[資料分析&機器學習] 第3.5講 決策樹(Decision Tree)以及隨機森林(Random Forest)介紹.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn import datasets\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target_names: ['setosa' 'versicolor' 'virginica']\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal length (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal length (cm)  petal length (cm)  target\n",
       "0                5.1                1.4       0\n",
       "1                4.9                1.4       0\n",
       "2                4.7                1.3       0"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris = datasets.load_iris()\n",
    "x = pd.DataFrame(iris['data'], columns=iris['feature_names'])\n",
    "print(\"target_names: \"+str(iris['target_names']))\n",
    "y = pd.DataFrame(iris['target'], columns=['target'])\n",
    "iris_data = pd.concat([x,y], axis=1)\n",
    "iris_data = iris_data[['sepal length (cm)','petal length (cm)','target']]\n",
    "iris_data = iris_data[iris_data['target'].isin([0,1])]\n",
    "iris_data.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    iris_data[['sepal length (cm)','petal length (cm)']], iris_data[['target']], test_size=0.3, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# 不需要做特徵標準化"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# sc = StandardScaler()\n",
    "# sc.fit(X_train)\n",
    "# X_train_std = sc.transform(X_train)\n",
    "# X_test_std = sc.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "tree = DecisionTreeClassifier(criterion = 'entropy', random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=None,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_split=1e-07, min_samples_leaf=1,\n",
       "            min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "            presort=False, random_state=0, splitter='best')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 0, 0, 0, 1, 1, 1])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,\n",
       "       1, 0, 0, 0, 1, 1, 1])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test['target'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    }
   ],
   "source": [
    "error = 0\n",
    "for i, v in enumerate(tree.predict(X_test)):\n",
    "    if v!= y_test['target'].values[i]:\n",
    "        print(i,v)\n",
    "        error+=1\n",
    "print(error)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree.score(X_test,y_test['target'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from matplotlib.colors import ListedColormap\n",
    "\n",
    "def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):\n",
    "\n",
    "    # setup marker generator and color map\n",
    "    markers = ('s', 'x', 'o', '^', 'v')\n",
