DeteccionDeDiabetes.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "ann_classification_diabetes.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true,
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/FraGoTe/redes-neuronales/blob/master/DeteccionDeDiabetes.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eyUhcF61WImH",
        "colab_type": "text"
      },
      "source": [
        "## REDES NEURONALES ARTIFICIALES"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2wPe_qWFHPm8",
        "colab_type": "text"
      },
      "source": [
        ""
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fHNy9zESXwk5",
        "colab_type": "text"
      },
      "source": [
        "\n",
        "##Carga de datos\n",
        "---"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MEj9ojRcWfki",
        "colab_type": "text"
      },
      "source": [
        "Mostrando lista de archivos:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-8NN__fMWgXh",
        "colab_type": "code",
        "outputId": "b96c246d-e259-43f9-966c-a8d32881a764",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        }
      },
      "source": [
        "%%bash\n",
        "if [ ! -f \"diabetes_data.csv\" ]; then\n",
        "    wget www.fragote.com/data/diabetes_data.csv\n",
        "fi\n",
        "\n",
        "ls -l "
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "total 28\n",
            "-rw-r--r-- 1 root root 23100 Sep 28 21:10 diabetes_data.csv\n",
            "drwxr-xr-x 1 root root  4096 Nov 21 16:30 sample_data\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FAjhMCNuXgD3",
        "colab_type": "text"
      },
      "source": [
        "##Funciones necesarias\n",
        "---"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RdEyMyC_YIPY",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 71
        },
        "outputId": "27549cf2-c971-48b4-fd99-6a9970e25300"
      },
      "source": [
        "# Funciones\n",
        "\n",
        "import numpy as np\n",
        "\n",
        "from sklearn.metrics import confusion_matrix\n",
        "from sklearn.utils.multiclass import unique_labels\n",
        "from sklearn.externals import joblib\n",
        "\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "def plot_confusion_matrix(y_true, y_pred,\n",
        "                          normalize=False,\n",
        "                          title=None):\n",
        "    \"\"\"\n",
        "    Esta función imprime y traza la matriz de confusión.\n",
        "     La normalización se puede aplicar configurando `normalize=True`.\n",
        "    \"\"\"\n",
        "    if not title:\n",
        "        if normalize:\n",
        "            title = 'Matriz de Confusión Normalizada'\n",
        "        else:\n",
        "            title = 'Matriz de Confusión sin Normalizar'\n",
        "\n",
        "    # Calculando la Matriz de Confusion\n",
        "    cm = confusion_matrix(y_true, y_pred)\n",
        "    # solo usar las etiquetas que se tienen en la data\n",
        "    classes = unique_labels(y_true, y_pred)\n",
        "    if normalize:\n",
        "        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
        "        print(\"Matriz de Confusión Normalizada\")\n",
        "    else:\n",
        "        print('Matriz de Confusión sin Normalizar')\n",
        "\n",
        "    print(cm)\n",
        "\n",
        "    fig, ax = plt.subplots()\n",
        "    im = ax.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)\n",
        "    ax.figure.colorbar(im, ax=ax)\n",
        "    ax.grid(linewidth=.0)\n",
        "    # Queremos mostrar todos los puntos...\n",
        "    ax.set(xticks=np.arange(cm.shape[1]),\n",
        "           yticks=np.arange(cm.shape[0]),\n",
        "           # ... etiquetando la lista de datos\n",
        "           xticklabels=classes, yticklabels=classes,\n",
        "           title=title,\n",
        "           ylabel='True label',\n",
        "           xlabel='Predicted label')\n",
        "\n",
        "    # rotando las etiquedas de los puntos.\n",
        "    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"right\",rotation_mode=\"anchor\")\n",
        "\n",
        "    # Loop over data dimensions and create text annotations.\n",
        "    fmt = '.2f' if normalize else 'd'\n",
        "    thresh = cm.max() / 2.\n",
        "    for i in range(cm.shape[0]):\n",
        "        for j in range(cm.shape[1]):\n",
        "            ax.text(j, i, format(cm[i, j], fmt),\n",
        "                    ha=\"center\", va=\"center\",\n",
