{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Generación de Red Neuronal para obtener resistencia característica del hormigón"
      ],
      "metadata": {
        "id": "CfJ_SkQsxXJl"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns"
      ],
      "metadata": {
        "id": "uM0MYAYCxZ7l"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Leemos el dataset\n",
        "concrete_data = pd.read_excel(\"ConcreteData.xls\")"
      ],
      "metadata": {
        "id": "YWAlFV5pxouh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Cambio los nombres de las categorías porque son muy largos\n",
        "concrete_data.columns = [\n",
        "    \"Cemento\",\n",
        "    \"Escoria\",\n",
        "    \"Ceniza\",\n",
        "    \"Agua\",\n",
        "    \"Super\",\n",
        "    \"AGrueso\",\n",
        "    \"AFino\",\n",
        "    \"Edad\",\n",
        "    \"Resistencia\"\n",
        "]"
      ],
      "metadata": {
        "id": "TTifa-Ns1EgT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Visualización incial del dataset\n",
        "print(concrete_data.head())\n",
        "print(concrete_data.info())\n",
        "print(concrete_data.describe())\n",
        "print(concrete_data.isnull().sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tVcNV83CzRpy",
        "outputId": "cc7330f1-809f-434f-8473-84ab0a19e2aa"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "   Cemento  Escoria  Ceniza   Agua  Super  AGrueso  AFino  Edad  Resistencia\n",
            "0    540.0      0.0     0.0  162.0    2.5   1040.0  676.0    28    79.986111\n",
            "1    540.0      0.0     0.0  162.0    2.5   1055.0  676.0    28    61.887366\n",
            "2    332.5    142.5     0.0  228.0    0.0    932.0  594.0   270    40.269535\n",
            "3    332.5    142.5     0.0  228.0    0.0    932.0  594.0   365    41.052780\n",
            "4    198.6    132.4     0.0  192.0    0.0    978.4  825.5   360    44.296075\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1030 entries, 0 to 1029\n",
            "Data columns (total 9 columns):\n",
            " #   Column       Non-Null Count  Dtype  \n",
            "---  ------       --------------  -----  \n",
            " 0   Cemento      1030 non-null   float64\n",
            " 1   Escoria      1030 non-null   float64\n",
            " 2   Ceniza       1030 non-null   float64\n",
            " 3   Agua         1030 non-null   float64\n",
            " 4   Super        1030 non-null   float64\n",
            " 5   AGrueso      1030 non-null   float64\n",
            " 6   AFino        1030 non-null   float64\n",
            " 7   Edad         1030 non-null   int64  \n",
            " 8   Resistencia  1030 non-null   float64\n",
            "dtypes: float64(8), int64(1)\n",
            "memory usage: 72.6 KB\n",
            "None\n",
            "           Cemento      Escoria       Ceniza         Agua        Super  \\\n",
            "count  1030.000000  1030.000000  1030.000000  1030.000000  1030.000000   \n",
            "mean    281.165631    73.895485    54.187136   181.566359     6.203112   \n",
            "std     104.507142    86.279104    63.996469    21.355567     5.973492   \n",
            "min     102.000000     0.000000     0.000000   121.750000     0.000000   \n",
            "25%     192.375000     0.000000     0.000000   164.900000     0.000000   \n",
            "50%     272.900000    22.000000     0.000000   185.000000     6.350000   \n",
            "75%     350.000000   142.950000   118.270000   192.000000    10.160000   \n",
            "max     540.000000   359.400000   200.100000   247.000000    32.200000   \n",
            "\n",
            "           AGrueso        AFino         Edad  Resistencia  \n",
            "count  1030.000000  1030.000000  1030.000000  1030.000000  \n",
            "mean    972.918592   773.578883    45.662136    35.817836  \n",
            "std      77.753818    80.175427    63.169912    16.705679  \n",
            "min     801.000000   594.000000     1.000000     2.331808  \n",
            "25%     932.000000   730.950000     7.000000    23.707115  \n",
            "50%     968.000000   779.510000    28.000000    34.442774  \n",
            "75%    1029.400000   824.000000    56.000000    46.136287  \n",
            "max    1145.000000   992.600000   365.000000    82.599225  \n",
            "Cemento        0\n",
            "Escoria        0\n",
            "Ceniza         0\n",
            "Agua           0\n",
            "Super          0\n",
            "AGrueso        0\n",
            "AFino          0\n",
            "Edad           0\n",
            "Resistencia    0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Realizamos un histograma para la visualización rápida de los datos\n",
        "sns.set_style(\"whitegrid\")\n",
        "plt.rcParams[\"figure.figsize\"] = (10, 6)\n",
        "concrete_data.hist(bins=50, figsize=(18, 12))\n",
        "plt.suptitle(\"Distribución de variables\", fontsize=16)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "ihVVaGM5zXyX",
        "outputId": "a5f3fc95-70cf-4b92-b6cb-576b691f289f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1800x1200 with 9 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Generamos la matriz de correlación\n",
        "plt.figure(figsize=(10, 8))\n",
        "sns.heatmap(concrete_data.corr(), annot=True, cmap=\"coolwarm\", fmt=\".2f\")\n",
        "plt.title(\"Matriz de correlación\")\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 699
        },
        "id": "_uvl5BcF0iVB",
        "outputId": "81e81fb9-fe7b-4fc4-90dc-851f225aecb2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "limite_resistencia = 40\n",
        "concrete_data[\"Aceptable\"] = (concrete_data[\"Resistencia\"] >= limite_resistencia).astype(int)\n",
        "print(concrete_data.head())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SsbOpQeU3_G7",
        "outputId": "11d55df1-77a1-4dc3-e2d0-cb537c0213a2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "   Cemento  Escoria  Ceniza   Agua  Super  AGrueso  AFino  Edad  Resistencia  \\\n",
            "0    540.0      0.0     0.0  162.0    2.5   1040.0  676.0    28    79.986111   \n",
            "1    540.0      0.0     0.0  162.0    2.5   1055.0  676.0    28    61.887366   \n",
            "2    332.5    142.5     0.0  228.0    0.0    932.0  594.0   270    40.269535   \n",
            "3    332.5    142.5     0.0  228.0    0.0    932.0  594.0   365    41.052780   \n",
            "4    198.6    132.4     0.0  192.0    0.0    978.4  825.5   360    44.296075   \n",
            "\n",
            "   Aceptable  \n",
            "0          1  \n",
            "1          1  \n",
            "2          1  \n",
            "3          1  \n",
            "4          1  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from scipy.stats import shapiro, levene, ttest_ind, mannwhitneyu\n",
        "num_vars = [\"Cemento\", \"Escoria\", \"Ceniza\", \"Agua\", \"Super\", \"AGrueso\", \"AFino\", \"Edad\"]\n",
        "\n",
        "#Función para d de Cohen\n",
        "def cohens_d(x, y):\n",
        "    n0, n1 = len(x), len(y)\n",
        "    s0, s1 = np.var(x, ddof=1), np.var(y, ddof=1)\n",
        "    s_pooled = np.sqrt(((n0 - 1) * s0 + (n1 - 1) * s1) / (n0 + n1 - 2))\n",
        "    return (np.mean(x) - np.mean(y)) / s_pooled\n",
        "\n",
        "cohen_results = []\n",
