07_ensemble_learning_and_random_forests.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Chapter 7 – Ensemble Learning and Random Forests**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "_This notebook contains all the sample code and solutions to the exercises in chapter 7._"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, let's import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures. We also check that Python 3.5 or later is installed (although Python 2.x may work, it is deprecated so we strongly recommend you use Python 3 instead), as well as Scikit-Learn ≥0.20."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Python ≥3.5 is required\n",
    "import sys\n",
    "assert sys.version_info >= (3, 5)\n",
    "\n",
    "# Scikit-Learn ≥0.20 is required\n",
    "import sklearn\n",
    "assert sklearn.__version__ >= \"0.20\"\n",
    "\n",
    "# Common imports\n",
    "import numpy as np\n",
    "import os\n",
    "\n",
    "# to make this notebook's output stable across runs\n",
    "np.random.seed(42)\n",
    "\n",
    "# To plot pretty figures\n",
    "%matplotlib inline\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "mpl.rc('axes', labelsize=14)\n",
    "mpl.rc('xtick', labelsize=12)\n",
    "mpl.rc('ytick', labelsize=12)\n",
    "\n",
    "# Where to save the figures\n",
    "PROJECT_ROOT_DIR = \".\"\n",
    "CHAPTER_ID = \"ensembles\"\n",
    "IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID)\n",
    "os.makedirs(IMAGES_PATH, exist_ok=True)\n",
    "\n",
    "def save_fig(fig_id, tight_layout=True, fig_extension=\"png\", resolution=300):\n",
    "    path = os.path.join(IMAGES_PATH, fig_id + \".\" + fig_extension)\n",
    "    print(\"Saving figure\", fig_id)\n",
    "    if tight_layout:\n",
    "        plt.tight_layout()\n",
    "    plt.savefig(path, format=fig_extension, dpi=resolution)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Voting classifiers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "heads_proba = 0.51\n",
    "coin_tosses = (np.random.rand(10000, 10) < heads_proba).astype(np.int32)\n",
    "cumulative_heads_ratio = np.cumsum(coin_tosses, axis=0) / np.arange(1, 10001).reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure law_of_large_numbers_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x252 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8,3.5))\n",
    "plt.plot(cumulative_heads_ratio)\n",
    "plt.plot([0, 10000], [0.51, 0.51], \"k--\", linewidth=2, label=\"51%\")\n",
    "plt.plot([0, 10000], [0.5, 0.5], \"k-\", label=\"50%\")\n",
    "plt.xlabel(\"Number of coin tosses\")\n",
    "plt.ylabel(\"Heads ratio\")\n",
    "plt.legend(loc=\"lower right\")\n",
    "plt.axis([0, 10000, 0.42, 0.58])\n",
    "save_fig(\"law_of_large_numbers_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.datasets import make_moons\n",
    "\n",
    "X, y = make_moons(n_samples=500, noise=0.30, random_state=42)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note**: to be future-proof, we set `solver=\"lbfgs\"`, `n_estimators=100`, and `gamma=\"scale\"` since these will be the default values in upcoming Scikit-Learn versions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.ensemble import VotingClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "log_clf = LogisticRegression(solver=\"lbfgs\", random_state=42)\n",
    "rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "svm_clf = SVC(gamma=\"scale\", random_state=42)\n",
    "\n",
    "voting_clf = VotingClassifier(\n",
    "    estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],\n",
    "    voting='hard')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('lr', LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=42, solver='lbfgs',\n",
       "          tol=0.0001, verbose=0, warm_start=False)), ('rf', RandomFor...f',\n",
       "  max_iter=-1, probability=False, random_state=42, shrinking=True,\n",
       "  tol=0.001, verbose=False))],\n",
       "         flatten_transform=None, n_jobs=None, voting='hard', weights=None)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LogisticRegression 0.864\n",
      "RandomForestClassifier 0.896\n",
      "SVC 0.896\n",
      "VotingClassifier 0.912\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "for clf in (log_clf, rnd_clf, svm_clf, voting_clf):\n",
    "    clf.fit(X_train, y_train)\n",
    "    y_pred = clf.predict(X_test)\n",
    "    print(clf.__class__.__name__, accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Soft voting:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('lr', LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=42, solver='lbfgs',\n",
       "          tol=0.0001, verbose=0, warm_start=False)), ('rf', RandomFor...bf',\n",
       "  max_iter=-1, probability=True, random_state=42, shrinking=True,\n",
       "  tol=0.001, verbose=False))],\n",
       "         flatten_transform=None, n_jobs=None, voting='soft', weights=None)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "log_clf = LogisticRegression(solver=\"lbfgs\", random_state=42)\n",
    "rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "svm_clf = SVC(gamma=\"scale\", probability=True, random_state=42)\n",
    "\n",
    "voting_clf = VotingClassifier(\n",
    "    estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],\n",
    "    voting='soft')\n",
    "voting_clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LogisticRegression 0.864\n",
      "RandomForestClassifier 0.896\n",
      "SVC 0.896\n",
      "VotingClassifier 0.92\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "for clf in (log_clf, rnd_clf, svm_clf, voting_clf):\n",
    "    clf.fit(X_train, y_train)\n",
    "    y_pred = clf.predict(X_test)\n",
    "    print(clf.__class__.__name__, accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bagging ensembles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import BaggingClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "bag_clf = BaggingClassifier(\n",
    "    DecisionTreeClassifier(random_state=42), n_estimators=500,\n",
    "    max_samples=100, bootstrap=True, random_state=42)\n",
    "bag_clf.fit(X_train, y_train)\n",
    "y_pred = bag_clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.904\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "print(accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.856\n"
     ]
    }
   ],
   "source": [
    "tree_clf = DecisionTreeClassifier(random_state=42)\n",
    "tree_clf.fit(X_train, y_train)\n",
    "y_pred_tree = tree_clf.predict(X_test)\n",
    "print(accuracy_score(y_test, y_pred_tree))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from matplotlib.colors import ListedColormap\n",
    "\n",
    "def plot_decision_boundary(clf, X, y, axes=[-1.5, 2.45, -1, 1.5], alpha=0.5, contour=True):\n",
