{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "BfC7dn-qjJrM"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "DTQ6BsJasE2Z"
      },
      "outputs": [],
      "source": [
        "fpt = pd.read_csv('FPT.csv')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LjGL4yrsAXR9"
      },
      "source": [
        "#1. Xử lý dữ liệu"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "ypZlj49yjTx3",
        "outputId": "ece9c0f5-0be0-4fe7-a678-fafc023ccc89"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "summary": "{\n  \"name\": \"fpt\",\n  \"rows\": 97406,\n  \"fields\": [\n    {\n      \"column\": \"Ticker\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 1,\n        \"samples\": [\n          \"FPT\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Date/Time\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 97406,\n        \"samples\": [\n          \"9/16/2020 13:28\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Open\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.359803058765985,\n        \"min\": 30.25,\n        \"max\": 58.4,\n        \"num_unique_values\": 802,\n        \"samples\": [\n          37.68\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"High\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.364950227705635,\n        \"min\": 30.25,\n        \"max\": 58.5,\n        \"num_unique_values\": 800,\n        \"samples\": [\n          45.35\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Low\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.3542454835986675,\n        \"min\": 30.22,\n        \"max\": 58.4,\n        \"num_unique_values\": 802,\n        \"samples\": [\n          37.75\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.359798823150364,\n        \"min\": 30.25,\n        \"max\": 58.4,\n        \"num_unique_values\": 802,\n        \"samples\": [\n          37.75\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Volume\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17532,\n        \"min\": 10,\n        \"max\": 1255930,\n        \"num_unique_values\": 6221,\n        \"samples\": [\n          46050\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Open Interest\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 0,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
              "type": "dataframe",
              "variable_name": "fpt"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-c89980d9-5ff8-4458-aaa9-9f02a025e097\" 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>Ticker</th>\n",
              "      <th>Date/Time</th>\n",
              "      <th>Open</th>\n",
              "      <th>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Close</th>\n",
              "      <th>Volume</th>\n",
              "      <th>Open Interest</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/25/2018 9:15</td>\n",
              "      <td>30.89</td>\n",
              "      <td>30.89</td>\n",
              "      <td>30.89</td>\n",
              "      <td>30.89</td>\n",
              "      <td>35410</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/25/2018 9:16</td>\n",
              "      <td>30.81</td>\n",
              "      <td>30.81</td>\n",
              "      <td>30.81</td>\n",
              "      <td>30.81</td>\n",
              "      <td>190</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/25/2018 9:17</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.81</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>1120</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/25/2018 9:18</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>2120</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/25/2018 9:19</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.74</td>\n",
              "      <td>22500</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97401</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/22/2020 14:24</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>27470</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97402</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/22/2020 14:25</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>14820</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97403</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/22/2020 14:26</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>58.20</td>\n",
              "      <td>500</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97404</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/22/2020 14:29</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>2500</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97405</th>\n",
              "      <td>FPT</td>\n",
              "      <td>12/22/2020 14:46</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>58.10</td>\n",
              "      <td>11170</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>97406 rows × 8 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-c89980d9-5ff8-4458-aaa9-9f02a025e097')\"\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-c89980d9-5ff8-4458-aaa9-9f02a025e097 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-c89980d9-5ff8-4458-aaa9-9f02a025e097');\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-445bea5c-208b-419b-bdb4-93cae9ecbfcb\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-445bea5c-208b-419b-bdb4-93cae9ecbfcb')\"\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-445bea5c-208b-419b-bdb4-93cae9ecbfcb button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_08427811-5d37-4e02-9e9f-6bc5b59eae32\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('fpt')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_08427811-5d37-4e02-9e9f-6bc5b59eae32 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('fpt');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "      Ticker         Date/Time   Open   High    Low  Close  Volume  \\\n",