        "\n",
        "for col in num_vars:\n",
        "    group0 = concrete_data[concrete_data[\"Aceptable\"] == 0][col]\n",
        "    group1 = concrete_data[concrete_data[\"Aceptable\"] == 1][col]\n",
        "    t_stat, p_t = ttest_ind(group0, group1)\n",
        "    d = cohens_d(group0, group1)\n",
        "    cohen_results.append({\"Variable\": col, \"Cohens_d\": d})\n",
        "    print(f\"\\nVariable: {col}\")\n",
        "    print(f\" T-test: t={t_stat:.3f}, p={p_t:.3f}\")\n",
        "    print(f\" Cohen's d for {col}: {d:.3f}\")\n",
        "\n",
        "cohen_df = pd.DataFrame(cohen_results)\n",
        "cohen_df = cohen_df.sort_values(by=\"Cohens_d\")\n",
        "plt.figure(figsize=(10, 6))\n",
        "sns.barplot(data=cohen_df, x=\"Cohens_d\", y=\"Variable\", palette=\"coolwarm\")\n",
        "plt.axvline(0, color=\"black\", linestyle=\"--\")\n",
        "plt.axvline(0.2, color=\"gray\", linestyle=\":\")\n",
        "plt.axvline(-0.2, color=\"gray\", linestyle=\":\")\n",
        "plt.axvline(0.5, color=\"orange\", linestyle=\":\")\n",
        "plt.axvline(-0.5, color=\"orange\", linestyle=\":\")\n",
        "plt.axvline(0.8, color=\"red\", linestyle=\":\")\n",
        "plt.axvline(-0.8, color=\"red\", linestyle=\":\")\n",
        "\n",
        "plt.title(\"Tamaño del efecto (Cohen's d) por variable\")\n",
        "plt.xlabel(\"Cohen's d\")\n",
        "plt.ylabel(\"Variable\")\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n",
        "#d_cohen = (media no aceptable - media aceptable) / desviación ajustada)\n",
        "\n",
        "#Tal y como hemos definido la d de Cohen (x_0 hormigón aceptable)y como\n",
        "#este gráfico represente la relación entre las medias de ambos grupos, si una\n",
        "#d de cohen es negativa quieren decir que influye en que el hormigón sea\n",
        "#aceptable y viceversa.\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "collapsed": true,
        "id": "GZkjvny-4h5h",
        "outputId": "e255c70c-66c1-4457-e01a-df8d20a6d543"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Variable: Cemento\n",
            " T-test: t=-14.750, p=0.000\n",
            " Cohen's d for Cemento: -0.953\n",
            "\n",
            "Variable: Escoria\n",
            " T-test: t=-1.832, p=0.067\n",
            " Cohen's d for Escoria: -0.118\n",
            "\n",
            "Variable: Ceniza\n",
            " T-test: t=2.922, p=0.004\n",
            " Cohen's d for Ceniza: 0.189\n",
            "\n",
            "Variable: Agua\n",
            " T-test: t=7.571, p=0.000\n",
            " Cohen's d for Agua: 0.489\n",
            "\n",
            "Variable: Super\n",
            " T-test: t=-9.647, p=0.000\n",
            " Cohen's d for Super: -0.623\n",
            "\n",
            "Variable: AGrueso\n",
            " T-test: t=3.743, p=0.000\n",
            " Cohen's d for AGrueso: 0.242\n",
            "\n",
            "Variable: AFino\n",
            " T-test: t=3.968, p=0.000\n",
            " Cohen's d for AFino: 0.256\n",
            "\n",
            "Variable: Edad\n",
            " T-test: t=-10.785, p=0.000\n",
            " Cohen's d for Edad: -0.697\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_5723/3040447711.py:26: FutureWarning: \n",
            "\n",
            "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n",
            "\n",
            "  sns.barplot(data=cohen_df, x=\"Cohens_d\", y=\"Variable\", palette=\"coolwarm\")\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Generación de un modelo predictivo de clasificación con TensorFlow/Keras"
      ],
      "metadata": {
        "id": "4AILXLgT8pJx"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras import layers, Input, regularizers\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report"
      ],
      "metadata": {
        "id": "BW0e9nTQ8yIZ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X = concrete_data[[\"Cemento\", \"Escoria\", \"Ceniza\", \"Agua\", \"Super\", \"AGrueso\", \"AFino\", \"Edad\"]]\n",
        "y = concrete_data[\"Aceptable\"]\n",
        "\n",
        "#Separamos entre entrenamiento y test\n",
        "X_train, X_test, y_train, y_test = train_test_split(\n",
        "    X, y, test_size=0.3, random_state=42)\n",
        "\n",
        "#Normalización de datos\n",
        "scaler = StandardScaler()\n",
        "X_train_scaled = scaler.fit_transform(X_train)\n",
        "X_test_scaled = scaler.transform(X_test)\n",
        "\n",
        "#Crear modelo de clasificación\n",
        "#model = tf.keras.models.Sequential([\n",
        "#    Input(shape=(X_train_scaled.shape[1],)),\n",
        "#    layers.Dense(32, activation=\"relu\"),\n",
        "#    layers.Dense(16, activation=\"relu\"),\n",
        "#    layers.Dense(1, activation=\"sigmoid\")\n",
        "#])\n",
        "\n",
        "# Modelo más complejo\n",
        "model = tf.keras.models.Sequential([\n",
        "    Input(shape=(X_train_scaled.shape[1],)),\n",
        "    layers.Dense(256, activation='relu',\n",
        "                 kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(128, activation='relu', kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(64, activation='relu', kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(32, activation='relu', kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(1, activation=\"sigmoid\")])\n",
        "\n",
        "#Compilamos el modelo\n",
        "model.compile(\n",
        "    optimizer=\"adam\",\n",
        "    loss=\"binary_crossentropy\",\n",
        "    metrics=[\"accuracy\"])\n",
        "\n",
        "#Que saque un resumen del modelo\n",
        "model.summary()\n",
        "\n",
        "#Entrenamos el modelo\n",
        "history = model.fit(\n",
        "    X_train_scaled,\n",
        "    y_train,\n",
        "    validation_split=0.2,\n",
        "    epochs=100,\n",
        "    batch_size=32,\n",
        "    verbose=1)\n",
        "\n",
        "#Predecimos sobre el conjunto de test\n",
        "y_pred_prob = model.predict(X_test_scaled)\n",
        "y_pred = (y_pred_prob >= 0.5).astype(int)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "v9dS5-DR8qpV",
        "outputId": "18ea20d3-d139-47fc-c6ce-a8e23ff5de24"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m2,304\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m8,256\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │         \u001b[38;5;34m2,080\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_4 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m33\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,304</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,080</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">33</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m45,569\u001b[0m (178.00 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">45,569</span> (178.00 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m45,569\u001b[0m (178.00 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">45,569</span> (178.00 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 20ms/step - accuracy: 0.7222 - loss: 0.7433 - val_accuracy: 0.7310 - val_loss: 0.7008\n",
            "Epoch 2/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.8073 - loss: 0.5845 - val_accuracy: 0.7655 - val_loss: 0.5884\n",
            "Epoch 3/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8438 - loss: 0.5108 - val_accuracy: 0.8207 - val_loss: 0.5595\n",