    "    x1s = np.linspace(axes[0], axes[1], 100)\n",
    "    x2s = np.linspace(axes[2], axes[3], 100)\n",
    "    x1, x2 = np.meshgrid(x1s, x2s)\n",
    "    X_new = np.c_[x1.ravel(), x2.ravel()]\n",
    "    y_pred = clf.predict(X_new).reshape(x1.shape)\n",
    "    custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])\n",
    "    plt.contourf(x1, x2, y_pred, alpha=0.3, cmap=custom_cmap)\n",
    "    if contour:\n",
    "        custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])\n",
    "        plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)\n",
    "    plt.plot(X[:, 0][y==0], X[:, 1][y==0], \"yo\", alpha=alpha)\n",
    "    plt.plot(X[:, 0][y==1], X[:, 1][y==1], \"bs\", alpha=alpha)\n",
    "    plt.axis(axes)\n",
    "    plt.xlabel(r\"$x_1$\", fontsize=18)\n",
    "    plt.ylabel(r\"$x_2$\", fontsize=18, rotation=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure decision_tree_without_and_with_bagging_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)\n",
    "plt.sca(axes[0])\n",
    "plot_decision_boundary(tree_clf, X, y)\n",
    "plt.title(\"Decision Tree\", fontsize=14)\n",
    "plt.sca(axes[1])\n",
    "plot_decision_boundary(bag_clf, X, y)\n",
    "plt.title(\"Decision Trees with Bagging\", fontsize=14)\n",
    "plt.ylabel(\"\")\n",
    "save_fig(\"decision_tree_without_and_with_bagging_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Random Forests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "bag_clf = BaggingClassifier(\n",
    "    DecisionTreeClassifier(splitter=\"random\", max_leaf_nodes=16, random_state=42),\n",
    "    n_estimators=500, max_samples=1.0, bootstrap=True, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "bag_clf.fit(X_train, y_train)\n",
    "y_pred = bag_clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "rnd_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16, random_state=42)\n",
    "rnd_clf.fit(X_train, y_train)\n",
    "\n",
    "y_pred_rf = rnd_clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.976"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sum(y_pred == y_pred_rf) / len(y_pred)  # almost identical predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sepal length (cm) 0.11249225099876374\n",
      "sepal width (cm) 0.023119288282510326\n",
      "petal length (cm) 0.44103046436395765\n",
      "petal width (cm) 0.4233579963547681\n"
     ]
    }
   ],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "iris = load_iris()\n",
    "rnd_clf = RandomForestClassifier(n_estimators=500, random_state=42)\n",
    "rnd_clf.fit(iris[\"data\"], iris[\"target\"])\n",
    "for name, score in zip(iris[\"feature_names\"], rnd_clf.feature_importances_):\n",
    "    print(name, score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.11249225, 0.02311929, 0.44103046, 0.423358  ])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rnd_clf.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6, 4))\n",
    "\n",
    "for i in range(15):\n",
    "    tree_clf = DecisionTreeClassifier(max_leaf_nodes=16, random_state=42 + i)\n",
    "    indices_with_replacement = np.random.randint(0, len(X_train), len(X_train))\n",
    "    tree_clf.fit(X[indices_with_replacement], y[indices_with_replacement])\n",
    "    plot_decision_boundary(tree_clf, X, y, axes=[-1.5, 2.45, -1, 1.5], alpha=0.02, contour=False)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Out-of-Bag evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9013333333333333"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bag_clf = BaggingClassifier(\n",
    "    DecisionTreeClassifier(random_state=42), n_estimators=500,\n",
    "    bootstrap=True, oob_score=True, random_state=40)\n",
    "bag_clf.fit(X_train, y_train)\n",
    "bag_clf.oob_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.31746032, 0.68253968],\n",
       "       [0.34117647, 0.65882353],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.08379888, 0.91620112],\n",
       "       [0.31693989, 0.68306011],\n",
       "       [0.02923977, 0.97076023],\n",
       "       [0.97687861, 0.02312139],\n",
       "       [0.97765363, 0.02234637],\n",
       "       [0.74404762, 0.25595238],\n",
       "       [0.        , 1.        ],\n",
       "       [0.71195652, 0.28804348],\n",
       "       [0.83957219, 0.16042781],\n",
       "       [0.97777778, 0.02222222],\n",
       "       [0.0625    , 0.9375    ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.97297297, 0.02702703],\n",
       "       [0.95238095, 0.04761905],\n",
       "       [1.        , 0.        ],\n",
       "       [0.01704545, 0.98295455],\n",
       "       [0.38947368, 0.61052632],\n",
       "       [0.88700565, 0.11299435],\n",
       "       [1.        , 0.        ],\n",
       "       [0.96685083, 0.03314917],\n",
       "       [0.        , 1.        ],\n",
       "       [0.99428571, 0.00571429],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.64804469, 0.35195531],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.13402062, 0.86597938],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.36065574, 0.63934426],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.27093596, 0.72906404],\n",
       "       [0.34146341, 0.65853659],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.00531915, 0.99468085],\n",
       "       [0.98265896, 0.01734104],\n",
       "       [0.91428571, 0.08571429],\n",
       "       [0.97282609, 0.02717391],\n",
       "       [0.97029703, 0.02970297],\n",
       "       [0.        , 1.        ],\n",
       "       [0.06134969, 0.93865031],\n",
       "       [0.98019802, 0.01980198],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.97790055, 0.02209945],\n",
       "       [0.79473684, 0.20526316],\n",
       "       [0.41919192, 0.58080808],\n",
       "       [0.99473684, 0.00526316],\n",
       "       [0.        , 1.        ],\n",
       "       [0.67613636, 0.32386364],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.87356322, 0.12643678],\n",
       "       [1.        , 0.        ],\n",
       "       [0.56140351, 0.43859649],\n",
       "       [0.16304348, 0.83695652],\n",
       "       [0.67539267, 0.32460733],\n",
       "       [0.90673575, 0.09326425],\n",
       "       [0.        , 1.        ],\n",
       "       [0.16201117, 0.83798883],\n",
       "       [0.89005236, 0.10994764],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.995     , 0.005     ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.07272727, 0.92727273],\n",
       "       [0.05418719, 0.94581281],\n",
       "       [0.29533679, 0.70466321],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.81871345, 0.18128655],\n",
       "       [0.01092896, 0.98907104],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.22513089, 0.77486911],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.9368932 , 0.0631068 ],\n",
