decision_tree_classification.ipyb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ubuntu007/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype int64 was converted to float64 by StandardScaler.\n",
      "  warnings.warn(msg, DataConversionWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[62  6]\n",
      " [ 3 29]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "\n",
    "\n",
    "plt.rcParams['figure.figsize'] = [20, 10]\n",
    "# Importing the dataset\n",
    "dataset = pd.read_csv('Social_Network_Ads.csv')\n",
    "X = dataset.iloc[:, [2, 3]].values\n",
    "y = dataset.iloc[:, 4].values\n",
    "\n",
    "# Splitting the dataset into the Training set and Test set\n",
    "from sklearn.cross_validation import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)\n",
    "\n",
    "# Feature Scaling\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "sc = StandardScaler()\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.transform(X_test)\n",
    "\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "classifier = DecisionTreeClassifier(criterion='entropy', random_state=0)\n",
    "classifier.fit(X_train,y_train)\n",
    "\n",
    "y_pred = classifier.predict(X_test)\n",
    "# Making the Confusion Matrix\n",
    "from sklearn.metrics import confusion_matrix\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)\n",
    "\n",
    "# Visualising the Training set results\n",
    "from matplotlib.colors import ListedColormap\n",
    "X_set, y_set = X_train, y_train\n",
    "X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),\n",
    "                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))\n",
    "plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n",
    "             alpha = 0.75, cmap = ListedColormap(('red', 'green')))\n",
    "plt.xlim(X1.min(), X1.max())\n",
    "plt.ylim(X2.min(), X2.max())\n",
    "for i, j in enumerate(np.unique(y_set)):\n",
    "    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],\n",
    "                c = ListedColormap(('red', 'green'))(i), label = j)\n",
    "plt.title('Decision tree (Training set)')\n",
    "plt.xlabel('Age')\n",
    "plt.ylabel('Estimated Salary')\n",
    "plt.legend()\n",
    "plt.show()\n",
    "\n",
    "# Visualising the Test set results\n",
    "from matplotlib.colors import ListedColormap\n",
    "X_set, y_set = X_test, y_test\n",
    "X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),\n",
    "                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))\n",
    "plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n",
    "             alpha = 0.75, cmap = ListedColormap(('red', 'green')))\n",
    "plt.xlim(X1.min(), X1.max())\n",
    "plt.ylim(X2.min(), X2.max())\n",
    "for i, j in enumerate(np.unique(y_set)):\n",
    "    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],\n",
    "                c = ListedColormap(('red', 'green'))(i), label = j)\n",
    "plt.title('Decision tree (Test set)')\n",
    "plt.xlabel('Age')\n",
    "plt.ylabel('Estimated Salary')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "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": "3.7.0"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}