            "Epoch 4/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8628 - loss: 0.4632 - val_accuracy: 0.8207 - val_loss: 0.5188\n",
            "Epoch 5/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8750 - loss: 0.4528 - val_accuracy: 0.8621 - val_loss: 0.4743\n",
            "Epoch 6/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8906 - loss: 0.4147 - val_accuracy: 0.8276 - val_loss: 0.4876\n",
            "Epoch 7/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8733 - loss: 0.4068 - val_accuracy: 0.8759 - val_loss: 0.4438\n",
            "Epoch 8/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8889 - loss: 0.3874 - val_accuracy: 0.8552 - val_loss: 0.4494\n",
            "Epoch 9/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.8941 - loss: 0.3726 - val_accuracy: 0.8759 - val_loss: 0.4369\n",
            "Epoch 10/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9010 - loss: 0.3497 - val_accuracy: 0.8690 - val_loss: 0.4158\n",
            "Epoch 11/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8924 - loss: 0.3536 - val_accuracy: 0.8690 - val_loss: 0.4242\n",
            "Epoch 12/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.9132 - loss: 0.3314 - val_accuracy: 0.8621 - val_loss: 0.4170\n",
            "Epoch 13/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 0.9149 - loss: 0.3191 - val_accuracy: 0.9103 - val_loss: 0.3677\n",
            "Epoch 14/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - accuracy: 0.9080 - loss: 0.3206 - val_accuracy: 0.8069 - val_loss: 0.4734\n",
            "Epoch 15/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9115 - loss: 0.3099 - val_accuracy: 0.9034 - val_loss: 0.3675\n",
            "Epoch 16/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 0.9236 - loss: 0.2878 - val_accuracy: 0.8759 - val_loss: 0.3660\n",
            "Epoch 17/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9167 - loss: 0.2977 - val_accuracy: 0.8897 - val_loss: 0.4063\n",
            "Epoch 18/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.9306 - loss: 0.3012 - val_accuracy: 0.8690 - val_loss: 0.3845\n",
            "Epoch 19/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9184 - loss: 0.2923 - val_accuracy: 0.9034 - val_loss: 0.3420\n",
            "Epoch 20/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.9288 - loss: 0.2735 - val_accuracy: 0.8690 - val_loss: 0.3930\n",
            "Epoch 21/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9271 - loss: 0.2782 - val_accuracy: 0.9034 - val_loss: 0.3536\n",
            "Epoch 22/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9184 - loss: 0.2709 - val_accuracy: 0.8552 - val_loss: 0.4924\n",
            "Epoch 23/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9253 - loss: 0.2835 - val_accuracy: 0.9034 - val_loss: 0.3394\n",
            "Epoch 24/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9149 - loss: 0.2650 - val_accuracy: 0.8897 - val_loss: 0.3411\n",
            "Epoch 25/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9375 - loss: 0.2419 - val_accuracy: 0.8759 - val_loss: 0.3877\n",
            "Epoch 26/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9358 - loss: 0.2481 - val_accuracy: 0.9103 - val_loss: 0.3485\n",
            "Epoch 27/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9271 - loss: 0.2735 - val_accuracy: 0.8690 - val_loss: 0.3973\n",
            "Epoch 28/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9340 - loss: 0.2421 - val_accuracy: 0.9241 - val_loss: 0.3187\n",
            "Epoch 29/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9358 - loss: 0.2465 - val_accuracy: 0.8966 - val_loss: 0.3530\n",
            "Epoch 30/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9462 - loss: 0.2398 - val_accuracy: 0.8966 - val_loss: 0.3324\n",
            "Epoch 31/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9358 - loss: 0.2360 - val_accuracy: 0.8966 - val_loss: 0.3762\n",
            "Epoch 32/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9427 - loss: 0.2333 - val_accuracy: 0.8897 - val_loss: 0.3488\n",
            "Epoch 33/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9514 - loss: 0.2117 - val_accuracy: 0.8966 - val_loss: 0.3692\n",
            "Epoch 34/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9531 - loss: 0.2229 - val_accuracy: 0.8897 - val_loss: 0.3703\n",
            "Epoch 35/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9392 - loss: 0.2241 - val_accuracy: 0.9034 - val_loss: 0.3463\n",
            "Epoch 36/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9549 - loss: 0.2173 - val_accuracy: 0.8966 - val_loss: 0.3384\n",
            "Epoch 37/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9358 - loss: 0.2213 - val_accuracy: 0.8897 - val_loss: 0.3313\n",
            "Epoch 38/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9375 - loss: 0.2261 - val_accuracy: 0.8759 - val_loss: 0.3840\n",
            "Epoch 39/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9479 - loss: 0.2446 - val_accuracy: 0.8828 - val_loss: 0.3448\n",
            "Epoch 40/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9479 - loss: 0.2122 - val_accuracy: 0.8828 - val_loss: 0.3730\n",
            "Epoch 41/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9549 - loss: 0.1945 - val_accuracy: 0.9034 - val_loss: 0.3038\n",
            "Epoch 42/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9514 - loss: 0.2210 - val_accuracy: 0.8759 - val_loss: 0.3875\n",
            "Epoch 43/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9531 - loss: 0.2126 - val_accuracy: 0.9034 - val_loss: 0.3318\n",
            "Epoch 44/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9531 - loss: 0.2081 - val_accuracy: 0.9034 - val_loss: 0.3820\n",
            "Epoch 45/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9566 - loss: 0.1994 - val_accuracy: 0.8897 - val_loss: 0.3820\n",
            "Epoch 46/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9670 - loss: 0.1890 - val_accuracy: 0.9172 - val_loss: 0.3101\n",
            "Epoch 47/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9514 - loss: 0.1943 - val_accuracy: 0.8897 - val_loss: 0.3807\n",
            "Epoch 48/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9427 - loss: 0.2091 - val_accuracy: 0.9103 - val_loss: 0.3179\n",
            "Epoch 49/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1962 - val_accuracy: 0.8897 - val_loss: 0.3062\n",
            "Epoch 50/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9583 - loss: 0.1952 - val_accuracy: 0.8966 - val_loss: 0.3482\n",
            "Epoch 51/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9566 - loss: 0.1847 - val_accuracy: 0.9103 - val_loss: 0.3207\n",
            "Epoch 52/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9549 - loss: 0.1946 - val_accuracy: 0.8897 - val_loss: 0.3695\n",
            "Epoch 53/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.9566 - loss: 0.1817 - val_accuracy: 0.9103 - val_loss: 0.3132\n",
            "Epoch 54/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1706 - val_accuracy: 0.8966 - val_loss: 0.3599\n",
            "Epoch 55/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9601 - loss: 0.1700 - val_accuracy: 0.9172 - val_loss: 0.3412\n",
            "Epoch 56/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9670 - loss: 0.1723 - val_accuracy: 0.9034 - val_loss: 0.3512\n",