       "       [0.76536313, 0.23463687],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.17127072, 0.82872928],\n",
       "       [0.65306122, 0.34693878],\n",
       "       [0.        , 1.        ],\n",
       "       [0.03076923, 0.96923077],\n",
       "       [0.49444444, 0.50555556],\n",
       "       [1.        , 0.        ],\n",
       "       [0.02673797, 0.97326203],\n",
       "       [0.98870056, 0.01129944],\n",
       "       [0.23121387, 0.76878613],\n",
       "       [0.5       , 0.5       ],\n",
       "       [0.9947644 , 0.0052356 ],\n",
       "       [0.00555556, 0.99444444],\n",
       "       [0.98963731, 0.01036269],\n",
       "       [0.25641026, 0.74358974],\n",
       "       [0.92972973, 0.07027027],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.80681818, 0.19318182],\n",
       "       [1.        , 0.        ],\n",
       "       [0.0106383 , 0.9893617 ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.98181818, 0.01818182],\n",
       "       [1.        , 0.        ],\n",
       "       [0.01036269, 0.98963731],\n",
       "       [0.97752809, 0.02247191],\n",
       "       [0.99453552, 0.00546448],\n",
       "       [0.01960784, 0.98039216],\n",
       "       [0.18367347, 0.81632653],\n",
       "       [0.98387097, 0.01612903],\n",
       "       [0.29533679, 0.70466321],\n",
       "       [0.98295455, 0.01704545],\n",
       "       [0.        , 1.        ],\n",
       "       [0.00561798, 0.99438202],\n",
       "       [0.75138122, 0.24861878],\n",
       "       [0.38624339, 0.61375661],\n",
       "       [0.42708333, 0.57291667],\n",
       "       [0.86315789, 0.13684211],\n",
       "       [0.92964824, 0.07035176],\n",
       "       [0.05699482, 0.94300518],\n",
       "       [0.82802548, 0.17197452],\n",
       "       [0.01546392, 0.98453608],\n",
       "       [0.        , 1.        ],\n",
       "       [0.02298851, 0.97701149],\n",
       "       [0.96721311, 0.03278689],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.01041667, 0.98958333],\n",
       "       [0.        , 1.        ],\n",
       "       [0.0326087 , 0.9673913 ],\n",
       "       [0.01020408, 0.98979592],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.93785311, 0.06214689],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.99462366, 0.00537634],\n",
       "       [0.        , 1.        ],\n",
       "       [0.38860104, 0.61139896],\n",
       "       [0.32065217, 0.67934783],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.31182796, 0.68817204],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.00588235, 0.99411765],\n",
       "       [0.        , 1.        ],\n",
       "       [0.98387097, 0.01612903],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.62264151, 0.37735849],\n",
       "       [0.92344498, 0.07655502],\n",
       "       [0.        , 1.        ],\n",
       "       [0.99526066, 0.00473934],\n",
       "       [1.        , 0.        ],\n",
       "       [0.98888889, 0.01111111],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.06451613, 0.93548387],\n",
       "       [1.        , 0.        ],\n",
       "       [0.05154639, 0.94845361],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.03278689, 0.96721311],\n",
       "       [1.        , 0.        ],\n",
       "       [0.95808383, 0.04191617],\n",
       "       [0.79532164, 0.20467836],\n",
       "       [0.55665025, 0.44334975],\n",
       "       [0.        , 1.        ],\n",
       "       [0.18604651, 0.81395349],\n",
       "       [1.        , 0.        ],\n",
       "       [0.93121693, 0.06878307],\n",
       "       [0.97740113, 0.02259887],\n",
       "       [1.        , 0.        ],\n",
       "       [0.00531915, 0.99468085],\n",
       "       [0.        , 1.        ],\n",
       "       [0.44623656, 0.55376344],\n",
       "       [0.86363636, 0.13636364],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.00558659, 0.99441341],\n",
       "       [0.        , 1.        ],\n",
       "       [0.96923077, 0.03076923],\n",
       "       [0.        , 1.        ],\n",
       "       [0.21649485, 0.78350515],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.98477157, 0.01522843],\n",
       "       [0.8       , 0.2       ],\n",
       "       [0.99441341, 0.00558659],\n",
       "       [0.        , 1.        ],\n",
       "       [0.08379888, 0.91620112],\n",
       "       [0.98984772, 0.01015228],\n",
       "       [0.01142857, 0.98857143],\n",
       "       [0.        , 1.        ],\n",
       "       [0.02747253, 0.97252747],\n",
       "       [1.        , 0.        ],\n",
       "       [0.79144385, 0.20855615],\n",
       "       [0.        , 1.        ],\n",
       "       [0.90804598, 0.09195402],\n",
       "       [0.98387097, 0.01612903],\n",
       "       [0.20634921, 0.79365079],\n",
       "       [0.19767442, 0.80232558],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.20338983, 0.79661017],\n",
       "       [0.98181818, 0.01818182],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.98969072, 0.01030928],\n",
       "       [0.        , 1.        ],\n",
       "       [0.48663102, 0.51336898],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.07821229, 0.92178771],\n",
       "       [0.11176471, 0.88823529],\n",
       "       [0.99415205, 0.00584795],\n",
       "       [0.03015075, 0.96984925],\n",
       "       [1.        , 0.        ],\n",
       "       [0.40837696, 0.59162304],\n",
       "       [0.04891304, 0.95108696],\n",
       "       [0.51595745, 0.48404255],\n",
       "       [0.51898734, 0.48101266],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.59903382, 0.40096618],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.24157303, 0.75842697],\n",
       "       [0.81052632, 0.18947368],\n",
       "       [0.08717949, 0.91282051],\n",
       "       [0.99453552, 0.00546448],\n",
       "       [0.82142857, 0.17857143],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.125     , 0.875     ],\n",
       "       [0.04712042, 0.95287958],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.89150943, 0.10849057],\n",
       "       [0.1978022 , 0.8021978 ],\n",
       "       [0.95238095, 0.04761905],\n",
       "       [0.00515464, 0.99484536],\n",
       "       [0.609375  , 0.390625  ],\n",
       "       [0.07692308, 0.92307692],\n",
       "       [0.99484536, 0.00515464],\n",
       "       [0.84210526, 0.15789474],\n",
       "       [0.        , 1.        ],\n",
       "       [0.99484536, 0.00515464],\n",
       "       [0.95876289, 0.04123711],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.26903553, 0.73096447],\n",
       "       [0.98461538, 0.01538462],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.00574713, 0.99425287],\n",
