Arvore_sonar.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Arvore_de_decisao_sonar.ipynb",
      "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/github/PauloAAlmeida/Python/blob/master/Arvore_sonar.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1MsOiuBgAvBy"
      },
      "source": [
        "## Sonar, Mines vs Rocks\n",
        "\n",
        "https://archive.ics.uci.edu/ml/datasets/Connectionist+Bench+%28Sonar,+Mines+vs.+Rocks%29\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OwXOcJUaTV-I",
        "outputId": "36dd345b-123b-41e0-9cda-ca4a4ca24d74",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 800
        }
      },
      "source": [
        "!pip install pydotplus\n",
        "!pip install dtreeviz"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: pydotplus in /usr/local/lib/python3.6/dist-packages (2.0.2)\n",
            "Requirement already satisfied: pyparsing>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from pydotplus) (2.4.7)\n",
            "Collecting dtreeviz\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/a7/3c/a0177c90c6e9aa01d77a0c82bb98c01a6958f337e18a8d2c4c0b2d52d95b/dtreeviz-1.1.2.tar.gz (48kB)\n",
            "\u001b[K     |████████████████████████████████| 51kB 1.5MB/s \n",
            "\u001b[?25hRequirement already satisfied: graphviz>=0.9 in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (0.10.1)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (1.1.2)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (1.18.5)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (0.22.2.post1)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (3.2.2)\n",
            "Collecting colour\n",
            "  Downloading https://files.pythonhosted.org/packages/74/46/e81907704ab203206769dee1385dc77e1407576ff8f50a0681d0a6b541be/colour-0.1.5-py2.py3-none-any.whl\n",
            "Requirement already satisfied: xgboost in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (0.90)\n",
            "Requirement already satisfied: pytest in /usr/local/lib/python3.6/dist-packages (from dtreeviz) (3.6.4)\n",
            "Collecting pyspark\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/f0/26/198fc8c0b98580f617cb03cb298c6056587b8f0447e20fa40c5b634ced77/pyspark-3.0.1.tar.gz (204.2MB)\n",
            "\u001b[K     |████████████████████████████████| 204.2MB 63kB/s \n",
            "\u001b[?25hRequirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas->dtreeviz) (2018.9)\n",
            "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.6/dist-packages (from pandas->dtreeviz) (2.8.1)\n",
            "Requirement already satisfied: scipy>=0.17.0 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->dtreeviz) (1.4.1)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->dtreeviz) (0.16.0)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->dtreeviz) (2.4.7)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib->dtreeviz) (0.10.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->dtreeviz) (1.2.0)\n",
            "Requirement already satisfied: pluggy<0.8,>=0.5 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (0.7.1)\n",
            "Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (1.15.0)\n",
            "Requirement already satisfied: more-itertools>=4.0.0 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (8.5.0)\n",
            "Requirement already satisfied: py>=1.5.0 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (1.9.0)\n",
            "Requirement already satisfied: attrs>=17.4.0 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (20.2.0)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (50.3.0)\n",
            "Requirement already satisfied: atomicwrites>=1.0 in /usr/local/lib/python3.6/dist-packages (from pytest->dtreeviz) (1.4.0)\n",
            "Collecting py4j==0.10.9\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/9e/b6/6a4fb90cd235dc8e265a6a2067f2a2c99f0d91787f06aca4bcf7c23f3f80/py4j-0.10.9-py2.py3-none-any.whl (198kB)\n",
            "\u001b[K     |████████████████████████████████| 204kB 35.6MB/s \n",
            "\u001b[?25hBuilding wheels for collected packages: dtreeviz, pyspark\n",