            "Epoch 57/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9531 - loss: 0.1850 - val_accuracy: 0.8897 - val_loss: 0.3498\n",
            "Epoch 58/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9497 - loss: 0.1851 - val_accuracy: 0.8897 - val_loss: 0.3942\n",
            "Epoch 59/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9566 - loss: 0.1873 - val_accuracy: 0.9310 - val_loss: 0.3349\n",
            "Epoch 60/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9601 - loss: 0.1791 - val_accuracy: 0.8966 - val_loss: 0.3641\n",
            "Epoch 61/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9566 - loss: 0.1728 - val_accuracy: 0.8966 - val_loss: 0.4033\n",
            "Epoch 62/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9514 - loss: 0.1852 - val_accuracy: 0.8966 - val_loss: 0.3831\n",
            "Epoch 63/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1690 - val_accuracy: 0.9241 - val_loss: 0.3150\n",
            "Epoch 64/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1757 - val_accuracy: 0.8897 - val_loss: 0.3630\n",
            "Epoch 65/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9705 - loss: 0.1557 - val_accuracy: 0.9310 - val_loss: 0.3347\n",
            "Epoch 66/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9618 - loss: 0.1718 - val_accuracy: 0.9034 - val_loss: 0.3448\n",
            "Epoch 67/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9653 - loss: 0.1664 - val_accuracy: 0.8966 - val_loss: 0.3567\n",
            "Epoch 68/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9583 - loss: 0.1764 - val_accuracy: 0.9034 - val_loss: 0.4340\n",
            "Epoch 69/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9531 - loss: 0.1802 - val_accuracy: 0.9034 - val_loss: 0.3772\n",
            "Epoch 70/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9653 - loss: 0.1687 - val_accuracy: 0.9172 - val_loss: 0.3736\n",
            "Epoch 71/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1574 - val_accuracy: 0.9103 - val_loss: 0.3861\n",
            "Epoch 72/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9722 - loss: 0.1632 - val_accuracy: 0.9241 - val_loss: 0.3083\n",
            "Epoch 73/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9792 - loss: 0.1357 - val_accuracy: 0.8966 - val_loss: 0.3527\n",
            "Epoch 74/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9618 - loss: 0.1676 - val_accuracy: 0.8897 - val_loss: 0.4025\n",
            "Epoch 75/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9722 - loss: 0.1440 - val_accuracy: 0.8966 - val_loss: 0.3636\n",
            "Epoch 76/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9757 - loss: 0.1504 - val_accuracy: 0.8966 - val_loss: 0.3907\n",
            "Epoch 77/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9635 - loss: 0.1583 - val_accuracy: 0.9034 - val_loss: 0.3710\n",
            "Epoch 78/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9705 - loss: 0.1474 - val_accuracy: 0.9034 - val_loss: 0.3609\n",
            "Epoch 79/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9740 - loss: 0.1495 - val_accuracy: 0.9103 - val_loss: 0.3768\n",
            "Epoch 80/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9722 - loss: 0.1500 - val_accuracy: 0.8897 - val_loss: 0.4712\n",
            "Epoch 81/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.9653 - loss: 0.1544 - val_accuracy: 0.8966 - val_loss: 0.3990\n",
            "Epoch 82/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9497 - loss: 0.1900 - val_accuracy: 0.8966 - val_loss: 0.4212\n",
            "Epoch 83/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9653 - loss: 0.1643 - val_accuracy: 0.8828 - val_loss: 0.3997\n",
            "Epoch 84/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 0.9705 - loss: 0.1668 - val_accuracy: 0.9034 - val_loss: 0.3600\n",
            "Epoch 85/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9688 - loss: 0.1526 - val_accuracy: 0.9103 - val_loss: 0.3325\n",
            "Epoch 86/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - accuracy: 0.9688 - loss: 0.1458 - val_accuracy: 0.8966 - val_loss: 0.3929\n",
            "Epoch 87/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.9705 - loss: 0.1504 - val_accuracy: 0.9034 - val_loss: 0.3749\n",
            "Epoch 88/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9670 - loss: 0.1608 - val_accuracy: 0.9103 - val_loss: 0.3125\n",
            "Epoch 89/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9705 - loss: 0.1504 - val_accuracy: 0.9034 - val_loss: 0.3736\n",
            "Epoch 90/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.9740 - loss: 0.1381 - val_accuracy: 0.9103 - val_loss: 0.3376\n",
            "Epoch 91/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.9757 - loss: 0.1379 - val_accuracy: 0.8828 - val_loss: 0.4160\n",
            "Epoch 92/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9705 - loss: 0.1503 - val_accuracy: 0.9034 - val_loss: 0.4057\n",
            "Epoch 93/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9826 - loss: 0.1273 - val_accuracy: 0.9034 - val_loss: 0.3384\n",
            "Epoch 94/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9774 - loss: 0.1273 - val_accuracy: 0.9172 - val_loss: 0.3627\n",
            "Epoch 95/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9844 - loss: 0.1214 - val_accuracy: 0.9172 - val_loss: 0.3776\n",
            "Epoch 96/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9809 - loss: 0.1318 - val_accuracy: 0.9034 - val_loss: 0.4106\n",
            "Epoch 97/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9792 - loss: 0.1249 - val_accuracy: 0.9241 - val_loss: 0.3838\n",
            "Epoch 98/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9792 - loss: 0.1309 - val_accuracy: 0.9310 - val_loss: 0.3780\n",
            "Epoch 99/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9774 - loss: 0.1254 - val_accuracy: 0.9103 - val_loss: 0.3951\n",
            "Epoch 100/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9670 - loss: 0.1467 - val_accuracy: 0.9172 - val_loss: 0.3924\n",
            "\u001b[1m10/10\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Métricas\n",
        "acc = accuracy_score(y_test, y_pred)\n",
        "cm = confusion_matrix(y_test, y_pred)\n",
        "\n",
        "# Accuracy del modelo\n",
        "print(f\"Accuracy del modelo: {acc:.3f}\")\n",
        "\n",
        "# Matriz de confusión\n",
        "plt.figure(figsize=(6, 5))\n",
        "sns.heatmap(\n",
        "    cm,\n",
        "    annot=True,\n",
        "    fmt=\"d\",\n",
        "    cmap=\"Blues\",\n",
        "    cbar=False,\n",
        "    xticklabels=[\"No aceptable (0)\", \"Aceptable (1)\"],\n",
        "    yticklabels=[\"No aceptable (0)\", \"Aceptable (1)\"]\n",
        ")\n",
        "plt.xlabel(\"Predicción\")\n",
        "plt.ylabel(\"Valor real\")\n",
        "plt.title(\"Matriz de confusión\")\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n",
        "# Classification report en tabla\n",
        "report = classification_report(y_test, y_pred, output_dict=True)\n",
        "report_df = pd.DataFrame(report).transpose()\n",
        "display(report_df.style.background_gradient(cmap=\"Blues\").format(\"{:.3f}\"))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 714
