMeans        {@link InstanceList} of class means.
+     * @param distanceMetric    {@link DistanceMetric} input.
+     */
+    constructor(priorDistribution: DiscreteDistribution, classMeans: InstanceList, distanceMetric: DistanceMetric);
+    /**
+     * The calculateMetric method takes an {@link Instance} and a String as inputs. It loops through the class means, if
+     * the corresponding class label is same as the given String it returns the negated distance between given instance and the
+     * current item of class means. Otherwise it returns the smallest negative number.
+     *
+     * @param instance {@link Instance} input.
+     * @param Ci       String input.
+     * @return The negated distance between given instance and the current item of class means.
+     */
+    calculateMetric(instance: Instance, Ci: string): number;
+}

package/dist/Model/KMeansModel.js

@@ -0,0 +1,48 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports", "./GaussianModel"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.KMeansModel = void 0;
+    const GaussianModel_1 = require("./GaussianModel");
+    class KMeansModel extends GaussianModel_1.GaussianModel {
+        /**
+         * The constructor that sets the classMeans, priorDistribution and distanceMetric according to given inputs.
+         *
+         * @param priorDistribution {@link DiscreteDistribution} input.
+         * @param classMeans        {@link InstanceList} of class means.
+         * @param distanceMetric    {@link DistanceMetric} input.
+         */
+        constructor(priorDistribution, classMeans, distanceMetric) {
+            super();
+            this.classMeans = classMeans;
+            this.priorDistribution = priorDistribution;
+            this.distanceMetric = distanceMetric;
+        }
+        /**
+         * The calculateMetric method takes an {@link Instance} and a String as inputs. It loops through the class means, if
+         * the corresponding class label is same as the given String it returns the negated distance between given instance and the
+         * current item of class means. Otherwise it returns the smallest negative number.
+         *
+         * @param instance {@link Instance} input.
+         * @param Ci       String input.
+         * @return The negated distance between given instance and the current item of class means.
+         */
+        calculateMetric(instance, Ci) {
+            for (let i = 0; i < this.classMeans.size(); i++) {
+                if (this.classMeans.get(i).getClassLabel() == Ci) {
+                    return -this.distanceMetric.distance(instance, this.classMeans.get(i));
+                }
+            }
+            return Number.NEGATIVE_INFINITY;
+        }
+    }
+    exports.KMeansModel = KMeansModel;
+});
+//# sourceMappingURL=KMeansModel.js.map

package/dist/Model/KMeansModel.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"KMeansModel.js","sourceRoot":"","sources":["../../source/Model/KMeansModel.ts"],"names":[],"mappings":";;;;;;;;;;;;IAAA,mDAA8C;IAM9C,MAAa,WAAY,SAAQ,6BAAa;QAK1C;;;;;;WAMG;QACH,YAAY,iBAAuC,EAAE,UAAwB,EAAE,cAA8B;YACzG,KAAK,EAAE,CAAC;YACR,IAAI,CAAC,UAAU,GAAG,UAAU,CAAC;YAC7B,IAAI,CAAC,iBAAiB,GAAG,iBAAiB,CAAC;YAC3C,IAAI,CAAC,cAAc,GAAG,cAAc,CAAC;QACzC,CAAC;QAED;;;;;;;;WAQG;QACH,eAAe,CAAC,QAAkB,EAAE,EAAU;YAC1C,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,UAAU,CAAC,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE;gBAC7C,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,aAAa,EAAE,IAAI,EAAE,EAAE;oBAC9C,OAAO,CAAC,IAAI,CAAC,cAAc,CAAC,QAAQ,CAAC,QAAQ,EAAE,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;iBAC1E;aACJ;YACD,OAAO,MAAM,CAAC,iBAAiB,CAAC;QACpC,CAAC;KAEJ;IArCD,kCAqCC"}

package/dist/Model/KnnInstance.d.ts

@@ -0,0 +1,14 @@
+import { Instance } from "../Instance/Instance";
+export declare class KnnInstance {
+    private readonly distance;
+    private readonly instance;
+    /**
+     * The constructor that sets the instance and distance value.
+     *
+     * @param instance {@link Instance} input.
+     * @param distance Double distance value.
+     */
+    constructor(instance: Instance, distance: number);
+    getInstance(): Instance;
+    getDistance(): number;
+}

package/dist/Model/KnnInstance.js

@@ -0,0 +1,33 @@
+(function (factory) {
+    if (typeof module === "object" && typeof module.exports === "object") {
+        var v = factory(require, exports);
+        if (v !== undefined) module.exports = v;
+    }
+    else if (typeof define === "function" && define.amd) {
+        define(["require", "exports"], factory);
+    }
+})(function (require, exports) {
+    "use strict";
+    Object.defineProperty(exports, "__esModule", { value: true });
+    exports.KnnInstance = void 0;
+    class KnnInstance {
+        /**
+         * The constructor that sets the instance and distance value.
+         *
+         * @param instance {@link Instance} input.
+         * @param distance Double distance value.
+         */
+        constructor(instance, distance) {
+            this.instance = instance;
+            this.distance = distance;
+        }
+        getInstance() {
+            return this.instance;
+        }
+        getDistance() {
+            return this.distance;
+        }
+    }
+    exports.KnnInstance = KnnInstance;
+});
+//# sourceMappingURL=KnnInstance.js.map

package/dist/Model/KnnInstance.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"KnnInstance.js","sourceRoot":"","sources":["../../source/Model/KnnInstance.ts"],"names":[],"mappings":";;;;;;;;;;;;IAEA,MAAa,WAAW;QAKpB;;;;;WAKG;QACH,YAAY,QAAkB,EAAE,QAAgB;YAC5C,IAAI,CAAC,QAAQ,GAAG,QAAQ,CAAC;YACzB,IAAI,CAAC,QAAQ,GAAG,QAAQ,CAAC;QAC7B,CAAC;QAED,WAAW;YACP,OAAO,IAAI,CAAC,QAAQ,CAAA;QACxB,CAAC;QAED,WAAW;YACP,OAAO,IAAI,CAAC,QAAQ,CAAA;QACxB,CAAC;KAEJ;IAxBD,kCAwBC"}