{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import cv2\n",
        "import numpy as np\n",
        "import pandas as pd"
      ],
      "metadata": {
        "id": "RRIHYeA8vZ2f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jYHkQveBL7JQ",
        "outputId": "7b23f722-2369-4842-c8ed-7e274bdbe589"
      },
      "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"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data\""
      ],
      "metadata": {
        "id": "dDXJUfqX8u1f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#verify the folders\n",
        "for folder in os.listdir(data_path):\n",
        "    print(folder, len(os.listdir(os.path.join(data_path, folder))), \"images\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "O53-h2jYt67_",
        "outputId": "f811f07c-4c56-4239-d025-e8afe0cb05dd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rottenbanana 2226 images\n",
            "rottenoranges 1601 images\n",
            "rottenapples 2342 images\n",
            "freshbanana 1581 images\n",
            "freshoranges 1466 images\n",
            "freshapples 1697 images\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/rottenbanana\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('rottenbanana')\n",
        "\n",
        "df_rottenbanana = pd.DataFrame(X_list)\n",
        "df_rottenbanana['target'] = y_list\n",
        "\n",
        "print(\"rottenbanana shape:\", df_rottenbanana.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wXi7RhlVufIi",
        "outputId": "5bafc4d8-e709-4e9a-dca8-35ad753cbc2b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rottenbanana shape: (2226, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/rottenoranges\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('rottenoranges')\n",
        "\n",
        "df_rottenoranges = pd.DataFrame(X_list)\n",
        "df_rottenoranges['target'] = y_list\n",
        "\n",
        "print(\"rottenoranges shape:\", df_rottenoranges.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5AxSMVuTy5On",
        "outputId": "1ed146c6-2bb7-40ef-f391-f7c4e70ac62f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rottenoranges shape: (1601, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/rottenapples\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('rottenapples')\n",
        "\n",
        "df_rottenapples = pd.DataFrame(X_list)\n",
        "df_rottenapples['target'] = y_list\n",
        "\n",
        "print(\"rottenapples shape:\", df_rottenapples.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xkumK75uzA5i",
        "outputId": "8e2e3b2b-e1bb-404a-a3fb-b9c379031195"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "rottenapples shape: (2342, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/freshbanana\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('freshbanana')\n",
        "\n",
        "df_freshbanana = pd.DataFrame(X_list)\n",
        "df_freshbanana['target'] = y_list\n",
        "\n",
        "print(\"freshbanana shape:\", df_freshbanana.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sebO1Zl5zUX6",
        "outputId": "3b455d4c-5d9f-41e2-906d-3b5c71015d93"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "freshbanana shape: (1581, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/freshoranges\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('freshoranges')\n",
        "\n",
        "df_freshoranges = pd.DataFrame(X_list)\n",
        "df_freshoranges['target'] = y_list\n",
        "\n",
        "print(\"freshoranges shape:\", df_freshoranges.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wLloeGpZz-fk",
        "outputId": "d8e6f564-a2b8-4768-b447-ec40bb9a5af7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "freshoranges shape: (1466, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "folder_path = \"/content/drive/MyDrive/Colab Notebooks/ML RESUME PROJECTS/image classiication/data/freshapples\"\n",
        "X_list = []\n",
        "y_list = []\n",
        "\n",
        "for file in os.listdir(folder_path):\n",
        "    img_path = os.path.join(folder_path, file)\n",
        "    img = cv2.imread(img_path)\n",
        "    img = cv2.resize(img, (64,64))\n",
        "    img_flat = img.flatten().astype(np.uint8)\n",
        "    X_list.append(img_flat)\n",
        "    y_list.append('freshapples')\n",
        "\n",
        "df_freshapples = pd.DataFrame(X_list)\n",
        "df_freshapples['target'] = y_list\n",
        "\n",
        "print(\"freshapples shape:\", df_freshapples.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2npMz_sO0Er6",
        "outputId": "0d7cbb85-64a9-4c53-ff52-5b8f55a1bb24"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "freshapples shape: (1697, 12289)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_all = pd.concat([\n",
        "    df_rottenbanana,\n",
        "    df_rottenoranges,\n",
        "    df_rottenapples,\n",
        "    df_freshbanana,\n",
        "    df_freshoranges,\n",
        "    df_freshapples\n",
        "], ignore_index=True)\n",
        "\n",
        "print(\"Merged DataFrame shape:\", df_all.shape)\n",
        "print(df_all['target'].value_counts())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bosmiLIr0Wd7",
        "outputId": "92d95ed4-e752-41ab-fad6-37a83c6fbee3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Merged DataFrame shape: (10913, 12289)\n",
            "target\n",
            "rottenapples     2342\n",
