TP2/7506R_TP2_GRUPO02_ENTREGA_N5.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "toc_visible": true,
      "authorship_tag": "ABX9TyPStOTV0gBd7MQhgsFq9w2i",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/kikiymini/7506R-1C2024-GRUPO02/blob/main/TP2/7506R_TP2_GRUPO2_Ensamble.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# <center>Organizaci&oacute;n de Datos</center>\n",
        "\n",
        "#### <center>C&aacute;tedra Ing. Rodriguez, Juan Manuel </center>\n",
        "\n",
        "## <center>Trabajo Práctico 2: Críticas cinematográficas</center>\n",
        "\n",
        "### <center> Grupo 2</center>\n",
        "\n",
        "## Integrantes:\n",
        "\n",
        "*   Aramayo Carolina\n",
        "*   Utrera Maximo Damian\n",
        "*   Villalba Ana Daniela\n",
        "*   Fiorilo Roy\n"
      ],
      "metadata": {
        "id": "A-dlbXGn0X2r"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Importación de librerias"
      ],
      "metadata": {
        "id": "qCmvDXED0aR_"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6HYtTc73zS6Z",
        "outputId": "95ccf7ab-d2d7-458f-9927-4df7f061c2db"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n",
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Package punkt is already up-to-date!\n",
            "[nltk_data] Downloading package omw-1.4 to /root/nltk_data...\n",
            "[nltk_data]   Package omw-1.4 is already up-to-date!\n",
            "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",
            "[nltk_data]   Package wordnet is already up-to-date!\n",
            "[nltk_data] Downloading package averaged_perceptron_tagger to\n",
            "[nltk_data]     /root/nltk_data...\n",
            "[nltk_data]   Package averaged_perceptron_tagger is already up-to-\n",
            "[nltk_data]       date!\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "from matplotlib import pyplot as plt\n",
        "import seaborn as sns\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "from sklearn.metrics import confusion_matrix, classification_report\n",
        "from nltk.corpus import stopwords\n",
        "from nltk.tokenize import word_tokenize\n",
        "import nltk\n",
        "\n",
        "nltk.download('stopwords')\n",
        "nltk.download('punkt')\n",
        "nltk.download('omw-1.4')\n",
        "nltk.download('wordnet')\n",
        "nltk.download('averaged_perceptron_tagger')\n",
        "\n",
        "# Modelos\n",
        "import joblib\n",
        "from sklearn.ensemble import VotingClassifier\n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings(\"ignore\")\n",
        "\n",
        "RAND_SEED = 42"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Lectura de archivo\n"
      ],
      "metadata": {
        "id": "ZtLRtdIn0fkw"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Desde google drive"
      ],
      "metadata": {
        "id": "DVCnSMwN0hUM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "drive.mount('/content/drive')\n",
        "root_path = \"/content/drive/MyDrive/7506R-1C2024-GRUPO02/TP2/\""
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gJLT3DlI0jAV",
        "outputId": "ab5f46f9-90be-4c83-c885-a915a8f794e1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Desde maquina local"
      ],
      "metadata": {
        "id": "nVAcXHsa0lN1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Si se esta trabajando en local, descomentar esta celta y comentar la de arriba\n",
        "# root_path = \"./\""
      ],
      "metadata": {
        "id": "9R1g6Gtt0mmk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train_path = root_path + 'Dataset/train.csv'\n",
        "test_path = root_path + 'Dataset/test.csv'\n",
        "sample_path = root_path + 'Dataset/sample_solution.csv'\n",
        "\n",
        "ds_train = pd.read_csv(train_path)\n",
        "ds_test = pd.read_csv(test_path)\n",
        "sample = pd.read_csv(sample_path)\n",
        "\n",
        "nb_path = root_path + 'Models/naive_bayes.pkl'\n",
        "rf_path = root_path + 'Models/random_forest.pkl'\n",
        "xgb_path = root_path + 'Models/xgboost.pkl'\n",
        "\n",
        "nb = joblib.load(nb_path)\n",
        "rf = joblib.load(rf_path)\n",
        "xgb = joblib.load(xgb_path)"
      ],
      "metadata": {
        "id": "QLfFfco40otX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Ensamble"
      ],
      "metadata": {
        "id": "LY05dWy02GHl"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Utils"
      ],
      "metadata": {
        "id": "K2canCPyQTwS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def map_sentiment(ds, invert=False):\n",
        "  return ds.map({'negativo': 0, 'positivo': 1}) if not invert else ds.map({0: 'negativo', 1: 'positivo'})"
      ],
      "metadata": {
        "id": "Nd0emy-QOO7n"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def build_results(pred):\n",
        "  res = ds_test.copy()\n",
        "  res.drop(columns=[\"review_es\"], inplace=True)\n",
        "  res['sentimiento'] = pred\n",
        "  return res"
      ],
      "metadata": {
        "id": "erzicwg-P4w2"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def print_positive_negatives(sentimientos):\n",
        "  total_positives = (sentimientos == \"positivo\").sum()\n",
        "  total_negatives = (sentimientos == \"negativo\").sum()\n",