    "    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')\n",
    "    cmap = ListedColormap(colors[:len(np.unique(y))])\n",
    "\n",
    "    # plot the decision surface\n",
    "    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n",
    "    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n",
    "    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),\n",
    "                           np.arange(x2_min, x2_max, resolution))\n",
    "    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)\n",
    "    Z = Z.reshape(xx1.shape)\n",
    "    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)\n",
    "    plt.xlim(xx1.min(), xx1.max())\n",
    "    plt.ylim(xx2.min(), xx2.max())\n",
    "\n",
    "    for idx, cl in enumerate(np.unique(y)):\n",
    "        plt.scatter(x=X[y == cl, 0], \n",
    "                    y=X[y == cl, 1],\n",
    "                    alpha=0.6, \n",
    "                    c=cmap(idx),\n",
    "                    edgecolor='black',\n",
    "                    marker=markers[idx], \n",
    "                    label=cl)\n",
    "\n",
    "    # highlight test samples\n",
    "    if test_idx:\n",
    "        # plot all samples\n",
    "        if not versiontuple(np.__version__) >= versiontuple('1.9.0'):\n",
    "            X_test, y_test = X[list(test_idx), :], y[list(test_idx)]\n",
    "            warnings.warn('Please update to NumPy 1.9.0 or newer')\n",
    "        else:\n",
    "            X_test, y_test = X[test_idx, :], y[test_idx]\n",
    "\n",
    "        plt.scatter(X_test[:, 0],\n",
    "                    X_test[:, 1],\n",
    "                    c='',\n",
    "                    alpha=1.0,\n",
    "                    edgecolor='black',\n",
    "                    linewidths=1,\n",
    "                    marker='o',\n",
    "                    s=55, label='test set')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAagAAAEYCAYAAAAJeGK1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10e327588>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_decision_regions(X_train.values, y_train['target'].values, classifier=tree)\n",
    "plt.xlabel('petal length [standardized]')\n",
    "plt.ylabel('petal width [standardized]')\n",
    "plt.legend(loc='upper left')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import export_graphviz"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "export_graphviz(tree, out_file='tree.dot', feature_names=['sepal length (cm)','petal length (cm)'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target_names: ['setosa' 'versicolor' 'virginica']\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>petal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.2</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.2</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   petal width (cm)  petal length (cm)  target\n",