              "0        FPT   12/25/2018 9:15  30.89  30.89  30.89  30.89   35410   \n",
              "1        FPT   12/25/2018 9:16  30.81  30.81  30.81  30.81     190   \n",
              "2        FPT   12/25/2018 9:17  30.74  30.81  30.74  30.74    1120   \n",
              "3        FPT   12/25/2018 9:18  30.74  30.74  30.74  30.74    2120   \n",
              "4        FPT   12/25/2018 9:19  30.74  30.74  30.74  30.74   22500   \n",
              "...      ...               ...    ...    ...    ...    ...     ...   \n",
              "97401    FPT  12/22/2020 14:24  58.20  58.20  58.20  58.20   27470   \n",
              "97402    FPT  12/22/2020 14:25  58.20  58.20  58.20  58.20   14820   \n",
              "97403    FPT  12/22/2020 14:26  58.20  58.20  58.20  58.20     500   \n",
              "97404    FPT  12/22/2020 14:29  58.10  58.10  58.10  58.10    2500   \n",
              "97405    FPT  12/22/2020 14:46  58.10  58.10  58.10  58.10   11170   \n",
              "\n",
              "       Open Interest  \n",
              "0                  0  \n",
              "1                  0  \n",
              "2                  0  \n",
              "3                  0  \n",
              "4                  0  \n",
              "...              ...  \n",
              "97401              0  \n",
              "97402              0  \n",
              "97403              0  \n",
              "97404              0  \n",
              "97405              0  \n",
              "\n",
              "[97406 rows x 8 columns]"
            ]
          },
          "execution_count": 339,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "fpt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "l_LX7XlbF1cS",
        "outputId": "4f1d3d80-f8bb-4c9b-a32d-e27b3f79f120"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "summary": "{\n  \"name\": \"fpt\",\n  \"rows\": 97406,\n  \"fields\": [\n    {\n      \"column\": \"Date/Time\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 97406,\n        \"samples\": [\n          \"9/16/2020 13:28\",\n          \"1/10/2020 10:36\",\n          \"6/24/2020 10:41\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.359798823150364,\n        \"min\": 30.25,\n        \"max\": 58.4,\n        \"num_unique_values\": 802,\n        \"samples\": [\n          37.75,\n          41.33,\n          36.67\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
              "type": "dataframe",
              "variable_name": "fpt"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-4a60b205-d5a5-449f-ad7b-bea4c2034539\" 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/Time</th>\n",
              "      <th>Close</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>12/25/2018 9:15</td>\n",
              "      <td>30.89</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>12/25/2018 9:16</td>\n",
              "      <td>30.81</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>12/25/2018 9:17</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>12/25/2018 9:18</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>12/25/2018 9:19</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97401</th>\n",
              "      <td>12/22/2020 14:24</td>\n",
              "      <td>58.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97402</th>\n",
              "      <td>12/22/2020 14:25</td>\n",
              "      <td>58.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97403</th>\n",
              "      <td>12/22/2020 14:26</td>\n",
              "      <td>58.20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97404</th>\n",
              "      <td>12/22/2020 14:29</td>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97405</th>\n",
              "      <td>12/22/2020 14:46</td>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>97406 rows × 2 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-4a60b205-d5a5-449f-ad7b-bea4c2034539')\"\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-4a60b205-d5a5-449f-ad7b-bea4c2034539 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-4a60b205-d5a5-449f-ad7b-bea4c2034539');\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-0bdb7d70-0a4b-4481-93ef-174ab1d4e8b5\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0bdb7d70-0a4b-4481-93ef-174ab1d4e8b5')\"\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-0bdb7d70-0a4b-4481-93ef-174ab1d4e8b5 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_eda1ebc5-4621-40e1-9765-0d7fcb77d746\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('fpt')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_eda1ebc5-4621-40e1-9765-0d7fcb77d746 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('fpt');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "              Date/Time  Close\n",
              "0       12/25/2018 9:15  30.89\n",
              "1       12/25/2018 9:16  30.81\n",