        "  print(f\"Positives: {total_positives}\\nNegatives: {total_negatives}\")"
      ],
      "metadata": {
        "id": "Uge8MOOPP-kU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def plot_confussion_matrix(true, pred):\n",
        "  #Creo matriz de confusión\n",
        "  tabla = confusion_matrix(true, pred)\n",
        "\n",
        "  #Grafico matriz de confusión\n",
        "  sns.heatmap(tabla, cmap='Blues',annot=True,fmt='g')\n",
        "  plt.xlabel('Predicciones')\n",
        "  plt.ylabel('Verdaderos')\n",
        "\n",
        "  #Reporte\n",
        "  print(classification_report(true, pred))"
      ],
      "metadata": {
        "id": "YyOmg2_pzVDo"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_test_text = ds_test[\"review_es\"]\n",
        "x_train_text = ds_train[\"review_es\"]\n",
        "y_train = map_sentiment(ds_train['sentimiento'])"
      ],
      "metadata": {
        "id": "DqlMci1L2_VS"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Vectorizacion"
      ],
      "metadata": {
        "id": "A0Q7NEIVQVmi"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def clean_text(text):\n",
        "  return text.strip()\n",
        "\n",
        "def tokenizer(text):\n",
        "  return [w for w in word_tokenize(text) if w.isalpha()]\n",
        "\n",
        "stoplist = stopwords.words(\"spanish\")"
      ],
      "metadata": {
        "id": "4zFhXJ49xXqv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tfidf_vect = TfidfVectorizer(\n",
        "    preprocessor=clean_text,\n",
        "    tokenizer=tokenizer,\n",
        "    min_df=5,\n",
        "    stop_words=stoplist,\n",
        "    ngram_range=(1, 2)\n",
        ")\n",
        "x_train = tfidf_vect.fit_transform(x_train_text)\n",
        "x_test = tfidf_vect.transform(x_test_text)\n",
        "x_train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AWoZ0VATJacc",
        "outputId": "8d549e0a-a247-4073-bbaa-09a95b3a92c0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<50000x189296 sparse matrix of type '<class 'numpy.float64'>'\n",
              "\twith 7169809 stored elements in Compressed Sparse Row format>"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Ensamblaje y votacion"
      ],
      "metadata": {
        "id": "4BTfjQ0nQY6n"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "ensemble_model = VotingClassifier(\n",
        "    estimators=[\n",
        "        ('mnb', nb),\n",
        "        ('rf', rf),\n",
        "        ('xgb', xgb)\n",
        "    ],\n",
        "    voting='hard'\n",
        ")\n",
        "\n",
        "ensemble_model.fit(x_train, y_train)"
      ],
      "metadata": {
        "collapsed": true,
        "id": "A1JH8G-i2nki",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 110
        },
        "outputId": "a95f7c63-28ae-4194-9f0d-15aeced8175d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "VotingClassifier(estimators=[('mnb', MultinomialNB(alpha=1)),\n",
              "                             ('rf',\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             ('xgb',\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))])"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>VotingClassifier(estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                             (&#x27;rf&#x27;,\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             (&#x27;xgb&#x27;,\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">VotingClassifier</label><div class=\"sk-toggleable__content\"><pre>VotingClassifier(estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                             (&#x27;rf&#x27;,\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             (&#x27;xgb&#x27;,\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>mnb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB(alpha=1)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>rf</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_depth=6, min_samples_split=6, n_estimators=350,\n",
              "                       n_jobs=-1, oob_score=True, random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>xgb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
              "              colsample_bylevel=None, colsample_bynode=None,\n",
              "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
              "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
              "              gamma=None, grow_policy=None, importance_type=None,\n",
              "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
              "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
              "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
              "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
              "              multi_strategy=None, n_estimators=200, n_jobs=None,\n",
              "              num_parallel_tree=None, random_state=0, ...)</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predicciones\n",
        "y_pred = ensemble_model.predict(x_test)\n",
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)"
      ],
      "metadata": {
        "id": "UfZGtGhb52Pq"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "resultados_ensamble = build_results(y_pred)\n",
        "print_positive_negatives(resultados_ensamble['sentimiento'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NJBTkXo6PeuM",