       "0               0.2                1.4       0\n",
       "1               0.2                1.4       0\n",
       "2               0.2                1.3       0"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris = datasets.load_iris()\n",
    "x = pd.DataFrame(iris['data'], columns=iris['feature_names'])\n",
    "print(\"target_names: \"+str(iris['target_names']))\n",
    "y = pd.DataFrame(iris['target'], columns=['target'])\n",
    "iris_data = pd.concat([x,y], axis=1)\n",
    "iris_data = iris_data[['petal width (cm)','petal length (cm)','target']]\n",
    "iris_data.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    iris_data[['petal width (cm)','petal length (cm)']], iris_data[['target']], test_size=0.3, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=3,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_split=1e-07, min_samples_leaf=1,\n",
       "            min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "            presort=False, random_state=0, splitter='best')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "tree = DecisionTreeClassifier(criterion = 'entropy', max_depth=3, random_state=0)\n",
    "tree.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAagAAAEYCAYAAAAJeGK1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10e3e2fd0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_decision_regions(X_train.values, y_train['target'].values, classifier=tree)\n",
    "plt.xlabel('petal length [standardized]')\n",
    "plt.ylabel('petal width [standardized]')\n",
    "plt.legend(loc='upper left')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "export_graphviz(tree, out_file='tree2.dot', feature_names=['sepal length (cm)','petal length (cm)'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "forest = RandomForestClassifier(criterion='entropy', n_estimators=10,random_state=3,n_jobs=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='entropy',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_split=1e-07, min_samples_leaf=1,\n",
       "            min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "            n_estimators=10, n_jobs=2, oob_score=False, random_state=3,\n",
       "            verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "forest.fit(X_train,y_train['target'].values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWkAAAD3CAYAAADfYKXJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3XtwXOd53/HvOXvBYrELgiQIgiAoUpTIVxdTN1KiKMm2\nZMm2VFtWFFuZyIkbxU5TN5c67UzSsSfutJ1kOqnTtGnSJI0Tx5faSik7smS7tuyoim1ZEiWREk3R\n5mvxThACQfAGgAvs7Zz+cQAQABe7i8tiD4DfZ4YDYs+e3QeH4IMXz3nf53V830dERMLJrXcAIiIy\nNSVpEZEQU5IWEQkxJWkRkRBTkhYRCbHoXL/