            "rottenbanana     2226\n",
            "freshapples      1697\n",
            "rottenoranges    1601\n",
            "freshbanana      1581\n",
            "freshoranges     1466\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Save to CSV\n",
        "df_all.to_csv(\"fruit_dataset.csv\", index=False)\n",
        "print(\"CSV saved as:\", \"fruit_dataset.csv\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Hqs_-9A6BkpV",
        "outputId": "0418d9e5-dbf6-40b3-9963-60e1c2adb0a9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CSV saved as: fruit_dataset.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "loading dataset"
      ],
      "metadata": {
        "id": "dL8zxlyZq0hv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "RMW9VmBqq0Sv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv('/content/fruit_dataset.csv')"
      ],
      "metadata": {
        "id": "m4vL0JnbFsQL"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "id": "cVjG80lnDy4O",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 255
        },
        "outputId": "a3bbf90f-9487-4dee-91b3-03f215540aab"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     0    1    2    3    4    5    6    7    8    9  ...  12279  12280  12281  \\\n",
              "0    0    0    0    0    0    0    0    0    0    0  ...      0      0      0   \n",
              "1  255  255  255  255  255  255  254  254  254  254  ...    254    254    254   \n",
              "2    0    0    0    0    0    0    0    0    0    0  ...      0      0      0   \n",
              "3    0    0    0    0    0    0    0    0    0    0  ...      0      0      0   \n",
              "4    0    0    0    0    0    0    0    0    0    0  ...      0      0      0   \n",
              "\n",
              "   12282  12283  12284  12285  12286  12287        target  \n",
              "0      0      0      0      0      0      0  rottenbanana  \n",
              "1    244    244    244    255    255    255  rottenbanana  \n",
              "2      0      0      0      0      0      0  rottenbanana  \n",
              "3      0      0      0      0      0      0  rottenbanana  \n",
              "4      0      0      0      0      0      0  rottenbanana  \n",
              "\n",
              "[5 rows x 12289 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7f735763-7b2d-45b8-b187-b8390373cc58\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "      <th>5</th>\n",
              "      <th>6</th>\n",
              "      <th>7</th>\n",
              "      <th>8</th>\n",
              "      <th>9</th>\n",
              "      <th>...</th>\n",
              "      <th>12279</th>\n",
              "      <th>12280</th>\n",
              "      <th>12281</th>\n",
              "      <th>12282</th>\n",
              "      <th>12283</th>\n",
              "      <th>12284</th>\n",
              "      <th>12285</th>\n",
              "      <th>12286</th>\n",
              "      <th>12287</th>\n",
              "      <th>target</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>rottenbanana</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>254</td>\n",
              "      <td>254</td>\n",
              "      <td>254</td>\n",
              "      <td>254</td>\n",
              "      <td>...</td>\n",
              "      <td>254</td>\n",
              "      <td>254</td>\n",
              "      <td>254</td>\n",
              "      <td>244</td>\n",
              "      <td>244</td>\n",
              "      <td>244</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>255</td>\n",
              "      <td>rottenbanana</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>rottenbanana</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>rottenbanana</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>rottenbanana</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 12289 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7f735763-7b2d-45b8-b187-b8390373cc58')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-7f735763-7b2d-45b8-b187-b8390373cc58 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-7f735763-7b2d-45b8-b187-b8390373cc58');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-4e00a366-d4f3-44b8-8fa7-389ea116336d\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-4e00a366-d4f3-44b8-8fa7-389ea116336d')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-4e00a366-d4f3-44b8-8fa7-389ea116336d button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df"
            }
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(df['target'].value_counts())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0fgwuVGcsIKa",
        "outputId": "ddc13cf6-c30a-443e-d105-54d2c2e3886a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "target\n",
            "rottenapples     2342\n",
            "rottenbanana     2226\n",
            "freshapples      1697\n",
            "rottenoranges    1601\n",
            "freshbanana      1581\n",
            "freshoranges     1466\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Features\n",
        "X = df.drop(\"target\", axis=1)\n",
        "# Target\n",
        "y = df[\"target\"]\n",
        "print(X.shape)\n",
        "print(y.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jmM8wZxtrFxz",
        "outputId": "47dd5d41-7f3e-4fef-c164-66cb82abaefc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(10913, 12288)\n",