        "                    color=\"white\" if cm[i, j] > thresh else \"black\")\n",
        "    fig.tight_layout()\n",
        "    plt.show()\n",
        "    return ax\n",
        "\n",
        "def saveFile(object_to_save, scaler_filename):\n",
        "    joblib.dump(object_to_save, scaler_filename)\n",
        "\n",
        "def loadFile(scaler_filename):\n",
        "    return joblib.load(scaler_filename)\n",
        "\n",
        "def plotHistogram(dataset_final):\n",
        "    dataset_final.hist(figsize=(20,14), edgecolor=\"black\", bins=40)\n",
        "    plt.show()\n",
        "\n",
        "def plotCorrelations(dataset_final):\n",
        "    fig, ax = plt.subplots(figsize=(10,8))   # size in inches\n",
        "    g = sns.heatmap(dataset_final.corr(), annot=True, cmap=\"YlGnBu\", ax=ax)\n",
        "    g.set_yticklabels(g.get_yticklabels(), rotation = 0)\n",
        "    g.set_xticklabels(g.get_xticklabels(), rotation = 45)\n",
        "    fig.tight_layout()\n",
        "    plt.show()\n"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/externals/joblib/__init__.py:15: DeprecationWarning: sklearn.externals.joblib is deprecated in 0.21 and will be removed in 0.23. Please import this functionality directly from joblib, which can be installed with: pip install joblib. If this warning is raised when loading pickled models, you may need to re-serialize those models with scikit-learn 0.21+.\n",
            "  warnings.warn(msg, category=DeprecationWarning)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yzNaCkq8XIEm",
        "colab_type": "text"
      },
      "source": [
        "\n",
        " ## PARTE I - PREPROCESAMIENTO DE DATOS\n",
        "---\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "q5HGp2W-XSkX",
        "colab_type": "code",
        "outputId": "3307f090-767b-462b-cb7b-b3caa7ddd032",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 714
        }
      },
      "source": [
        "# Importando librerías\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "# Importando Datasets\n",
        "dataset_csv = pd.read_csv('diabetes_data.csv')\n",
        "\n",
        "# Columnas de la data\n",
        "print (\"\\nColumnas del DataSet: \")\n",
        "print (dataset_csv.columns)\n",
        "\n",
        "# Describir la data original\n",
        "print (\"\\nDataset original:\\n\", dataset_csv.describe(include='all'))\n",
        "\n",
        "\n",
        "# Revisamos los tipos de datos de las Columnas\n",
        "print (\"\\nTipos de Columnas del Dataset: \")\n",
        "print(dataset_csv.dtypes)\n",
        "\n",
        "\n",
        "print (\"\\nDataset Total: \")\n",
        "print(\"\\n\",dataset_csv.head())\n",
        "\n",
        "dataset_columns = dataset_csv.columns\n",
        "dataset_values = dataset_csv.values"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Columnas del DataSet: \n",
            "Index(['Embarazos', 'Glucosa', 'Presion', 'EspesorPiel', 'Insulina', 'IMC',\n",
            "       'DiabetesFamiliar', 'Edad', 'PacienteDiabetico'],\n",
            "      dtype='object')\n",
            "\n",
            "Dataset original:\n",
            "         Embarazos     Glucosa  ...        Edad  PacienteDiabetico\n",
            "count  768.000000  768.000000  ...  768.000000         768.000000\n",
            "mean     3.845052  120.894531  ...   33.240885           0.348958\n",
            "std      3.369578   31.972618  ...   11.760232           0.476951\n",
            "min      0.000000    0.000000  ...   21.000000           0.000000\n",
            "25%      1.000000   99.000000  ...   24.000000           0.000000\n",
            "50%      3.000000  117.000000  ...   29.000000           0.000000\n",
            "75%      6.000000  140.250000  ...   41.000000           1.000000\n",
            "max     17.000000  199.000000  ...   81.000000           1.000000\n",
            "\n",
            "[8 rows x 9 columns]\n",
            "\n",
            "Tipos de Columnas del Dataset: \n",
            "Embarazos              int64\n",
            "Glucosa                int64\n",
            "Presion                int64\n",
            "EspesorPiel            int64\n",
            "Insulina               int64\n",
            "IMC                  float64\n",
            "DiabetesFamiliar     float64\n",
            "Edad                   int64\n",
            "PacienteDiabetico      int64\n",
            "dtype: object\n",
            "\n",
            "Dataset Total: \n",
            "\n",