       "       [0.85142857, 0.14857143],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.76506024, 0.23493976],\n",
       "       [0.8969697 , 0.1030303 ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.73333333, 0.26666667],\n",
       "       [0.47727273, 0.52272727],\n",
       "       [0.        , 1.        ],\n",
       "       [0.92473118, 0.07526882],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.87709497, 0.12290503],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.74752475, 0.25247525],\n",
       "       [0.09146341, 0.90853659],\n",
       "       [0.44329897, 0.55670103],\n",
       "       [0.22395833, 0.77604167],\n",
       "       [0.        , 1.        ],\n",
       "       [0.87046632, 0.12953368],\n",
       "       [0.78212291, 0.21787709],\n",
       "       [0.00507614, 0.99492386],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.02884615, 0.97115385],\n",
       "       [0.96571429, 0.03428571],\n",
       "       [0.93478261, 0.06521739],\n",
       "       [1.        , 0.        ],\n",
       "       [0.49756098, 0.50243902],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.01604278, 0.98395722],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.96987952, 0.03012048],\n",
       "       [0.        , 1.        ],\n",
       "       [0.05747126, 0.94252874],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.98989899, 0.01010101],\n",
       "       [0.01675978, 0.98324022],\n",
       "       [1.        , 0.        ],\n",
       "       [0.13541667, 0.86458333],\n",
       "       [0.        , 1.        ],\n",
       "       [0.00546448, 0.99453552],\n",
       "       [0.        , 1.        ],\n",
       "       [0.41836735, 0.58163265],\n",
       "       [0.11309524, 0.88690476],\n",
       "       [0.22110553, 0.77889447],\n",
       "       [1.        , 0.        ],\n",
       "       [0.97647059, 0.02352941],\n",
       "       [0.22826087, 0.77173913],\n",
       "       [0.98882682, 0.01117318],\n",
       "       [0.        , 1.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [1.        , 0.        ],\n",
       "       [0.96428571, 0.03571429],\n",
       "       [0.33507853, 0.66492147],\n",
       "       [0.98235294, 0.01764706],\n",
       "       [1.        , 0.        ],\n",
       "       [0.        , 1.        ],\n",
       "       [0.99465241, 0.00534759],\n",
       "       [0.        , 1.        ],\n",
       "       [0.06043956, 0.93956044],\n",
       "       [0.97619048, 0.02380952],\n",
       "       [1.        , 0.        ],\n",
       "       [0.03108808, 0.96891192],\n",
       "       [0.57291667, 0.42708333]])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bag_clf.oob_decision_function_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.912"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "y_pred = bag_clf.predict(X_test)\n",
    "accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature importance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import fetch_openml\n",
    "\n",
    "mnist = fetch_openml('mnist_784', version=1)\n",
    "mnist.target = mnist.target.astype(np.uint8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
       "            oob_score=False, random_state=42, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "rnd_clf.fit(mnist[\"data\"], mnist[\"target\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_digit(data):\n",
    "    image = data.reshape(28, 28)\n",
    "    plt.imshow(image, cmap = mpl.cm.hot,\n",
    "               interpolation=\"nearest\")\n",
    "    plt.axis(\"off\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure mnist_feature_importance_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_digit(rnd_clf.feature_importances_)\n",
    "\n",
    "cbar = plt.colorbar(ticks=[rnd_clf.feature_importances_.min(), rnd_clf.feature_importances_.max()])\n",
    "cbar.ax.set_yticklabels(['Not important', 'Very important'])\n",
    "\n",
    "save_fig(\"mnist_feature_importance_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# AdaBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AdaBoostClassifier(algorithm='SAMME.R',\n",
       "          base_estimator=DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=1,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best'),\n",
       "          learning_rate=0.5, n_estimators=200, random_state=42)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "\n",
    "ada_clf = AdaBoostClassifier(\n",
    "    DecisionTreeClassifier(max_depth=1), n_estimators=200,\n",
    "    algorithm=\"SAMME.R\", learning_rate=0.5, random_state=42)\n",
    "ada_clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_decision_boundary(ada_clf, X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure boosting_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "m = len(X_train)\n",
    "\n",
    "fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)\n",
    "for subplot, learning_rate in ((0, 1), (1, 0.5)):\n",
    "    sample_weights = np.ones(m)\n",
    "    plt.sca(axes[subplot])\n",
    "    for i in range(5):\n",
    "        svm_clf = SVC(kernel=\"rbf\", C=0.05, gamma=\"scale\", random_state=42)\n",
    "        svm_clf.fit(X_train, y_train, sample_weight=sample_weights)\n",
    "        y_pred = svm_clf.predict(X_train)\n",
    "        sample_weights[y_pred != y_train] *= (1 + learning_rate)\n",
    "        plot_decision_boundary(svm_clf, X, y, alpha=0.2)\n",
    "        plt.title(\"learning_rate = {}\".format(learning_rate), fontsize=16)\n",
    "    if subplot == 0:\n",
    "        plt.text(-0.7, -0.65, \"1\", fontsize=14)\n",
    "        plt.text(-0.6, -0.10, \"2\", fontsize=14)\n",
    "        plt.text(-0.5,  0.10, \"3\", fontsize=14)\n",
    "        plt.text(-0.4,  0.55, \"4\", fontsize=14)\n",
    "        plt.text(-0.3,  0.90, \"5\", fontsize=14)\n",
    "    else:\n",
    "        plt.ylabel(\"\")\n",
    "\n",
    "save_fig(\"boosting_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['base_estimator_',\n",
       " 'classes_',\n",
       " 'estimator_errors_',\n",
       " 'estimator_weights_',\n",
       " 'estimators_',\n",
       " 'feature_importances_',\n",
       " 'n_classes_']"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(m for m in dir(ada_clf) if not m.startswith(\"_\") and m.endswith(\"_\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Gradient Boosting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(42)\n",
    "X = np.random.rand(100, 1) - 0.5\n",
    "y = 3*X[:, 0]**2 + 0.05 * np.random.randn(100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(criterion='mse', max_depth=2, max_features=None,\n",