            "(10913,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Encode target**"
      ],
      "metadata": {
        "id": "ww0O5SqiraKP"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import LabelEncoder\n",
        "\n",
        "# Create encoder\n",
        "le = LabelEncoder()\n",
        "\n",
        "# Fit on y and transform\n",
        "y_enc = le.fit_transform(y)\n",
        "\n",
        "# Check mapping\n",
        "label_mapping = dict(zip(le.classes_, le.transform(le.classes_)))\n",
        "print(\"Label mapping:\", label_mapping)\n",
        "\n",
        "print(\"Encoded y shape:\", y_enc.shape)\n",
        "print(\"First 10 encoded labels:\", y_enc[:10])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "b1uiyJxWrUP5",
        "outputId": "4c6e6529-e877-4057-a2a8-998c27db8275"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Label mapping: {'freshapples': np.int64(0), 'freshbanana': np.int64(1), 'freshoranges': np.int64(2), 'rottenapples': np.int64(3), 'rottenbanana': np.int64(4), 'rottenoranges': np.int64(5)}\n",
            "Encoded y shape: (10913,)\n",
            "First 10 encoded labels: [4 4 4 4 4 4 4 4 4 4]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Train-test split**"
      ],
      "metadata": {
        "id": "jVlICnkKrfGT"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y_enc, test_size=0.2, random_state=42, stratify=y_enc)\n",
        "print(X_train.shape)\n",
        "print(X_test.shape)\n",
        "print(y_train.shape)\n",
        "print(y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dN0vUxG8rdn4",
        "outputId": "c3f04af5-493f-4724-87e3-3896c03351af"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(8730, 12288)\n",
            "(2183, 12288)\n",
            "(8730,)\n",
            "(2183,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Scale the data and reduce dimensionality"
      ],
      "metadata": {
        "id": "5mG4wNmF3mJv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
        "#  Fit scaler on training data\n",
        "scaler = StandardScaler()\n",
        "X_train_scaled = scaler.fit_transform(X_train)\n",
        "X_test_scaled = scaler.transform(X_test)"
      ],
      "metadata": {
        "id": "JkMhNWcA3riD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.decomposition import PCA\n",
        "#  Fit PCA on training data\n",
        "pca = PCA(n_components=0.95)\n",
        "X_train = pca.fit_transform(X_train_scaled)\n",
        "X_test = pca.transform(X_test_scaled)"
      ],
      "metadata": {
        "id": "uqETOPY_4Al0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Save train set\n",
        "df_train = pd.DataFrame(X_train)\n",
        "df_train[\"target\"] = y_train\n",
        "df_train.to_csv(\"X_train_pca.csv\", index=False)\n",
        "\n",
        "# Save test set\n",
        "df_test = pd.DataFrame(X_test)\n",
        "df_test[\"target\"] = y_test\n",
        "df_test.to_csv(\"X_test_pca.csv\", index=False)\n",
        "\n",
        "print(\"PCA-transformed train & test saved to CSV\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qH5JIDWy9SpQ",
        "outputId": "a37870ff-ce42-40e4-fc0c-8d749f49798e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "PCA-transformed train & test saved to CSV\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ML utilities\n",
        "from sklearn.pipeline import Pipeline\n",
        "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
        "\n",
        "# Classifiers\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "from sklearn.naive_bayes import GaussianNB\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.svm import SVC\n",
        "import xgboost as xgb"
      ],
      "metadata": {
        "id": "OnCnSxe_rsIf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "KNN"
      ],
      "metadata": {
        "id": "NgBQ3EYj2ZNw"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "knn = KNeighborsClassifier(n_neighbors=5)\n",
        "knn.fit(X_train, y_train)\n",
        "y_pred = knn.predict(X_test)\n",
        "\n",
        "print(\"=== KNN ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X4exR8G32Xb8",
        "outputId": "153022d2-bc2e-47d6-f7fb-143ddb25e8dc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== KNN ===\n",
            "Accuracy: 0.7998167659184608\n",
            "Confusion Matrix:\n",
            " [[288   0  10  42   0   0]\n",
            " [  5 288   2  12   3   6]\n",
            " [  5   9 262  14   0   3]\n",
            " [ 36   1  51 374   0   7]\n",
            " [  5  37   2  51 340  10]\n",
            " [ 10  13  34  69   0 194]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.83      0.85      0.84       340\n",
            "           1       0.83      0.91      0.87       316\n",
            "           2       0.73      0.89      0.80       293\n",
            "           3       0.67      0.80      0.73       469\n",
            "           4       0.99      0.76      0.86       445\n",
            "           5       0.88      0.61      0.72       320\n",
            "\n",
            "    accuracy                           0.80      2183\n",
            "   macro avg       0.82      0.80      0.80      2183\n",
            "weighted avg       0.82      0.80      0.80      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Naive Bayes"
      ],
      "metadata": {
        "id": "eFmZGDQV8cna"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "nb = GaussianNB()\n",
