arghyadeep99/decisiontrees.ipynb

## decisiontrees.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "DecisionTrees.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/arghyadeep99/b72c5db62e055794fbd479a1818548d1/decisiontrees.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "I6qKGWQz4i3b",
        "colab_type": "text"
      },
      "source": [
        "# Decision Trees\n",
        "“The possible solutions to a given problem emerge as the leaves of a tree, each node representing a point of deliberation and decision.”\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EYd2O_Lm5BcF",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn import datasets\n",
        "from sklearn.tree import DecisionTreeClassifier"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DdxxbmYG5JyE",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "iris = datasets.load_iris()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0HuImXCiaEZK",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "x_setosa = iris['data'][:50, (2)]\n",
        "y_setosa = iris['data'][:50, (3)]\n",
        "x_versicolor = iris['data'][50:100, (2)]\n",
        "y_versicolor = iris['data'][50:100, (3)]\n",
        "x_virginica = iris['data'][100:150, (2)]\n",
        "y_virginica = iris['data'][100:150, (3)]\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mlOnK2fMcaoo",
        "colab_type": "code",
        "outputId": "a3bc127a-eb2f-412e-e82c-664afbfcadbc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 302
        }
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "plt.xlabel('petal_length')\n",
        "plt.ylabel('petal_width')\n",
        "plt.plot(x_setosa,y_setosa, 'ro') #plotting setosa flower\n",
        "plt.plot(x_versicolor,y_versicolor, 'go')  #plotting versicolor flower\n",
        "plt.plot(x_virginica,y_virginica, 'yo')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7f997e46fdd8>]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAELCAYAAADdriHjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6eb3gp-qgLJy",
        "colab_type": "code",
        "outputId": "c3de0087-b15f-4025-a73b-8fae326e2184",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "source": [
        "iris.feature_names[2:]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['petal length (cm)', 'petal width (cm)']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gtKZzGge5OxQ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X = iris.data[:,2:]\n",