gi32v1GW6SDIZJ5PJ1eOtKwprbIprehTX9IU1tjDG\ntaP1VqfU44tmJO1GwvulhDU2xTU9imv6whpbWOMqZeFEKiKyBClJi4iEmJK0iEiIKUmLiISYkrSI\nSIgpSYuIhJiStIhIiClJi4iEmJK0iEiIKUmLiISYkrSISIgpSYuIhJiStIhIiClJi4iEmJK0iEiI\nKUmLiISYkrSISIgpSYuIhJiStIhIiClJi4iEWMXdwo0xjwGPjXyaAG4C2q2152sXloiIQBVJ2lr7\neeDzAMaY/wl8TglaRGR+VF3uMMZsA6631v51DeMRkZDI5/Kc6ztHPpevdyhLWsWR9DifAv5jpScl\nk3HcSH1K3al0oi7vW42wxqa4pmcpxOV5Hq/ueZVMLENDSwPZrizJfJJtt2zDdaf/f3spXLNaqipJ\nG2NaAGOtfa7SczOZ3KyDmolUOsHgwHBd3ruSsMamuKZnqcS1Z+9u0telWBlvCl5/JRRyBZ5/4UVu\nuXFrXWObK6GMq6H0w9X+WHwH8OxcxSIi4ZTP5ck2DBONTxy/ReNRsg3DKn3UQbVJ2gCHaxmIiNTf\nYP8giZZ4yWOJljiD/YPzHJFUVe6w1n6m1oGIyPTlc3nOns7guDFi8diMzh/sHyTVnCIWj5FqTjF8\nOAdrLn/u8PkcqY2pOYhapmM6Nw5FJCQ8z+P1fa+RbRgm1ZZksDdDQzbBTVtururm3vjzEy1xhg/n\nxs5vyCYo5AoTSh6FXIGGbGJGPwhkdpSkRRag1/e9Rvq6FMvjLcTiEVIrmynkCry+77Wqbu6NPx+A\nNYydf9OWmycm8POXErjMPyVpkQVm9ObeWIIdMf7m3uiId3I5o5rzi4Uit9y49dK5G1MaQdeRkrTI\nAlPNzb1lK5ZNWc6o5vzlrcuJxWMsb11eyy9FqqAkLbLAVHNzr1w5Y8u1N+jm4AKiLngiC0wsHhu7\nuTfe6M09oOxcZ6Ds+SpthItG0iIL0Pibe5Nnd1w4e6FiOUM3BxcOJWmRBch13bGbe76Xx9l4aZ50\nNeWQ8efr5mC4KUmLLDLjyyGV5jrr5mD4KUmLLECVFrOonLF4KEmLLECVFrOonLF4aHaHyAIznU51\no+UMJeiFS0laZIFRp7qlRUlaZIFJNacYPl96c43h8zlSzVqMspgoSYssMJUWs6i0sbjoxqHIAlRu\nMYssLkrSIiFXqpNducUstXzf6Z4/mw0JJKAkLRJS5Rrzjzb2j8VjpNLpOd1UtZr3rfb8mWxIIBMp\nSYuEVLlOdtPdtXs+33e2GxLIRPqxJlJn+Vyec33nJsxvrteu3bN9X+02PveqGkkbYz4JfACIA39h\nrf3bmkYlsgSUKytU25h/rs32fesV92JWcSRtjLkbuAO4E3gnsK7GMYksCaNlgfZr22lZs4L2a9tJ\nXxc07K/XXOjZvq/mcM+9asod7wX2AU8C3wC+WdOIRJaASmUBmJvG/KVKKeWMn4NdyBXo7+sf+3s1\n76s53HPP8X2/7BOMMZ8F1gPvB64EngausdaWPHFvZq/vRlTqFinn7Omz2Ixl+ZrLf/U/99Y5TNLQ\nsrKFV/e8SiaWoaGlgez5LMl8km23bKs4S8LzvBmfWygU+OqTX6W4oki6Pc1AzwCRsxE+9PCHiEYr\nV0hn895L2ZaGLU6px6upSZ8BDlhrc4A1xgwDq4DeUk/OZEr/qlNrqXRiTqchzaWwxqa4pqdcXNOd\nU+y4MQZ7M6RWNuN53tgO367rMtibwdkYI3Mxx3Xmhkuv3Rm8dubixP9jpeLas3c36etSrIw3Bc9Z\nGYxmn3/hxQkzLErFvWfvbsy91+JG3SCudTG8gscLL+2qenbGaNy+l8dJxUrGXU+h/B5rKP1wNUn6\neeATxpg/IdjroYkgcYsseTOdUxyLx2gYbqDnrbdwGh2iDREK/UX8IZ+G4dk15h8tpYxNoRsxfoZF\nJBopGff15m0Tzm1IBJnDjbtj51ZbsqjFHO6lqGKSttZ+0xjzDuBlghr2b1prizWPTGQBmM2cYs/3\nOX/yAm6TQ+PyRobODeFd9FnlTjGkqlI1MyyOnDxcMu6XXniRZtNU9lzNzphfVU3Bs9b+Xq0DEVlo\nqhmxTjXqzOfy5BtzXHPtNRRyBTL9GdZc1UE0HqXnpz3TGrFONn6Pw9HXTjYnicajwQ4tnQ1Txu2u\ncMicGaJlDZeVYUb3R6yWloXPDa04FJmh2cwJHn9uNB6lubW56nMricVjxIbiHHj1wNgovefQWyOj\n9Dayw9kp406tSjLwZqaqMsxUtCx8bilJi8xQNbty1+LcariOQ8vaZWOJNp6I4w/5uD1OxfeON8Q5\nd/LsjMswWhY+t5SkRWZoOrtylzsXGCtJALOeT5zP5ckmsrSvWUMhX2AoM8SypkaiLVF6zveMvUep\nuKMXYxSa81WVYTKDGXq7T9HWsZpkKnnpvWdYApLSlKRFZmE2u3LfcP2NfOPbT0GrT3N7mv6fDUCf\nw4MPPDSrmAb7B2loidN35jTFSJFoQ4TMxYtEihEaRkopU8W9cd1VHPcOA1OXYdIt6Qlxv7Zv91jc\nWhY+95SkRWZhNrty/3j/Xt52/9vG5iNv2BDMR/7x/r2zKgukmlN0vdzFFXdeQUMkKFHEk+AVPY7/\n6DhbbrtpyrjzuXzFMsw3vv0U697TSbwxSMarrmojN5TjG99+ive/9wM1LeMsRarii8yB6e7KXetu\nccMDWbyiN+Exr+gxPJAtG3elZd35XB5a/bEEPSreGIdWn3wur2Xhc0wjaZE6KFWSKPQXJ5QkZloW\nGOwf5Kobr6Rvfx9+gz9288/JOlx145UVX7tcCef4wWM0t6dLntfcnqa3+5S29ppjStIidVBNSWI2\nr507XGDTTZtL3vyrVHIoV8Jp61jNa/t2s+qqtsvO6+8ZoG3L6nnZ2mspUblDpE6qLUlMVy070SVT\nSehzyA1N7MORG8pBnzM2y2M0jhWrVihBz5JG0iJ1MNuSRCWzmTlSqR/Jgw88NPG1e+ZmVoqUpiQt\nUgfTKUnMZNfu2cwcGV2MkiZFpj9D61XNY4/fcuNWotEoDz/4wUvzpLesnjCClrmlJC1SB5MXwozO\nRx5fkphph73JC0qm08kun8szFMvQ95PesRF+z6G3cLIOTbHUhHOTqSQbNl85l5dFSlCSFqmTSgth\nZtphb7Y9RXpP97D+zg1j0wNb1rRQyBU49qOjDLZpMcp8U5IWqZNysyiqXV5dqtPcbPqCNCQaIO4Q\njUcp5AoM9Q/R2NwYJOy4MzYql/mjJC1SZ6Wa+lcaDfef7+fYW0dLzkWeTU+R7HCWpuYmDu85TLQx\nQrIlyblDZykMFWlqbiI7nFX9eZ4pSYuEUKXR8KHBgyy/sWXKTnMz7SmSak5x/pXzdL59LZGGCE7E\noWlFE8Vska4fniS1Scu655uStEgVatnAvtTsjfGjYc/zuHDmAstWLsN13aBTXSo/riRxkVii4bJS\nyEx7iiTSCZJNTTiug1f0cOMuftQnkU7M6dct1VGSFimjlg3sK83eeNu1W/jCl/+O5IYELetaePNF\nS+boMB94z8/RxVHefP1n+A0+TSuTXDyZwck6rFy1YsKNwenujzjYP0jn1Z3kz+XHlqtns8Fy9c6r\nO9XFrg6UpEXKqGUD+0qzN771zDe4+dGbghFzvsDajZ0UdhR4/js/oBgvcvW7rwq2vHIdmlcvo5Ar\ncPB7h7jh3ltmHFOqOUX2cI72a9svbZ/VHGyfVc2Scpl7WhYuMoXxneo8zyM7lMXzvGl1qtu/u4lC\n3pnwWCHvsPelWNkueBfOXhjrNue4DpFoBMd1xrrNReMubsSlkCsw0DdAIVfAjbgk0rObfTG+zOK6\nLg2JBlzXVRe7OqpqJG2M2QP0j3x6xFr7q7ULSSQcJneqizVGyQ8Vqu5Ut393E9/8Sis/2TPEw4+d\nJhrzKeQdnvz8Kn76+kXu+s2pd+U+9uZR0u1phoeH8B0fJ+Lg53wc3yHZ2og7GOHQC4dwUy7pthQ9\nx07hDXqs37h+1iWJ2WxkIHOvYpI2xiQAx1p7d+3DEQmPyZ3qXNchlohP2anukPMzjhy99MtpscUh\n33Y1P3ylBXsWtv7cEXZ/fSO9h/JsvuU8Df5F4PK2n8Pnc1y3aTNv7P0xLRuX4TgjI/Eo+L7P2RNn\ncS+6mPddQyQWAd9nVUcbxXyRg987xI2zKHfA7DYykLlXzUj6RiBpjPnuyPM/Za19qbZhSdhNTkhz\nyXEcfN+vyWtPRyKep+tNj7W3ebiRcck379H1pge3XX7OqR9dy5X5a8Y+f+cqePFghJ7nN/C954Ok\nXhh2uPk/vULjqZGywkh/jVg86K/RkE2QTCXpPzFAPlsgnriUIPPZAhe6+lm7cS1uxMVxHNyIi+f5\nc1LuGG+6Nx2lNqpJ0hngj4G/ATYB3zbGGGttodSTk8n4hG/o+ZQK8RShsMY207ii2Qhnd13PtdEt\ncxxROPzgB3Bx/XdoaIny6te7ufLGDMkVjWTODnFkb5I8N/DNryT5yG9Hxs6JZiPEohHSiYnX9N57\nYefOS5+vXw/xBoc7bt/OV5/8KsUVRdLtaQZ6BoicjfChhz9E/7l+tt9/K/u/t5/4yjjNa5rpf6uf\n3Jkcb7v9ehrTjXgDRXJulkg8QjFXJOpF2XDtenwvTypdujF/PSy27/35Vk2S/hlw0FrrAz8zxpwh\nmGJ/otSTn/7pT+YwvOqFZfRVSlhjm21c+UKRgaHhOYwokE4nGBiY+9edjmw2woYb8xzcN0jD8uvp\nOnqRtugJeo9ehx9vYvCtE0Tv3c/X35g4IOl67ho6b78Ue7EIL74YIT/u5qG1DtuyPk/8/euY+6+l\nWChwpvsMm69fSyQa5Ym/f537HzAMn81x5/vfzvDgMGe6z7B+y5UkUgm6ftxF7nyejs42PM8D34OY\nOzYDw0nHGKzz9RuVSidCE8t4oYxril+CqknSHwW2AL9hjOkAmoG3pnpy8p8enkF0sxeG/9hTCWts\ns41rMfc/u/32Ipx4NwWeJetAbqCFk68vB9+nIZbnStaycve9pc8bMZqge3oc2tt9tm8vsmtXhL17\nHZ7+L9ex7pqXufDcKVatz9K4opHjx49x+lgD50+t5Cd7kjQ0BuWQRCrB2s1rgWCKXpOXAo+xZd9B\nD4+iZmAsUtUk6b8FPm+MeR7wgY9OVeoQWWyuaL6HI4ee4/D5UyxfF+PciTybW1q4Yvk9Fc/t6nLG\nEvSOHUUiEdixo8jRoy6D54dxk8dZveUKGtMu6eYibuNK3GaPoYHjrN2wgRVtlbvkaR/Bxa9ikrbW\n5oAPz0MsInVx7JhDZ6dP5FJ5mWIxSLJr1rg8/8376enJ4zgD+H6a3vYY6x7NE4+XP3f9eh8oTjge\nicDGjR6rH+qmqSVHY9oln