            "    Embarazos  Glucosa  Presion  ...  DiabetesFamiliar  Edad  PacienteDiabetico\n",
            "0          6      148       72  ...             0.627    50                  1\n",
            "1          1       85       66  ...             0.351    31                  0\n",
            "2          8      183       64  ...             0.672    32                  1\n",
            "3          1       89       66  ...             0.167    21                  0\n",
            "4          0      137       40  ...             2.288    33                  1\n",
            "\n",
            "[5 rows x 9 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EtC94NJFbWvD",
        "colab_type": "text"
      },
      "source": [
        "Escalamiento/Normalización de Features (StandardScaler: (x-u)/s): mean = 0 and standard deviation = 1"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MZV9NGL6bbfy",
        "colab_type": "code",
        "outputId": "fca657e6-78ef-42ef-8adc-00aacf3595bc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 391
        }
      },
      "source": [
        "# Escalamiento/Normalización de Features (StandardScaler: (x-u)/s)\n",
        "stdScaler = StandardScaler()\n",
        "dataset_values[:,0:8] = stdScaler.fit_transform(dataset_values[:,0:8])\n",
        "\n",
        "\n",
        "# Dataset final normalizado\n",
        "dataset_final = pd.DataFrame(dataset_values,columns=dataset_columns, dtype=np.float64)\n",
        "print (\"\\nDataset Final:\")\n",
        "print(dataset_final.describe(include='all'))\n",
        "print(\"\\n\", dataset_final.head())"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Dataset Final:\n",
            "          Embarazos       Glucosa  ...          Edad  PacienteDiabetico\n",
            "count  7.680000e+02  7.680000e+02  ...  7.680000e+02         768.000000\n",
            "mean   2.544261e-17  3.614007e-18  ...  1.857600e-16           0.348958\n",
            "std    1.000652e+00  1.000652e+00  ...  1.000652e+00           0.476951\n",
            "min   -1.141852e+00 -3.783654e+00  ... -1.041549e+00           0.000000\n",
            "25%   -8.448851e-01 -6.852363e-01  ... -7.862862e-01           0.000000\n",
            "50%   -2.509521e-01 -1.218877e-01  ... -3.608474e-01           0.000000\n",
            "75%    6.399473e-01  6.057709e-01  ...  6.602056e-01           1.000000\n",
            "max    3.906578e+00  2.444478e+00  ...  4.063716e+00           1.000000\n",
            "\n",
            "[8 rows x 9 columns]\n",
            "\n",
            "    Embarazos   Glucosa   Presion  ...  DiabetesFamiliar      Edad  PacienteDiabetico\n",
            "0   0.639947  0.848324  0.149641  ...          0.468492  1.425995                1.0\n",
            "1  -0.844885 -1.123396 -0.160546  ...         -0.365061 -0.190672                0.0\n",
            "2   1.233880  1.943724 -0.263941  ...          0.604397 -0.105584                1.0\n",
            "3  -0.844885 -0.998208 -0.160546  ...         -0.920763 -1.041549                0.0\n",
            "4  -1.141852  0.504055 -1.504687  ...          5.484909 -0.020496                1.0\n",
            "\n",
            "[5 rows x 9 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OZ9cXe5pZEkK",
        "colab_type": "text"
      },
      "source": [
        "Graficando datos:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3uE5G5yiZGN7",
        "colab_type": "code",
        "outputId": "8d6ff7a7-e0dd-44dc-ece7-e5b22639d776",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "# Distribuciones de la data y Correlaciones\n",
        "print(\"\\n Histogramas:\")\n",
        "plotHistogram(dataset_final)\n",
        "\n",
        "print(\"\\n Correlaciones:\")\n",
        "plotCorrelations(dataset_final)"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            " Histogramas:\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABIUAAAMoCAYAAABRaVATAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkiRJkqQp9P8By+ipFTKx1T8AAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 1440x1008 with 9 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n",
            " Correlaciones:\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAp0AAAI4CAYAAAAoBFJjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n",
            "text/plain": [
              "<Figure size 720x576 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2d1U-5FXJ7OU",
        "colab_type": "text"
      },
      "source": [