        "y = iris.target"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "APiN_J_-5cL7",
        "colab_type": "code",
        "outputId": "f3e6ee8d-6b30-4a6b-c97a-3c6393472a57",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 126
        }
      },
      "source": [
        "tree_clf = DecisionTreeClassifier(max_depth=2)\n",
        "tree_clf.fit(X, y)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=2,\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,\n",
              "                       random_state=None, splitter='best')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5VbZ10hh5tWv",
        "colab_type": "code",
        "outputId": "d6fb6b75-7147-4b2f-af0b-ba07b81e07e2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 164
        }
      },
      "source": [
        "from sklearn.tree import export_graphviz\n",
        "import pydotplus\n",
        "from PIL import Image\n",
        "import os\n",
        "\n",
        "dot_data = export_graphviz(tree_clf, feature_names=iris.feature_names[2:],class_names=iris.target_names,rounded=True,filled=True)\n",
        "graph = pydotplus.graph_from_dot_data(dot_data)\n",
        "\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "#os.chdir(\"/drive/My Drive\")\n",
        "graph.write_png(\"iris.png\")\n",
        "\n",
        "\n",
        "print(os.getcwd())\n",
        "print( os.listdir() )"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob&scope=email%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdocs.test%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive.photos.readonly%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fpeopleapi.readonly&response_type=code\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /content/drive\n",
            "/content\n",
            "['.config', 'drive', 'iris.png', 'sample_data']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mGU24FRG6TGB",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from google.colab import files\n",
        "files.download( \"iris.png\" )  "
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "INVnLTQ7BuoZ",
        "colab_type": "text"
      },
      "source": [
        "<figure>\n",
        "<center>\n",
        "<img src='https://drive.google.com/uc?id=1clWhVpjxGMbDfxN47ApMfWmnn4h1c_a3'/>\n",
        "  </center>\n",
        "  <center><figcaption><b>Iris Decision Tree</b></figcaption></center>\n",