       "           max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           presort=False, random_state=42, splitter='best')"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "tree_reg1 = DecisionTreeRegressor(max_depth=2, random_state=42)\n",
    "tree_reg1.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(criterion='mse', max_depth=2, max_features=None,\n",
       "           max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           presort=False, random_state=42, splitter='best')"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y2 = y - tree_reg1.predict(X)\n",
    "tree_reg2 = DecisionTreeRegressor(max_depth=2, random_state=42)\n",
    "tree_reg2.fit(X, y2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(criterion='mse', max_depth=2, max_features=None,\n",
       "           max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           presort=False, random_state=42, splitter='best')"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y3 = y2 - tree_reg2.predict(X)\n",
    "tree_reg3 = DecisionTreeRegressor(max_depth=2, random_state=42)\n",
    "tree_reg3.fit(X, y3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_new = np.array([[0.8]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = sum(tree.predict(X_new) for tree in (tree_reg1, tree_reg2, tree_reg3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.75026781])"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_predictions(regressors, X, y, axes, label=None, style=\"r-\", data_style=\"b.\", data_label=None):\n",
    "    x1 = np.linspace(axes[0], axes[1], 500)\n",
    "    y_pred = sum(regressor.predict(x1.reshape(-1, 1)) for regressor in regressors)\n",
    "    plt.plot(X[:, 0], y, data_style, label=data_label)\n",
    "    plt.plot(x1, y_pred, style, linewidth=2, label=label)\n",
    "    if label or data_label:\n",
    "        plt.legend(loc=\"upper center\", fontsize=16)\n",
    "    plt.axis(axes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure gradient_boosting_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 792x792 with 6 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(11,11))\n",
    "\n",
    "plt.subplot(321)\n",
    "plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label=\"$h_1(x_1)$\", style=\"g-\", data_label=\"Training set\")\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "plt.title(\"Residuals and tree predictions\", fontsize=16)\n",
    "\n",
    "plt.subplot(322)\n",
    "plot_predictions([tree_reg1], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label=\"$h(x_1) = h_1(x_1)$\", data_label=\"Training set\")\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "plt.title(\"Ensemble predictions\", fontsize=16)\n",
    "\n",
    "plt.subplot(323)\n",
    "plot_predictions([tree_reg2], X, y2, axes=[-0.5, 0.5, -0.5, 0.5], label=\"$h_2(x_1)$\", style=\"g-\", data_style=\"k+\", data_label=\"Residuals\")\n",
    "plt.ylabel(\"$y - h_1(x_1)$\", fontsize=16)\n",
    "\n",
    "plt.subplot(324)\n",
    "plot_predictions([tree_reg1, tree_reg2], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label=\"$h(x_1) = h_1(x_1) + h_2(x_1)$\")\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "\n",
    "plt.subplot(325)\n",
    "plot_predictions([tree_reg3], X, y3, axes=[-0.5, 0.5, -0.5, 0.5], label=\"$h_3(x_1)$\", style=\"g-\", data_style=\"k+\")\n",
    "plt.ylabel(\"$y - h_1(x_1) - h_2(x_1)$\", fontsize=16)\n",
    "plt.xlabel(\"$x_1$\", fontsize=16)\n",
    "\n",
    "plt.subplot(326)\n",
    "plot_predictions([tree_reg1, tree_reg2, tree_reg3], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label=\"$h(x_1) = h_1(x_1) + h_2(x_1) + h_3(x_1)$\")\n",
    "plt.xlabel(\"$x_1$\", fontsize=16)\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "\n",
    "save_fig(\"gradient_boosting_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GradientBoostingRegressor(alpha=0.9, criterion='friedman_mse', init=None,\n",
       "             learning_rate=1.0, loss='ls', max_depth=2, max_features=None,\n",
       "             max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "             min_impurity_split=None, min_samples_leaf=1,\n",
       "             min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "             n_estimators=3, n_iter_no_change=None, presort='auto',\n",
       "             random_state=42, subsample=1.0, tol=0.0001,\n",
       "             validation_fraction=0.1, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import GradientBoostingRegressor\n",
    "\n",
    "gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=3, learning_rate=1.0, random_state=42)\n",
    "gbrt.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GradientBoostingRegressor(alpha=0.9, criterion='friedman_mse', init=None,\n",
       "             learning_rate=0.1, loss='ls', max_depth=2, max_features=None,\n",
       "             max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "             min_impurity_split=None, min_samples_leaf=1,\n",
       "             min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "             n_estimators=200, n_iter_no_change=None, presort='auto',\n",
       "             random_state=42, subsample=1.0, tol=0.0001,\n",
       "             validation_fraction=0.1, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gbrt_slow = GradientBoostingRegressor(max_depth=2, n_estimators=200, learning_rate=0.1, random_state=42)\n",
    "gbrt_slow.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure gbrt_learning_rate_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)\n",
    "\n",
    "plt.sca(axes[0])\n",
    "plot_predictions([gbrt], X, y, axes=[-0.5, 0.5, -0.1, 0.8], label=\"Ensemble predictions\")\n",
    "plt.title(\"learning_rate={}, n_estimators={}\".format(gbrt.learning_rate, gbrt.n_estimators), fontsize=14)\n",
    "plt.xlabel(\"$x_1$\", fontsize=16)\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "\n",
    "plt.sca(axes[1])\n",
    "plot_predictions([gbrt_slow], X, y, axes=[-0.5, 0.5, -0.1, 0.8])\n",
    "plt.title(\"learning_rate={}, n_estimators={}\".format(gbrt_slow.learning_rate, gbrt_slow.n_estimators), fontsize=14)\n",
    "plt.xlabel(\"$x_1$\", fontsize=16)\n",
    "\n",
    "save_fig(\"gbrt_learning_rate_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Gradient Boosting with Early stopping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GradientBoostingRegressor(alpha=0.9, criterion='friedman_mse', init=None,\n",
       "             learning_rate=0.1, loss='ls', max_depth=2, max_features=None,\n",
       "             max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "             min_impurity_split=None, min_samples_leaf=1,\n",
       "             min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "             n_estimators=56, n_iter_no_change=None, presort='auto',\n",
       "             random_state=42, subsample=1.0, tol=0.0001,\n",