        "nb.fit(X_train, y_train)\n",
        "y_pred = nb.predict(X_test)\n",
        "\n",
        "print(\"=== Naive Bayes ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "upieyjX62ck2",
        "outputId": "87170015-b901-42df-eda0-f468d8105021"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== Naive Bayes ===\n",
            "Accuracy: 0.5451213925790197\n",
            "Confusion Matrix:\n",
            " [[121  11   3 144  51  10]\n",
            " [  5 143   7  27  49  85]\n",
            " [  8  33 111 105  27   9]\n",
            " [ 62  21  16 336  14  20]\n",
            " [ 32  82   0  16 298  17]\n",
            " [ 16  24  16  60  23 181]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.50      0.36      0.41       340\n",
            "           1       0.46      0.45      0.45       316\n",
            "           2       0.73      0.38      0.50       293\n",
            "           3       0.49      0.72      0.58       469\n",
            "           4       0.65      0.67      0.66       445\n",
            "           5       0.56      0.57      0.56       320\n",
            "\n",
            "    accuracy                           0.55      2183\n",
            "   macro avg       0.56      0.52      0.53      2183\n",
            "weighted avg       0.56      0.55      0.54      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Decision Tree"
      ],
      "metadata": {
        "id": "D9Pzm77r8kin"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "dt = DecisionTreeClassifier(random_state=42)\n",
        "dt.fit(X_train, y_train)\n",
        "y_pred = dt.predict(X_test)\n",
        "\n",
        "print(\"=== Decision Tree ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AnVfOKH_8f9B",
        "outputId": "f3cfd65c-695d-4c23-b685-a704fc29e2f0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== Decision Tree ===\n",
            "Accuracy: 0.6775080164910673\n",
            "Confusion Matrix:\n",
            " [[239   7   9  54  10  21]\n",
            " [  6 255  16  11  14  14]\n",
            " [ 25  10 181  34   3  40]\n",
            " [ 58  10  43 279  21  58]\n",
            " [ 12  13   6  28 343  43]\n",
            " [ 22  13  20  60  23 182]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.66      0.70      0.68       340\n",
            "           1       0.83      0.81      0.82       316\n",
            "           2       0.66      0.62      0.64       293\n",
            "           3       0.60      0.59      0.60       469\n",
            "           4       0.83      0.77      0.80       445\n",
            "           5       0.51      0.57      0.54       320\n",
            "\n",
            "    accuracy                           0.68      2183\n",
            "   macro avg       0.68      0.68      0.68      2183\n",
            "weighted avg       0.68      0.68      0.68      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Random Forest"
      ],
      "metadata": {
        "id": "3TGFtiKF8ywK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "rf = RandomForestClassifier(random_state=42)\n",
        "rf.fit(X_train, y_train)\n",
        "y_pred = rf.predict(X_test)\n",
        "\n",
        "print(\"=== Random Forest ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EazoOQyS8ySB",
        "outputId": "f72620ea-4ed4-424a-a857-d32332b61c85"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== Random Forest ===\n",
            "Accuracy: 0.8176820888685296\n",
            "Confusion Matrix:\n",
            " [[262   1   6  59   6   6]\n",
            " [  5 271   2  11  20   7]\n",
            " [  4   3 222  43  16   5]\n",
            " [ 22   1  16 407  15   8]\n",
            " [  1   5   0   6 425   8]\n",
            " [ 10  14  11  65  22 198]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.86      0.77      0.81       340\n",
            "           1       0.92      0.86      0.89       316\n",
            "           2       0.86      0.76      0.81       293\n",
            "           3       0.69      0.87      0.77       469\n",
            "           4       0.84      0.96      0.90       445\n",
            "           5       0.85      0.62      0.72       320\n",
            "\n",
            "    accuracy                           0.82      2183\n",
            "   macro avg       0.84      0.80      0.81      2183\n",
            "weighted avg       0.83      0.82      0.82      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "AdaBoost"
      ],
      "metadata": {
        "id": "UYzYo4Kc9GaZ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "ada = AdaBoostClassifier(random_state=42)\n",
        "ada.fit(X_train, y_train)\n",
        "y_pred = ada.predict(X_test)\n",
        "\n",
        "print(\"=== AdaBoost ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6ECM3jrs8nYX",
        "outputId": "dd4cb104-6bd1-4d71-beea-c1b22d1c7ee4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== AdaBoost ===\n",
            "Accuracy: 0.5794777828676134\n",
            "Confusion Matrix:\n",
            " [[ 88  11  15 194  13  19]\n",
            " [  8 233  20   7   9  39]\n",
            " [  9   4 165  93   0  22]\n",
            " [ 43   6  27 339  19  35]\n",
            " [ 22  24   2  39 327  31]\n",
            " [ 25  18  39  99  26 113]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.45      0.26      0.33       340\n",