        "Dividiendo data en conjuntos de Entrenamiento y Prueba:\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PuveIiylKCpF",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Obteniendo valores a procesar\n",
        "X = dataset_final.iloc[:, 0:8].values\n",
        "y = dataset_final.iloc[:, 8].values\n",
        "\n",
        "# Dividiendo el Dataset en sets de Training y Test\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5Wi1j84IZldb",
        "colab_type": "text"
      },
      "source": [
        "---\n",
        "## PARTE II - CONSTRUYENDO LA RED NEURONAL ARTIFICIAL\n",
        "---"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HwlyGxY_Ztc4",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 202
        },
        "outputId": "7a59961a-18a6-4447-e960-dbbc06ad047f"
      },
      "source": [
        "# Importando Keras y Tensorflow\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "from keras.initializers import RandomUniform\n",
        "\n",
        "# Inicializando la Red Neuronal\n",
        "neural_network = Sequential()\n",
        "\n",
        "# kernel_initializer Define la forma como se asignará los Pesos iniciales Wi\n",
        "initial_weights = RandomUniform(minval = -0.5, maxval = 0.5)\n",
        "\n",
        "# Agregado la Capa de entrada y la primera capa oculta\n",
        "# 10 Neuronas en la capa de entrada y 8 Neuronas en la primera capa oculta\n",
        "neural_network.add(Dense(units = 5, kernel_initializer = initial_weights, activation = 'relu', input_dim = 8))\n",
        "\n",
        "# Agregando capa oculta\n",
        "neural_network.add(Dense(units = 3, kernel_initializer = initial_weights, activation = 'relu'))\n",
        "\n",
        "# Agregando capa de salida\n",
        "neural_network.add(Dense(units = 1, kernel_initializer = initial_weights, activation = 'sigmoid'))"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<p style=\"color: red;\">\n",
              "The default version of TensorFlow in Colab will soon switch to TensorFlow 2.x.<br>\n",
              "We recommend you <a href=\"https://www.tensorflow.org/guide/migrate\" target=\"_blank\">upgrade</a> now \n",
              "or ensure your notebook will continue to use TensorFlow 1.x via the <code>%tensorflow_version 1.x</code> magic:\n",
              "<a href=\"https://colab.research.google.com/notebooks/tensorflow_version.ipynb\" target=\"_blank\">more info</a>.</p>\n"
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:66: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:541: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4432: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_vtufIOTZwDy",
        "colab_type": "text"
      },
      "source": [
        "Arquitectura de la Red Neuronal Artificial:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9YrVSTD0Z0cj",
        "colab_type": "code",
        "outputId": "4a9628ce-9a6e-4745-8e6b-772d3c74c352",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 255
        }
      },
      "source": [
        "# Imprimir Arquitectura de la Red\n",
        "neural_network.summary()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "dense_1 (Dense)              (None, 5)                 45        \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 3)                 18        \n",
            "_________________________________________________________________\n",
            "dense_3 (Dense)              (None, 1)                 4         \n",
            "=================================================================\n",
            "Total params: 67\n",
            "Trainable params: 67\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4LZkSTA6Z4zI",
        "colab_type": "text"
      },
      "source": [
        "Entrenamiento:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "j1xPCglyZ61i",
        "colab_type": "code",
        "outputId": "724ff26e-24df-4dc1-f331-9f8761fbb92e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "# Compilando la Red Neuronal\n",
        "# optimizer: Algoritmo de optimización | binary_crossentropy = 2 Classes\n",
        "# loss: error\n",
        "neural_network.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])\n",
        "\n",
        "\n",
        "# Entrenamiento\n",
        "neural_network.fit(X_train, y_train, batch_size = 32, epochs = 100)"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:793: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3657: The name tf.log is deprecated. Please use tf.math.log instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/nn_impl.py:183: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
