{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 157,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gMz11RCXQmcK",
        "outputId": "e28e8f62-4518-46fc-ff82-065239ddba85"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: opendatasets in /usr/local/lib/python3.12/dist-packages (0.1.22)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from opendatasets) (4.67.1)\n",
            "Requirement already satisfied: kaggle in /usr/local/lib/python3.12/dist-packages (from opendatasets) (1.7.4.5)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from opendatasets) (8.2.1)\n",
            "Requirement already satisfied: bleach in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (6.2.0)\n",
            "Requirement already satisfied: certifi>=14.05.14 in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (2025.8.3)\n",
            "Requirement already satisfied: charset-normalizer in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (3.4.3)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (3.10)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (5.29.5)\n",
            "Requirement already satisfied: python-dateutil>=2.5.3 in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (2.9.0.post0)\n",
            "Requirement already satisfied: python-slugify in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (8.0.4)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (2.32.4)\n",
            "Requirement already satisfied: setuptools>=21.0.0 in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (75.2.0)\n",
            "Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (1.17.0)\n",
            "Requirement already satisfied: text-unidecode in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (1.3)\n",
            "Requirement already satisfied: urllib3>=1.15.1 in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (2.5.0)\n",
            "Requirement already satisfied: webencodings in /usr/local/lib/python3.12/dist-packages (from kaggle->opendatasets) (0.5.1)\n"
          ]
        }
      ],
      "source": [
        "!pip install opendatasets"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#importing required libraries\n",
        "import os\n",
        "import opendatasets as od\n",
        "import pandas as pd\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "zl1WW0LDQ1H2"
      },
      "execution_count": 158,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#download dataset\n",
        "od.download(\"https://www.kaggle.com/datasets/emrekaany/google-daily-stock-prices-2004-today\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jsB9_VmxQ3Ck",
        "outputId": "7bd340ce-882b-46ee-b9ee-a4df32b40985"
      },
      "execution_count": 159,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Skipping, found downloaded files in \"./google-daily-stock-prices-2004-today\" (use force=True to force download)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "os.listdir(\"google-daily-stock-prices-2004-today\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SeT8ay40Q7s0",
        "outputId": "afef4417-1c73-42f0-d15b-ad40fa1f2fc5"
      },
      "execution_count": 160,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['googl_daily_prices.csv']"
            ]
          },
          "metadata": {},
          "execution_count": 160
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "raw_df = pd.read_csv(\"/content/google-daily-stock-prices-2004-today/googl_daily_prices.csv\")"
      ],
      "metadata": {
        "id": "4-Yq5PCVRIXI"
      },
      "execution_count": 161,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "raw_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "CRH6s-X0RPNO",
        "outputId": "4896b3f7-af6a-4081-a6c9-ad6cd8f5b841"
      },
      "execution_count": 162,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         date  1. open   2. high   3. low  4. close   5. volume\n",
              "0  2025-09-30  242.810  243.2900  239.245    243.10  34724346.0\n",
              "1  2025-09-29  247.850  251.1486  242.770    244.05  32505777.0\n",
              "2  2025-09-26  247.065  249.4200  245.970    246.54  18503194.0\n",
              "3  2025-09-25  244.400  246.4900  240.740    245.79  31020383.0\n",
              "4  2025-09-24  251.660  252.3501  246.440    247.14  28201003.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c093cc38-ba3f-4482-9d4e-27782311c74a\" 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>date</th>\n",
              "      <th>1. open</th>\n",
              "      <th>2. high</th>\n",
              "      <th>3. low</th>\n",
              "      <th>4. close</th>\n",
              "      <th>5. volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2025-09-30</td>\n",
              "      <td>242.810</td>\n",
              "      <td>243.2900</td>\n",
              "      <td>239.245</td>\n",
              "      <td>243.10</td>\n",
              "      <td>34724346.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2025-09-29</td>\n",
              "      <td>247.850</td>\n",
              "      <td>251.1486</td>\n",
              "      <td>242.770</td>\n",
              "      <td>244.05</td>\n",
              "      <td>32505777.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2025-09-26</td>\n",
              "      <td>247.065</td>\n",
              "      <td>249.4200</td>\n",
              "      <td>245.970</td>\n",
              "      <td>246.54</td>\n",
              "      <td>18503194.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2025-09-25</td>\n",
              "      <td>244.400</td>\n",
              "      <td>246.4900</td>\n",
              "      <td>240.740</td>\n",
              "      <td>245.79</td>\n",
              "      <td>31020383.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2025-09-24</td>\n",
              "      <td>251.660</td>\n",
              "      <td>252.3501</td>\n",
              "      <td>246.440</td>\n",
              "      <td>247.14</td>\n",
