@jsmlt/jsmlt/distribution/supervised/trees/random-forest.js

JavaScript Machine Learning

"use strict";

Object.defineProperty(exports, "__esModule", {
  value: true
});
exports["default"] = void 0;

var _base = require("../base");

var _decisionTree = _interopRequireDefault(require("./decision-tree"));

var Arrays = _interopRequireWildcard(require("../../arrays"));

var Random = _interopRequireWildcard(require("../../random"));

function _getRequireWildcardCache() { if (typeof WeakMap !== "function") return null; var cache = new WeakMap(); _getRequireWildcardCache = function _getRequireWildcardCache() { return cache; }; return cache; }

function _interopRequireWildcard(obj) { if (obj && obj.__esModule) { return obj; } var cache = _getRequireWildcardCache(); if (cache && cache.has(obj)) { return cache.get(obj); } var newObj = {}; if (obj != null) { var hasPropertyDescriptor = Object.defineProperty && Object.getOwnPropertyDescriptor; for (var key in obj) { if (Object.prototype.hasOwnProperty.call(obj, key)) { var desc = hasPropertyDescriptor ? Object.getOwnPropertyDescriptor(obj, key) : null; if (desc && (desc.get || desc.set)) { Object.defineProperty(newObj, key, desc); } else { newObj[key] = obj[key]; } } } } newObj["default"] = obj; if (cache) { cache.set(obj, newObj); } return newObj; }

function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { "default": obj }; }

function _typeof(obj) { if (typeof Symbol === "function" && typeof Symbol.iterator === "symbol") { _typeof = function _typeof(obj) { return typeof obj; }; } else { _typeof = function _typeof(obj) { return obj && typeof Symbol === "function" && obj.constructor === Symbol && obj !== Symbol.prototype ? "symbol" : typeof obj; }; } return _typeof(obj); }

function _toConsumableArray(arr) { return _arrayWithoutHoles(arr) || _iterableToArray(arr) || _nonIterableSpread(); }

function _nonIterableSpread() { throw new TypeError("Invalid attempt to spread non-iterable instance"); }

function _iterableToArray(iter) { if (Symbol.iterator in Object(iter) || Object.prototype.toString.call(iter) === "[object Arguments]") return Array.from(iter); }

function _arrayWithoutHoles(arr) { if (Array.isArray(arr)) { for (var i = 0, arr2 = new Array(arr.length); i < arr.length; i++) { arr2[i] = arr[i]; } return arr2; } }

function ownKeys(object, enumerableOnly) { var keys = Object.keys(object); if (Object.getOwnPropertySymbols) { var symbols = Object.getOwnPropertySymbols(object); if (enumerableOnly) symbols = symbols.filter(function (sym) { return Object.getOwnPropertyDescriptor(object, sym).enumerable; }); keys.push.apply(keys, symbols); } return keys; }

function _objectSpread(target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i] != null ? arguments[i] : {}; if (i % 2) { ownKeys(source, true).forEach(function (key) { _defineProperty(target, key, source[key]); }); } else if (Object.getOwnPropertyDescriptors) { Object.defineProperties(target, Object.getOwnPropertyDescriptors(source)); } else { ownKeys(source).forEach(function (key) { Object.defineProperty(target, key, Object.getOwnPropertyDescriptor(source, key)); }); } } return target; }

function _defineProperty(obj, key, value) { if (key in obj) { Object.defineProperty(obj, key, { value: value, enumerable: true, configurable: true, writable: true }); } else { obj[key] = value; } return obj; }

function _classCallCheck(instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } }

function _defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } }

function _createClass(Constructor, protoProps, staticProps) { if (protoProps) _defineProperties(Constructor.prototype, protoProps); if (staticProps) _defineProperties(Constructor, staticProps); return Constructor; }

function _possibleConstructorReturn(self, call) { if (call && (_typeof(call) === "object" || typeof call === "function")) { return call; } return _assertThisInitialized(self); }

function _assertThisInitialized(self) { if (self === void 0) { throw new ReferenceError("this hasn't been initialised - super() hasn't been called"); } return self; }

function _getPrototypeOf(o) { _getPrototypeOf = Object.setPrototypeOf ? Object.getPrototypeOf : function _getPrototypeOf(o) { return o.__proto__ || Object.getPrototypeOf(o); }; return _getPrototypeOf(o); }

function _inherits(subClass, superClass) { if (typeof superClass !== "function" && superClass !== null) { throw new TypeError("Super expression must either be null or a function"); } subClass.prototype = Object.create(superClass && superClass.prototype, { constructor: { value: subClass, writable: true, configurable: true } }); if (superClass) _setPrototypeOf(subClass, superClass); }

function _setPrototypeOf(o, p) { _setPrototypeOf = Object.setPrototypeOf || function _setPrototypeOf(o, p) { o.__proto__ = p; return o; }; return _setPrototypeOf(o, p); }