            "Instructions for updating:\n",
            "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1033: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1020: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3005: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.\n",
            "\n",
            "Epoch 1/100\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:190: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:197: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:207: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:216: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.\n",
            "\n",
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:223: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.\n",
            "\n",
            "614/614 [==============================] - 5s 8ms/step - loss: 0.6919 - acc: 0.6401\n",
            "Epoch 2/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.6881 - acc: 0.6401\n",
            "Epoch 3/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.6836 - acc: 0.6401\n",
            "Epoch 4/100\n",
            "614/614 [==============================] - 0s 156us/step - loss: 0.6765 - acc: 0.6401\n",
            "Epoch 5/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.6666 - acc: 0.6401\n",
            "Epoch 6/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.6537 - acc: 0.6401\n",
            "Epoch 7/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.6407 - acc: 0.6401\n",
            "Epoch 8/100\n",
            "614/614 [==============================] - 0s 158us/step - loss: 0.6276 - acc: 0.6401\n",
            "Epoch 9/100\n",
            "614/614 [==============================] - 0s 152us/step - loss: 0.6146 - acc: 0.6401\n",
            "Epoch 10/100\n",
            "614/614 [==============================] - 0s 164us/step - loss: 0.6021 - acc: 0.6401\n",
            "Epoch 11/100\n",
            "614/614 [==============================] - 0s 164us/step - loss: 0.5906 - acc: 0.6401\n",
            "Epoch 12/100\n",
            "614/614 [==============================] - 0s 147us/step - loss: 0.5800 - acc: 0.6401\n",
            "Epoch 13/100\n",
            "614/614 [==============================] - 0s 174us/step - loss: 0.5710 - acc: 0.6401\n",
            "Epoch 14/100\n",
            "614/614 [==============================] - 0s 161us/step - loss: 0.5631 - acc: 0.6401\n",
            "Epoch 15/100\n",
            "614/614 [==============================] - 0s 150us/step - loss: 0.5560 - acc: 0.6401\n",
            "Epoch 16/100\n",
            "614/614 [==============================] - 0s 145us/step - loss: 0.5502 - acc: 0.6401\n",
            "Epoch 17/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.5447 - acc: 0.6401\n",
            "Epoch 18/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.5399 - acc: 0.6401\n",
            "Epoch 19/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.5358 - acc: 0.6401\n",
            "Epoch 20/100\n",
            "614/614 [==============================] - 0s 136us/step - loss: 0.5321 - acc: 0.6401\n",
            "Epoch 21/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.5289 - acc: 0.6401\n",
            "Epoch 22/100\n",
            "614/614 [==============================] - 0s 176us/step - loss: 0.5263 - acc: 0.6401\n",
            "Epoch 23/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.5239 - acc: 0.6401\n",
            "Epoch 24/100\n",
            "614/614 [==============================] - 0s 140us/step - loss: 0.5214 - acc: 0.6401\n",
            "Epoch 25/100\n",
            "614/614 [==============================] - 0s 147us/step - loss: 0.5194 - acc: 0.6401\n",
            "Epoch 26/100\n",
            "614/614 [==============================] - 0s 140us/step - loss: 0.5174 - acc: 0.6401\n",
            "Epoch 27/100\n",
            "614/614 [==============================] - 0s 137us/step - loss: 0.5155 - acc: 0.6401\n",
            "Epoch 28/100\n",
            "614/614 [==============================] - 0s 161us/step - loss: 0.5136 - acc: 0.7508\n",
            "Epoch 29/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.5118 - acc: 0.7541\n",
            "Epoch 30/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.5103 - acc: 0.7606\n",
            "Epoch 31/100\n",
            "614/614 [==============================] - 0s 154us/step - loss: 0.5088 - acc: 0.7622\n",
            "Epoch 32/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.5070 - acc: 0.7638\n",
            "Epoch 33/100\n",
