Machine_Learning_para_a_Detecção_do_Câncer_de_Mama.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Machine Learning para a Detecção do Câncer de Mama.ipynb",
      "provenance": [],
      "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/carlosfab/data_science/blob/master/Machine_Learning_para_a_Detec%C3%A7%C3%A3o_do_C%C3%A2ncer_de_Mama.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E_uJn-uQZlK7",
        "colab_type": "text"
      },
      "source": [
        "# Machine Learning para a Detecção do Câncer de Mama\n",
        "\n",
        "* **[Link para o artigo completo no blog Sigmoidal](http://sigmoidal.ai/machine-learning-para-a-deteccao-de-cancer-de-mama/)**\n",
        "\n",
        "A utilização de *Machine Learning* para a detecção do câncer de mama vem crescendo cada vez mais, e contribuído para diagnósticos mais rápidos e precisos.\n",
        "\n",
        "[De acordo com a Sociedade Brasileira de Mastologia](https://noticias.r7.com/saude/uma-em-cada-12-mulheres-recebera-diagnostico-de-cancer-de-mama-02102019), uma em cada 12 mulheres terá um tumor nas mamas até os 90 anos. Infelizmente, [o câncer de mama é a principal causa de morte entre as mulheres](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6468737/), de todos os diferentes tipos de câncer.\n",
        "\n",
        "<p align=center>\n",
        "  <img src=\"http://sigmoidal.ai/wp-content/uploads/2019/10/3877.jpg\" width=\"400px\">\n",
        "</p>\n",
        "\n",
        "Uma das principais características do câncer de mama é que quanto mais precoce for o seu diagnóstico, maiores são as chances de tratamento. Entretanto, uma pesquisa realizada revelou que mais de 3,8 milhões de mulheres na faixa de 50 a 69 anos nunca haviam feito autoexame ou mamografia.\n",
        "\n",
        "A fim de aumentar a conscientização a respeito da prevenção e diagnóstico precoce, há todo ano a campanha [Outubro Rosa](http://www.outubrorosa.org.br/objetivo.htm), que visa alertar principalmente as mulheres sobre esta causa.\n",
        "\n",
        "Contribuindo com essa conscientização e com a campanha Outubro Rosa, preparei um projeto de *Data Science* onde construi um modelo de *Machine Learning* capaz de detectar o câncer de mama."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "y3yD447plfoy",
        "colab_type": "text"
      },
      "source": [
        "## Importar os Dados\n",
        "\n",
        "Para a construção do modelo de *Machine Learning* foi usado o banco de dados Wisconsin, disponibilizado no [Repositório de Machine Learning da UCI](https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+(Diagnostic)).\n",
        "\n",
        "Os dados que serão utilizados nesta análise também estão disponíveis para download por meio [deste link direto](https://www.dropbox.com/s/z8nw6pfumdw3bb9/breast-cancer-wisconsin.csv?raw=1), e consistem basicamente em um arquivo csv contendo 569 entradas e 32 colunas onde as observações foram obtidas por meio da aspiração com agulha fina de células da mama. Ressalta-se ainda que a variável alvo pode ser classificada em benigna ou maligna.\n",
        "\n",
        "Este arquivo será importando para uma estrutura DataFrame utilizando a biblioteca pandas a fim de possibilitar sua manipulação e análise."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z7Yfo6Xslv1M",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# importar os pacotes necessários\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "from xgboost import XGBClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import accuracy_score\n",
        "from sklearn.impute import SimpleImputer\n",
        "\n",
        "# configurar o notebook\n",
        "sns.set_style()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1fD95uTPl8mw",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# importar o dataset em csv \n",
        "data_path = \"https://www.dropbox.com/s/z8nw6pfumdw3bb9/breast-cancer-wisconsin.csv?raw=1\" \n",
        "df = pd.read_csv(data_path)\n",
        "\n",
        "# eliminar uma coluna com erro\n",
        "df.drop('Unnamed: 32', axis=1, inplace=True)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RmWnFAV9xcYu",
        "colab_type": "text"
      },
      "source": [
        "## Análise Exploratória\n",
        "\n",
        "A primeira coisa que faremos após importar o dataset será examinar as dimensões do DataFrame e as primeiras entradas. Isso possibilitará criar uma consciência situacional inicial a respeito do formato de entrada e da estrutura geral dos dados.\n",
        "\n",
        "* A coluna `id` representa o número de identificação.\n",
        "* A coluna `diagnosis` é a variável alvo.\n",
        "  * **M -** *Maligno*\n",
        "  * **B -** *Benigno*\n",
        "* A descrição completa para cada uma das *features* está disponível [neste link](http://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29).\n",
        "\n",
        "\n",
        "Uma característica é um número de identificação (ID), outro é o diagnóstico de câncer, e 30 são medidas laboratoriais numéricas. O diagnóstico é codificado como “M” para indicar maligno ou “B” para indicar benigno."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dJD1uRUzxjrU",
        "colab_type": "code",
        "outputId": "df86ce9c-0cc1-4b53-d266-24b8fe3f96bc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        }
      },
      "source": [
        "# dimensões do df\n",
        "print(\"DIMENSÕES DO DATAFRAME:\")\n",
        "print(\"Linhas:\\t\\t{}\".format(df.shape[0]))\n",
        "print(\"Colunas:\\t{}\".format(df.shape[1]))"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "DIMENSÕES DO DATAFRAME:\n",
            "Linhas:\t\t569\n",
            "Colunas:\t32\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "B59GBVIdxsUK",
        "colab_type": "text"
      },
      "source": [