        },
        "id": "t3EKg1JU-lQO",
        "outputId": "fb34d069-422e-4ca7-a040-e4625aceeb4d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy del modelo: 0.890\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x500 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<pandas.io.formats.style.Styler at 0x7d2ca80fd640>"
            ],
            "text/html": [
              "<style type=\"text/css\">\n",
              "#T_4b5c6_row0_col0, #T_4b5c6_row0_col1, #T_4b5c6_row0_col2, #T_4b5c6_row3_col3, #T_4b5c6_row4_col3 {\n",
              "  background-color: #08306b;\n",
              "  color: #f1f1f1;\n",
              "}\n",
              "#T_4b5c6_row0_col3, #T_4b5c6_row2_col0, #T_4b5c6_row2_col1, #T_4b5c6_row2_col2, #T_4b5c6_row4_col0, #T_4b5c6_row4_col1, #T_4b5c6_row4_col2 {\n",
              "  background-color: #3b8bc2;\n",
              "  color: #f1f1f1;\n",
              "}\n",
              "#T_4b5c6_row1_col0, #T_4b5c6_row1_col1, #T_4b5c6_row1_col2, #T_4b5c6_row2_col3 {\n",
              "  background-color: #f7fbff;\n",
              "  color: #000000;\n",
              "}\n",
              "#T_4b5c6_row1_col3 {\n",
              "  background-color: #a8cee4;\n",
              "  color: #000000;\n",
              "}\n",
              "#T_4b5c6_row3_col0, #T_4b5c6_row3_col1, #T_4b5c6_row3_col2 {\n",
              "  background-color: #6aaed6;\n",
              "  color: #f1f1f1;\n",
              "}\n",
              "</style>\n",
              "<table id=\"T_4b5c6\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th class=\"blank level0\" >&nbsp;</th>\n",
              "      <th id=\"T_4b5c6_level0_col0\" class=\"col_heading level0 col0\" >precision</th>\n",
              "      <th id=\"T_4b5c6_level0_col1\" class=\"col_heading level0 col1\" >recall</th>\n",
              "      <th id=\"T_4b5c6_level0_col2\" class=\"col_heading level0 col2\" >f1-score</th>\n",
              "      <th id=\"T_4b5c6_level0_col3\" class=\"col_heading level0 col3\" >support</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th id=\"T_4b5c6_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n",
              "      <td id=\"T_4b5c6_row0_col0\" class=\"data row0 col0\" >0.915</td>\n",
              "      <td id=\"T_4b5c6_row0_col1\" class=\"data row0 col1\" >0.915</td>\n",
              "      <td id=\"T_4b5c6_row0_col2\" class=\"data row0 col2\" >0.915</td>\n",
              "      <td id=\"T_4b5c6_row0_col3\" class=\"data row0 col3\" >201.000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th id=\"T_4b5c6_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n",
              "      <td id=\"T_4b5c6_row1_col0\" class=\"data row1 col0\" >0.843</td>\n",
              "      <td id=\"T_4b5c6_row1_col1\" class=\"data row1 col1\" >0.843</td>\n",
              "      <td id=\"T_4b5c6_row1_col2\" class=\"data row1 col2\" >0.843</td>\n",
              "      <td id=\"T_4b5c6_row1_col3\" class=\"data row1 col3\" >108.000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th id=\"T_4b5c6_level0_row2\" class=\"row_heading level0 row2\" >accuracy</th>\n",
              "      <td id=\"T_4b5c6_row2_col0\" class=\"data row2 col0\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row2_col1\" class=\"data row2 col1\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row2_col2\" class=\"data row2 col2\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row2_col3\" class=\"data row2 col3\" >0.890</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th id=\"T_4b5c6_level0_row3\" class=\"row_heading level0 row3\" >macro avg</th>\n",
              "      <td id=\"T_4b5c6_row3_col0\" class=\"data row3 col0\" >0.879</td>\n",
              "      <td id=\"T_4b5c6_row3_col1\" class=\"data row3 col1\" >0.879</td>\n",
              "      <td id=\"T_4b5c6_row3_col2\" class=\"data row3 col2\" >0.879</td>\n",
              "      <td id=\"T_4b5c6_row3_col3\" class=\"data row3 col3\" >309.000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th id=\"T_4b5c6_level0_row4\" class=\"row_heading level0 row4\" >weighted avg</th>\n",
              "      <td id=\"T_4b5c6_row4_col0\" class=\"data row4 col0\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row4_col1\" class=\"data row4 col1\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row4_col2\" class=\"data row4 col2\" >0.890</td>\n",
              "      <td id=\"T_4b5c6_row4_col3\" class=\"data row4 col3\" >309.000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "nuevo_hormigon = pd.DataFrame([{\n",
        "    \"Cemento\": 350,\n",
        "    \"Escoria\": 50,\n",
        "    \"Ceniza\": 0,\n",
        "    \"Agua\": 200,\n",
        "    \"Super\": 0,\n",
        "    \"AGrueso\": 1000,\n",
        "    \"AFino\": 750,\n",
        "    \"Edad\": 14\n",
        "}])\n",
        "\n",
        "nuevo_hormigon2 = pd.DataFrame([{\n",
        "    \"Cemento\": 400,\n",
        "    \"Escoria\": 0,\n",
        "    \"Ceniza\": 250,\n",
        "    \"Agua\": 150,\n",
        "    \"Super\": 12.5,\n",
        "    \"AGrueso\": 700,\n",
        "    \"AFino\": 1050,\n",
        "    \"Edad\": 28\n",
        "}])\n",
        "\n",
        "nuevo_hormigon3 = pd.DataFrame([{\n",
        "    \"Cemento\": 400,\n",
        "    \"Escoria\": 0,\n",
        "    \"Ceniza\": 250,\n",
        "    \"Agua\": 150,\n",
        "    \"Super\": 12.5,\n",
        "    \"AGrueso\": 700,\n",
        "    \"AFino\": 1050,\n",
        "    \"Edad\": 1\n",
        "}])\n",
        "\n",
        "nuevo_hormigon_scaled = scaler.transform(nuevo_hormigon)\n",
        "nuevo_hormigon2_scaled = scaler.transform(nuevo_hormigon2)\n",
        "nuevo_hormigon3_scaled = scaler.transform(nuevo_hormigon3)\n",
        "\n",
        "prob_aceptable = model.predict(nuevo_hormigon_scaled)[0][0]\n",
        "pred_aceptable = int(prob_aceptable >= 50.0)\n",
        "\n",
        "prob_aceptable2 = model.predict(nuevo_hormigon2_scaled)[0][0]\n",
        "pred_aceptable2 = int(prob_aceptable2 >= 50.0)\n",
        "\n",
        "prob_aceptable3 = model.predict(nuevo_hormigon3_scaled)[0][0]\n",
        "pred_aceptable3 = int(prob_aceptable3 >= 50.0)\n",
        "\n",
        "print(f\"\\nProbabilidad de ser aceptable: {prob_aceptable:.3f}\")\n",
        "print(f\"Clasificación predicha: {pred_aceptable}\")\n",
        "\n",
        "if pred_aceptable == 1:\n",
        "    print(\"El nuevo hormigón es ACEPTABLE\")\n",
        "else:\n",
        "    print(\"El nuevo hormigón es NO ACEPTABLE\")\n",
        "\n",
        "print(f\"\\nProbabilidad de ser aceptable: {prob_aceptable2:.3f}\")\n",
        "print(f\"Clasificación predicha: {pred_aceptable2}\")\n",
        "\n",
        "if pred_aceptable2 == 1:\n",
        "    print(\"El nuevo hormigón 2 es ACEPTABLE\")\n",
        "else:\n",
        "    print(\"El nuevo hormigón 2 es NO ACEPTABLE\")\n",
        "\n",
        "print(f\"\\nProbabilidad de ser aceptable: {prob_aceptable3:.3f}\")\n",
        "print(f\"Clasificación predicha: {pred_aceptable3}\")\n",
        "\n",
        "if pred_aceptable3 == 1:\n",
        "    print(\"El nuevo hormigón 3 es ACEPTABLE\")\n",
        "else:\n",
        "    print(\"El nuevo hormigón 3 es NO ACEPTABLE\")\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W73fSELp_7BV",
        "outputId": "f5908f84-23f4-4f13-be4a-db4e6015a829"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 62ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