            "           1       0.79      0.74      0.76       316\n",
            "           2       0.62      0.56      0.59       293\n",
            "           3       0.44      0.72      0.55       469\n",
            "           4       0.83      0.73      0.78       445\n",
            "           5       0.44      0.35      0.39       320\n",
            "\n",
            "    accuracy                           0.58      2183\n",
            "   macro avg       0.59      0.56      0.57      2183\n",
            "weighted avg       0.59      0.58      0.57      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "took a little more time"
      ],
      "metadata": {
        "id": "9RjtfuMG9Ybb"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Gradient Boosting"
      ],
      "metadata": {
        "id": "YVQ8uldm9dsA"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "gb = GradientBoostingClassifier(random_state=42)\n",
        "gb.fit(X_train, y_train)\n",
        "y_pred = gb.predict(X_test)\n",
        "\n",
        "print(\"=== Gradient Boosting ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 391
        },
        "id": "0JEKc1pE9LtT",
        "outputId": "b1cd2022-c1fd-4dd1-8bc6-cffddee55110"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m/tmp/ipython-input-707962318.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mgb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mGradientBoostingClassifier\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m42\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"=== Gradient Boosting ===\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/base.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1387\u001b[0m                 )\n\u001b[1;32m   1388\u001b[0m             ):\n\u001b[0;32m-> 1389\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mfit_method\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mestimator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1390\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1391\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/ensemble/_gb.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight, monitor)\u001b[0m\n\u001b[1;32m    785\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    786\u001b[0m         \u001b[0;31m# fit the boosting stages\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 787\u001b[0;31m         n_stages = self._fit_stages(\n\u001b[0m\u001b[1;32m    788\u001b[0m             \u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    789\u001b[0m             \u001b[0my_train\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/ensemble/_gb.py\u001b[0m in \u001b[0;36m_fit_stages\u001b[0;34m(self, X, y, raw_predictions, sample_weight, random_state, X_val, y_val, sample_weight_val, begin_at_stage, monitor)\u001b[0m\n\u001b[1;32m    881\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    882\u001b[0m             \u001b[0;31m# fit next stage of trees\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 883\u001b[0;31m             raw_predictions = self._fit_stage(\n\u001b[0m\u001b[1;32m    884\u001b[0m                 \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    885\u001b[0m                 \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/ensemble/_gb.py\u001b[0m in \u001b[0;36m_fit_stage\u001b[0;34m(self, i, X, y, raw_predictions, sample_weight, sample_mask, random_state, X_csc, X_csr)\u001b[0m\n\u001b[1;32m    487\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    488\u001b[0m             \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mX_csc\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mX_csc\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 489\u001b[0;31m             tree.fit(\n\u001b[0m\u001b[1;32m    490\u001b[0m                 \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mneg_g_view\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheck_input\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    491\u001b[0m             )\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/base.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1387\u001b[0m                 )\n\u001b[1;32m   1388\u001b[0m             ):\n\u001b[0;32m-> 1389\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mfit_method\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mestimator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1390\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1391\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/tree/_classes.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight, check_input)\u001b[0m\n\u001b[1;32m   1402\u001b[0m         \"\"\"\n\u001b[1;32m   1403\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1404\u001b[0;31m         super()._fit(\n\u001b[0m\u001b[1;32m   1405\u001b[0m             \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1406\u001b[0m             \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/sklearn/tree/_classes.py\u001b[0m in \u001b[0;36m_fit\u001b[0;34m(self, X, y, sample_weight, check_input, missing_values_in_feature_mask)\u001b[0m\n\u001b[1;32m    470\u001b[0m             )\n\u001b[1;32m    471\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 472\u001b[0;31m         \u001b[0mbuilder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuild\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtree_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmissing_values_in_feature_mask\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    473\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    474\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_outputs_\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mis_classifier\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "took so much more time"