        "Já as primeiras 5 entradas desse conjunto de dados permitem adquirirmos uma noção inicial sobre o tipo de formato, exemplos de entrada e formulação das hipóteses iniciais do processo investigativo."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9zfOZFI0xtu6",
        "colab_type": "code",
        "outputId": "0978963c-2c67-4d19-bc59-64b4637a8bf7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 241
        }
      },
      "source": [
        "# ver as 5 primeiras entradas\n",
        "df.head()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>diagnosis</th>\n",
              "      <th>radius_mean</th>\n",
              "      <th>texture_mean</th>\n",
              "      <th>perimeter_mean</th>\n",
              "      <th>area_mean</th>\n",
              "      <th>smoothness_mean</th>\n",
              "      <th>compactness_mean</th>\n",
              "      <th>concavity_mean</th>\n",
              "      <th>concave points_mean</th>\n",
              "      <th>symmetry_mean</th>\n",
              "      <th>fractal_dimension_mean</th>\n",
              "      <th>radius_se</th>\n",
              "      <th>texture_se</th>\n",
              "      <th>perimeter_se</th>\n",
              "      <th>area_se</th>\n",
              "      <th>smoothness_se</th>\n",
              "      <th>compactness_se</th>\n",
              "      <th>concavity_se</th>\n",
              "      <th>concave points_se</th>\n",
              "      <th>symmetry_se</th>\n",
              "      <th>fractal_dimension_se</th>\n",
              "      <th>radius_worst</th>\n",
              "      <th>texture_worst</th>\n",
              "      <th>perimeter_worst</th>\n",
              "      <th>area_worst</th>\n",
              "      <th>smoothness_worst</th>\n",
              "      <th>compactness_worst</th>\n",
              "      <th>concavity_worst</th>\n",
              "      <th>concave points_worst</th>\n",
              "      <th>symmetry_worst</th>\n",
              "      <th>fractal_dimension_worst</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>842302</td>\n",
              "      <td>M</td>\n",
              "      <td>17.99</td>\n",
              "      <td>10.38</td>\n",
              "      <td>122.80</td>\n",
              "      <td>1001.0</td>\n",
              "      <td>0.11840</td>\n",
              "      <td>0.27760</td>\n",
              "      <td>0.3001</td>\n",
              "      <td>0.14710</td>\n",
              "      <td>0.2419</td>\n",
              "      <td>0.07871</td>\n",
              "      <td>1.0950</td>\n",
              "      <td>0.9053</td>\n",
              "      <td>8.589</td>\n",
              "      <td>153.40</td>\n",
              "      <td>0.006399</td>\n",
              "      <td>0.04904</td>\n",
              "      <td>0.05373</td>\n",
              "      <td>0.01587</td>\n",
              "      <td>0.03003</td>\n",
              "      <td>0.006193</td>\n",
              "      <td>25.38</td>\n",
              "      <td>17.33</td>\n",
              "      <td>184.60</td>\n",
              "      <td>2019.0</td>\n",
              "      <td>0.1622</td>\n",
              "      <td>0.6656</td>\n",
              "      <td>0.7119</td>\n",
              "      <td>0.2654</td>\n",
              "      <td>0.4601</td>\n",
              "      <td>0.11890</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>842517</td>\n",
              "      <td>M</td>\n",
              "      <td>20.57</td>\n",
              "      <td>17.77</td>\n",
              "      <td>132.90</td>\n",
              "      <td>1326.0</td>\n",
              "      <td>0.08474</td>\n",
              "      <td>0.07864</td>\n",
              "      <td>0.0869</td>\n",
              "      <td>0.07017</td>\n",
              "      <td>0.1812</td>\n",
              "      <td>0.05667</td>\n",
              "      <td>0.5435</td>\n",
              "      <td>0.7339</td>\n",
              "      <td>3.398</td>\n",
              "      <td>74.08</td>\n",
              "      <td>0.005225</td>\n",
              "      <td>0.01308</td>\n",
              "      <td>0.01860</td>\n",
              "      <td>0.01340</td>\n",
              "      <td>0.01389</td>\n",
              "      <td>0.003532</td>\n",
              "      <td>24.99</td>\n",
              "      <td>23.41</td>\n",
              "      <td>158.80</td>\n",
              "      <td>1956.0</td>\n",
              "      <td>0.1238</td>\n",
              "      <td>0.1866</td>\n",
              "      <td>0.2416</td>\n",
              "      <td>0.1860</td>\n",
              "      <td>0.2750</td>\n",
              "      <td>0.08902</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>84300903</td>\n",
              "      <td>M</td>\n",
              "      <td>19.69</td>\n",
              "      <td>21.25</td>\n",
              "      <td>130.00</td>\n",
              "      <td>1203.0</td>\n",
              "      <td>0.10960</td>\n",
              "      <td>0.15990</td>\n",
              "      <td>0.1974</td>\n",
              "      <td>0.12790</td>\n",
              "      <td>0.2069</td>\n",
              "      <td>0.05999</td>\n",
              "      <td>0.7456</td>\n",
              "      <td>0.7869</td>\n",
              "      <td>4.585</td>\n",
              "      <td>94.03</td>\n",
              "      <td>0.006150</td>\n",
              "      <td>0.04006</td>\n",
              "      <td>0.03832</td>\n",
              "      <td>0.02058</td>\n",
              "      <td>0.02250</td>\n",
              "      <td>0.004571</td>\n",
              "      <td>23.57</td>\n",
              "      <td>25.53</td>\n",
              "      <td>152.50</td>\n",
              "      <td>1709.0</td>\n",
              "      <td>0.1444</td>\n",
              "      <td>0.4245</td>\n",
              "      <td>0.4504</td>\n",