        "outputId": "227c5ea5-e553-4f6e-94b5-b396e079d636"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Positives: 5246\n",
            "Negatives: 3353\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predicciones\n",
        "y_pred = ensemble_model.predict(x_train)"
      ],
      "metadata": {
        "id": "_xPnv7g4zKJl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)\n",
        "y_train_str = map_sentiment(pd.Series(y_train), invert=True)\n",
        "plot_confussion_matrix(y_train_str, y_pred) # grafico"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 605
        },
        "id": "D-hMiNebzrU5",
        "outputId": "a4ab16e2-dfc3-4d98-c0ca-665271380201"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "    negativo       0.94      0.89      0.92     25000\n",
            "    positivo       0.90      0.95      0.92     25000\n",
            "\n",
            "    accuracy                           0.92     50000\n",
            "   macro avg       0.92      0.92      0.92     50000\n",
            "weighted avg       0.92      0.92      0.92     50000\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Soft"
      ],
      "metadata": {
        "id": "3v7Yov0q6_zB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "ensemble_model_soft = VotingClassifier(\n",
        "    estimators=[\n",
        "        ('mnb', nb),\n",
        "        ('rf', rf),\n",
        "        ('xgb', xgb)\n",
        "    ],\n",
        "    voting='soft'\n",
        ")\n",
        "\n",
        "ensemble_model_soft.fit(x_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 110
        },
        "id": "dM-ZeU6V6_Sb",
        "outputId": "9efbdac8-695b-4ed7-cecf-344bbccae3f5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "VotingClassifier(estimators=[('mnb', MultinomialNB(alpha=1)),\n",
              "                             ('rf',\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             ('xgb',\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))],\n",
              "                 voting='soft')"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>VotingClassifier(estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                             (&#x27;rf&#x27;,\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             (&#x27;xgb&#x27;,\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))],\n",
              "                 voting=&#x27;soft&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">VotingClassifier</label><div class=\"sk-toggleable__content\"><pre>VotingClassifier(estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                             (&#x27;rf&#x27;,\n",
              "                              RandomForestClassifier(max_depth=6,\n",
              "                                                     min_samples_split=6,\n",
              "                                                     n_estimators=350,\n",
              "                                                     n_jobs=-1, oob_score=True,\n",
              "                                                     random_state=42)),\n",
              "                             (&#x27;xgb&#x27;,\n",
              "                              XGBClassifier(base_score=None, booster=None,\n",
              "                                            callbacks=None,\n",
              "                                            colsample_bylevel=None,\n",
              "                                            colsample_bynode=None,\n",
              "                                            colsample_bytree=None, device=None,\n",
              "                                            early_stopping_rounds=Non...\n",
              "                                            grow_policy=None,\n",
              "                                            importance_type=None,\n",
              "                                            interaction_constraints=None,\n",
              "                                            learning_rate=None, max_bin=None,\n",
              "                                            max_cat_threshold=None,\n",
              "                                            max_cat_to_onehot=None,\n",
              "                                            max_delta_step=None, max_depth=None,\n",
              "                                            max_leaves=None,\n",
              "                                            min_child_weight=None, missing=nan,\n",
              "                                            monotone_constraints=None,\n",
              "                                            multi_strategy=None,\n",
              "                                            n_estimators=200, n_jobs=None,\n",
              "                                            num_parallel_tree=None,\n",
              "                                            random_state=0, ...))],\n",
              "                 voting=&#x27;soft&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>mnb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB(alpha=1)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>rf</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_depth=6, min_samples_split=6, n_estimators=350,\n",