        "</figure>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X_pbMqGy7N4h",
        "colab_type": "code",
        "outputId": "e12fc671-6c66-4d13-a4d9-396a3535ff23",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 302
        }
      },
      "source": [
        "plt.xlabel('petal_length')\n",
        "plt.ylabel('petal_width')\n",
        "plt.plot(x_setosa,y_setosa, 'ro') #plotting setosa flower\n",
        "plt.plot(x_versicolor,y_versicolor, 'go')  #plotting versicolor flower\n",
        "plt.plot(x_virginica,y_virginica, 'yo')\n",
        "plt.plot([0,7], [0.8, 0.8], 'k-', lw=2)\n",
        "plt.plot([0,7], [1.75, 1.75], 'k-', lw=2)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7f26ea718400>]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 37
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAELCAYAAADdriHjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3X2UXHWd5/H3J91JIKAJCy3SQNKw\nQkLQWZAeFXHnsCa6gI/j4Cpmx4XV6TE9jnJ0dtY1e2ThTHbHccfV0UmclmenF8cBdXkaWYyiDkaH\nTkR5mrCYITzECZE1QSZuSDrf/aNuJ1WVerhVXbeqbtXndU6d7nvrd3/3ezjQX+793e/9KiIwMzOb\nMafTAZiZWXdxYjAzsxJODGZmVsKJwczMSjgxmJlZCScGMzMr4cRgZmYlnBjMzKyEE4OZmZUY7HQA\nzTjuuONiZGSk02GYmeXKpk2bfh4RQ/XG5TIxjIyMMDU11ekwzMxyRdK2NON8K8nMzEo4MZiZWQkn\nBjMzK+HEYGZmJZwYzMysRKaJQdLJkr4t6WFJD0n6cIUx50vaLen+5POJLGMys96zY8ckGzeOcM89\nc9i4cYQdOyabOqaZeXpR1o+r7gc+GhGbJb0I2CTp7oh4uGzc9yLizRnHYmY9aMeOSbZsGePAgT0A\n7N27jS1bxgA4/vhVqY955JHLkETEC6nn6VWZXjFExM8iYnPy+y+BR4ATszynmfWXrVvXHPwDP+PA\ngT1s3bqmoWNg38GkkHaeXtW2NQZJI8DZwA8rfH2upB9L+htJZ1Y5fkzSlKSpnTt3ZhipmeXJ3r1P\nNLS/3nezGdsr2pIYJB0N3AJcHhHPlX29GVgSEf8C+Bzw9UpzRMRERIxGxOjQUN2KbjPrE/PnL25o\nf73vZjO2V2SeGCTNpZAUJiPiq+XfR8RzEfF88vudwFxJx2Udl5n1hlNPXcucOQtK9s2Zs4BTT13b\n0DEwF2leQ/P0qqyfShJwDfBIRHy6ypiXJuOQ9KokpmezjMvMesfxx69i6dIJ5s9fAoj585ewdOlE\nzQXjSsecccZ1LFt2bUPz9CpFRHaTS68Dvgc8ABxIdn8cWAwQEV+Q9EFgNYUnmH4FfCQivl9r3tHR\n0fBL9MzMGiNpU0SM1huX6eOqEfG3gOqM+Tzw+SzjMDOz9HL52m0zy4cdOybZunUNe/c+wfz5izn1\n1LUtuTXz6KPjbN8+AUwDAwwPj3H66etmPa8VODGYWSaaKTxLo5AU1hftmT647eTQGn5XkpllopnC\nszQKVwrp91vjnBjMLBPNFJ6lM93gfmuUE4OZZaKZwrN0Bhrcb41yYjCzTDRTeJbG8PBYQ/utcU4M\nZpaJZgrP0jj99HUMD6/m0BXCAMPDq73w3EKZFrhlxQVuZmaN64oCNzPrb+V1DMceexHPPntnSV0D\nUHdMvauMNPUSrRrTDp2Ow1cMZpaJ8jqGSqR5FP4G7as6Zs6cBTVvQVU6T/kxrRrTDlnGkfaKwWsM\nZpaJys1wShUa41RPCtBc053yY1o1ph26IQ4nBjPLRCsb3DTTdKd4f6vGtEM3xOHEYGaZaGWDm2aa\n7hTvb9WYduiGOJwYzCwTlZvhlCo0xplbc0wzTXfKj2nVmHbohjicGMwsE5XqGIaHV5dsL1t2LWec\ncV3NMc003Sk/plVj2qEb4vBTSWZmfcJPJZlZz9qxY5KNG0e45545bNw4wo4dk02N6ZRujg1c4GZm\nOZOmz0NWvSBaoZtjm+ErBjPLlTzVJFTSzbHNcGIws1zJU01CIzF0Q2wznBjMLFfyVJPQSAzdENsM\nJwYzy5U81SRU0s2xzXBiMLNcyVNNQiXdHNsM1zGYmfUJ92Mws1zKqodDp3ocdLq3QjN8xWBmXSNN\nDweYi6Tkld2VdUuvhW7p8TDDlc9mljtpejjAvppJAbqnriEPNQuVODGYWdfIqodDp2oH8lCzUIkT\ng5l1jax6OHSqdiAPNQuVODGYWddI08OhsMYwr+aIbqlryEPNQiVODGbWNdL0cDjjjOtYtuzahno4\ndKp2IA81C5X4qSQzsz7RFU8lSTpZ0rclPSzpIUkfrjBGkv5M0mOSfiLplVnGZGZmtWVd4LYf+GhE\nbJb0ImCTpLsj4uGiMRcCpyWfVwPrk59m1sUqFW5B7cKzNIVoedNMAVu3F7219VaSpP8FfD4i7i7a\n9xfAPRFxU7K9BTg/In5WbR7fSjLrrEqFW9I8Cn9P9qWep5PFXq3QTAFbJ4veuuJWUjFJI8DZwA/L\nvjoReLJo+6lkn5l1qUqFW4Wis/RJAfJR7FVLMwVseSh6a0tikHQ0cAtweUQ81+QcY5KmJE3t3Lmz\ntQGaWUOyKkTLm2YK2PJQ9JZ5YpA0l0JSmIyIr1YY8jRwctH2Scm+EhExERGjETE6NDSUTbBmlkpW\nhWh500wBWx6K3rJ+KknANcAjEfHpKsNuBd6bPJ30GmB3rfUFM+u8SoVbhaKzuQ3Nk4dir1qaKWDL\nQ9Fb1lcM5wG/Dbxe0v3J5yJJH5D0gWTMncBW4DHgi8B4xjGZ2SxVKtxatuxazjjjupqFZ/UK0fKm\nmQK2PBS9ucDNzKxPuFGPmbVd+fP5Rx75MnbtugeYBgYYHh7j9NPX1Tymk8/0d1MsneTEYGYtUf58\n/t6929i7d1vRiGm2b18PcDA5VDpmy5YxgLb/Qe6mWDrNL9Ezs5ZI12QHtm+fqHlMp57p76ZYOs2J\nwcxaIv1z+NN1j+nEM/3dFEunOTGYWUukfw5/oO4xnXimv5ti6TQnBjNriXRNdmB4eKzmMZ16pr+b\nYuk0JwYza4lKz+cvWrSCQ1cIAwwPry55Kqmbnunvplg6zXUMZmZ9wnUMZtZSt39/JUfu3cAc4AAw\nPWeYebGDrGsUHn10PHmS6dB5Fi48r+689c7di30UWsVXDGZW1+3fX8lRezcgHdoXQck2UHKrqBV9\nBwpJYX2Fb2bSU+V56507b30UWqXr+jGYWX4dWZYU4PCkAK2vUSier9SB0q2yeeudu1f7KLSKE4OZ\n1ZX+D0WraxSm6w+pMG+9c/dqH4VWcWIws7oO1B+SaHWNwkD9IRXmrXfuXu2j0CpODGZW16/mr6B8\nObLS8mSraxSK5ytV+qerfN565+7VPgqt0leLz6p0U9TMLGea/bvtxWczM2tKX9Ux5PHqyCwLWT2P\nP/nAJGs2rOGJ3U+weOFi1q5Yy6pX5ONRTjukrxKDmWXXd2DygUnGbhtjz77CvNt2b2PstsK8Tg75\n4ltJZn0mq+fx12xYczApzNizbw9rNvTec/69zonBrM9k9Tz+E7srH19tv3UvJwazPpPV8/iLF1Y+\nvtp+615ODGZ9Jqvn8deuWMuCuaXzLpi7gLUreu85/17nxGDWZ7LqO7DqFauYeMsESxYuQYglC5cw\n8ZYJLzznUF8VuJmZ9TMXuJlZVZMPTDLymRHmXDmHkc+MMPnAZFNjWnGerOzYMcnGjSPcc88cNm4c\nYceO9p0771zHYNZn0tQbtKImoZN1DVnVavSL1LeSJL0D+CTwEkDJJyLixdmFV5lvJZk1b+QzI2zb\nve2w/UsWLuHxyx9PPaYV58nKxo0j7N17+Lnnz1/Cuedme+5ulkVrzz8B3hIRjzQflpl1Wpp6g1bU\nJHSyrqGfeidkoZE1hh1OCmb5l6beoBU1CZ2sa+in3glZqJsYJL0juY00JemvJF0ysy/Zb2Y5kqbe\noBU1CZ2sa+in3glZSHMr6S1Fv+8B3li0HcBXWxqRmWVqZuG31ltQ04xpxXmyMrPAnMUbZPtBI4vP\n50XEvfX2tYMXn83MGpdFHcPnUu4rDuJaSc9IerDK9+dL2i3p/uTziQbiMTOzDNS9lSTpXOC1wJCk\njxR99WLqd+q+Hvg8cGONMd+LiDfXi8PMKmumOc6Jf3oi25/ffnB70fxFLDxiYckcUPs20Pgd40xs\nmmA6phnQAGPnjHHF6Hklt2+OPfYinn32Tt/OyZk0awzzgKOTsS8q2v8ccHGtAyPiu5JGmg3OzGpr\npoisPCkA7Nq7i117dx2c47KvX4YkXph+oeK