              "      <td>0.2430</td>\n",
              "      <td>0.3613</td>\n",
              "      <td>0.08758</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>84348301</td>\n",
              "      <td>M</td>\n",
              "      <td>11.42</td>\n",
              "      <td>20.38</td>\n",
              "      <td>77.58</td>\n",
              "      <td>386.1</td>\n",
              "      <td>0.14250</td>\n",
              "      <td>0.28390</td>\n",
              "      <td>0.2414</td>\n",
              "      <td>0.10520</td>\n",
              "      <td>0.2597</td>\n",
              "      <td>0.09744</td>\n",
              "      <td>0.4956</td>\n",
              "      <td>1.1560</td>\n",
              "      <td>3.445</td>\n",
              "      <td>27.23</td>\n",
              "      <td>0.009110</td>\n",
              "      <td>0.07458</td>\n",
              "      <td>0.05661</td>\n",
              "      <td>0.01867</td>\n",
              "      <td>0.05963</td>\n",
              "      <td>0.009208</td>\n",
              "      <td>14.91</td>\n",
              "      <td>26.50</td>\n",
              "      <td>98.87</td>\n",
              "      <td>567.7</td>\n",
              "      <td>0.2098</td>\n",
              "      <td>0.8663</td>\n",
              "      <td>0.6869</td>\n",
              "      <td>0.2575</td>\n",
              "      <td>0.6638</td>\n",
              "      <td>0.17300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>84358402</td>\n",
              "      <td>M</td>\n",
              "      <td>20.29</td>\n",
              "      <td>14.34</td>\n",
              "      <td>135.10</td>\n",
              "      <td>1297.0</td>\n",
              "      <td>0.10030</td>\n",
              "      <td>0.13280</td>\n",
              "      <td>0.1980</td>\n",
              "      <td>0.10430</td>\n",
              "      <td>0.1809</td>\n",
              "      <td>0.05883</td>\n",
              "      <td>0.7572</td>\n",
              "      <td>0.7813</td>\n",
              "      <td>5.438</td>\n",
              "      <td>94.44</td>\n",
              "      <td>0.011490</td>\n",
              "      <td>0.02461</td>\n",
              "      <td>0.05688</td>\n",
              "      <td>0.01885</td>\n",
              "      <td>0.01756</td>\n",
              "      <td>0.005115</td>\n",
              "      <td>22.54</td>\n",
              "      <td>16.67</td>\n",
              "      <td>152.20</td>\n",
              "      <td>1575.0</td>\n",
              "      <td>0.1374</td>\n",
              "      <td>0.2050</td>\n",
              "      <td>0.4000</td>\n",
              "      <td>0.1625</td>\n",
              "      <td>0.2364</td>\n",
              "      <td>0.07678</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         id diagnosis  ...  symmetry_worst  fractal_dimension_worst\n",
              "0    842302         M  ...          0.4601                  0.11890\n",
              "1    842517         M  ...          0.2750                  0.08902\n",
              "2  84300903         M  ...          0.3613                  0.08758\n",
              "3  84348301         M  ...          0.6638                  0.17300\n",
              "4  84358402         M  ...          0.2364                  0.07678\n",
              "\n",
              "[5 rows x 32 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ruN79pMhx5Cs",
        "colab_type": "text"
      },
      "source": [
        "Por meio do método describe, é possível ver um resumo estatístico das variáveis numéricas."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bAyqxTw0mBXY",
        "colab_type": "code",
        "outputId": "a86852f1-9dba-47c8-9986-f3a7e6727585",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 334
        }
      },
      "source": [
        "df.describe()"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>radius_mean</th>\n",
              "      <th>texture_mean</th>\n",
              "      <th>perimeter_mean</th>\n",
              "      <th>area_mean</th>\n",
              "      <th>smoothness_mean</th>\n",
              "      <th>compactness_mean</th>\n",
              "      <th>concavity_mean</th>\n",
              "      <th>concave points_mean</th>\n",
              "      <th>symmetry_mean</th>\n",
              "      <th>fractal_dimension_mean</th>\n",
              "      <th>radius_se</th>\n",
              "      <th>texture_se</th>\n",
              "      <th>perimeter_se</th>\n",
              "      <th>area_se</th>\n",
              "      <th>smoothness_se</th>\n",
              "      <th>compactness_se</th>\n",
              "      <th>concavity_se</th>\n",
              "      <th>concave points_se</th>\n",
              "      <th>symmetry_se</th>\n",
              "      <th>fractal_dimension_se</th>\n",
              "      <th>radius_worst</th>\n",
              "      <th>texture_worst</th>\n",
              "      <th>perimeter_worst</th>\n",
              "      <th>area_worst</th>\n",
              "      <th>smoothness_worst</th>\n",
              "      <th>compactness_worst</th>\n",
              "      <th>concavity_worst</th>\n",
              "      <th>concave points_worst</th>\n",
              "      <th>symmetry_worst</th>\n",
              "      <th>fractal_dimension_worst</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>5.690000e+02</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "      <td>569.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>3.037183e+07</td>\n",
              "      <td>14.127292</td>\n",
              "      <td>19.289649</td>\n",
              "      <td>91.969033</td>\n",
              "      <td>654.889104</td>\n",
              "      <td>0.096360</td>\n",
              "      <td>0.104341</td>\n",
              "      <td>0.088799</td>\n",
              "      <td>0.048919</td>\n",