            "614/614 [==============================] - 0s 166us/step - loss: 0.5056 - acc: 0.7704\n",
            "Epoch 34/100\n",
            "614/614 [==============================] - 0s 148us/step - loss: 0.5044 - acc: 0.7720\n",
            "Epoch 35/100\n",
            "614/614 [==============================] - 0s 140us/step - loss: 0.5031 - acc: 0.7752\n",
            "Epoch 36/100\n",
            "614/614 [==============================] - 0s 158us/step - loss: 0.5020 - acc: 0.7769\n",
            "Epoch 37/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.5012 - acc: 0.7785\n",
            "Epoch 38/100\n",
            "614/614 [==============================] - 0s 137us/step - loss: 0.4999 - acc: 0.7801\n",
            "Epoch 39/100\n",
            "614/614 [==============================] - 0s 134us/step - loss: 0.4987 - acc: 0.7834\n",
            "Epoch 40/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.4980 - acc: 0.7818\n",
            "Epoch 41/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4971 - acc: 0.7801\n",
            "Epoch 42/100\n",
            "614/614 [==============================] - 0s 165us/step - loss: 0.4964 - acc: 0.7801\n",
            "Epoch 43/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.4954 - acc: 0.7834\n",
            "Epoch 44/100\n",
            "614/614 [==============================] - 0s 168us/step - loss: 0.4943 - acc: 0.7818\n",
            "Epoch 45/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4936 - acc: 0.7818\n",
            "Epoch 46/100\n",
            "614/614 [==============================] - 0s 151us/step - loss: 0.4928 - acc: 0.7818\n",
            "Epoch 47/100\n",
            "614/614 [==============================] - 0s 156us/step - loss: 0.4921 - acc: 0.7818\n",
            "Epoch 48/100\n",
            "614/614 [==============================] - 0s 141us/step - loss: 0.4914 - acc: 0.7801\n",
            "Epoch 49/100\n",
            "614/614 [==============================] - 0s 156us/step - loss: 0.4905 - acc: 0.7801\n",
            "Epoch 50/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4900 - acc: 0.7801\n",
            "Epoch 51/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.4894 - acc: 0.7866\n",
            "Epoch 52/100\n",
            "614/614 [==============================] - 0s 138us/step - loss: 0.4883 - acc: 0.7866\n",
            "Epoch 53/100\n",
            "614/614 [==============================] - 0s 141us/step - loss: 0.4876 - acc: 0.7883\n",
            "Epoch 54/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.4871 - acc: 0.7899\n",
            "Epoch 55/100\n",
            "614/614 [==============================] - 0s 166us/step - loss: 0.4864 - acc: 0.7883\n",
            "Epoch 56/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.4855 - acc: 0.7866\n",
            "Epoch 57/100\n",
            "614/614 [==============================] - 0s 155us/step - loss: 0.4849 - acc: 0.7883\n",
            "Epoch 58/100\n",
            "614/614 [==============================] - 0s 136us/step - loss: 0.4845 - acc: 0.7866\n",
            "Epoch 59/100\n",
            "614/614 [==============================] - 0s 147us/step - loss: 0.4838 - acc: 0.7883\n",
            "Epoch 60/100\n",
            "614/614 [==============================] - 0s 135us/step - loss: 0.4831 - acc: 0.7899\n",
            "Epoch 61/100\n",
            "614/614 [==============================] - 0s 138us/step - loss: 0.4826 - acc: 0.7883\n",
            "Epoch 62/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.4822 - acc: 0.7899\n",
            "Epoch 63/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.4811 - acc: 0.7899\n",
            "Epoch 64/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.4806 - acc: 0.7915\n",
            "Epoch 65/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.4802 - acc: 0.7932\n",
            "Epoch 66/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4797 - acc: 0.7899\n",
            "Epoch 67/100\n",
            "614/614 [==============================] - 0s 155us/step - loss: 0.4790 - acc: 0.7915\n",
            "Epoch 68/100\n",
            "614/614 [==============================] - 0s 156us/step - loss: 0.4783 - acc: 0.7883\n",
            "Epoch 69/100\n",
            "614/614 [==============================] - 0s 145us/step - loss: 0.4779 - acc: 0.7899\n",
            "Epoch 70/100\n",
            "614/614 [==============================] - 0s 136us/step - loss: 0.4774 - acc: 0.7883\n",
            "Epoch 71/100\n",
