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

JavaScript Machine Learning

'use strict';

Object.defineProperty(exports, "__esModule", {
  value: true
});

var _extends = Object.assign || function (target) { for (var i = 1; i < arguments.length; i++) { var source = arguments[i]; for (var key in source) { if (Object.prototype.hasOwnProperty.call(source, key)) { target[key] = source[key]; } } } return target; };

var _createClass = 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); } } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; }();

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

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

var _decisionTree2 = _interopRequireDefault(_decisionTree);

var _arrays = require('../../arrays');

var Arrays = _interopRequireWildcard(_arrays);

var _random = require('../../random');

var Random = _interopRequireWildcard(_random);

function _interopRequireWildcard(obj) { if (obj && obj.__esModule) { return obj; } else { var newObj = {}; if (obj != null) { for (var key in obj) { if (Object.prototype.hasOwnProperty.call(obj, key)) newObj[key] = obj[key]; } } newObj.default = obj; return newObj; } }

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

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

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

function _possibleConstructorReturn(self, call) { if (!self) { throw new ReferenceError("this hasn't been initialised - super() hasn't been called"); } return call && (typeof call === "object" || typeof call === "function") ? call : self; }

function _inherits(subClass, superClass) { if (typeof superClass !== "function" && superClass !== null) { throw new TypeError("Super expression must either be null or a function, not " + typeof superClass); } subClass.prototype = Object.create(superClass && superClass.prototype, { constructor: { value: subClass, enumerable: false, writable: true, configurable: true } }); if (superClass) Object.setPrototypeOf ? Object.setPrototypeOf(subClass, superClass) : subClass.__proto__ = superClass; } // Internal dependencies


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

    _classCallCheck(this, RandomForest);

    // Parse options
    var _this = _possibleConstructorReturn(this, (RandomForest.__proto__ || Object.getPrototypeOf(RandomForest)).call(this));

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

    var options = _extends({}, optionsDefault, optionsUser);

    // Set options
    _this.criterion = options.criterion;
    _this.numFeatures = options.numFeatures;
    _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 = [].concat(_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 _decisionTree2.default({
          criterion: this.criterion,
          numFeatures: this.numFeatures
        });

        // 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'];