              "      <td>0.181162</td>\n",
              "      <td>0.062798</td>\n",
              "      <td>0.405172</td>\n",
              "      <td>1.216853</td>\n",
              "      <td>2.866059</td>\n",
              "      <td>40.337079</td>\n",
              "      <td>0.007041</td>\n",
              "      <td>0.025478</td>\n",
              "      <td>0.031894</td>\n",
              "      <td>0.011796</td>\n",
              "      <td>0.020542</td>\n",
              "      <td>0.003795</td>\n",
              "      <td>16.269190</td>\n",
              "      <td>25.677223</td>\n",
              "      <td>107.261213</td>\n",
              "      <td>880.583128</td>\n",
              "      <td>0.132369</td>\n",
              "      <td>0.254265</td>\n",
              "      <td>0.272188</td>\n",
              "      <td>0.114606</td>\n",
              "      <td>0.290076</td>\n",
              "      <td>0.083946</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>1.250206e+08</td>\n",
              "      <td>3.524049</td>\n",
              "      <td>4.301036</td>\n",
              "      <td>24.298981</td>\n",
              "      <td>351.914129</td>\n",
              "      <td>0.014064</td>\n",
              "      <td>0.052813</td>\n",
              "      <td>0.079720</td>\n",
              "      <td>0.038803</td>\n",
              "      <td>0.027414</td>\n",
              "      <td>0.007060</td>\n",
              "      <td>0.277313</td>\n",
              "      <td>0.551648</td>\n",
              "      <td>2.021855</td>\n",
              "      <td>45.491006</td>\n",
              "      <td>0.003003</td>\n",
              "      <td>0.017908</td>\n",
              "      <td>0.030186</td>\n",
              "      <td>0.006170</td>\n",
              "      <td>0.008266</td>\n",
              "      <td>0.002646</td>\n",
              "      <td>4.833242</td>\n",
              "      <td>6.146258</td>\n",
              "      <td>33.602542</td>\n",
              "      <td>569.356993</td>\n",
              "      <td>0.022832</td>\n",
              "      <td>0.157336</td>\n",
              "      <td>0.208624</td>\n",
              "      <td>0.065732</td>\n",
              "      <td>0.061867</td>\n",
              "      <td>0.018061</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>8.670000e+03</td>\n",
              "      <td>6.981000</td>\n",
              "      <td>9.710000</td>\n",
              "      <td>43.790000</td>\n",
              "      <td>143.500000</td>\n",
              "      <td>0.052630</td>\n",
              "      <td>0.019380</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.106000</td>\n",
              "      <td>0.049960</td>\n",
              "      <td>0.111500</td>\n",
              "      <td>0.360200</td>\n",
              "      <td>0.757000</td>\n",
              "      <td>6.802000</td>\n",
              "      <td>0.001713</td>\n",
              "      <td>0.002252</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.007882</td>\n",
              "      <td>0.000895</td>\n",
              "      <td>7.930000</td>\n",
              "      <td>12.020000</td>\n",
              "      <td>50.410000</td>\n",
              "      <td>185.200000</td>\n",
              "      <td>0.071170</td>\n",
              "      <td>0.027290</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.156500</td>\n",
              "      <td>0.055040</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>8.692180e+05</td>\n",
              "      <td>11.700000</td>\n",
              "      <td>16.170000</td>\n",
              "      <td>75.170000</td>\n",
              "      <td>420.300000</td>\n",
              "      <td>0.086370</td>\n",
              "      <td>0.064920</td>\n",
              "      <td>0.029560</td>\n",
              "      <td>0.020310</td>\n",
              "      <td>0.161900</td>\n",
              "      <td>0.057700</td>\n",
              "      <td>0.232400</td>\n",
              "      <td>0.833900</td>\n",
              "      <td>1.606000</td>\n",
              "      <td>17.850000</td>\n",
              "      <td>0.005169</td>\n",
              "      <td>0.013080</td>\n",
              "      <td>0.015090</td>\n",
              "      <td>0.007638</td>\n",
              "      <td>0.015160</td>\n",
              "      <td>0.002248</td>\n",
              "      <td>13.010000</td>\n",
              "      <td>21.080000</td>\n",
              "      <td>84.110000</td>\n",
              "      <td>515.300000</td>\n",
              "      <td>0.116600</td>\n",
              "      <td>0.147200</td>\n",
              "      <td>0.114500</td>\n",
              "      <td>0.064930</td>\n",
              "      <td>0.250400</td>\n",
              "      <td>0.071460</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>9.060240e+05</td>\n",
              "      <td>13.370000</td>\n",
              "      <td>18.840000</td>\n",
              "      <td>86.240000</td>\n",
              "      <td>551.100000</td>\n",
              "      <td>0.095870</td>\n",
              "      <td>0.092630</td>\n",
              "      <td>0.061540</td>\n",
              "      <td>0.033500</td>\n",
              "      <td>0.179200</td>\n",
              "      <td>0.061540</td>\n",
              "      <td>0.324200</td>\n",
              "      <td>1.108000</td>\n",
              "      <td>2.287000</td>\n",
              "      <td>24.530000</td>\n",
              "      <td>0.006380</td>\n",
              "      <td>0.020450</td>\n",
              "      <td>0.025890</td>\n",
              "      <td>0.010930</td>\n",
              "      <td>0.018730</td>\n",
              "      <td>0.003187</td>\n",
              "      <td>14.970000</td>\n",
              "      <td>25.410000</td>\n",
              "      <td>97.660000</td>\n",