843eMs35q/cHjp2OaR7et54EFX2RQ+4FCUdn27YfG\nuMgsPxpZY1gSEYdXjNQ/bgS4PSJeXuG784FbgKeA7cAfRMRD9eb0GoNZQTNFZLpSTZ9vZt7BqwaZ\njumS7256Nbz0iPpz9HuRWSe1rMBN0m0Unj5COvxfqIh4azMBJjYDSyLieUkXAV8HTqsSxxgwBrB4\nsZ9FNoP2F5HNzFueFABeMj/dHC4y635pFp//O/CnwD8AvwK+mHyeB346m5NHxHMR8Xzy+53AXEnH\nVRk7ERGjETE6NDQ0m9Oa9Yx2F5HNzDugw5cXn9mbbg4XmXW/uokhIr4TEd8BzouId0XEbcnnPcC/\nnM3JJb1UyWWIpFcl8Tw7mznN+kkzRWTDRw/XnXfunLnMG5hXdd6xc8YOO+bqrbA/at+EcJFZPjTy\nuOpRkk6d2ZB0CnBUrQMk3QRsBJZKekrS+yR9QNIHkiEXAw9K+jHwZ8C7I48NIsw6pJnmOE9/9OnD\nksOi+YtK5rju7ddx7duurTrvujetY/Xo6oNXDgMa4PQlq3nF8utLGgAND69ueUMgy14ji88XABPA\nVgpvVl0C/G5E3JVdeJV58dnMrHEtL3CLiG9QWBj+MPAhYGknkoJZL8uqsc34HeMMXjWIrhSDVw0y\nfsd43fOWH7PyxpUda7pTzk14slX3ikHS6yPiW9VemBcRbX9Xkq8YrBeV1yRA4b7+bPsml9cczFg9\nupp1b1pX8byDcwbZf2B/zXlbEVszypvwQGHtwrep6kt7xZAmMVwZEVdIuq7C1xER/77ZIJvlxGC9\nKKvGNpVqDqCwLrD/E/urnjeNdjTdKecmPM1rWR1DRFyR/LysFYGZWWVZ1SRUSgrF+2czfzua7pRz\nE57spV5jkPRTSZPJU0VnZhmUWT/KqiahUs1B8f7ZzN+Opjvl3IQne408rroc+AvgWOBTSaL4WjZh\nmfWfrBrbVKo5KN5f6byDc+q/Rq1dTXfKuQlP9hpJDNPAvuTnAeCZ5GNmLdBMTUIalWoOZhaeq533\n+rdff9gxK05Z0fLYmnH88atYunTC9REZaqSOYQ/wAPBp4JsR0bEKZS8+m5k1rmWLz0UuAV4HjAPv\nl/R94LsRsaHJGM16WjN9EsqtvHElG/7h0H9iK05ZwenHnl7SB2HpsUvZ8uyWqttj54xx3uLzSmK5\n6LSLuPP/3Fl1u10tOK07pb5iOHiAtAy4ELgceElEHJlFYLX4isG6XStqEsqTwmwMaKDq00mVdKpG\nwbLV8spnSbdIegz4LLAAeC9wTPMhmvWuNRvWlCQFgD379rBmw5rUc7QqKUD1R1araTRW6y2N3Er6\nb8CPIir/GybpDRFxd2vCMsu3dvdJyEKeYrXWauRdSVPVkkLiky2Ix6wntLtPQhbyFKu1ViOPq9bT\nfL9Asx7TipqEFaesaFk81YrcqulUjYJ1h1YmBvdRMEu0oibhm+/95mHJYcUpKw6rL1h+3PKa26tH\nV3PDb95QEsvq0dU1t73w3N8afiqp6kTS5oh4ZUsmq8NPJZmZNa7lTyWl8HgL5zLrS+V9EcbvGK/b\nAyFND4dm+jxk1RvCul+a125X7MMww/0YzFqjUu1DufL6gjT1Es3UVGTVG8I6q5X9GCr1YZjhfgxm\nLZK2L0JxD4Q0PRya6fOQVW8I66xW9mNwHwazNkhbN1A8Lk29RDM1Fb1Qh2HNa6TADUlvAs4EjpjZ\nFxFXtToos360eOHiVFcMxfUF1Y5pdEzaWFzb0B8aeSXGF4B3Ab9PoWbhncCSjOIy6zuVah/KldcX\npKmXaKamIqveEJYPjTyV9NqIeC/wi4i4EjgXOD2bsMz6T6Xah3r1BWnqJZqpqciqN4TlQyP9GH4Y\nEa+W9APgHcCzwEMR8bIsA6zEi89mZo3Loh/D7ZIWAZ8CNlOodL66yfjMzKxLNXIr6U8iYldE3EJh\nbWEZ8EfZhGWWnW4q3GqmoM0sa43cSjrslRftfA1GMd9KsmZ1U+FWMwVtZrPRsldiSHqppHOAIyWd\nLemVyed8Cg17zHKjFQ10soylnBvmWCekWWP418ClwEnAp4v2Pwd8PIOYzDLTTYVbzRS0mbVDmsrn\nG4AbJP1Wsr5gllvdVLjVTEGbWTs0svh8r6RrJP0NgKTlkt6XUVxmmeimwq1mCtrM2qGRxHAdcBcw\nnGw/Clze8ojMMtRNhVvNFLSZtUMjTyXdFxG/LulHEXF2su/+iDirxjHXAm8GnomIl1f4XsBngYuA\nPcClEbG5Xix+KsnMrHFZNOr5J0nHkrTwlPQaYHedY64HLqjx/YXAaclnDFjfQDxmbTN+xziDVw2i\nK8XgVYOM3zHe8JhWNcvppjoM602NVD5/BLgVOFXSvcAQcHGtAyLiu5JGagx5G3BjFC5bfiBpkaQT\nIuJnDcRllqnxO8ZZP3Xo/1mmY/rg9ro3rUs1prxmYdvubYzdNgaQulnOtt3buOzrlyGJF6ZfSD2P\nWaMauWJ4GPgacB+wA/gihXWG2TgReLJo+6lkn1nXmNg0UXd/vTHN1E9UOmbfgX0Hk0Laecwa1Uhi\nuJHCazD+K/A5Cm9W/VIWQVUiaUzSlKSpnTt3tuu0ZkzHdN399ca0slnObMea1dNIYnh5RLw/Ir6d\nfH6HQtOe2XgaOLlo+6Rk32EiYiIiRiNidGhoaJanNUtvQAN199cbU60WoV6znLRc62Ct1Ehi2Jws\nOAMg6dXAbB8NuhV4rwpeA+z2+oJ1m7FzxururzemVc1y5s6Zy7yBeQ3NY9aoRhafzwG+L2nmmnUx\nsEXSA0BExK+VHyDpJuB84DhJTwFXAHMpHPAF4E4Kj6o+RuFxVfeXtq4zs8A8sWmC6ZhmQAOMnTN2\ncH+aMTMLw2s2rOGJ3U+weOFi1q5YW7dZTqVjGp3HrFGN1DHUbOMZEfVr+1vEdQxmZo1reaOedv7h\nNzOzzmlkjcHMzPqAE4OZmZVwYjAzsxJODGZmVsKJwczMSjgxmJlZCScGMzMr4cRgZmYlnBjMzKxE\nI+9Kyr1CJ1Ezs3xL+yqjZvmKwczMSvTVFUPWWdbMrBf4isHMzEo4MZiZWQknBjMzK+HEYGZmJZwY\nzMyshBODmZmVcGIwM7MSTgxmZlbCicHMzEo4MZiZWQknBjMzK+HEYGZmJZwY+t3kJIyMwJw5hZ+T\nk52OyMw6rK/ermplJidhbAz27Clsb9tW2AZYtapzcZlZR/mKoZ+tWXMoKczYs6ew38z6lhNDP3vi\nicb2m1lfcGLoZ4sXN7bfzPqCE0M/W7sWFiwo3bdgQWG/mfUtJ4Z+tmoVTEzAkiUgFX5OTHjh2azP\nZZ4YJF0gaYukxyR9rML3l0raKen+5PP+rGOyIqtWweOPw4EDhZ9OCmZ9L9PEIGkA+HPgQmA5cImk\n5RWG/lVEnJV8rs4yJqvDdQ1mfS/rOoZXAY9FxFYASV8G3gY8nPF5rRmuazAzsr+VdCLwZNH2U8m+\ncr8l6SeSbpZ0csYxWTWuazAzumPx+TZgJCJ+DbgbuKHSIEljkqYkTe3cubOtAfYN1zWYGdknhqeB\n4iuAk5J9B0XEsxGxN9m8Gjin0kQRMRERoxExOjQ0lEmwfc91DWZG9onhPuA0SadImge8G7i1eICk\nE4o23wo8knFMVo3rGsyMjBNDROwHPgjcReEP/lci4iFJV0l6azLsQ5IekvRj4EPApVnGZDW4rsHM\nAEVEp2No2OjoaExNTXU6DDOzXJG0KSJG643rhsVna5U0NQgrVxauBmY+Z55Zesz4eP05XOtg1tN8\nxdArymsQoLA+UHwraOVK2LChsXnL50hzHjPrSmmvGJwYesXISKEgrdySJYVXXUDhCqEZxXOkOY+Z\ndSXfSuo3WdYgFM/hWgeznufE0CuyrEEonsO1DmY9z4mhV6SpQVixovF5y+dwrYNZz3Ni6BVpahC+\n+c3Dk8Py5aXHrF5dew7XOpj1PC8+m5n1CS8+m5lZU5wYesn4OAwOFm7xDA7CiSeWFrOtXFm/OM3F\na2Z9L+tGPdYu4+Owfv2h7elp2L69dMyGDfCtb8HM7cPyRjxu1GNmeI2hdwwOFpJBM2aK01y8ZtbT\nvMbQb5pNCnCoOM3Fa2aGE0PvGBho/tiZ4jQXr5kZTgy9Y2YtoJ7y9yUVF6e5eM3McGLoHevWFYrT\nZq4cBgZgeLh0zIoV8KUvVS9Oc/GameHFZzOzvuHF57xLU09QXrdwzDGldQvln3nzCreGao055hg3\n6jHrc65j6EZp6gkq1S3s2lV73n37Cp9adu06NE+l87rWwazn+VZSN0pTTzCbuoVGuVGPWU/wraQ8\nS1NP0K6kUH5e1zqY9Twnhm6Upp5gNnULjXKjHrO+4sTQjdLUE6StW5gtN+ox6ztODN0oTT1BpbqF\nRYtqzzt3Lhx5ZO0xixa5UY9Zn/Pis5lZn/Dic69ppnagvM5hfLzyPjOzIq5jyINmagcq1TkUb5fv\nW7eutTGbWW75VlIeNFM70Eidw8AA7N/fbHRmlhO+ldRLmqkdaKTOoZ01EWbW9ZwY8qCZ2oFG6hza\nWRNhZl3PiSEPmqkdaKTOoV01EWaWC04MedBM7UClOofVqyvv88KzmRXJfPFZ0gXAZ4EB4OqI+OOy\n7+cDNwLnAM8C74qIx2vN2XeLz2ZmLdAVi8+SBoA/By4ElgOXSFpeNux9wC8i4mXA/wA+mWVMZmZW\nW9a3kl4FPBYRWyPiBeDLwNvKxrwNuCH5/WZghVTemNjMzNol68RwIvBk0fZTyb6KYyJiP7AbODbj\nuMzMrIrcLD5LGpM0JWlq586dnQ7HzKxnZZ0YngZOLto+KdlXcYykQWAhhUXoEhExERGjETE6NDSU\nUbhmZpb1u5LuA06TdAqFBPBu4D1lY24F/h2wEbgY+FbUeVRq06ZNP5dU4R0RqRwH/LzJYzshT/Hm\nKVbIV7x5ihXyFW+eYoXZxbskzaBME0NE7Jf0QeAuCo+rXhsRD0m6CpiKiFuBa4AvSXoM+L8Ukke9\neZu+ZJA0leZxrW6Rp3jzFCvkK948xQr5ijdPsUJ74s387aoRcSdwZ9m+TxT9/v+Ad2Ydh5mZpZOb\nxWczM2uPfkwME50OoEF5ijdPsUK+4s1TrJCvePMUK7Qh3lz2YzAzs+z04xWDmZnV0FeJQdIFkrZI\nekzSxzodTy2SrpX0jKQHOx1LPZJOlvRtSQ9LekjShzsdUzWSjpD0d5J+nMR6ZadjSkPSgKQfSbq9\n07HUIulxSQ9Iul9S17/pUtIiSTdL+ntJj0g6t9MxVSJpafLPdObznKTLMztfv9xKSl7o9yjwBgqv\n5rgPuCQiHu5oYFVI+g3geeDGiHh5p+OpRdIJwAkRsVnSi4BNwNu78Z9t8h6uoyLieUlzgb8FPhwR\nP+hwaDVJ+ggwCrw4It7c6XiqkfQ4MBoRuagLkHQD8L2IuFrSPGBBROzqdFy1JH/LngZeHRHN1nPV\n1E9XDGle6Nc1IuK7FOo6ul5E/CwiNie//xJ4hMPfidUVouD5ZHNu8unq/zuSdBLwJuDqTsfSSyQt\nBH6DQi0VEfFCtyeFxArgp1klBeivxJDmhX42S5JGgLOBH3Y2kuqS2zL3A88Ad0dE18aa+Azwh8CB\nTgeSQgD/W9ImSd3eGvAUYCdwXXKb7mpJR3U6qBTeDdyU5Qn6KTFYxiQdDdwCXB4Rz3U6nmoiYjoi\nzqLw7q5XSeraW3WS3gw8ExGbOh1LSq+LiFdS6MHye8kt0W41CLwSWB8RZwP/BHT72uM84K3AX2d5\nnn5KDGle6GdNSu7X3wJMRsRXOx1PGsltg28DF3Q6lhrOA96a3Lv/MvB6SX/Z2ZCqi4ink5/PAF+j\ncAu3Wz0FPFV0xXgzhUTRzS4ENkfEjixP0k+J4eAL/ZKs+24KL/CzWUoWdK8BHomIT3c6nlokDUla\nlPx+JIWHEf6+s1FVFxH/KSJOiogRCv/Ofisi/m2Hw6pI0lHJwwckt2TeCHTtU3UR8Y/Ak5KWJrtW\nAF33wESZS8j4NhK04V1J3aLaC/06HFZVkm4CzgeOk/QUcEVEXNPZqKo6D/ht4IHk3j3Ax5P3ZHWb\nE4Abkic75gBfiYiufgQ0R44HvpY0YBwE/mdEfKOzIdX1+8Bk8j+LW4HLOhxPVUmyfQPwu5mfq18e\nVzUzs3T66VaSmZml4MRgZmYlnBjMzKyEE4OZmZVwYjAzsxJODGZmVsKJwQyQdKmk4RTjrpd0cY3v\n75HU0kbtyauhx4u2z+/2129bvjkxmBVcCtRNDB2yCBivO8qsRZwYrCdJGkmar0wmDVhulrRA0jmS\nvpO8/fMuSSckVwCjFCpg75d0pKRPSLpP0oOSJpLXfjQawxslbZS0WdJfJy8ZnGlmc2Wy/wFJy5L9\nQ5LuThoIXS1pm6TjgD8G/nkS26eS6Y8uajAz2Ux8ZtU4MVgvWwqsi4gzgOeA3wM+B1wcEecA1wJr\nI+JmYApYFRFnRcSvgM9HxK8nTZKOBBpqjpP8Qf/PwMrkbaNTwEeKhvw82b8e+INk3xUU3oV0JoUX\nui1O9n+Mwvv3z4qI/5DsOxu4HFgOnErhtSRmLdE370qyvvRkRNyb/P6XwMeBlwN3J/+DPQD8rMqx\n/0rSHwILgH8GPATc1sC5X0Phj/a9ybnmARuLvp95A+0m4B3J768DfhMgIr4h6Rc15v+7iHgKIHk/\n1QiFbnRms+bEYL2s/EVgvwQeioiafX0lHQGso9Ci8klJ/wU4osFzi0IToEuqfL83+TlNc/8d7i36\nvdk5zCryrSTrZYuLmru/B/gBMDSzT9JcSWcm3/8SeFHy+0wS+HmyLlD1KaQafgCcJ+llybmOknR6\nnWPuBf5NMv6NwDEVYjPLnBOD9bItFLqIPULhj+znKPyR/6SkHwP3A69Nxl4PfCG5LbMX+CKFXgJ3\nUejl0ZCI2EnhSaebJP2Ewm2kZXUOuxJ4o6QHgXcC/wj8MiKepXBL6sGixWezzPi129aTkt7TtyeL\nx7kgaT4wnfQOOZdCy8mzOh2X9R/flzTrHouBr0iaA7wA/E6H47E+5SsGsyZI+hpwStnu/xgRd3Ui\nHrNWcmIwM7MSXnw2M7MSTgzVfRe7AAAAG0lEQVRmZlbCicHMzEo4MZiZWQknBjMzK/H/AcWMH7En\nOreRAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5MHZUVvakhGk",