       "             validation_fraction=0.1, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "X_train, X_val, y_train, y_val = train_test_split(X, y, random_state=49)\n",
    "\n",
    "gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=120, random_state=42)\n",
    "gbrt.fit(X_train, y_train)\n",
    "\n",
    "errors = [mean_squared_error(y_val, y_pred)\n",
    "          for y_pred in gbrt.staged_predict(X_val)]\n",
    "bst_n_estimators = np.argmin(errors) + 1\n",
    "\n",
    "gbrt_best = GradientBoostingRegressor(max_depth=2, n_estimators=bst_n_estimators, random_state=42)\n",
    "gbrt_best.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "min_error = np.min(errors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving figure early_stopping_gbrt_plot\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 4))\n",
    "\n",
    "plt.subplot(121)\n",
    "plt.plot(errors, \"b.-\")\n",
    "plt.plot([bst_n_estimators, bst_n_estimators], [0, min_error], \"k--\")\n",
    "plt.plot([0, 120], [min_error, min_error], \"k--\")\n",
    "plt.plot(bst_n_estimators, min_error, \"ko\")\n",
    "plt.text(bst_n_estimators, min_error*1.2, \"Minimum\", ha=\"center\", fontsize=14)\n",
    "plt.axis([0, 120, 0, 0.01])\n",
    "plt.xlabel(\"Number of trees\")\n",
    "plt.ylabel(\"Error\", fontsize=16)\n",
    "plt.title(\"Validation error\", fontsize=14)\n",
    "\n",
    "plt.subplot(122)\n",
    "plot_predictions([gbrt_best], X, y, axes=[-0.5, 0.5, -0.1, 0.8])\n",
    "plt.title(\"Best model (%d trees)\" % bst_n_estimators, fontsize=14)\n",
    "plt.ylabel(\"$y$\", fontsize=16, rotation=0)\n",
    "plt.xlabel(\"$x_1$\", fontsize=16)\n",
    "\n",
    "save_fig(\"early_stopping_gbrt_plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "gbrt = GradientBoostingRegressor(max_depth=2, warm_start=True, random_state=42)\n",
    "\n",
    "min_val_error = float(\"inf\")\n",
    "error_going_up = 0\n",
    "for n_estimators in range(1, 120):\n",
    "    gbrt.n_estimators = n_estimators\n",
    "    gbrt.fit(X_train, y_train)\n",
    "    y_pred = gbrt.predict(X_val)\n",
    "    val_error = mean_squared_error(y_val, y_pred)\n",
    "    if val_error < min_val_error:\n",
    "        min_val_error = val_error\n",
    "        error_going_up = 0\n",
    "    else:\n",
    "        error_going_up += 1\n",
    "        if error_going_up == 5:\n",
    "            break  # early stopping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "61\n"
     ]
    }
   ],
   "source": [
    "print(gbrt.n_estimators)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Minimum validation MSE: 0.002712853325235463\n"
     ]
    }
   ],
   "source": [
    "print(\"Minimum validation MSE:\", min_val_error)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using XGBoost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    import xgboost\n",
    "except ImportError as ex:\n",
    "    print(\"Error: the xgboost library is not installed.\")\n",
    "    xgboost = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "Validation MSE: 0.0028512559726563943\n"
     ]
    }
   ],
   "source": [
    "if xgboost is not None:  # not shown in the book\n",
    "    xgb_reg = xgboost.XGBRegressor(random_state=42)\n",
    "    xgb_reg.fit(X_train, y_train)\n",
    "    y_pred = xgb_reg.predict(X_val)\n",
    "    val_error = mean_squared_error(y_val, y_pred) # Not shown\n",
    "    print(\"Validation MSE:\", val_error)           # Not shown"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[0]\tvalidation_0-rmse:0.286719\n",
      "Will train until validation_0-rmse hasn't improved in 2 rounds.\n",
      "[1]\tvalidation_0-rmse:0.258221\n",
      "[2]\tvalidation_0-rmse:0.232634\n",
      "[3]\tvalidation_0-rmse:0.210526\n",
      "[4]\tvalidation_0-rmse:0.190232\n",
      "[5]\tvalidation_0-rmse:0.172196\n",
      "[6]\tvalidation_0-rmse:0.156394\n",
      "[7]\tvalidation_0-rmse:0.142241\n",
      "[8]\tvalidation_0-rmse:0.129789\n",
      "[9]\tvalidation_0-rmse:0.118752\n",
      "[10]\tvalidation_0-rmse:0.108388\n",
      "[11]\tvalidation_0-rmse:0.100155\n",
      "[12]\tvalidation_0-rmse:0.09208\n",
      "[13]\tvalidation_0-rmse:0.084791\n",
      "[14]\tvalidation_0-rmse:0.078699\n",
      "[15]\tvalidation_0-rmse:0.073248\n",
      "[16]\tvalidation_0-rmse:0.069391\n",
      "[17]\tvalidation_0-rmse:0.066277\n",
      "[18]\tvalidation_0-rmse:0.063458\n",
      "[19]\tvalidation_0-rmse:0.060326\n",
      "[20]\tvalidation_0-rmse:0.0578\n",
      "[21]\tvalidation_0-rmse:0.055643\n",
      "[22]\tvalidation_0-rmse:0.053943\n",
      "[23]\tvalidation_0-rmse:0.053138\n",
      "[24]\tvalidation_0-rmse:0.052415\n",
      "[25]\tvalidation_0-rmse:0.051821\n",
      "[26]\tvalidation_0-rmse:0.051226\n",
      "[27]\tvalidation_0-rmse:0.051135\n",
      "[28]\tvalidation_0-rmse:0.05091\n",
      "[29]\tvalidation_0-rmse:0.050893\n",
      "[30]\tvalidation_0-rmse:0.050725\n",
      "[31]\tvalidation_0-rmse:0.050471\n",
      "[32]\tvalidation_0-rmse:0.050285\n",
      "[33]\tvalidation_0-rmse:0.050492\n",
      "[34]\tvalidation_0-rmse:0.050348\n",
      "Stopping. Best iteration:\n",
      "[32]\tvalidation_0-rmse:0.050285\n",
      "\n",
      "Validation MSE: 0.002528626115371327\n"
     ]
    }
   ],
   "source": [
    "if xgboost is not None:  # not shown in the book\n",
    "    xgb_reg.fit(X_train, y_train,\n",
    "                eval_set=[(X_val, y_val)], early_stopping_rounds=2)\n",
    "    y_pred = xgb_reg.predict(X_val)\n",
    "    val_error = mean_squared_error(y_val, y_pred)  # Not shown\n",
    "    print(\"Validation MSE:\", val_error)            # Not shown"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:46] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "<<742 more lines>>\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:49] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "[16:33:50] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n",
      "4.29 ms ± 46.2 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit xgboost.XGBRegressor().fit(X_train, y_train) if xgboost is not None else None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12.9 ms ± 827 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit GradientBoostingRegressor().fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# Exercise solutions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1. to 7."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "See Appendix A."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 8. Voting Classifier"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Load the MNIST data and split it into a training set, a validation set, and a test set (e.g., use 50,000 instances for training, 10,000 for validation, and 10,000 for testing)._"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The MNIST dataset was loaded earlier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_val, X_test, y_train_val, y_test = train_test_split(\n",