            "614/614 [==============================] - 0s 147us/step - loss: 0.4769 - acc: 0.7899\n",
            "Epoch 72/100\n",
            "614/614 [==============================] - 0s 140us/step - loss: 0.4762 - acc: 0.7915\n",
            "Epoch 73/100\n",
            "614/614 [==============================] - 0s 139us/step - loss: 0.4757 - acc: 0.7915\n",
            "Epoch 74/100\n",
            "614/614 [==============================] - 0s 145us/step - loss: 0.4752 - acc: 0.7899\n",
            "Epoch 75/100\n",
            "614/614 [==============================] - 0s 145us/step - loss: 0.4751 - acc: 0.7866\n",
            "Epoch 76/100\n",
            "614/614 [==============================] - 0s 141us/step - loss: 0.4743 - acc: 0.7883\n",
            "Epoch 77/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4738 - acc: 0.7883\n",
            "Epoch 78/100\n",
            "614/614 [==============================] - 0s 158us/step - loss: 0.4733 - acc: 0.7899\n",
            "Epoch 79/100\n",
            "614/614 [==============================] - 0s 141us/step - loss: 0.4730 - acc: 0.7899\n",
            "Epoch 80/100\n",
            "614/614 [==============================] - 0s 136us/step - loss: 0.4725 - acc: 0.7899\n",
            "Epoch 81/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.4726 - acc: 0.7899\n",
            "Epoch 82/100\n",
            "614/614 [==============================] - 0s 141us/step - loss: 0.4717 - acc: 0.7866\n",
            "Epoch 83/100\n",
            "614/614 [==============================] - 0s 143us/step - loss: 0.4714 - acc: 0.7866\n",
            "Epoch 84/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.4710 - acc: 0.7850\n",
            "Epoch 85/100\n",
            "614/614 [==============================] - 0s 151us/step - loss: 0.4703 - acc: 0.7866\n",
            "Epoch 86/100\n",
            "614/614 [==============================] - 0s 146us/step - loss: 0.4699 - acc: 0.7866\n",
            "Epoch 87/100\n",
            "614/614 [==============================] - 0s 151us/step - loss: 0.4694 - acc: 0.7850\n",
            "Epoch 88/100\n",
            "614/614 [==============================] - 0s 142us/step - loss: 0.4693 - acc: 0.7883\n",
            "Epoch 89/100\n",
            "614/614 [==============================] - 0s 149us/step - loss: 0.4686 - acc: 0.7818\n",
            "Epoch 90/100\n",
            "614/614 [==============================] - 0s 166us/step - loss: 0.4684 - acc: 0.7883\n",
            "Epoch 91/100\n",
            "614/614 [==============================] - 0s 165us/step - loss: 0.4678 - acc: 0.7866\n",
            "Epoch 92/100\n",
            "614/614 [==============================] - 0s 151us/step - loss: 0.4674 - acc: 0.7834\n",
            "Epoch 93/100\n",
            "614/614 [==============================] - 0s 170us/step - loss: 0.4669 - acc: 0.7850\n",
            "Epoch 94/100\n",
            "614/614 [==============================] - 0s 150us/step - loss: 0.4666 - acc: 0.7866\n",
            "Epoch 95/100\n",
            "614/614 [==============================] - 0s 135us/step - loss: 0.4661 - acc: 0.7834\n",
            "Epoch 96/100\n",
            "614/614 [==============================] - 0s 137us/step - loss: 0.4658 - acc: 0.7883\n",
            "Epoch 97/100\n",
            "614/614 [==============================] - 0s 144us/step - loss: 0.4649 - acc: 0.7866\n",
            "Epoch 98/100\n",
            "614/614 [==============================] - 0s 135us/step - loss: 0.4646 - acc: 0.7866\n",
            "Epoch 99/100\n",
            "614/614 [==============================] - 0s 138us/step - loss: 0.4641 - acc: 0.7899\n",
            "Epoch 100/100\n",
            "614/614 [==============================] - 0s 147us/step - loss: 0.4638 - acc: 0.7866\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7feaa77827f0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wRk23KN0Z_L8",
        "colab_type": "text"
      },
      "source": [
        "---\n",
        "## PARTE III - PREDICCIONES Y EVALUACIONES DE LA RED\n",
        "---"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6-bkah_jaKo2",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Haciendo predicción de los resultados del Test\n",
        "y_pred = neural_network.predict(X_test)\n",
        "y_pred_norm = (y_pred > 0.5)\n",
        "\n",
        "y_pred_norm = y_pred_norm.astype(int)\n",
        "y_test = y_test.astype(int)\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VE49E-iHaMM9",
        "colab_type": "text"
      },
      "source": [