              "                       n_jobs=-1, oob_score=True, random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>xgb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
              "              colsample_bylevel=None, colsample_bynode=None,\n",
              "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
              "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
              "              gamma=None, grow_policy=None, importance_type=None,\n",
              "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
              "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
              "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
              "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
              "              multi_strategy=None, n_estimators=200, n_jobs=None,\n",
              "              num_parallel_tree=None, random_state=0, ...)</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predicciones\n",
        "y_pred = ensemble_model_soft.predict(x_test)\n",
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)"
      ],
      "metadata": {
        "id": "npn5Jj8G7Bno"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "resultados_ensemble_soft = build_results(y_pred)\n",
        "print_positive_negatives(resultados_ensemble_soft['sentimiento'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "S1n8MfHz7DJN",
        "outputId": "1cdc9374-940a-4a9f-9a1b-579d63fcf670"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Positives: 4952\n",
            "Negatives: 3647\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predicciones\n",
        "y_pred = ensemble_model_soft.predict(x_train)"
      ],
      "metadata": {
        "id": "p2UE2-lr0fnw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)\n",
        "y_train_str = map_sentiment(pd.Series(y_train), invert=True)\n",
        "plot_confussion_matrix(y_train_str, y_pred) # grafico"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "D7i-e_bw0mUQ",
        "outputId": "e58593b9-3382-4090-9249-1511d771304a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "    negativo       0.96      0.94      0.95     25000\n",
            "    positivo       0.94      0.96      0.95     25000\n",
            "\n",
            "    accuracy                           0.95     50000\n",
            "   macro avg       0.95      0.95      0.95     50000\n",
            "weighted avg       0.95      0.95      0.95     50000\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## stacking"
      ],
      "metadata": {
        "id": "DoR9Q2WKEI15"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import StackingClassifier\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "\n",
        "# Define base estimators\n",
        "estimators = [\n",
        "    ('mnb', nb),\n",
        "    ('rf', rf),\n",
        "    ('xgb', xgb),\n",
        "]\n",
        "\n",
        "# Initialize StackingClassifier\n",
        "stack_clf = StackingClassifier(\n",
        "    estimators=estimators,\n",
        "    final_estimator=LogisticRegression(),\n",
        "    stack_method='predict',  # Use predict method of base estimators\n",
        "    cv=5  # 5-fold cross-validation during stacking\n",
        ")\n",
        "\n",
        "# Train the StackingClassifier\n",
        "stack_clf.fit(x_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 164
        },
        "id": "0n6TWmyMEKAI",
        "outputId": "b4e2b357-8556-418f-fc66-da9f40693edb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "StackingClassifier(cv=5,\n",
              "                   estimators=[('mnb', MultinomialNB(alpha=1)),\n",
              "                               ('rf',\n",
              "                                RandomForestClassifier(max_depth=6,\n",
              "                                                       min_samples_split=6,\n",
              "                                                       n_estimators=350,\n",
              "                                                       n_jobs=-1,\n",
              "                                                       oob_score=True,\n",
              "                                                       random_state=42)),\n",
              "                               ('xgb',\n",
              "                                XGBClassifier(base_score=None, booster=None,\n",
              "                                              callbacks=None,\n",
              "                                              colsample_bylevel=None,\n",
              "                                              colsample_bynode=None,\n",
              "                                              colsample_bytree=None,\n",
              "                                              device=None,\n",
              "                                              early_stopping_rou...\n",
              "                                              interaction_constraints=None,\n",
              "                                              learning_rate=None, max_bin=None,\n",
              "                                              max_cat_threshold=None,\n",
              "                                              max_cat_to_onehot=None,\n",