      ],
      "metadata": {
        "id": "-jU-m4XN9uyr"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "XGBoost"
      ],
      "metadata": {
        "id": "DcCzq53-9nZP"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_model = xgb.XGBClassifier(n_estimators=100, eval_metric='mlogloss', use_label_encoder=False, random_state=42)\n",
        "xgb_model.fit(X_train, y_train)\n",
        "y_pred = xgb_model.predict(X_test)\n",
        "\n",
        "print(\"=== XGBoost ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 480
        },
        "id": "FKIx7AtR9tE1",
        "outputId": "716685f3-5452-409b-fc32-5da59128621a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/xgboost/training.py:183: UserWarning: [09:12:11] WARNING: /workspace/src/learner.cc:738: \n",
            "Parameters: { \"use_label_encoder\" } are not used.\n",
            "\n",
            "  bst.update(dtrain, iteration=i, fobj=obj)\n"
          ]
        },
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m/tmp/ipython-input-417072136.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mxgb_model\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mxgb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mXGBClassifier\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_estimators\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0meval_metric\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'mlogloss'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0muse_label_encoder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrandom_state\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m42\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mxgb_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mxgb_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"=== XGBoost ===\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/xgboost/core.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    727\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marg\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    728\u001b[0m                 \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0marg\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 729\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    730\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    731\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0minner_f\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/xgboost/sklearn.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight, base_margin, eval_set, verbose, xgb_model, sample_weight_eval_set, base_margin_eval_set, feature_weights)\u001b[0m\n\u001b[1;32m   1681\u001b[0m             )\n\u001b[1;32m   1682\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1683\u001b[0;31m             self._Booster = train(\n\u001b[0m\u001b[1;32m   1684\u001b[0m                 \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1685\u001b[0m                 \u001b[0mtrain_dmatrix\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/xgboost/core.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    727\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marg\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    728\u001b[0m                 \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mk\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0marg\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 729\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    730\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    731\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0minner_f\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/xgboost/training.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(params, dtrain, num_boost_round, evals, obj, maximize, early_stopping_rounds, evals_result, verbose_eval, xgb_model, callbacks, custom_metric)\u001b[0m\n\u001b[1;32m    181\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcb_container\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbefore_iteration\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbst\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mevals\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    182\u001b[0m             \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 183\u001b[0;31m         \u001b[0mbst\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdtrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0miteration\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfobj\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    184\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mcb_container\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mafter_iteration\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbst\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mevals\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    185\u001b[0m             \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/xgboost/core.py\u001b[0m in \u001b[0;36mupdate\u001b[0;34m(self, dtrain, iteration, fobj)\u001b[0m\n\u001b[1;32m   2245\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mfobj\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2246\u001b[0m             _check_call(\n\u001b[0;32m-> 2247\u001b[0;31m                 _LIB.XGBoosterUpdateOneIter(\n\u001b[0m\u001b[1;32m   2248\u001b[0m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mctypes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc_int\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miteration\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtrain\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2249\u001b[0m                 )\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Logistic Regression"