        "Aplicando la Matriz de Confusión:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_spodbINaRRr",
        "colab_type": "code",
        "outputId": "6859d562-f918-4c2c-e84e-752b1c6dc30d",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 85
        }
      },
      "source": [
        "# Aplicando la Matriz de Confusión\n",
        "from sklearn.metrics import confusion_matrix\n",
        "cm = confusion_matrix(y_test, y_pred_norm)\n",
        "print (\"\\nMatriz de Confusión: \\n\", cm)"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "Matriz de Confusión: \n",
            " [[91 16]\n",
            " [16 31]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fBAH2hDYWCya",
        "colab_type": "text"
      },
      "source": [
        "Graficando la Matriz de Confusión:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2m1ZYV8aaY_i",
        "colab_type": "code",
        "outputId": "16f5121f-3ad8-4752-c1cd-8162355946bf",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 365
        }
      },
      "source": [
        "plot_confusion_matrix(y_test, y_pred_norm, normalize=False,title=\"Matriz de Confusión: Paciente Con Diabetes\")"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Matriz de Confusión sin Normalizar\n",
            "[[91 16]\n",
            " [16 31]]\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZAAAAEYCAYAAAByXKB5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ns7o4gJiZWV0cQMzMrC7/D7IEB5iOFOvqAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7fea6e440f60>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZKJq794CIv3R",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "d8a84bbf-50b4-4837-9963-053c7553dd0e"
      },
      "source": [
        "def saveModel(model, full_path, model_name_h5):\n",
        "    # Guardar el modelo en disco: Model and Architecture to single file\n",
        "    final_model_name = full_path + model_name_h5\n",
        "    model.save(final_model_name)\n",
        "    return final_model_name\n",
        "    \n",
        "base_path = ''\n",
        "# Guardando StandardScaler a disco\n",
        "saveFile(stdScaler,\"\".join([base_path,\"model/stdScaler.save\"]))\n",
        "\n",
        "# Guardar la RNA en disco\n",
        "model_file_name = saveModel(neural_network,\"\".join([base_path,\"model/\"]),\"diabetes_model.h5\")\n",
        "print(\"Modelo guardado en disco >> \", model_file_name)\n"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Modelo guardado en disco >>  model/diabetes_model.h5\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jxneuta8JURb",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 425
        },
        "outputId": "d13b94f7-5359-488e-9cbd-c645a07e1718"
      },
      "source": [
        "from tensorflow import keras\n",
        "\n",
        "model = keras.models.load_model('model/diabetes_model.h5')\n",
        "\n",
        "keras.experimental.export_saved_model(model, 'modelo_diabetes/')\n"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Signatures INCLUDED in export for Classify: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Regress: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Predict: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Train: ['train']\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Eval: None\n",
            "WARNING:tensorflow:Export includes no default signature!\n",
            "INFO:tensorflow:No assets to save.\n",
            "INFO:tensorflow:No assets to write.\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Classify: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Regress: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Predict: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Train: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval']\n",
            "WARNING:tensorflow:Export includes no default signature!\n",
            "INFO:tensorflow:No assets to save.\n",
            "INFO:tensorflow:No assets to write.\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Classify: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Regress: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Predict: ['serving_default']\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Train: None\n",
            "INFO:tensorflow:Signatures INCLUDED in export for Eval: None\n",
            "INFO:tensorflow:No assets to save.\n",
            "INFO:tensorflow:No assets to write.\n",
            "INFO:tensorflow:SavedModel written to: modelo_diabetes/saved_model.pb\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}