/**
 * Random forest learner. Builds multiple decision trees with a random subsample of the samples,
 * and averages their predictions for the final prediction model.
 */
var RandomForest =
/*#__PURE__*/
function (_Classifier) {
  _inherits(RandomForest, _Classifier);

  /**
   * Constructor. Initialize class members and store user-defined options.
   *
   * @param {Object} [optionsUser] - User-defined options for random forest
   * @param {number} [optionsUser.numTrees = 10] - Number of decision trees to build
   * @param {string} [optionsUser.criterion = 'gini'] - Splitting criterion. Either 'gini', for the
   *   Gini coefficient, or 'entropy' for the Shannon entropy
   * @param {number|string} [optionsUser.numFeatures = 1.0] - Number of features to subsample at
   *   each node. Either a number (float), in which case the input fraction of features is used
   *   (e.g., 1.0 for all features), or a string. If string, 'sqrt' and 'log2' are supported,
   *   causing the algorithm to use sqrt(n) and log2(n) features, respectively (where n is the
   *   total number of features)
   * @param {number} [optionsUser.maxDepth = -1] - Maximum depth of each decision tree. The depth of
   *   a decision tree is the number of nodes in the longest path from the decision tree root to a
   *   leaf. It is an indicator of the complexity of the tree. Use -1 for no maximum depth
   * @param {boolean} [bootstrap = true] - Whether to select samples for each tree by bootstrapping.
   *   If false, all samples are used for each tree. If true, n samples are drawn with replacement
   *   from the full set of samples for each tree (where n is the total number of samples)
   * @param {number} [optionsUser.numTrees = 10] - Number of trees to construct
   */
  function RandomForest() {
    var _this;

    var optionsUser = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : {};

    _classCallCheck(this, RandomForest);

    _this = _possibleConstructorReturn(this, _getPrototypeOf(RandomForest).call(this)); // Parse options

    var optionsDefault = {
      criterion: 'gini',
      numFeatures: 1.0,
      maxDepth: -1,
      numTrees: 10,
      bootstrap: true
    };

    var options = _objectSpread({}, optionsDefault, {}, optionsUser); // Set options


    _this.criterion = options.criterion;
    _this.numFeatures = options.numFeatures;
    _this.maxDepth = options.maxDepth;
    _this.numTrees = options.numTrees;
    _this.bootstrap = options.bootstrap;
    return _this;
  }
  /**
   * @see {@link Classifier#train}
   */


  _createClass(RandomForest, [{
    key: "train",
    value: function train(X, y) {
      if (X.length !== y.length) {
        throw new Error('Number of data points should match number of labels.');
      } // Construct and train decision trees


      this.trees = []; // All sample indices

      var sampleIndices = _toConsumableArray(Array(X.length)).map(function (x, i) {
        return i;
      });

      for (var i = 0; i < this.numTrees; i += 1) {
        // Construct decision tree
        var tree = new _decisionTree["default"]({
          criterion: this.criterion,
          numFeatures: this.numFeatures,
          maxDepth: this.maxDepth
        }); // Select the input samples. If bootstrapping is disabled, use all samples. If it is enabled,
        // use a bootstrapped sample of all samples

        var treeX = void 0;
        var treeY = void 0;

        if (this.bootstrap) {
          var treeSamples = Random.sample(sampleIndices, X.length, true);
          treeX = treeSamples.map(function (sampleIndex) {
            return X[sampleIndex];
          });
          treeY = treeSamples.map(function (sampleIndex) {
            return y[sampleIndex];
          });
        } else {
          treeX = X;
          treeY = y;
        } // Train the tree


        tree.train(treeX, treeY); // Add the trained tree to the list of trees

        this.trees.push(tree);
      }
    }
    /**
     * @see {@link Classifier#predict}
     */

  }, {
    key: "predict",
    value: function predict(X) {
      var _this2 = this;

      if (typeof this.trees === 'undefined') {
        throw new Error('Model has to be trained in order to make predictions.');
      } // Make prediction for each data point


      var predictions = X.map(function (x) {
        return _this2.predictSample(x);
      });
      return predictions;
    }
    /**
     * Make a prediction for a single sample.
     *
     * @param {Array.<number>} sampleFeatures - Data point features
     * @return {mixed} Prediction. Label of class with highest prevalence among k nearest neighbours
     */

  }, {
    key: "predictSample",
    value: function predictSample(sampleFeatures) {
      // Gather predictions from all trees
      var predictions = this.trees.map(function (x) {
        return x.predictSample(sampleFeatures);
      }); // Count the number of votes for each class

      var predictionCounts = Arrays.valueCounts(predictions); // Predict the class with the most predictions

      return predictionCounts.reduce(function (r, x) {
        return x[1] > r[1] ? x : r;
      }, [-1, -1])[0];
    }
  }]);

  return RandomForest;
}(_base.Classifier);

exports["default"] = RandomForest;
module.exports = exports.default;