              "      <td>686.500000</td>\n",
              "      <td>0.131300</td>\n",
              "      <td>0.211900</td>\n",
              "      <td>0.226700</td>\n",
              "      <td>0.099930</td>\n",
              "      <td>0.282200</td>\n",
              "      <td>0.080040</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>8.813129e+06</td>\n",
              "      <td>15.780000</td>\n",
              "      <td>21.800000</td>\n",
              "      <td>104.100000</td>\n",
              "      <td>782.700000</td>\n",
              "      <td>0.105300</td>\n",
              "      <td>0.130400</td>\n",
              "      <td>0.130700</td>\n",
              "      <td>0.074000</td>\n",
              "      <td>0.195700</td>\n",
              "      <td>0.066120</td>\n",
              "      <td>0.478900</td>\n",
              "      <td>1.474000</td>\n",
              "      <td>3.357000</td>\n",
              "      <td>45.190000</td>\n",
              "      <td>0.008146</td>\n",
              "      <td>0.032450</td>\n",
              "      <td>0.042050</td>\n",
              "      <td>0.014710</td>\n",
              "      <td>0.023480</td>\n",
              "      <td>0.004558</td>\n",
              "      <td>18.790000</td>\n",
              "      <td>29.720000</td>\n",
              "      <td>125.400000</td>\n",
              "      <td>1084.000000</td>\n",
              "      <td>0.146000</td>\n",
              "      <td>0.339100</td>\n",
              "      <td>0.382900</td>\n",
              "      <td>0.161400</td>\n",
              "      <td>0.317900</td>\n",
              "      <td>0.092080</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>9.113205e+08</td>\n",
              "      <td>28.110000</td>\n",
              "      <td>39.280000</td>\n",
              "      <td>188.500000</td>\n",
              "      <td>2501.000000</td>\n",
              "      <td>0.163400</td>\n",
              "      <td>0.345400</td>\n",
              "      <td>0.426800</td>\n",
              "      <td>0.201200</td>\n",
              "      <td>0.304000</td>\n",
              "      <td>0.097440</td>\n",
              "      <td>2.873000</td>\n",
              "      <td>4.885000</td>\n",
              "      <td>21.980000</td>\n",
              "      <td>542.200000</td>\n",
              "      <td>0.031130</td>\n",
              "      <td>0.135400</td>\n",
              "      <td>0.396000</td>\n",
              "      <td>0.052790</td>\n",
              "      <td>0.078950</td>\n",
              "      <td>0.029840</td>\n",
              "      <td>36.040000</td>\n",
              "      <td>49.540000</td>\n",
              "      <td>251.200000</td>\n",
              "      <td>4254.000000</td>\n",
              "      <td>0.222600</td>\n",
              "      <td>1.058000</td>\n",
              "      <td>1.252000</td>\n",
              "      <td>0.291000</td>\n",
              "      <td>0.663800</td>\n",
              "      <td>0.207500</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                 id  radius_mean  ...  symmetry_worst  fractal_dimension_worst\n",
              "count  5.690000e+02   569.000000  ...      569.000000               569.000000\n",
              "mean   3.037183e+07    14.127292  ...        0.290076                 0.083946\n",
              "std    1.250206e+08     3.524049  ...        0.061867                 0.018061\n",
              "min    8.670000e+03     6.981000  ...        0.156500                 0.055040\n",
              "25%    8.692180e+05    11.700000  ...        0.250400                 0.071460\n",
              "50%    9.060240e+05    13.370000  ...        0.282200                 0.080040\n",
              "75%    8.813129e+06    15.780000  ...        0.317900                 0.092080\n",
              "max    9.113205e+08    28.110000  ...        0.663800                 0.207500\n",
              "\n",
              "[8 rows x 31 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "X9i5OLtt-P43",
        "colab_type": "text"
      },
      "source": [
        "Com exceção da coluna `diagnosis`, todas as outras são do tipo numérica (`int` e `float`). Apesar dessa ser a nossa conclusão olhando as primeiras entradas, é prudente analisar por meio do atributo `dtypes` para ter certeza que nenhuma foi importada como `string`."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4olnGxiAvUw0",
        "colab_type": "code",
        "outputId": "96bc0262-3788-446d-9bca-3e2861109d2b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 578
        }
      },
      "source": [
        "df.dtypes"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "id                           int64\n",
              "diagnosis                   object\n",
              "radius_mean                float64\n",
              "texture_mean               float64\n",
              "perimeter_mean             float64\n",
              "area_mean                  float64\n",
              "smoothness_mean            float64\n",
              "compactness_mean           float64\n",
              "concavity_mean             float64\n",
              "concave points_mean        float64\n",
              "symmetry_mean              float64\n",
              "fractal_dimension_mean     float64\n",
              "radius_se                  float64\n",
              "texture_se                 float64\n",
              "perimeter_se               float64\n",
              "area_se                    float64\n",
              "smoothness_se              float64\n",
              "compactness_se             float64\n",
              "concavity_se               float64\n",
              "concave points_se          float64\n",
              "symmetry_se                float64\n",
              "fractal_dimension_se       float64\n",
              "radius_worst               float64\n",