      ],
      "metadata": {
        "id": "cVF6t_td9oZ0"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "lr = LogisticRegression(max_iter=1000, random_state=42)\n",
        "lr.fit(X_train, y_train)\n",
        "y_pred = lr.predict(X_test)\n",
        "\n",
        "print(\"=== Logistic Regression ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3Hyrqs5V9trq",
        "outputId": "b11970af-c5a8-4b1c-f2d8-949add167423"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== Logistic Regression ===\n",
            "Accuracy: 0.7480531378836464\n",
            "Confusion Matrix:\n",
            " [[227   9   6  67   2  29]\n",
            " [  7 283   3   3   7  13]\n",
            " [ 13   2 238  22   1  17]\n",
            " [ 68   3  32 320  12  34]\n",
            " [ 13  11   1  14 374  32]\n",
            " [ 25   8  14  55  27 191]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.64      0.67      0.66       340\n",
            "           1       0.90      0.90      0.90       316\n",
            "           2       0.81      0.81      0.81       293\n",
            "           3       0.67      0.68      0.67       469\n",
            "           4       0.88      0.84      0.86       445\n",
            "           5       0.60      0.60      0.60       320\n",
            "\n",
            "    accuracy                           0.75      2183\n",
            "   macro avg       0.75      0.75      0.75      2183\n",
            "weighted avg       0.75      0.75      0.75      2183\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/sklearn/linear_model/_logistic.py:465: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
            "STOP: TOTAL NO. OF ITERATIONS REACHED LIMIT.\n",
            "\n",
            "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
            "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
            "Please also refer to the documentation for alternative solver options:\n",
            "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
            "  n_iter_i = _check_optimize_result(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "SVC"
      ],
      "metadata": {
        "id": "Ygj8VQJc9qix"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "svc = SVC(random_state=42)\n",
        "svc.fit(X_train, y_train)\n",
        "y_pred = svc.predict(X_test)\n",
        "\n",
        "print(\"=== SVC ===\")\n",
        "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
        "print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YNUh055l9hcj",
        "outputId": "d134b0bb-7ed9-4880-ad85-4e82936d44ea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== SVC ===\n",
            "Accuracy: 0.9060925332111773\n",
            "Confusion Matrix:\n",
            " [[303   0   0  31   1   5]\n",
            " [  7 304   0   1   3   1]\n",
            " [  4   2 269  13   0   5]\n",
            " [  7   1  15 433   5   8]\n",
            " [  2   1   0   6 428   8]\n",
            " [  4   0  11  59   5 241]]\n",
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.93      0.89      0.91       340\n",
            "           1       0.99      0.96      0.97       316\n",
            "           2       0.91      0.92      0.91       293\n",
            "           3       0.80      0.92      0.86       469\n",
            "           4       0.97      0.96      0.97       445\n",
            "           5       0.90      0.75      0.82       320\n",
            "\n",
            "    accuracy                           0.91      2183\n",
            "   macro avg       0.92      0.90      0.91      2183\n",
            "weighted avg       0.91      0.91      0.91      2183\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "✅ SVC (Support Vector Classifier) is clearly the winner here (91% accuracy) — this is expected since:\n",
        "\n",
        "You scaled the data ✅\n",
        "\n",
        "You did PCA (reduces noise & keeps variance) ✅\n",
        "\n",
        "SVC works very well on high-dimensional but dense feature spaces (like PCA image features).\n",
        "\n",
        "⚡ Random Forest also did well (82%), but SVC is significantly better."
      ],
      "metadata": {
        "id": "i6zF3_gaAH7D"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pickle\n",
        "\n",
        "# ---- Save the trained SVC model ----\n",
        "with open(\"svc_model.pkl\", \"wb\") as f:\n",
        "    pickle.dump(svc, f)\n",
        "\n",
        "print(\"SVC model saved as svc_model.pkl\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7uFLb8WC_697",
        "outputId": "5286a2d1-de14-43fa-ea67-06b590bea87d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "SVC model saved as svc_model.pkl\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "fdPko5vsBlUv"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}