              "      <td>28201003.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c093cc38-ba3f-4482-9d4e-27782311c74a')\"\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-c093cc38-ba3f-4482-9d4e-27782311c74a 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-c093cc38-ba3f-4482-9d4e-27782311c74a');\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-2582d95f-0015-4b3a-acf0-6b7d28ed75fd\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-2582d95f-0015-4b3a-acf0-6b7d28ed75fd')\"\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-2582d95f-0015-4b3a-acf0-6b7d28ed75fd 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": "raw_df",
              "summary": "{\n  \"name\": \"raw_df\",\n  \"rows\": 5313,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 5313,\n        \"samples\": [\n          \"2021-08-30\",\n          \"2010-05-10\",\n          \"2015-06-08\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"1. open\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 612.1734512006673,\n        \"min\": 85.4,\n        \"max\": 3025.0,\n        \"num_unique_values\": 5098,\n        \"samples\": [\n          2902.94,\n          1440.0,\n          2857.38\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"2. high\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 618.2806692169981,\n        \"min\": 86.52,\n        \"max\": 3030.9315,\n        \"num_unique_values\": 5098,\n        \"samples\": [\n          2925.075,\n          1442.32,\n          2743.29\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"3. low\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 605.6491240554433,\n        \"min\": 83.34,\n        \"max\": 2977.98,\n        \"num_unique_values\": 5151,\n        \"samples\": [\n          1105.15,\n          1347.32,\n          537.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"4. close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 612.0915219846729,\n        \"min\": 83.43,\n        \"max\": 2996.77,\n        \"num_unique_values\": 5169,\n        \"samples\": [\n          1106.5,\n          950.44,\n          1422.86\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"5. volume\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 12616124.474814428,\n        \"min\": 465638.0,\n        \"max\": 127747554.0,\n        \"num_unique_values\": 5285,\n        \"samples\": [\n          2964489.0,\n          4101200.0,\n          29130102.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 162
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "raw_df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hbTXK0NeRRFt",
        "outputId": "dcff175a-074b-47f3-d63d-878ad94f88c2"
      },
      "execution_count": 163,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 5313 entries, 0 to 5312\n",
            "Data columns (total 6 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   date       5313 non-null   object \n",
            " 1   1. open    5313 non-null   float64\n",
            " 2   2. high    5313 non-null   float64\n",
            " 3   3. low     5313 non-null   float64\n",
            " 4   4. close   5313 non-null   float64\n",
            " 5   5. volume  5313 non-null   float64\n",
            "dtypes: float64(5), object(1)\n",
            "memory usage: 249.2+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#rename column names\n",
        "raw_df.columns = raw_df.columns.str.replace(r'\\d+\\.\\s+', '', regex=True)\n",
        "display(raw_df.head())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "3Nm9EbGORWs_",
        "outputId": "cf0788d5-35ab-4d23-962e-727bea74b6ee"
      },
      "execution_count": 164,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "         date     open      high      low   close      volume\n",
              "0  2025-09-30  242.810  243.2900  239.245  243.10  34724346.0\n",
              "1  2025-09-29  247.850  251.1486  242.770  244.05  32505777.0\n",
              "2  2025-09-26  247.065  249.4200  245.970  246.54  18503194.0\n",
              "3  2025-09-25  244.400  246.4900  240.740  245.79  31020383.0\n",
              "4  2025-09-24  251.660  252.3501  246.440  247.14  28201003.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-90441c02-7742-4daa-86eb-4157e38af203\" 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>date</th>\n",
              "      <th>open</th>\n",
              "      <th>high</th>\n",
              "      <th>low</th>\n",
              "      <th>close</th>\n",
              "      <th>volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2025-09-30</td>\n",
              "      <td>242.810</td>\n",
              "      <td>243.2900</td>\n",
              "      <td>239.245</td>\n",
              "      <td>243.10</td>\n",
              "      <td>34724346.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2025-09-29</td>\n",
              "      <td>247.850</td>\n",
              "      <td>251.1486</td>\n",
              "      <td>242.770</td>\n",
              "      <td>244.05</td>\n",
              "      <td>32505777.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2025-09-26</td>\n",
              "      <td>247.065</td>\n",
              "      <td>249.4200</td>\n",
              "      <td>245.970</td>\n",
              "      <td>246.54</td>\n",
              "      <td>18503194.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2025-09-25</td>\n",
              "      <td>244.400</td>\n",
              "      <td>246.4900</td>\n",
              "      <td>240.740</td>\n",
              "      <td>245.79</td>\n",
              "      <td>31020383.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2025-09-24</td>\n",
              "      <td>251.660</td>\n",
              "      <td>252.3501</td>\n",
              "      <td>246.440</td>\n",
              "      <td>247.14</td>\n",