            "\n",
            "Probabilidad de ser aceptable: 25.397\n",
            "Clasificación predicha: 0\n",
            "El nuevo hormigón es NO ACEPTABLE\n",
            "\n",
            "Probabilidad de ser aceptable: 63.689\n",
            "Clasificación predicha: 1\n",
            "El nuevo hormigón 2 es ACEPTABLE\n",
            "\n",
            "Probabilidad de ser aceptable: 41.557\n",
            "Clasificación predicha: 0\n",
            "El nuevo hormigón 3 es NO ACEPTABLE\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Generación de un modelo predictivo de regresión con TensorFlow/Keras"
      ],
      "metadata": {
        "id": "MhHgaUWc-V99"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Variables de entrada y salida\n",
        "X = concrete_data[[\"Cemento\", \"Escoria\", \"Ceniza\", \"Agua\", \"Super\", \"AGrueso\", \"AFino\", \"Edad\"]]\n",
        "# Cambiamos el set y, ya no es la aceptabilidad si no la resistencia\n",
        "y = concrete_data[\"Resistencia\"]\n",
        "\n",
        "# Separamos entre entrenamiento y test\n",
        "X_train, X_test, y_train, y_test = train_test_split(\n",
        "    X, y, test_size=0.3, random_state=42)\n",
        "\n",
        "# Normalización de datos\n",
        "scaler = StandardScaler()\n",
        "X_train_scaled = scaler.fit_transform(X_train)\n",
        "X_test_scaled = scaler.transform(X_test)\n",
        "\n",
        "# Crear modelo de regresión\n",
        "model = tf.keras.models.Sequential([\n",
        "    Input(shape=(X_train_scaled.shape[1],)),\n",
        "    layers.Dense(256, activation='relu',\n",
        "                 kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(128, activation='relu',\n",
        "                 kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(64, activation='relu',\n",
        "                 kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(32, activation='relu',\n",
        "                 kernel_regularizer=regularizers.l2(5e-4)),\n",
        "    layers.Dropout(0.1),\n",
        "    layers.Dense(1, activation=\"linear\")\n",
        "])\n",
        "# Ahora la función final es lineal, no tipo sigmoide\n",
        "\n",
        "# Compilamos el modelo\n",
        "model.compile(\n",
        "    optimizer=\"adam\",\n",
        "    loss=\"mse\",\n",
        "    metrics=[\"mae\"])\n",
        "\n",
        "# Resumen del modelo\n",
        "model.summary()\n",
        "\n",
        "# Entrenamos el modelo\n",
        "history = model.fit(\n",
        "    X_train_scaled,\n",
        "    y_train,\n",
        "    validation_split=0.2,\n",
        "    epochs=100,\n",
        "    batch_size=32,\n",
        "    verbose=1\n",
        ")\n",
        "\n",
        "# Predecimos sobre el conjunto de test\n",
        "y_pred = model.predict(X_test_scaled)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "4fdCfYVk-b3Z",
        "outputId": "8f318844-eb3c-4d88-be36-c4bb108b5ad6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential_3\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_3\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ dense_15 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m2,304\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_12 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_16 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_13 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_17 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m8,256\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_14 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_18 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │         \u001b[38;5;34m2,080\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_15 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m)             │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_19 (\u001b[38;5;33mDense\u001b[0m)                │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m33\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ dense_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,304</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_12 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_16 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_13 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_17 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_14 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_18 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,080</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)             │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_19 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">33</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m45,569\u001b[0m (178.00 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">45,569</span> (178.00 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m45,569\u001b[0m (178.00 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">45,569</span> (178.00 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 30ms/step - loss: 1454.5956 - mae: 34.2102 - val_loss: 1253.3474 - val_mae: 31.8581\n",
            "Epoch 2/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 700.0846 - mae: 21.6260 - val_loss: 212.6747 - val_mae: 12.2193\n",
            "Epoch 3/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 301.5124 - mae: 13.7156 - val_loss: 251.6842 - val_mae: 12.9048\n",
            "Epoch 4/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 235.5535 - mae: 12.2167 - val_loss: 177.5538 - val_mae: 11.0728\n",
            "Epoch 5/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 206.5096 - mae: 11.4875 - val_loss: 193.6500 - val_mae: 11.4782\n",
            "Epoch 6/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 207.5003 - mae: 11.6226 - val_loss: 164.4402 - val_mae: 10.7464\n",
            "Epoch 7/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 195.5566 - mae: 11.1015 - val_loss: 173.0048 - val_mae: 10.9128\n",
            "Epoch 8/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 198.4404 - mae: 11.3695 - val_loss: 154.9412 - val_mae: 10.3958\n",
            "Epoch 9/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 186.2319 - mae: 10.9501 - val_loss: 158.4459 - val_mae: 10.5126\n",
            "Epoch 10/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 170.0865 - mae: 10.3837 - val_loss: 147.7721 - val_mae: 10.2485\n",
            "Epoch 11/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 169.0460 - mae: 10.4456 - val_loss: 166.7020 - val_mae: 10.7796\n",
            "Epoch 12/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 174.1445 - mae: 10.4655 - val_loss: 145.6185 - val_mae: 10.0717\n",
            "Epoch 13/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 162.1849 - mae: 10.0730 - val_loss: 128.4220 - val_mae: 9.5587\n",
            "Epoch 14/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 152.9608 - mae: 9.9534 - val_loss: 122.9619 - val_mae: 9.2505\n",
            "Epoch 15/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 144.3456 - mae: 9.5171 - val_loss: 114.5506 - val_mae: 8.8810\n",
            "Epoch 16/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 128.2380 - mae: 8.9045 - val_loss: 114.7111 - val_mae: 8.8823\n",
            "Epoch 17/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 124.1986 - mae: 8.6831 - val_loss: 101.1963 - val_mae: 8.2729\n",