3U5ezoomzSmYeXaHMlUvOIsC+0juDRoxaEsaceOObzySoQTJy6NdkfL\nFF1dDufOOQwMOLS3x3jssVV8/vNFTp1yePzxGHfcUWDv3tLn9vQ4QHEkUU/kurBm0ykopGlK5Tmf\nvVSMbErlaV6entBtrtwsi1g8RiqdDl99VeaMVhzKktbZ6dPe7tPT44zc4LuUZAsF6O93WL3a59FH\n86RS8OijeVav9jl1yqGvz5ny3PZ2n87OqW/KFpwmLmQKHHmjwIUzgwwNZbhwZjD4PFMg1azl1xLQ\nSFoWvUolibVrPTzPpafH4amngv8SbW0+69Z59PZ63HyzR3yktXM8HiTq115z2b7dmzByHj13fA26\nlNtvL/LCZ36REwPPcv3P+yQaXZpSOS4Oxhke8jixN8nbbjyKYVMtL4ssEBpJy6I2Ws548cUIxZGJ\nF6OJ9ZVXIuza5bJ7dwTfB88Ljnse+D7s3h2hvd0fS9Cj4nHYvj14ciQC27cXJxzfvn3qBD1q7VoP\nt/9d9P7ApynbSyp6kaZsL70/8One+36O/njFXHz5sghoJC2LWmenz4kTl0oSo9PgRksSN9/skc06\n/PjHwXilrc2nt9eht9fhhhu8siULCBL+rl0TM/KuXZGyI2lgrFbd2fku/HM5ht+6wKrEMtpuitPY\nfpyrt54Bf+XsvnhZFDSSlkUtEoGODo+2Nn+sJNHT49DW5tPR4VUc8R4/7oyNwEcVi8EIvViEb30r\nSnd3kPAfeqhAe7tPd7fDt74VnXBeoZBjcPA0hUJu7LH164MSTDQaJ5VaRTQaJxKB9g2ZObwCstBp\nJC2L2rFjDnv2RFi1ysfzgpkVo+WMPXsinD7t0dvrsGWLx6lTDq4bjKZXr/Y5dMjh0KEomzZ57NgR\nZNzxNej9+30OHHBZvdrnttsKxGJw221FHn88xtGjDqtXu9x6a4HuzHNE156laVWMvtN5CidX0JG8\nZ9abBsjSoO8SWdQ6O33a2nz27XPp7XXwPOjtddi3z6WtzWfbNo9bbiniOEECh+Cj48BddxXZtMkb\nK5XkchNnb9x3X5FrrinS2Ojz8svB7I6XX47Q2OhzzTVFtm3z6M48R8c90HH9apa1raDj+tV03APd\nmefqe2FkwVCSlkXv3DmHyS1KfD94vFiEF16IlCxZ7NoV4bbbimPT7HbuZMIKwngc3ve+Ih0dE0sp\nHR0+73tfEd/PEV17lmhs4iKTaCxGtOPshNKHyFSUpGVRe/VVF2td0mlobfVx3eBjOg3Wunzxi1EO\nHIhw8qTL1q1FYjHYurXIyZMuBw5E+Md/jJSdvVFudsfw8AWaVpVeBdjUFmN4+EJNvmZZXJSkZVHb\nts1jzRqP/n7o6wvKHX19Dv39sGaNxy/9UoG1az0KBdi5M0YmE3wsFIJpcvfcUyw5e2P8dL6pjicS\ny7h4uvQWWxd78yQSy2ryNcvioiQti9rx4w7nzzsMDl4qefg+DA4Gj/f0OHzsY3na24NVhH/+53FO\nnQpKGo89lmf37ks16F/4BSasMJxcox4tlYwed5w4hZMrKOQnJupCPk+hewXRaLxExCITKUnLoub7\nwU3AVGpiUTqV8nGc4Hg8Do88MjGRPvJInt5e57Ia9I4dl2rUr73mTjgei0083tXl0JG8h+7noPuN\nU1zoPUv3G6fofg46kpW76ImApuDJIlBu2ffGjT5XXOHR1+fS1+dw9GjQfL+11ae11WPjRp9cDp54\nYmLt+IknYjz6aJ5bb728i92OHcWxJeWjPTqmOg4unal7KZzNMdx9gdbEMqIpjaClekrSsqCV62LX\n0+Owb5/Pnj0RYjFIpy81U3rrLYfjxyMsX+5z+HCEU6eCRkqPPJLniSdiY53uHn00f9mCl0jk0orB\nUl3uxh8fNbpgRWS6VO6QBa1cF7v2dp/Nmz1iMbh4EQYGghuHAwMOFy9CLAYXLjhjCfrRR/MkkxM7\n3b32mv6LSH1pJC2hULl5fmmj5YWpOtEBrFwZdLnL5+HYseBjY2Pw+AMPFFm1yi/b6U6knjRMkLqr\n1Knu2DGn7Pnl5io/80yErq4IjY3Q0BDcRGxoCJJ0V1eEZ56JsH27V7bTnUg9KUlL3U0uWUye2jbT\nTnTFItx3X5GODo+zZx0GBhgpd8DZsw4dHR733Vec4lVFwkFJWuputGQx1fLrcp3qJu/IPXmucrEI\nQ0MAPo4TjMiDj/7I4yLhVlWSNsa0GWNOGGOuqXVAsjTNtHn+5B25J89V/vKXo/T2usTjwewO1w0+\nxuPQ2+vyta/ptoyEW8XvUGNMDPhfgMYdUjOza54/9VzmNWt8/uzPHM6cccjnHdJpn4EBB9/3aWvz\n+OAHC7X7okTmQDUj6T8G/grornEsskRNLllMXn49vsn+5PMq3VQEWLEiKHH4I+vCfT8ofazQDlWy\nAJQdSRtjHgNOW2ufMcZ8spoXTCbjRCL1KXWn04m6vG81whpbGOI6cgTOnIH16+Gd7wxGwu95T4zv\nfx+6u2H//hhHjkBv76XjxSJ8//tw4EAwY8OYy491d8PBg8Frb97MWFP/lhZYvRpOn45w4ECEO++s\nPtb5uF6xQoRoLEKqofr3SoXg33EqYY0trHFNVqnc8VHAN8bcB9wEfNEY8wFrbc9UJ2Qy9emRm04n\nGBgYrst7VxLW2MISV2sr3HRTME86kwniymSGueUWaGsLHj96NMqRI5DN+mP7FHZ3O6TTsGKFz7Fj\nDt/9rn/ZHoY7dhRpbHSxNgI44zab9bnjjiI33OAxMFBdnPN1vfKxIoV8kcFcde+VSicYDMG/Yylh\njS2UcTWUfrhskrbWvmP078aYfwI+Xi5Bi8xUueXVx445DA/D0JBDdzc89VQUzws+B5/OTg/XdUsu\nZikW4c03I5w+ffmyb9eNsG3b5XOkRcJEU/Ak9Do7fTo6fBob/QlbYDU2Bo+vX+9POTPktddcLfuW\nBa3q+UfW2rtrGIcscZWWhY9u8JrJXOpkNzQEt90WzM6YamZIsGqwoGXfsmBpkqjU3eROdjBxxofn\nBdtZNTb6JJPBbt6jI+mXXgqSc29vUIMeX5N+8cXxiXoiLfuWhUK/60ndVVoW7vvQ3e0wNOTQ1hYs\nSGlr8xkacjh40OHQIbds432RhUxJWuqu0rLw9et9Egl/rAb90EOFsRp1a6vP3XcXJix6GX29W28t\njt14nOkca5F6U5KWUCi3LLyryyGXc+jomDha7ujwyeWCuc9TNeafbYc9kXpTkpZQKNfJbv16n1tv\nLZYdLU+l0qYAlTrsidSbkrTUXbEIjz8e5eTJicvCT550ePzx6FiiLreN1VQml1KeeipadYc9kTBQ\nkpa6e+aZYHl2V5fL1q3Brtxbtxbp6nI5cCBozD8bM+2wJxIGStJSd/fdV2TtWo9CAXbujDE4GHws\nFGDt2tk35i9XShEJOyVpqbt4HD72sTzt7cEqwM98JmiG1N7u87GP5We1bLuaTQFEwkxJWkIhHodH\nHslPeOyRR2aXoKHypgCaRy1hpxWHEgoHDzo8//zEb8edO2PcdVeBq6+e+QyMSpsCVLrxKFJvGklL\n3R086LBzZ4yjR4MVhb/7u8GKwqNHg8cPHpzdaHemM0NEwkBJWuru9GmHXC4oeWzY4E34mMsFx0WW\nKpU7pO527Ag61WWzDn19wbLwfN7hjjuKNDT4I8dFliYlaQmFHTs88nnGmvYD3HlncKNPZClTuUNC\nQXOZRUpTkpa6q2a3cJGlSkla6m7yXOZ4XHOZRUapJi11p7nMIlPTSFpCodJcZjXul6Wq4kjaGBMB\nPgsYwAc+bq19o9aBiYyavAdiJDKxjg3le0qLLGTVjKQfBLDW3gn8PvCHNY1IZBI17pelrGKSttZ+\nHfj1kU/XA+drGpHIJGrcL0tZVTcOrbUFY8wXgIeBD5V7bjIZJxKpT6k7nU7U5X2rEdbYFlJc994L\nO3dO/Dwen9/VLvNxvWKFCNFYhFRD9e+VCum/I4Q3trDGNVnVszustb9ijPl3wC5jzHXW2oulnpfJ\n5OYsuOlIpxMMDAzX5b0rCWtsCymu0Rp0Pn/pRuGzz87vSHq+rlc+VqSQLzKYq+69UukEgyH8d4Tw\nxhbKuBpKP1xxyGuM+Ygx5pMjn2YAb+SPyLxQ435ZyqqpS/wDcLMx5gfAM8DvWGuHahuWyCVq3C9L\nWcVyx0hZ4xfmIRaRkrTYRZYyrTiUBaFUIlbjflkKtOJQRCTElKRFREJMSVpEJMSUpEVEQkxJWkQk\nxJSkRURCTElaRCTE5nyedPJ//Mlcv2R1XIekF9I5s2GNbZZx5W/bTv72O+cwIBGZbM6T9C//69Rc\nv2RVwtosCMIb22ziSnzlS/wl2+c4IhGZTOUOEZEQU5IWEQkx9e6QGYu9vIvI4cNz/8JRl0QhhN1w\n5ymuyDtbOWLzHGF/Vc93CDYfDaOwxhbGuHa03lrycSVpmZHhD3+EX33phZq8dqIhynC2UJPXno15\ni+sERH77UNVPj0Vd8mH8oUZ4YwtlXLsfK/mwkrTMWP72O2ryuol0gnwIb7TOZ1zTubaxdILhEF4v\nCG9sYYxrqo3gVJMWEQkxJWkRkRBTkhYRCTElaRGREFOSFhEJsbKzO4wxMeBzwAagAfgDa+3T8xCX\niIhQeST9y8AZa+3bgfuBP699SCIiMqrSPOkngK+O/N0BwrfCQERkESubpK21gwDGmDRBsv79Si+Y\nTMaJROpT6k6nE3V532qENTbFNT2Ka/rCGltY45qs4opDY8w64EngL6y1X6n0/EwmNxdxTVtY24FC\neGNTXNOjuKYvrLGFMa70FI9XunG4Gvgu8FvW2mfnPCoRESmr0kj6U8By4NPGmE+PPPaAtXaotmGJ\niAhUrkl/AvjEPMUigOd59F0cnPJ4a1MK1y1d86907orGJGeHMmOfZ/wcg4OXfuUr99oiUh/qghcy\nfRcHGXjya6yMXv5Pc6ZQgIc/SFu6eUbn9r37vTR875lLx2MR4vliVa8tIvWhJB1CK6NRVsfjJY9V\nui1b7tzuScfjsQg5p1j1a4vI/FOSDplMLst3TveyLHL5P82FYoF35LJ1iEpE6kVJOmS+9cYb3Hbi\nOOtKHDsxcvw333nPfIclInWiJB1C64Crpzj28nwGIiJ1pyQ9z3K5HLuOH5vy+FAux2kgVeLYaSBX\nKNA70F/y3O7z5zl/4QKtscs34jlbKNBcKJY4S0TCTEl6nu06fozk3/wVnSWmunV5Hq9sMtxP0Chl\nMgewvaemnMHR03ea5uPHaHUuP3vY99nXfZJ04VL7lbgfITdudsdUK55EpH6UpOeZ7/msdRyuLJGk\nfd/H8SFdp0cwAAAHVklEQVQLlFqwmgV8D6L5HPESG9I34tMejbKhRAIvFosMLl9G+uEPjs3iiKcS\n5EbmSacJ5kmLSLgoSc+z88ND+IUCeJdvJ+97HofPnCYOlJpEFwf2vdWF19dHY4kmVpF8Hs9xiJQY\nh0cdh4gbnTAPOp1OkHRKT9cTkXBQkq4Dh9KNvEdT63JgVYnjF0Y+Jl2HlHP5KzSWKHOIyMKmNcAh\nsyqZJgtkSvzJAm1NaQq+T5HL/3j+5SUQEVnYNJIOmcFClihw+fyM4B/r3HAGpiiX4Hl4kUiNIxSR\n+aQkXQcnfR+nRJI9OTISLpekAc4DZ0qMmi8AQz4c9i6fatdVKqmLSOgpSc+zW67oZN/Vm8mXmIFx\nrlBgY6KR4skuSqXUIrCqsQmiUXz38hFzayHPDx94EKezs+R7b79i/SyjF5H5piQ9z+KRGJuTySk7\n1WXyec4Bp0qcew7IFAt4IzXpySKOw02dnbz96k1zHreI1IeS9DxrbUrBuLnK46WBe17fTe6n+0se\nzwF3b9qE09DAUIlVhU4+z1WtrXMcsYjUk5J0yCSjCdYBV5WYTuf7Pk0NCTqTyZLtSBO5HDndOBRZ\nVJSk51mlxvwD6zdwGmgqcWPw9LjnlaKl3SKLj5J0HZRrzH9t+2q8VIpsiSTuFQrs2HAl6Vu2Tlku\n0dJukcVFSTpkYpEYHfE4V0Qvrzn7rsvpeFxbXIksIVUlaWPMduCPrLV31zYcAeieoqVod6FYcv60\niCxeFZO0Meb3gI8AF2sfjly1aiXn/8XHx+rP48WAzava5jskEamjakbSh4CfB75U41gEiLpRrlvT\nUe8wRCQkKiZpa+3XjDEbqn3BZDJOpEQbzfmQTifq8r7VGI0t4+fowyPuX17S6MejNZWY168jrNdM\ncU1PWOOC8MYW1rgmm/Mbh5lMqXkHtZdOJxgYKNUqv/7Gx5bwoyQefJjBEs9LjByfr68jrNdMcU1P\nWOOC8MYWxrimmj6r2R3zzHVdzc4Qkaqpn7SISIhVNZK21h4Fbq9tKCIiMplG0iIiIaYkLSISYkrS\nIiIhpiQtIhJiStIiIiGmJC0iEmJK0iIiIaYkLSISYkrSIiIhpiQtIhJiStIiIiGmJC0iEmJK0iIi\nIaYkLSISYkrSIiIhpiQtIhJiStIiIiGmJC0iEmJK0iIiIaYkLSISYo7v+/WOQUREpqCRtIhIiClJ\ni4iEmJK0iEiIKUmLiISYkrSISIgpSYuIhJiStIhIiEXrHcBMGWMagf8NtAEDwK9Ya09Pes6fAneN\nHAd4yFp7oUbxuMBfADcCWeDXrLUHxx1/EPj3QAH4nLX2s7WIYwZx/Rvg14DRa/cvrbV2PmIbef/t\nwB9Za++e9HhdrlcVcdXtehljYsDngA1AA/AH1tqnxx2v1/dYpbjqcs2MMRHgs4ABfODj1to3xh2v\n6/dYtRZskgb+FbDPWvsfjDG/CPw+8IlJz9kKvNda2zcP8fwckLDW7jDG3A78V+AhGPsm/m/ArcBF\n4EfGmKettafqGdeIrcA/t9bunodYJjDG/B7wEYJrMv7xel6vKeMaUbfrBfwycMZa+xFjzArgdeBp\nqPs1mzKuEfW6Zg8CWGvvNMbcDfwh4fg/OS0LudxxF/Cdkb9/G7hv/MGREeQm4K+NMT8yxnx0vuKx\n1r4EbBt37FrgoLX2nLU2BzwPvKPG8VQTFwT/gT5pjHneGPPJeYpp1CHg50s8Xs/rVS4uqO/1egL4\n9MjfHYIR4Kh6XrNycUGdrpm19uvAr498uh44P+5wvb/HqrYgkrQx5mPGmDfG/wGWAaOli4GRz8dr\nAv6M4Kf8/cBvGGNuqGGYzePiASgaY6JTHCsVbz3iAvh74OPAu4C7jDHvn6e4sNZ+DciXOFTP61Uu\nLqjv9Rq01g4YY9LAVwl+exxVt2tWIS6o7zUrGGO+QJALvjzuUF2/x6ZjQSRpa+3fWmvfNv4PwQVO\njzwlzcSfkgAZ4E+ttRlr7QDw/wjqsrXSPy4eANdaW5jiWKl45z0uY4wD/Hdrbd/IaOJbwM3zFFc5\n9bxeUwrD9TLGrAOeA75krf3KuEN1vWZTxRWGa2at/RVgM/BZY0zTyMOh/B4rZSHXpH8E/DPgZeAB\n4IeTjm8G/o8x5maCH0Z3AV+ocTwPAjtHar/7xh37KbBppF43SPBr1R/XMJZq42oG3jDGXEtQl3sX\nwQ2geqvn9SqnrtfLGLMa+C7wW9baZycdrts1qxBX3a6ZMeYjQKe19j8TDNq8kT8Q3u+xyyzkJP2X\nwBeMMc8DOeDDAMaYf0tQa3raGPMl4CWCX12/aK3dX8N4ngTebYx5gaAu96vGmA8DKWvtX4/E9QzB\nD4zPWWtP1jCW6cT1KYIRUBZ41lr7f+cprsuE5HpVique1+tTwHLg08aY0RrwZ4GmOl+zSnHV65r9\nA/B3xpgfADHgd4CHjTGh+x4rR61KRURCbEHUpEVEliolaRGREFOSFhEJMSVpEZEQU5IWEQkxJWkR\nkRBTkhYRCbH/Dzznx4/hw4XAAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11220d128>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_decision_regions(X_train.values, y_train['target'].values, classifier=forest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}