              "texture_worst              float64\n",
              "perimeter_worst            float64\n",
              "area_worst                 float64\n",
              "smoothness_worst           float64\n",
              "compactness_worst          float64\n",
              "concavity_worst            float64\n",
              "concave points_worst       float64\n",
              "symmetry_worst             float64\n",
              "fractal_dimension_worst    float64\n",
              "dtype: object"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2aijBwMF-vQo",
        "colab_type": "text"
      },
      "source": [
        "Como em qualquer projeto de *Data Science*, a verificação da presença de valores ausentes no *dataset* é de extrema importância, pois é o reflexo direto da qualidade do mesmo."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "X1b3HY5WvdEb",
        "colab_type": "code",
        "outputId": "132b5869-f294-48a9-85cd-f4361a813f79",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 578
        }
      },
      "source": [
        "df.isnull().sum()"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "id                         0\n",
              "diagnosis                  0\n",
              "radius_mean                0\n",
              "texture_mean               0\n",
              "perimeter_mean             0\n",
              "area_mean                  0\n",
              "smoothness_mean            0\n",
              "compactness_mean           0\n",
              "concavity_mean             0\n",
              "concave points_mean        0\n",
              "symmetry_mean              0\n",
              "fractal_dimension_mean     0\n",
              "radius_se                  0\n",
              "texture_se                 0\n",
              "perimeter_se               0\n",
              "area_se                    0\n",
              "smoothness_se              0\n",
              "compactness_se             0\n",
              "concavity_se               0\n",
              "concave points_se          0\n",
              "symmetry_se                0\n",
              "fractal_dimension_se       0\n",
              "radius_worst               0\n",
              "texture_worst              0\n",
              "perimeter_worst            0\n",
              "area_worst                 0\n",
              "smoothness_worst           0\n",
              "compactness_worst          0\n",
              "concavity_worst            0\n",
              "concave points_worst       0\n",
              "symmetry_worst             0\n",
              "fractal_dimension_worst    0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NLyJr4sH_5B1",
        "colab_type": "text"
      },
      "source": [
        "Mesmo todos os valores sendo numéricos, particularmente eu gosto de verificar a quantidade de valores únicos para cada *feature*, pois isso permite verificar se os números podem estar representando classes, por exemplo."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "03UyshwIv8_j",
        "colab_type": "code",
        "outputId": "e9159c86-38e1-43a1-8d79-412380c2853f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 612
        }
      },
      "source": [
        "# valores únicos\n",
        "print(\"\\nVALORES ÚNICOS:\")\n",
        "print(df.nunique().sort_values())"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "VALORES ÚNICOS:\n",
            "diagnosis                    2\n",
            "smoothness_worst           411\n",
            "symmetry_mean              432\n",
            "radius_mean                456\n",
            "radius_worst               457\n",
            "smoothness_mean            474\n",
            "texture_mean               479\n",
            "concave points_worst       492\n",
            "symmetry_se                498\n",
            "fractal_dimension_mean     499\n",
            "symmetry_worst             500\n",
            "concave points_se          507\n",
            "texture_worst              511\n",
            "perimeter_worst            514\n",
            "texture_se                 519\n",
            "perimeter_mean             522\n",
            "area_se                    528\n",
            "compactness_worst          529\n",
            "perimeter_se               533\n",
            "concavity_se               533\n",
            "fractal_dimension_worst    535\n",
            "concavity_mean             537\n",
            "compactness_mean           537\n",
            "concavity_worst            539\n",
            "area_mean                  539\n",
            "radius_se                  540\n",
            "compactness_se             541\n",
            "concave points_mean        542\n",
            "area_worst                 544\n",
            "fractal_dimension_se       545\n",
            "smoothness_se              547\n",
            "id                         569\n",
            "dtype: int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MViHBQbZw-wp",
        "colab_type": "text"
      },
      "source": [
        "Agora irei verificar o balanceamento do *dataset* vendo a porcentagem de valores da variável alvo. Como se pode ver abaixo, existem um pequeno desbalanceamento de valores."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "L1YC709QAXF1",
        "colab_type": "code",
        "outputId": "f7709fe1-f1c1-483d-e41b-a6c4950f167e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        }
      },
      "source": [
        "# ver porcentagem dos diagnósticos\n",
        "print(\"Diagnósticos:\")\n",
        "print(df.diagnosis.value_counts() / df.shape[0])\n",
        "\n",
        "# plotar o gráfico de barras com os diagnósticos\n",
        "fig, ax = plt.subplots()\n",
        "sns.countplot('diagnosis', data=df, ax=ax)\n",
        "ax.set_title(\"Diagnósticos\")\n",