    "    mnist.data, mnist.target, test_size=10000, random_state=42)\n",
    "X_train, X_val, y_train, y_val = train_test_split(\n",
    "    X_train_val, y_train_val, test_size=10000, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Then train various classifiers, such as a Random Forest classifier, an Extra-Trees classifier, and an SVM._"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier\n",
    "from sklearn.svm import LinearSVC\n",
    "from sklearn.neural_network import MLPClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "random_forest_clf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "extra_trees_clf = ExtraTreesClassifier(n_estimators=100, random_state=42)\n",
    "svm_clf = LinearSVC(random_state=42)\n",
    "mlp_clf = MLPClassifier(random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training the RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
      "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
      "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
      "            min_samples_leaf=1, min_samples_split=2,\n",
      "            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
      "            oob_score=False, random_state=42, verbose=0, warm_start=False)\n",
      "Training the ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
      "           max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
      "           min_impurity_decrease=0.0, min_impurity_split=None,\n",
      "           min_samples_leaf=1, min_samples_split=2,\n",
      "           min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
      "           oob_score=False, random_state=42, verbose=0, warm_start=False)\n",
      "Training the LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,\n",
      "     intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
      "     multi_class='ovr', penalty='l2', random_state=42, tol=0.0001,\n",
      "     verbose=0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/ageron/miniconda3/envs/tf2b/lib/python3.7/site-packages/sklearn/svm/base.py:931: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
      "  \"the number of iterations.\", ConvergenceWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training the MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,\n",
      "       beta_2=0.999, early_stopping=False, epsilon=1e-08,\n",
      "       hidden_layer_sizes=(100,), learning_rate='constant',\n",
      "       learning_rate_init=0.001, max_iter=200, momentum=0.9,\n",
      "       n_iter_no_change=10, nesterovs_momentum=True, power_t=0.5,\n",
      "       random_state=42, shuffle=True, solver='adam', tol=0.0001,\n",
      "       validation_fraction=0.1, verbose=False, warm_start=False)\n"
     ]
    }
   ],
   "source": [
    "estimators = [random_forest_clf, extra_trees_clf, svm_clf, mlp_clf]\n",
    "for estimator in estimators:\n",
    "    print(\"Training the\", estimator)\n",
    "    estimator.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.9692, 0.9715, 0.8641, 0.9603]"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[estimator.score(X_val, y_val) for estimator in estimators]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The linear SVM is far outperformed by the other classifiers. However, let's keep it for now since it may improve the voting classifier's performance."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Next, try to combine them into an ensemble that outperforms them all on the validation set, using a soft or hard voting classifier._"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import VotingClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "named_estimators = [\n",
    "    (\"random_forest_clf\", random_forest_clf),\n",
    "    (\"extra_trees_clf\", extra_trees_clf),\n",
    "    (\"svm_clf\", svm_clf),\n",
    "    (\"mlp_clf\", mlp_clf),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "voting_clf = VotingClassifier(named_estimators)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/ageron/miniconda3/envs/tf2b/lib/python3.7/site-packages/sklearn/svm/base.py:931: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
      "  \"the number of iterations.\", ConvergenceWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('random_forest_clf', RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "   ...=True, solver='adam', tol=0.0001,\n",
       "       validation_fraction=0.1, verbose=False, warm_start=False))],\n",
       "         flatten_transform=None, n_jobs=None, voting='hard', weights=None)"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9704"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.score(X_val, y_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.9692, 0.9715, 0.8641, 0.9603]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[estimator.score(X_val, y_val) for estimator in voting_clf.estimators_]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's remove the SVM to see if performance improves. It is possible to remove an estimator by setting it to `None` using `set_params()` like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VotingClassifier(estimators=[('random_forest_clf', RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "   ...=True, solver='adam', tol=0.0001,\n",
       "       validation_fraction=0.1, verbose=False, warm_start=False))],\n",
       "         flatten_transform=None, n_jobs=None, voting='hard', weights=None)"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.set_params(svm_clf=None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This updated the list of estimators:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('random_forest_clf',\n",
       "  RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "              max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "              min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "              min_samples_leaf=1, min_samples_split=2,\n",
       "              min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
       "              oob_score=False, random_state=42, verbose=0, warm_start=False)),\n",
       " ('extra_trees_clf',\n",
       "  ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
       "             max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "             min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "             min_samples_leaf=1, min_samples_split=2,\n",
       "             min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
       "             oob_score=False, random_state=42, verbose=0, warm_start=False)),\n",
       " ('svm_clf', None),\n",
       " ('mlp_clf',\n",
       "  MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,\n",