              "2       12/25/2018 9:17  30.74\n",
              "3       12/25/2018 9:18  30.74\n",
              "4       12/25/2018 9:19  30.74\n",
              "...                 ...    ...\n",
              "97401  12/22/2020 14:24  58.20\n",
              "97402  12/22/2020 14:25  58.20\n",
              "97403  12/22/2020 14:26  58.20\n",
              "97404  12/22/2020 14:29  58.10\n",
              "97405  12/22/2020 14:46  58.10\n",
              "\n",
              "[97406 rows x 2 columns]"
            ]
          },
          "execution_count": 340,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "fpt = fpt[['Date/Time', 'Close']]\n",
        "fpt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 533
        },
        "id": "ZQPbneNW-fef",
        "outputId": "56b2255a-9bc3-4655-aef7-06945c934139"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "<ipython-input-341-1c712fd65419>:2: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  fpt['Date'] = fpt['Date/Time'].str.split().str[0]\n"
          ]
        },
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "repr_error": "0",
              "type": "dataframe",
              "variable_name": "fpt"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-58624a14-856d-4fef-a0ef-7f28adae11e1\" 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>Time</th>\n",
              "      <th>Close</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>12/25/2018 9:21</td>\n",
              "      <td>30.66</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>12/26/2018 14:46</td>\n",
              "      <td>30.89</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>266</th>\n",
              "      <td>12/27/2018 14:46</td>\n",
              "      <td>31.19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>388</th>\n",
              "      <td>12/28/2018 14:46</td>\n",
              "      <td>31.49</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>505</th>\n",
              "      <td>1/2/2019 14:46</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96564</th>\n",
              "      <td>12/16/2020 14:46</td>\n",
              "      <td>57.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96762</th>\n",
              "      <td>12/17/2020 14:46</td>\n",
              "      <td>56.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96975</th>\n",
              "      <td>12/18/2020 14:46</td>\n",
              "      <td>56.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97189</th>\n",
              "      <td>12/21/2020 14:46</td>\n",
              "      <td>57.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97405</th>\n",
              "      <td>12/22/2020 14:46</td>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>499 rows × 2 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-58624a14-856d-4fef-a0ef-7f28adae11e1')\"\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-58624a14-856d-4fef-a0ef-7f28adae11e1 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-58624a14-856d-4fef-a0ef-7f28adae11e1');\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-920658f0-b401-4080-9319-12752cb05398\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-920658f0-b401-4080-9319-12752cb05398')\"\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-920658f0-b401-4080-9319-12752cb05398 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_091023bd-47fe-4fca-8e3a-0a3bf3ad3cc7\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('fpt')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_091023bd-47fe-4fca-8e3a-0a3bf3ad3cc7 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('fpt');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "                   Time  Close\n",
              "6       12/25/2018 9:21  30.66\n",
              "132    12/26/2018 14:46  30.89\n",
              "266    12/27/2018 14:46  31.19\n",
              "388    12/28/2018 14:46  31.49\n",
              "505      1/2/2019 14:46  30.74\n",
              "...                 ...    ...\n",
              "96564  12/16/2020 14:46  57.10\n",
              "96762  12/17/2020 14:46  56.50\n",
              "96975  12/18/2020 14:46  56.90\n",
              "97189  12/21/2020 14:46  57.50\n",
              "97405  12/22/2020 14:46  58.10\n",
              "\n",
              "[499 rows x 2 columns]"
            ]
          },
          "execution_count": 341,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Chuyển dữ liệu từ Time về Date\n",
        "fpt['Date'] = fpt['Date/Time'].str.split().str[0]\n",
        "last_records = fpt.groupby('Date').tail(1)\n",
        "time = last_records['Date/Time'].tolist()\n",
        "fpt = fpt[fpt['Date/Time'].isin(time)]\n",
        "fpt = fpt[['Date/Time', 'Close']].copy()\n",
        "fpt.rename(columns={'Date/Time': 'Time'}, inplace=True)\n",
        "fpt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "g7X7ZDdR_A_-",
        "outputId": "9ac3c163-ff31-40eb-911e-b40368aa02d3"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "repr_error": "0",
              "type": "dataframe",
              "variable_name": "fpt"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-f3eacbd5-a9f4-44f2-80d3-04488ed9ca2e\" 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>Close</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>12/25/2018</td>\n",
              "      <td>30.66</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>12/26/2018</td>\n",