        "plt.show()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Diagnósticos:\n",
            "B    0.627417\n",
            "M    0.372583\n",
            "Name: diagnosis, dtype: float64\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qRGrJ04RFwyv",
        "colab_type": "text"
      },
      "source": [
        "Para ter a noção de como as variáveis estão distribuídas, vou plotar o histograma de todas as variáveis numéricas, excluindo a coluna `id`, uma vez que ela Não acrescenta nenhuma informação importante.\n",
        "\n",
        "Preste sempre atenção em como os valores de algumas variáveis estão mais bem distribuídos em torno de uma média e outras tendem a puxar o histograma para a esquerda."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6Nyl-k5fAZTP",
        "colab_type": "code",
        "outputId": "451f4e60-6d30-4c75-fb79-48ebeb2d6ead",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 639
        }
      },
      "source": [
        "# plotar o histograma das features\n",
        "fix, ax = plt.subplots(figsize=(12,8))\n",
        "df.drop('id', axis=1).hist(ax=ax)\n",
        "plt.tight_layout()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:2: UserWarning: To output multiple subplots, the figure containing the passed axes is being cleared\n",
            "  \n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1UAAAI4CAYAAACC4sP2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nMzMzMzMbwf8Dld0mYWERSWIAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 864x576 with 30 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kmaL7wxMIqyD",
        "colab_type": "text"
      },
      "source": [
        "Para ver a força da correlação entre as variáveis, uma opção é plotar um *heatmap*. Repare no mapa abaixo como diversas variáveis possuem correlação positiva."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "--HipGyvDsVI",
        "colab_type": "code",
        "outputId": "79c98d5b-2636-442a-e30e-992180edd044",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 708
        }
      },
      "source": [
        "# plotar heatmap\n",
        "fig, ax = plt.subplots(figsize=(10,10))\n",
        "sns.heatmap(df.drop('id', axis=1).corr(), cmap='coolwarm', ax=ax)\n",
        "plt.show()"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqoAAAKzCAYAAADWXC85AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 720x720 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SEySiTKmGihk",
        "colab_type": "text"
      },
      "source": [
        "## Preparação dos dados\n",
        "\n",
        "Como parte do pré-processamento dos dados, que irão alimentar o modelo de *Machine Learning*, vou usar o `StardardScaler`, que vem junto com `sklearn.preprocessing`, para padronizar nossos dados numéricos.\n",
        "\n",
        "Se você olhar no começo do código, vai reparar que a nossa variável alvo é categórica, onde *M* representa os tumores malignos e *B* os benignos. Usando `LabelEncoder` somos capazes de converter variáveis categóricas em numéricas e alimentar o modelo adequadamente."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cgGGE3-yJIPI",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "# separar as variáveis independentes da variável alvo\n",
        "X = df.drop(['diagnosis', 'id'], axis=1)\n",
        "y = df['diagnosis']\n",
        "\n",
        "# padronizar as colunas numéricas\n",
        "X = StandardScaler().fit_transform(X)\n",
        "\n",
        "# label encoder na variável alvo\n",
        "y = LabelEncoder().fit_transform(y)\n",
        "\n",
        "# dividir o dataset entre treino e teste\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "PHUzXT3OJb_T",
        "colab_type": "text"
      },
      "source": [
        "Vale destacar que o cálculo utilizar por `StandardScaler` para calcular os *scores* é $z = \\frac{x-u}{s}$, onde $u$ é a média das amostras do conjunto de treino e $s$ é o desvio padrão dessa amostra.\n",
        "\n",
        "Por fim, antes de construir o modelo de fato, dividimos o *dataset* entre treino e teste usando o `train_test_split`, função que facilitar muito o trabalho, e que se encontra em `sklearn.model_selection`."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8KebSxoHp98D",
        "colab_type": "text"
      },
      "source": [
        "## Modelo de Machine Learning para detecção do câncer de mama\n",
        "\n",
        "Este problema de detecção de câncer consiste em classificar corretamente um tumor entre benigno e maligno, ou seja, é necessário que o modelo de *Machine Learning* dê uma classificação ao ser alimentado com diversas variáveis independentes (*features*).\n",
        "\n",
        "Aqui, usarei um modelo do tipo *Random Forest* (Floresta Aleatória) devido à sua flexibilidade e facilidade de uso (uma vez que funciona muito bem mesmo sem o ajuste nos hiperparâmetros)."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lqBYq6OrqDf1",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 136
        },
        "outputId": "d17d7f1c-e6dd-4c98-f2b3-56efd6bc1e58"
      },
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "\n",
        "# instanciando o modelo de Random Forest\n",
        "ml_model = RandomForestClassifier(n_estimators = 10, criterion = 'entropy',\n",
        "                                  random_state = 42)\n",
        "\n",
        "# treinando o modelo \n",
        "ml_model.fit(X_train, y_train)"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "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_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=10,\n",
              "                       n_jobs=None, oob_score=False, random_state=42, verbose=0,\n",
              "                       warm_start=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0EN8H269xW9_",
        "colab_type": "text"
      },
      "source": [