       "         beta_2=0.999, early_stopping=False, epsilon=1e-08,\n",
       "         hidden_layer_sizes=(100,), learning_rate='constant',\n",
       "         learning_rate_init=0.001, max_iter=200, momentum=0.9,\n",
       "         n_iter_no_change=10, nesterovs_momentum=True, power_t=0.5,\n",
       "         random_state=42, shuffle=True, solver='adam', tol=0.0001,\n",
       "         validation_fraction=0.1, verbose=False, warm_start=False))]"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.estimators"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "However, it did not update the list of _trained_ estimators:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "             max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "             min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "             min_samples_leaf=1, min_samples_split=2,\n",
       "             min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
       "             oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       " ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None,\n",
       "            oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       " LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,\n",
       "      intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
       "      multi_class='ovr', penalty='l2', random_state=42, tol=0.0001,\n",
       "      verbose=0),\n",
       " MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,\n",
       "        beta_2=0.999, early_stopping=False, epsilon=1e-08,\n",
       "        hidden_layer_sizes=(100,), learning_rate='constant',\n",
       "        learning_rate_init=0.001, max_iter=200, momentum=0.9,\n",
       "        n_iter_no_change=10, nesterovs_momentum=True, power_t=0.5,\n",
       "        random_state=42, shuffle=True, solver='adam', tol=0.0001,\n",
       "        validation_fraction=0.1, verbose=False, warm_start=False)]"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.estimators_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So we can either fit the `VotingClassifier` again, or just remove the SVM from the list of trained estimators:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "del voting_clf.estimators_[2]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's evaluate the `VotingClassifier` again:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9732"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.score(X_val, y_val)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A bit better! The SVM was hurting performance. Now let's try using a soft voting classifier. We do not actually need to retrain the classifier, we can just set `voting` to `\"soft\"`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "voting_clf.voting = \"soft\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9672"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.score(X_val, y_val)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nope, hard voting wins in this case."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "_Once you have found one, try it on the test set. How much better does it perform compared to the individual classifiers?_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9704"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "voting_clf.voting = \"hard\"\n",
    "voting_clf.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.9645, 0.9691, 0.9602]"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[estimator.score(X_test, y_test) for estimator in voting_clf.estimators_]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The voting classifier only very slightly reduced the error rate of the best model in this case."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 9. Stacking Ensemble"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Run the individual classifiers from the previous exercise to make predictions on the validation set, and create a new training set with the resulting predictions: each training instance is a vector containing the set of predictions from all your classifiers for an image, and the target is the image's class. Train a classifier on this new training set._"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_val_predictions = np.empty((len(X_val), len(estimators)), dtype=np.float32)\n",
    "\n",
    "for index, estimator in enumerate(estimators):\n",
    "    X_val_predictions[:, index] = estimator.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[5., 5., 5., 5.],\n",
       "       [8., 8., 8., 8.],\n",
       "       [2., 2., 2., 2.],\n",
       "       ...,\n",
       "       [7., 7., 7., 7.],\n",
       "       [6., 6., 6., 6.],\n",
       "       [7., 7., 7., 7.]], dtype=float32)"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_val_predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators=200, n_jobs=None,\n",
       "            oob_score=True, random_state=42, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rnd_forest_blender = RandomForestClassifier(n_estimators=200, oob_score=True, random_state=42)\n",
    "rnd_forest_blender.fit(X_val_predictions, y_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9696"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rnd_forest_blender.oob_score_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You could fine-tune this blender or try other types of blenders (e.g., an `MLPClassifier`), then select the best one using cross-validation, as always."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Congratulations, you have just trained a blender, and together with the classifiers they form a stacking ensemble! Now let's evaluate the ensemble on the test set. For each image in the test set, make predictions with all your classifiers, then feed the predictions to the blender to get the ensemble's predictions. How does it compare to the voting classifier you trained earlier?_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test_predictions = np.empty((len(X_test), len(estimators)), dtype=np.float32)\n",
    "\n",
    "for index, estimator in enumerate(estimators):\n",
    "    X_test_predictions[:, index] = estimator.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = rnd_forest_blender.predict(X_test_predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9669"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This stacking ensemble does not perform as well as the voting classifier we trained earlier, it's not quite as good as the best individual classifier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.4"
  },
  "nav_menu": {
   "height": "252px",
   "width": "333px"
  },
  "toc": {
   "navigate_menu": true,
   "number_sections": true,
   "sideBar": true,
   "threshold": 6,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}