              "                                              max_delta_step=None,\n",
              "                                              max_depth=None, max_leaves=None,\n",
              "                                              min_child_weight=None,\n",
              "                                              missing=nan,\n",
              "                                              monotone_constraints=None,\n",
              "                                              multi_strategy=None,\n",
              "                                              n_estimators=200, n_jobs=None,\n",
              "                                              num_parallel_tree=None,\n",
              "                                              random_state=0, ...))],\n",
              "                   final_estimator=LogisticRegression(),\n",
              "                   stack_method='predict')"
            ],
            "text/html": [
              "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>StackingClassifier(cv=5,\n",
              "                   estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                               (&#x27;rf&#x27;,\n",
              "                                RandomForestClassifier(max_depth=6,\n",
              "                                                       min_samples_split=6,\n",
              "                                                       n_estimators=350,\n",
              "                                                       n_jobs=-1,\n",
              "                                                       oob_score=True,\n",
              "                                                       random_state=42)),\n",
              "                               (&#x27;xgb&#x27;,\n",
              "                                XGBClassifier(base_score=None, booster=None,\n",
              "                                              callbacks=None,\n",
              "                                              colsample_bylevel=None,\n",
              "                                              colsample_bynode=None,\n",
              "                                              colsample_bytree=None,\n",
              "                                              device=None,\n",
              "                                              early_stopping_rou...\n",
              "                                              interaction_constraints=None,\n",
              "                                              learning_rate=None, max_bin=None,\n",
              "                                              max_cat_threshold=None,\n",
              "                                              max_cat_to_onehot=None,\n",
              "                                              max_delta_step=None,\n",
              "                                              max_depth=None, max_leaves=None,\n",
              "                                              min_child_weight=None,\n",
              "                                              missing=nan,\n",
              "                                              monotone_constraints=None,\n",
              "                                              multi_strategy=None,\n",
              "                                              n_estimators=200, n_jobs=None,\n",
              "                                              num_parallel_tree=None,\n",
              "                                              random_state=0, ...))],\n",
              "                   final_estimator=LogisticRegression(),\n",
              "                   stack_method=&#x27;predict&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StackingClassifier</label><div class=\"sk-toggleable__content\"><pre>StackingClassifier(cv=5,\n",
              "                   estimators=[(&#x27;mnb&#x27;, MultinomialNB(alpha=1)),\n",
              "                               (&#x27;rf&#x27;,\n",
              "                                RandomForestClassifier(max_depth=6,\n",
              "                                                       min_samples_split=6,\n",
              "                                                       n_estimators=350,\n",
              "                                                       n_jobs=-1,\n",
              "                                                       oob_score=True,\n",
              "                                                       random_state=42)),\n",
              "                               (&#x27;xgb&#x27;,\n",
              "                                XGBClassifier(base_score=None, booster=None,\n",
              "                                              callbacks=None,\n",
              "                                              colsample_bylevel=None,\n",
              "                                              colsample_bynode=None,\n",
              "                                              colsample_bytree=None,\n",
              "                                              device=None,\n",
              "                                              early_stopping_rou...\n",
              "                                              interaction_constraints=None,\n",