        "O algoritmo *Random Forest*, que usa métodos *ensemble*, tem esse nome por que cria uma combinação de várias árvores de decisão - uma \"floresta\" realmente - verificando qual combinação apresenta melhor desempenho e acurácia.\n",
        "\n",
        "Vamos dar uma checada no desempenho do modelo quando se depara pela primeira vez com o conjunto de testes."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QkN89ocNyb9U",
        "colab_type": "text"
      },
      "source": [
        "## Desempenho do modelo de detecção de câncer de mama\n",
        "\n",
        "Cada caso é um caso. Nem sempre uma excelente acurácia vai significar que seu modelo está bom. \n",
        "\n",
        "Por exemplo, quando se trata de detectar câncer, queremos maximizar o número de verdadeiros positivos e minimizar o número de falsos negativos. No entanto, esta é uma balança difícil de equilibrar, e o *trade-off* pode ser bem subjetivo inclusive.\n",
        "\n",
        "Aqui, além da métrica de acurácia vou usar a função `classification_report` para ver ver o desempenho do modelo sobre as métricas de precisão, *recall*, *f1-score* e *support*."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1h20z7a_sYJm",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 221
        },
        "outputId": "a0308453-5ee7-47d2-f8be-4677540ece12"
      },
      "source": [
        "from sklearn.metrics import classification_report\n",
        "from sklearn.metrics import accuracy_score\n",
        "from sklearn.metrics import confusion_matrix\n",
        "\n",
        "# realizar as previsões no dataset de teste\n",
        "y_pred = ml_model.predict(X_test)\n",
        "\n",
        "# ver acurácia geral\n",
        "print('[Acurácia] Random Forest:', accuracy_score(y_test, y_pred))\n",
        "\n",
        "# imprimir o classification report\n",
        "print('\\n[Classification Report] Random Forest')\n",
        "print( classification_report(y_test, y_pred) )"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[Acurácia] Random Forest: 0.9649122807017544\n",
            "\n",
            "[Classification Report] Random Forest\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.95      1.00      0.97       111\n",
            "           1       1.00      0.90      0.95        60\n",
            "\n",
            "    accuracy                           0.96       171\n",
            "   macro avg       0.97      0.95      0.96       171\n",
            "weighted avg       0.97      0.96      0.96       171\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "L-vpMdIA3asj",
        "colab_type": "text"
      },
      "source": [
        "Aparentemente, o modelo está com ótimos valores nas métricas consideradas. Mas como eu disse lá em cima, cada caso é um caso.\n",
        "\n",
        "Eu acho muito interessante você sempre dar uma checada na matriz de confusão. Para exemplificar, imagine que seu modelo é capaz de detectar com 99,999% de acurácia sempre que um paciente não apresenta um tumor maligno, mas apenas 85% de acurácia quando prevê que o mesmo paciente apresentar esse tumor maligno.\n",
        "\n",
        "Há vezes em que é melhor ter mais falsos positivos e investigar mais profundamente o caso (como também é o caso de fraudes no cartão de crédito), e ter um modelo menos preciso. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "m4gmoM6Ft98s",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 111
        },
        "outputId": "64b1963f-5ec0-47e9-cef9-0047b342aa55"
      },
      "source": [
        "# plotar a matriz de confusão\n",
        "pd.DataFrame(confusion_matrix(y_test, y_pred),\n",
        "             index=['neg', 'pos'], columns=['pred_neg', 'pred_pos'])"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>pred_neg</th>\n",
              "      <th>pred_pos</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>neg</th>\n",
              "      <td>111</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>pos</th>\n",
              "      <td>6</td>\n",
              "      <td>54</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     pred_neg  pred_pos\n",
              "neg       111         0\n",
              "pos         6        54"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eNXUi8Yp2UFw",
        "colab_type": "text"
      },
      "source": [
        "Como você pode confirmar, o modelo classificatório Random Forest foi capaz de atingir uma acurácia superior a 96% e lidou muito bem com ambas as classes."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HTjh4gubyax7",
        "colab_type": "text"
      },
      "source": [
        "## Outubro Rosa e Machine Learning\n",
        "\n",
        "Apesar da campanha Outubro Rosa ser em Outubro, a conscientização deve existir durante o ano todo. A importância de um dianóstico precoce do câncer de mama deve estar clara na cabeça de todo mundo. \n",
        "\n",
        "Avanços e descobertas no campo da Inteligência Artificial ocorrem a todo momento, principalmente na área da saúde. Deteccção de Câncer por meio de algoritmos de <em>Machine Learning</em> ajudam cada vez mais os médicos a diagnosticarem seus pacientes, aumentando drásticamente as chances dos tratamentos concencionais.\n",
        "\n",
        "No entanto, mesmo a construção de modelos altamente confiáveis para a detecção de câncer de mama não substitui uma variável, a principal <em>feature</em>, o diagnóstico precoce ;)\n",
        "\n",
        "Espero ter contribuido um pouco com a causa, apresentando um modelo 100% replicável por qualquer pessoa (basta abrir o código no [Google Colab](https://colab.research.google.com) e executar cada linha.\n",
        "\n",
        "Sinta-se à vontade para modificar, expandir e melhorar esse modelo. Abraços!"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bzOrOpV53Mow",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}