              "      <td>28201003.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-90441c02-7742-4daa-86eb-4157e38af203')\"\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-90441c02-7742-4daa-86eb-4157e38af203 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-90441c02-7742-4daa-86eb-4157e38af203');\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-d42d1ad5-b465-4a31-b5a5-e8e81ed94a00\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-d42d1ad5-b465-4a31-b5a5-e8e81ed94a00')\"\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-d42d1ad5-b465-4a31-b5a5-e8e81ed94a00 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",
              "summary": "{\n  \"name\": \"display(raw_df\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"2025-09-29\",\n          \"2025-09-24\",\n          \"2025-09-26\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"open\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.408195270227335,\n        \"min\": 242.81,\n        \"max\": 251.66,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          247.85,\n          251.66,\n          247.065\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"high\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.669504586180536,\n        \"min\": 243.29,\n        \"max\": 252.3501,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          251.1486,\n          252.3501,\n          249.42\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"low\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.15870147370719,\n        \"min\": 239.245,\n        \"max\": 246.44,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          242.77,\n          246.44,\n          245.97\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.7002146923256427,\n        \"min\": 243.1,\n        \"max\": 247.14,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          244.05,\n          247.14,\n          246.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"volume\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6323793.936636005,\n        \"min\": 18503194.0,\n        \"max\": 34724346.0,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          32505777.0,\n          28201003.0,\n          18503194.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "raw_df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eIQqWuNDRktE",
        "outputId": "97c4c0a8-da84-4c0f-d829-2a91c9a5f20e"
      },
      "execution_count": 165,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 5313 entries, 0 to 5312\n",
            "Data columns (total 6 columns):\n",
            " #   Column  Non-Null Count  Dtype  \n",
            "---  ------  --------------  -----  \n",
            " 0   date    5313 non-null   object \n",
            " 1   open    5313 non-null   float64\n",
            " 2   high    5313 non-null   float64\n",
            " 3   low     5313 non-null   float64\n",
            " 4   close   5313 non-null   float64\n",
            " 5   volume  5313 non-null   float64\n",
            "dtypes: float64(5), object(1)\n",
            "memory usage: 249.2+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#using MinMaxSclaler to slace column\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "\n",
        "scaler = MinMaxScaler()\n",
        "\n",
        "#columns to scale\n",
        "scale_cols = ['open', 'high', 'low', 'volume']\n",
        "\n",
        "#apply the scaler to the selected columns\n",
        "raw_df[scale_cols] = scaler.fit_transform(raw_df[scale_cols])\n",
        "\n",
        "display(raw_df.head())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "NlyQzKFsR7Qi",
        "outputId": "fdfb1f2e-b523-426a-beab-eb30e6c06645"
      },
      "execution_count": 166,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "         date      open      high       low   close    volume\n",
              "0  2025-09-30  0.053548  0.053243  0.053860  243.10  0.269156\n",
              "1  2025-09-29  0.055263  0.055912  0.055078  244.05  0.251726\n",
              "2  2025-09-26  0.054996  0.055325  0.056183  246.54  0.141713\n",
              "3  2025-09-25  0.054089  0.054330  0.054376  245.79  0.240056\n",
              "4  2025-09-24  0.056559  0.056320  0.056346  247.14  0.217905"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-27513fe5-65bd-4d9a-b915-d09ab71583e5\" 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>date</th>\n",
              "      <th>open</th>\n",
              "      <th>high</th>\n",
              "      <th>low</th>\n",
              "      <th>close</th>\n",
              "      <th>volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2025-09-30</td>\n",
              "      <td>0.053548</td>\n",
              "      <td>0.053243</td>\n",
              "      <td>0.053860</td>\n",
              "      <td>243.10</td>\n",
              "      <td>0.269156</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2025-09-29</td>\n",
              "      <td>0.055263</td>\n",
              "      <td>0.055912</td>\n",
              "      <td>0.055078</td>\n",
              "      <td>244.05</td>\n",
              "      <td>0.251726</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2025-09-26</td>\n",
              "      <td>0.054996</td>\n",
              "      <td>0.055325</td>\n",
              "      <td>0.056183</td>\n",
              "      <td>246.54</td>\n",
              "      <td>0.141713</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2025-09-25</td>\n",
              "      <td>0.054089</td>\n",
              "      <td>0.054330</td>\n",
              "      <td>0.054376</td>\n",
              "      <td>245.79</td>\n",
              "      <td>0.240056</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2025-09-24</td>\n",
              "      <td>0.056559</td>\n",
              "      <td>0.056320</td>\n",
              "      <td>0.056346</td>\n",
              "      <td>247.14</td>\n",
              "      <td>0.217905</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-27513fe5-65bd-4d9a-b915-d09ab71583e5')\"\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-27513fe5-65bd-4d9a-b915-d09ab71583e5 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-27513fe5-65bd-4d9a-b915-d09ab71583e5');\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-8c9e1918-5f7b-4310-a63f-40ab3ca3b792\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-8c9e1918-5f7b-4310-a63f-40ab3ca3b792')\"\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-8c9e1918-5f7b-4310-a63f-40ab3ca3b792 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",
