{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Integration of Ensemble Models with Hyper-parameter Optimisation in Sklearn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This example shows how to integrate the random hyperboxes classifier with the Random Search Cross-Validation functionality implemented by scikit-learn.\n",
    "\n",
    "Note that this example uses the random hyperboxes model and Random Search for illustration. However, other hyperbox-based ensemble learning algorithms in the library can be used similarly for any hyper-parameter tunning methods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "import os\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from sklearn.model_selection import train_test_split\n",
    "from hbbrain.numerical_data.ensemble_learner.random_hyperboxes import RandomHyperboxesClassifier\n",
    "from hbbrain.numerical_data.incremental_learner.onln_gfmm import OnlineGFMM"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load dataset, normalize numerical features into the range of [0, 1] and build training and testing datasets.\n",
    "This example will use the breast cancer dataset in sklearn for illustration purposes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_breast_cancer\n",
    "from sklearn.preprocessing import MinMaxScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = load_breast_cancer()\n",
    "X = df.data\n",
    "y = df.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = MinMaxScaler()\n",
    "X = scaler.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8, random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using Random Search with 5-fold cross-validation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "parameters = {'n_estimators': [20, 30, 50, 100, 200, 500], \n",
    "              'max_samples': [0.2, 0.3, 0.4, 0.5, 0.6],\n",
    "              'max_features' : [0.2, 0.3, 0.4, 0.5, 0.6],\n",
    "              'class_balanced' : [True, False],\n",
    "              'feature_balanced' : [True, False],\n",
    "              'n_jobs' : [4],\n",
    "              'random_state' : [0],\n",
    "              'base_estimator__theta' : np.arange(0.05, 0.61, 0.05),\n",
    "              'base_estimator__gamma' : [0.5, 1, 2, 4, 8, 16]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Init base learner. This example uses the original online learning algorithm to train a GFMM classifier\n",
    "base_estimator = OnlineGFMM()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Using random search with only 40 random combinations of parameters\n",
    "random_hyperboxes_clf = RandomHyperboxesClassifier(base_estimator=base_estimator)\n",
    "clf_rd_search = RandomizedSearchCV(random_hyperboxes_clf, parameters, n_iter=40, cv=5, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5,\n",
       "                   estimator=RandomHyperboxesClassifier(base_estimator=OnlineGFMM(C=array([], dtype=float64),\n",
       "                                                                                  V=array([], dtype=float64),\n",
       "                                                                                  W=array([], dtype=float64))),\n",
       "                   n_iter=40,\n",
       "                   param_distributions={'base_estimator__gamma': [0.5, 1, 2, 4,\n",
       "                                                                  8, 16],\n",
       "                                        'base_estimator__theta': array([0.05, 0.1 , 0.15, 0.2 , 0.25, 0.3 , 0.35, 0.4 , 0.45, 0.5 , 0.55,\n",
       "       0.6 ]),\n",
       "                                        'class_balanced': [True, False],\n",
       "                                        'feature_balanced': [True, False],\n",
       "                                        'max_features': [0.2, 0.3, 0.4, 0.5,\n",
       "                                                         0.6],\n",
       "                                        'max_samples': [0.2, 0.3, 0.4, 0.5,\n",
       "                                                        0.6],\n",
       "                                        'n_estimators': [20, 30, 50, 100, 200,\n",
       "                                                         500],\n",
       "                                        'n_jobs': [4], 'random_state': [0]},\n",
       "                   random_state=0)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf_rd_search.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best average score =  0.9714285714285715\n",
      "Best params:  {'random_state': 0, 'n_jobs': 4, 'n_estimators': 500, 'max_samples': 0.6, 'max_features': 0.5, 'feature_balanced': True, 'class_balanced': False, 'base_estimator__theta': 0.15000000000000002, 'base_estimator__gamma': 16}\n"
     ]
    }
   ],
   "source": [
    "print(\"Best average score = \", clf_rd_search.best_score_)\n",
    "print(\"Best params: \", clf_rd_search.best_params_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "best_gfmm_rd_search = clf_rd_search.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Testing the performance on the test set\n",
    "y_pred_rd_search = best_gfmm_rd_search.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy (random-search) =  96.49%\n"
     ]
    }
   ],
   "source": [
    "acc_rd_search = accuracy_score(y_test, y_pred_rd_search)\n",
    "print(f'Accuracy (random-search) = {acc_rd_search * 100: .2f}%')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}