            "  Building wheel for dtreeviz (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for dtreeviz: filename=dtreeviz-1.1.2-cp36-none-any.whl size=52359 sha256=384ae2aab0972d229f7d7bb963c123266e4e0b7457b6fcf2ff94417a73f9580e\n",
            "  Stored in directory: /root/.cache/pip/wheels/6c/42/13/06bfd7ecac5313d2bea233a1e1165fec14a4d3680fa856db57\n",
            "  Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pyspark: filename=pyspark-3.0.1-py2.py3-none-any.whl size=204612243 sha256=196771dc01d46dfb36f0de42aa4efb6da80f05041420c8fc23c652a834605888\n",
            "  Stored in directory: /root/.cache/pip/wheels/5e/bd/07/031766ca628adec8435bb40f0bd83bb676ce65ff4007f8e73f\n",
            "Successfully built dtreeviz pyspark\n",
            "Installing collected packages: colour, py4j, pyspark, dtreeviz\n",
            "Successfully installed colour-0.1.5 dtreeviz-1.1.2 py4j-0.10.9 pyspark-3.0.1\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PDVQg6ZJ_WXn",
        "outputId": "3c4cb94e-e3ef-4d22-afc9-3d9be78f1268",
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 73
        }
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn import datasets, tree\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
        "from sklearn.feature_extraction import DictVectorizer\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "\n",
        "from google.colab import files\n",
        "uploaded = files.upload()\n"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-4603bfc8-0036-4fb0-b4ba-2dd47b289cf7\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-4603bfc8-0036-4fb0-b4ba-2dd47b289cf7\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving sonar.all-data.xlsx to sonar.all-data.xlsx\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pQzY_XVp__pZ",
        "outputId": "e9f66683-6e4b-4555-bbe3-0b91e3532659",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 433
        }
      },
      "source": [
        "sonar = pd.read_excel('sonar.all-data.xlsx', sheet_name=0) \n",
        "print(\"\\nDimensões: {0}\".format(sonar.shape))\n",
        "print(\"\\nCampos: {0}\".format(sonar.keys()))\n",
        "print(sonar.describe(), sep='\\n')\n",
        "\n",
        "X = sonar.iloc[:,0:(sonar.shape[1] - 1)]\n",
        "\n",
        "le = LabelEncoder()\n",
        "y = le.fit_transform(sonar.iloc[:,(sonar.shape[1] - 1)])\n",
        "\n",
        "# Particiona a base de dados\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, test_size=0.1)\n",
        "\n",
        "\n"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Dimensões: (207, 61)\n",
            "\n",
            "Campos: Index(['0.0200', '0.0371', '0.0428', '0.0207', '0.0954', '0.0986', '0.1539',\n",
            "       '0.1601', '0.3109', '0.2111', '0.1609', '0.1582', '0.2238', '0.0645',\n",
            "       '0.0660', '0.2273', '0.3100', '0.2999', '0.5078', '0.4797', '0.5783',\n",
            "       '0.5071', '0.4328', '0.5550', '0.6711', '0.6415', '0.7104', '0.8080',\n",
            "       '0.6791', '0.3857', '0.1307', '0.2604', '0.5121', '0.7547', '0.8537',\n",
            "       '0.8507', '0.6692', '0.6097', '0.4943', '0.2744', '0.0510', '0.2834',\n",
            "       '0.2825', '0.4256', '0.2641', '0.1386', '0.1051', '0.1343', '0.0383',\n",
            "       '0.0324', '0.0232', '0.0027', '0.0065', '0.0159', '0.0072', '0.0167',\n",
            "       '0.0180', '0.0084', '0.0090', '0.0032', 'R'],\n",
            "      dtype='object')\n",
            "           0.0200      0.0371      0.0428  ...      0.0084      0.0090      0.0032\n",
            "count  207.000000  207.000000  207.000000  ...  207.000000  207.000000  207.000000\n",
            "mean     0.029208    0.038443    0.043837  ...    0.007947    0.007936    0.006523\n",
            "std      0.023038    0.033040    0.038521  ...    0.006485    0.006196    0.005038\n",
            "min      0.001500    0.000600    0.001500  ...    0.000300    0.000100    0.000600\n",
            "25%      0.013300    0.016400    0.018900  ...    0.003600    0.003650    0.003100\n",
            "50%      0.022800    0.030800    0.034200  ...    0.005800    0.006300    0.005300\n",
            "75%      0.035800    0.048100    0.058200  ...    0.010400    0.010350    0.008550\n",