              "summary": "{\n  \"name\": \"display(raw_df\",\n  \"rows\": 5,\n  \"fields\": [\n    {\n      \"column\": \"date\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"2025-09-29\",\n          \"2025-09-24\",\n          \"2025-09-26\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"open\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.001159407834476571,\n        \"min\": 0.05354810178255545,\n        \"max\": 0.056558715471492715,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.05526262076472989,\n          0.056558715471492715,\n          0.054995577629609466\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"high\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0012462607846017927,\n        \"min\": 0.05324323723093731,\n        \"max\": 0.056320286753397064,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.05591222558395795,\n          0.056320286753397064,\n          0.055325147317214315\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"low\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0010912242882386725,\n        \"min\": 0.05385989276732167,\n        \"max\": 0.05634552137744245,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.05507766077992428,\n          0.05634552137744245,\n          0.05618315230909543\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.7002146923256427,\n        \"min\": 243.1,\n        \"max\": 247.14,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          244.05,\n          247.14,\n          246.54\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"volume\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.0496833653622562,\n        \"min\": 0.14171342298147055,\n        \"max\": 0.2691561305535344,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.25172577540394664,\n          0.21790499288209964,\n          0.14171342298147055\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "#spliting train & test df\n",
        "X_train, X_test = train_test_split(raw_df, test_size=0.2, random_state=42)\n"
      ],
      "metadata": {
        "id": "qE759hHiTbgY"
      },
      "execution_count": 167,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#initializing target column\n",
        "train_target_col = X_train['close']\n",
        "test_target_col = X_test['close']"
      ],
      "metadata": {
        "id": "kHIYVx0zRuqw"
      },
      "execution_count": 168,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train = X_train.drop('date', axis=1)\n",
        "X_train = X_train.drop('close', axis=1)\n",
        "X_test = X_test.drop('date', axis=1)\n",
        "X_test = X_test.drop('close', axis=1)"
      ],
      "metadata": {
        "id": "5QLRQu9zUkdE"
      },
      "execution_count": 169,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from xgboost import XGBRegressor"
      ],
      "metadata": {
        "id": "Xr4-_Ma_UmMl"
      },
      "execution_count": 170,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#creating a function that evaluate the model\n",
        "from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error\n",
        "\n",
        "def xgb_model_evaluation(df, target_col):\n",
        "\n",
        "  # Make predictions on the test set\n",
        "  predictions = xgb_model.predict(df)\n",
        "\n",
        "  # Calculate RMSE\n",
        "  rmse = np.sqrt(mean_squared_error(target_col, predictions))\n",
        "  print(f\"RMSE: {rmse}\")\n",
        "\n",
        "  # Calculate MAPE\n",
        "  mape = mean_absolute_percentage_error(target_col, predictions)\n",
        "  print(f\"MAPE: {mape}\")"
      ],
      "metadata": {
        "id": "lQWEfUtfYu8V"
      },
      "execution_count": 171,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%%time\n",
        "xgb_model = XGBRegressor(n_estimators=1500, learning_rate=0.01, n_jobs=25, random_state=47, max_depth=16).fit(X_train, train_target_col)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7rj5tIMZVaUT",
        "outputId": "144efc80-4833-4752-d9a5-13566a4f1d3f"
      },
      "execution_count": 172,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CPU times: user 48.1 s, sys: 476 ms, total: 48.6 s\n",
            "Wall time: 36.1 s\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_model_evaluation(X_train, train_target_col)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NlhOaQxSZVH0",
        "outputId": "69cf251d-1dd3-44ce-e467-bec7a4378a83"
      },
      "execution_count": 173,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RMSE: 0.8930120580153202\n",
            "MAPE: 0.0009947761695732408\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_model_evaluation(X_test, test_target_col)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wnmCmaVpZXJ8",
        "outputId": "8f89c10f-2789-41ff-94d8-5bb6ba27a666"
      },
      "execution_count": 174,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RMSE: 11.429648677781845\n",
            "MAPE: 0.007749489179507017\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import joblib\n",
        "\n",
        "# Define the filename for the model\n",
        "model_filename = 'xgb_regressor_model.joblib'\n",
        "\n",
        "# Save the model to the file\n",
        "joblib.dump(xgb_model, model_filename)\n",
        "\n",
        "print(f\"Model saved to {model_filename}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "heGYy9dbqrKV",
        "outputId": "09c92760-379a-4b2c-ea6b-ff2fccf020c5"
      },
      "execution_count": 175,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model saved to xgb_regressor_model.joblib\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "2cdNDOOxpx6j"
      },
      "execution_count": 175,
      "outputs": []
    }
  ]
}