        "colab_type": "text"
      },
      "source": [
        "# Gini Value\n",
        "<figure>\n",
        "<center>\n",
        "<img src='https://drive.google.com/uc?id=1Lc3WThnirb-7s6ZOK67R7BVl9TXxjWS7'/>\n",
        "  </center>\n",
        "  <center><figcaption><b>Gini </b></figcaption></center>\n",
        "</figure>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a6A2TSPmkhpb",
        "colab_type": "text"
      },
      "source": [
        "# Cost Function of CART Algorithm\n",
        "<figure>\n",
        "<center>\n",
        "<img src='https://drive.google.com/uc?id=1Lec6EMQCfcwWd1sm6KIyQE4wfkRJOa_D'/>\n",
        "  </center>\n",
        "  <center><figcaption><b></b></figcaption></center>\n",
        "</figure>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CfzjlbiDkSJ9",
        "colab_type": "text"
      },
      "source": [
        "# Task for Students\n",
        "1. Look into Decision Trees for Regression. \n",
        "2. Explore Random Forests Algorithm."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fdeQCp-yHtL7",
        "colab_type": "text"
      },
      "source": [
        "https://stackoverflow.com/questions/20224526/how-to-extract-the-decision-rules-from-scikit-learn-decision-tree add this"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZYmCau5_FEjX",
        "colab_type": "code",
        "outputId": "780de91d-eedb-4915-b6bf-53b420198f1e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 337
        }
      },
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from math import log\n",
        "\n",
        "x = np.array([i/100 for i in range(100)])\n",
        "gini = -1+((x)**2+(1-x)**2)\n",
        "entropy = x*np.log(x)+(1-x)*np.log(1-x)\n",
        "plt.plot(x, gini)\n",
        "plt.plot(x, entropy)\n",
        "plt.legend(['gini','entropy'])\n",
        "plt.show()\n"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:6: RuntimeWarning: divide by zero encountered in log\n",
            "  \n",
            "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:6: RuntimeWarning: invalid value encountered in multiply\n",
            "  \n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAD8CAYAAACfF6SlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n+iOoPuh3aOsAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CpwRPSDwmRDZ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}