              "                                              learning_rate=None, max_bin=None,\n",
              "                                              max_cat_threshold=None,\n",
              "                                              max_cat_to_onehot=None,\n",
              "                                              max_delta_step=None,\n",
              "                                              max_depth=None, max_leaves=None,\n",
              "                                              min_child_weight=None,\n",
              "                                              missing=nan,\n",
              "                                              monotone_constraints=None,\n",
              "                                              multi_strategy=None,\n",
              "                                              n_estimators=200, n_jobs=None,\n",
              "                                              num_parallel_tree=None,\n",
              "                                              random_state=0, ...))],\n",
              "                   final_estimator=LogisticRegression(),\n",
              "                   stack_method=&#x27;predict&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>mnb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB(alpha=1)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>rf</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-21\" type=\"checkbox\" ><label for=\"sk-estimator-id-21\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(max_depth=6, min_samples_split=6, n_estimators=350,\n",
              "                       n_jobs=-1, oob_score=True, random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>xgb</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" ><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
              "              colsample_bylevel=None, colsample_bynode=None,\n",
              "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
              "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
              "              gamma=None, grow_policy=None, importance_type=None,\n",
              "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
              "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
              "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
              "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
              "              multi_strategy=None, n_estimators=200, n_jobs=None,\n",
              "              num_parallel_tree=None, random_state=0, ...)</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><label>final_estimator</label></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" ><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = stack_clf.predict(x_test)\n",
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)"
      ],
      "metadata": {
        "id": "xvFUS3uLEf81"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "resultados_stacking = build_results(y_pred)\n",
        "print_positive_negatives(resultados_stacking['sentimiento'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wgV0EyFAEkes",
        "outputId": "2cf2396a-7c41-4d60-9b17-559d1bbdcecc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Positives: 4475\n",
            "Negatives: 4124\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predicciones\n",
        "y_pred = stack_clf.predict(x_train)"
      ],
      "metadata": {
        "id": "6wAHwodH0rUo"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = map_sentiment(pd.Series(y_pred), invert=True)\n",
        "y_train_str = map_sentiment(pd.Series(y_train), invert=True)\n",
        "plot_confussion_matrix(y_train_str, y_pred) # grafico"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "D8obkLQa0t46",
        "outputId": "8ae62762-2eac-4946-b709-6160956524c9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "    negativo       0.92      0.93      0.93     25000\n",
            "    positivo       0.93      0.92      0.93     25000\n",
            "\n",
            "    accuracy                           0.93     50000\n",
            "   macro avg       0.93      0.93      0.93     50000\n",
            "weighted avg       0.93      0.93      0.93     50000\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Guardado"
      ],
      "metadata": {
        "id": "5X4z3p9vPpTw"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# ensemble\n",
        "resultados_ensamble.to_csv(root_path + \"Dataset/resultados_ensamble.csv\", index=False)\n",
        "joblib.dump(ensemble_model, root_path + 'Models/ensemble_hard.pkl')\n",
        "\n",
        "# full ensemble soft\n",
        "resultados_ensemble_soft.to_csv(root_path + \"Dataset/resultados_ensemble_soft.csv\", index=False)\n",
        "joblib.dump(ensemble_model_soft, root_path + 'Models/ensemble_soft.pkl')\n",
        "\n",
        "# stacking\n",
        "resultados_stacking.to_csv(root_path + \"Dataset/resultados_stacking.csv\", index=False)\n",
        "joblib.dump(stack_clf, root_path + 'Models/stacking.pkl')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Uy7TFHkoPoQg",
        "outputId": "6bde4326-1125-4317-cc5a-0974080a59f0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['/content/drive/MyDrive/7506R-1C2024-GRUPO02/TP2/Models/stacking.pkl']"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    }
  ]
}