            "Epoch 18/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 118.9071 - mae: 8.5522 - val_loss: 92.1096 - val_mae: 7.7468\n",
            "Epoch 19/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 111.7193 - mae: 8.1150 - val_loss: 80.3426 - val_mae: 7.1374\n",
            "Epoch 20/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 98.7884 - mae: 7.5178 - val_loss: 72.7159 - val_mae: 6.6073\n",
            "Epoch 21/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 94.0173 - mae: 7.5906 - val_loss: 67.7452 - val_mae: 6.3620\n",
            "Epoch 22/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 78.5978 - mae: 6.9362 - val_loss: 67.9323 - val_mae: 6.3792\n",
            "Epoch 23/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 84.9473 - mae: 6.9911 - val_loss: 64.9307 - val_mae: 6.1462\n",
            "Epoch 24/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 78.6265 - mae: 6.8186 - val_loss: 59.2069 - val_mae: 5.8914\n",
            "Epoch 25/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 79.5143 - mae: 6.8853 - val_loss: 64.3533 - val_mae: 5.9962\n",
            "Epoch 26/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 77.3029 - mae: 6.6508 - val_loss: 55.8334 - val_mae: 5.6351\n",
            "Epoch 27/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 77.1848 - mae: 6.6284 - val_loss: 52.5859 - val_mae: 5.3760\n",
            "Epoch 28/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 73.4564 - mae: 6.5892 - val_loss: 58.9222 - val_mae: 5.7564\n",
            "Epoch 29/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 71.4165 - mae: 6.4128 - val_loss: 53.6296 - val_mae: 5.6569\n",
            "Epoch 30/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 63.5675 - mae: 6.1088 - val_loss: 46.2461 - val_mae: 5.1179\n",
            "Epoch 31/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 69.1219 - mae: 6.2498 - val_loss: 55.6234 - val_mae: 5.6088\n",
            "Epoch 32/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 69.0713 - mae: 6.2812 - val_loss: 50.1831 - val_mae: 5.3654\n",
            "Epoch 33/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 64.0211 - mae: 6.0448 - val_loss: 44.2284 - val_mae: 4.9763\n",
            "Epoch 34/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 62.3427 - mae: 5.9692 - val_loss: 44.0079 - val_mae: 4.9836\n",
            "Epoch 35/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 59.7362 - mae: 5.8998 - val_loss: 51.6597 - val_mae: 5.3723\n",
            "Epoch 36/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 61.9060 - mae: 5.9616 - val_loss: 42.9048 - val_mae: 4.9260\n",
            "Epoch 37/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 61.9400 - mae: 5.9048 - val_loss: 42.7907 - val_mae: 4.8219\n",
            "Epoch 38/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 60.7747 - mae: 5.8750 - val_loss: 39.0852 - val_mae: 4.6915\n",
            "Epoch 39/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 57.8644 - mae: 5.8864 - val_loss: 42.0603 - val_mae: 4.8269\n",
            "Epoch 40/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 50.5708 - mae: 5.4193 - val_loss: 38.9485 - val_mae: 4.7514\n",
            "Epoch 41/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 60.9656 - mae: 6.0234 - val_loss: 42.2131 - val_mae: 4.8912\n",
            "Epoch 42/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 67.6072 - mae: 6.2116 - val_loss: 39.2614 - val_mae: 4.7371\n",
            "Epoch 43/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 54.8225 - mae: 5.6774 - val_loss: 38.9853 - val_mae: 4.6760\n",
            "Epoch 44/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 54.2048 - mae: 5.6465 - val_loss: 36.4297 - val_mae: 4.5399\n",
            "Epoch 45/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 49.8061 - mae: 5.4301 - val_loss: 38.3552 - val_mae: 4.6927\n",
            "Epoch 46/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 54.7441 - mae: 5.5663 - val_loss: 45.1409 - val_mae: 5.1473\n",
            "Epoch 47/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 50.9150 - mae: 5.5029 - val_loss: 43.7131 - val_mae: 5.0500\n",
            "Epoch 48/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 58.2235 - mae: 5.6484 - val_loss: 47.2906 - val_mae: 5.3425\n",
            "Epoch 49/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 45.8242 - mae: 5.1670 - val_loss: 45.9698 - val_mae: 5.2964\n",
            "Epoch 50/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 48.3092 - mae: 5.1844 - val_loss: 36.0091 - val_mae: 4.5512\n",
            "Epoch 51/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 48.9578 - mae: 5.4147 - val_loss: 34.7368 - val_mae: 4.4115\n",
            "Epoch 52/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 47.4496 - mae: 5.2479 - val_loss: 35.6631 - val_mae: 4.4951\n",
            "Epoch 53/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 55.2417 - mae: 5.6321 - val_loss: 37.1017 - val_mae: 4.6702\n",
            "Epoch 54/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 48.9619 - mae: 5.1586 - val_loss: 37.5335 - val_mae: 4.6060\n",
            "Epoch 55/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 42.9210 - mae: 4.9789 - val_loss: 37.4024 - val_mae: 4.6105\n",
            "Epoch 56/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 44.0609 - mae: 5.1108 - val_loss: 36.9526 - val_mae: 4.6066\n",
            "Epoch 57/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 46.3025 - mae: 5.2141 - val_loss: 39.9672 - val_mae: 4.8377\n",
            "Epoch 58/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 46.9010 - mae: 5.2753 - val_loss: 32.3969 - val_mae: 4.3369\n",
            "Epoch 59/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 44.6867 - mae: 5.0701 - val_loss: 34.4829 - val_mae: 4.6329\n",
            "Epoch 60/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 48.6307 - mae: 5.2132 - val_loss: 34.8917 - val_mae: 4.5577\n",
            "Epoch 61/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 45.8044 - mae: 5.0352 - val_loss: 33.8123 - val_mae: 4.3393\n",
            "Epoch 62/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 49.5430 - mae: 5.3731 - val_loss: 33.2894 - val_mae: 4.4472\n",
            "Epoch 63/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 49.9956 - mae: 5.3019 - val_loss: 32.8909 - val_mae: 4.4694\n",
            "Epoch 64/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 48.2371 - mae: 5.3213 - val_loss: 33.9493 - val_mae: 4.4944\n",
            "Epoch 65/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 51.6559 - mae: 5.5576 - val_loss: 33.5049 - val_mae: 4.3617\n",
            "Epoch 66/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 41.8794 - mae: 4.9791 - val_loss: 35.7598 - val_mae: 4.5851\n",
            "Epoch 67/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 42.6256 - mae: 4.9194 - val_loss: 33.5246 - val_mae: 4.4185\n",
            "Epoch 68/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 45.8821 - mae: 5.1577 - val_loss: 34.2303 - val_mae: 4.5338\n",
            "Epoch 69/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 41.3332 - mae: 4.9913 - val_loss: 32.2419 - val_mae: 4.3621\n",
            "Epoch 70/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 44.8804 - mae: 5.1260 - val_loss: 31.0901 - val_mae: 4.2592\n",