            "max      0.137100    0.233900    0.305900  ...    0.044000    0.036400    0.043900\n",
            "\n",
            "[8 rows x 60 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Fo2oEQF40BfK",
        "outputId": "ed5f229f-aa95-4d30-ab79-24e65a61ce99",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 260
        }
      },
      "source": [
        "sonar_tree = DecisionTreeClassifier(random_state=0, criterion='entropy')\n",
        "sonar_tree = sonar_tree.fit(X_train, y_train)\n",
        "print(\"Acurácia (base de treinamento):\", sonar_tree.score(X_train, y_train))\n",
        "\n",
        "y_pred = sonar_tree.predict(X_test)\n",
        "print(\"Acurácia de previsão:\", accuracy_score(y_test, y_pred))\n",
        "print(classification_report(y_test, y_pred, target_names=[\"Mina\", \"Rocha\"]))\n",
        "      \n",
        "cnf_matrix = confusion_matrix(y_test, y_pred)\n",
        "cnf_table = pd.DataFrame(data=cnf_matrix, index=[\"Mina\", \"Rocha\"], columns=[\"Mina (prev)\", \"Rocha (prev)\"])\n",
        "print(cnf_table)\n",
        "\n"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Acurácia (base de treinamento): 1.0\n",
            "Acurácia de previsão: 0.7142857142857143\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "        Mina       0.64      0.78      0.70         9\n",
            "       Rocha       0.80      0.67      0.73        12\n",
            "\n",
            "    accuracy                           0.71        21\n",
            "   macro avg       0.72      0.72      0.71        21\n",
            "weighted avg       0.73      0.71      0.72        21\n",
            "\n",
            "       Mina (prev)  Rocha (prev)\n",
            "Mina             7             2\n",
            "Rocha            4             8\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "x-yvOCPzBl_d",
        "outputId": "0f6c60e9-254f-4d4a-ae7b-165d92ffcbe4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 69
        }
      },
      "source": [
        "from dtreeviz.trees import *\n",
        "\n",
        "viz = dtreeviz(sonar_tree,\n",
        "              X_train,\n",
        "              y_train,\n",
        "              target_name=\"Classe\",\n",
        "              feature_names=np.arange(0,60),\n",
        "              class_names=[\"mina\", \"rocha\"])  \n",
        "\n",
        "viz.view()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "findfont: Font family ['Arial'] not found. Falling back to DejaVu Sans.\n",
            "findfont: Font family ['Arial'] not found. Falling back to DejaVu Sans.\n",
            "findfont: Font family ['Arial'] not found. Falling back to DejaVu Sans.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V_A92_qYTCkY",
        "outputId": "a4bd94c4-8403-4e47-8286-b86be4d59318",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 201
        }
      },
      "source": [
        "import pydotplus \n",
        "# Create DOT data\n",
        "dot_data = tree.export_graphviz(sonar_tree, out_file=None, \n",
        "                                proportion=False,\n",
        "                                rounded =True,\n",
        "                                filled=True,\n",
        "                                feature_names=np.arange(0,60),  \n",
        "                                class_names=[\"mina\", \"rocha\"])\n",
        "\n",
        "# Draw graph\n",
        "graph = pydotplus.graph_from_dot_data(dot_data)  \n",
        "\n",
        "# Show graph\n",
        "Image(graph.create_png())\n"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "error",
          "ename": "NameError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-7-6afb7188c793>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     13\u001b[0m \u001b[0;31m# Show graph\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mImage\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgraph\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_png\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;31mNameError\u001b[0m: name 'Image' is not defined"
          ]
        }
      ]
    }
  ]
}