            "Epoch 71/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 38.8509 - mae: 4.7238 - val_loss: 31.6676 - val_mae: 4.3096\n",
            "Epoch 72/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 44.3367 - mae: 4.9872 - val_loss: 30.4656 - val_mae: 4.2293\n",
            "Epoch 73/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 41.4311 - mae: 5.0268 - val_loss: 31.6616 - val_mae: 4.2123\n",
            "Epoch 74/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 42.0857 - mae: 5.0507 - val_loss: 37.6248 - val_mae: 4.7596\n",
            "Epoch 75/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 44.1123 - mae: 5.0124 - val_loss: 30.0170 - val_mae: 4.1981\n",
            "Epoch 76/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 40.8651 - mae: 4.8663 - val_loss: 31.9939 - val_mae: 4.3935\n",
            "Epoch 77/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 45.8835 - mae: 5.1156 - val_loss: 38.5357 - val_mae: 4.7904\n",
            "Epoch 78/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 41.7872 - mae: 4.9111 - val_loss: 33.5746 - val_mae: 4.3970\n",
            "Epoch 79/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 49.0578 - mae: 5.3585 - val_loss: 36.0139 - val_mae: 4.4795\n",
            "Epoch 80/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 50.1618 - mae: 5.3035 - val_loss: 32.7257 - val_mae: 4.3247\n",
            "Epoch 81/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 41.4147 - mae: 4.8876 - val_loss: 33.0256 - val_mae: 4.3895\n",
            "Epoch 82/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 38.4202 - mae: 4.8250 - val_loss: 35.0617 - val_mae: 4.5530\n",
            "Epoch 83/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 46.2146 - mae: 5.0689 - val_loss: 32.4092 - val_mae: 4.3373\n",
            "Epoch 84/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 43.2464 - mae: 4.9299 - val_loss: 33.5346 - val_mae: 4.2849\n",
            "Epoch 85/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 41.4032 - mae: 4.9344 - val_loss: 31.2776 - val_mae: 4.2730\n",
            "Epoch 86/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 45.7319 - mae: 5.2315 - val_loss: 34.6854 - val_mae: 4.5732\n",
            "Epoch 87/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 42.1313 - mae: 4.9785 - val_loss: 31.3445 - val_mae: 4.1637\n",
            "Epoch 88/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 43.8736 - mae: 4.9890 - val_loss: 37.1850 - val_mae: 4.6720\n",
            "Epoch 89/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 39.9338 - mae: 4.7589 - val_loss: 30.1002 - val_mae: 4.2084\n",
            "Epoch 90/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 40.8007 - mae: 4.9944 - val_loss: 34.1712 - val_mae: 4.5417\n",
            "Epoch 91/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 44.2930 - mae: 5.1136 - val_loss: 36.5578 - val_mae: 4.4959\n",
            "Epoch 92/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 38.4952 - mae: 4.8245 - val_loss: 35.4686 - val_mae: 4.6253\n",
            "Epoch 93/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 47.5017 - mae: 5.1013 - val_loss: 39.3799 - val_mae: 4.9060\n",
            "Epoch 94/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 45.0599 - mae: 5.1233 - val_loss: 31.7054 - val_mae: 4.1886\n",
            "Epoch 95/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 45.5763 - mae: 5.0968 - val_loss: 29.7222 - val_mae: 4.2519\n",
            "Epoch 96/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 39.7897 - mae: 4.6666 - val_loss: 34.1756 - val_mae: 4.5337\n",
            "Epoch 97/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 41.7784 - mae: 4.8892 - val_loss: 38.8454 - val_mae: 4.8611\n",
            "Epoch 98/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 39.7560 - mae: 4.7943 - val_loss: 34.2926 - val_mae: 4.5816\n",
            "Epoch 99/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 39.6847 - mae: 4.8391 - val_loss: 29.2810 - val_mae: 4.0881\n",
            "Epoch 100/100\n",
            "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - loss: 39.6328 - mae: 4.6427 - val_loss: 31.8623 - val_mae: 4.2461\n",
            "\u001b[1m10/10\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = model.predict(X_test_scaled).flatten()\n",
        "plt.figure(figsize=(6, 6))\n",
        "sns.scatterplot(x=y_test, y=y_pred)\n",
        "plt.xlabel(\"Resistencia real\")\n",
        "plt.ylabel(\"Resistencia predicha\")\n",
        "plt.title(\"Predicción vs valor real\")\n",
        "plt.plot([y_test.min(), y_test.max()],\n",
        "         [y_test.min(), y_test.max()],\n",
        "         color=\"red\", linestyle=\"--\")\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 624
        },
        "id": "IrIVK8r--rnJ",
        "outputId": "08dcef11-631d-4684-f3b9-9688f453005c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m10/10\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step \n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "nuevo_hormigon = pd.DataFrame([{\n",
        "    \"Cemento\": 350,\n",
        "    \"Escoria\": 50,\n",
        "    \"Ceniza\": 0,\n",
        "    \"Agua\": 200,\n",
        "    \"Super\": 0,\n",
        "    \"AGrueso\": 1000,\n",
        "    \"AFino\": 750,\n",
        "    \"Edad\": 14\n",
        "}])\n",
        "\n",
        "nuevo_hormigon2 = pd.DataFrame([{\n",
        "    \"Cemento\": 400,\n",
        "    \"Escoria\": 0,\n",
        "    \"Ceniza\": 250,\n",
        "    \"Agua\": 150,\n",
        "    \"Super\": 12.5,\n",
        "    \"AGrueso\": 700,\n",
        "    \"AFino\": 1050,\n",
        "    \"Edad\": 28\n",
        "}])\n",
        "\n",
        "nuevo_hormigon3 = pd.DataFrame([{\n",
        "    \"Cemento\": 400,\n",
        "    \"Escoria\": 0,\n",
        "    \"Ceniza\": 250,\n",
        "    \"Agua\": 150,\n",
        "    \"Super\": 12.5,\n",
        "    \"AGrueso\": 700,\n",
        "    \"AFino\": 1050,\n",
        "    \"Edad\": 1\n",
        "}])\n",
        "\n",
        "nuevo_hormigon_scaled = scaler.transform(nuevo_hormigon)\n",
        "resistencia_predicha = model.predict(nuevo_hormigon_scaled)[0][0]\n",
        "print(f\"Resistencia predicha para nuevo hormigon: {resistencia_predicha:.2f} MPa\")\n",
        "\n",
        "nuevo_hormigon_scaled2 = scaler.transform(nuevo_hormigon2)\n",
        "resistencia_predicha = model.predict(nuevo_hormigon_scaled2)[0][0]\n",
        "print(f\"Resistencia predicha para nuevo hormigon: {resistencia_predicha:.2f} MPa\")\n",
        "\n",
        "nuevo_hormigon_scaled3 = scaler.transform(nuevo_hormigon3)\n",
        "resistencia_predicha = model.predict(nuevo_hormigon_scaled3)[0][0]\n",
        "print(f\"Resistencia predicha para nuevo hormigon: {resistencia_predicha:.2f} MPa\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JeqsKYO6_hwI",
        "outputId": "1025b3ad-3ba8-4478-c5ed-0dfe90c9ee3f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 154ms/step\n",
            "Resistencia predicha para nuevo hormigon: 25.40 MPa\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 113ms/step\n",
            "Resistencia predicha para nuevo hormigon: 63.69 MPa\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 158ms/step\n",
            "Resistencia predicha para nuevo hormigon: 41.56 MPa\n"
          ]
        }
      ]
    }
  ]
}