              "      <td>30.89</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>266</th>\n",
              "      <td>12/27/2018</td>\n",
              "      <td>31.19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>388</th>\n",
              "      <td>12/28/2018</td>\n",
              "      <td>31.49</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>505</th>\n",
              "      <td>1/2/2019</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96564</th>\n",
              "      <td>12/16/2020</td>\n",
              "      <td>57.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96762</th>\n",
              "      <td>12/17/2020</td>\n",
              "      <td>56.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96975</th>\n",
              "      <td>12/18/2020</td>\n",
              "      <td>56.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97189</th>\n",
              "      <td>12/21/2020</td>\n",
              "      <td>57.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97405</th>\n",
              "      <td>12/22/2020</td>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>499 rows × 2 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-f3eacbd5-a9f4-44f2-80d3-04488ed9ca2e')\"\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-f3eacbd5-a9f4-44f2-80d3-04488ed9ca2e 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-f3eacbd5-a9f4-44f2-80d3-04488ed9ca2e');\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-3d75cf86-b5e5-4994-9001-54c04e2d384d\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-3d75cf86-b5e5-4994-9001-54c04e2d384d')\"\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-3d75cf86-b5e5-4994-9001-54c04e2d384d button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_86f7d1df-3005-4962-aa28-a7122316815a\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('fpt')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_86f7d1df-3005-4962-aa28-a7122316815a button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('fpt');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "             Date  Close\n",
              "6      12/25/2018  30.66\n",
              "132    12/26/2018  30.89\n",
              "266    12/27/2018  31.19\n",
              "388    12/28/2018  31.49\n",
              "505      1/2/2019  30.74\n",
              "...           ...    ...\n",
              "96564  12/16/2020  57.10\n",
              "96762  12/17/2020  56.50\n",
              "96975  12/18/2020  56.90\n",
              "97189  12/21/2020  57.50\n",
              "97405  12/22/2020  58.10\n",
              "\n",
              "[499 rows x 2 columns]"
            ]
          },
          "execution_count": 342,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Xóa time\n",
        "fpt[\"Time\"] = fpt[\"Time\"].str.replace(r\"(\\d{4})(\\d)\", r\"\\1 \\2\", regex=True)\n",
        "fpt[\"Date\"] = fpt[\"Time\"].str.split().str[0]\n",
        "fpt = fpt[[\"Date\", \"Close\"]]\n",
        "fpt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 568
        },
        "id": "-Pa8TxAQj-mi",
        "outputId": "2584c50c-d7b7-45ea-e6a4-f589484a26ca"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "<ipython-input-343-5fd93553a194>:6: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  fpt['Date'] = fpt['Date'].apply(str_to_datetime)\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<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",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>2018-12-25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>132</th>\n",
              "      <td>2018-12-26</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>266</th>\n",
              "      <td>2018-12-27</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>388</th>\n",
              "      <td>2018-12-28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>505</th>\n",
              "      <td>2019-01-02</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96564</th>\n",
              "      <td>2020-12-16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96762</th>\n",
              "      <td>2020-12-17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96975</th>\n",
              "      <td>2020-12-18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97189</th>\n",
              "      <td>2020-12-21</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97405</th>\n",
              "      <td>2020-12-22</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>499 rows × 1 columns</p>\n",
              "</div><br><label><b>dtype:</b> datetime64[ns]</label>"
            ],
            "text/plain": [
              "6       2018-12-25\n",
              "132     2018-12-26\n",
              "266     2018-12-27\n",
              "388     2018-12-28\n",
              "505     2019-01-02\n",
              "           ...    \n",
              "96564   2020-12-16\n",
              "96762   2020-12-17\n",
              "96975   2020-12-18\n",
              "97189   2020-12-21\n",
              "97405   2020-12-22\n",
              "Name: Date, Length: 499, dtype: datetime64[ns]"
            ]
          },
          "execution_count": 343,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import datetime\n",
        "\n",
        "def str_to_datetime(s):\n",
        "  return datetime.datetime.strptime(s, \"%m/%d/%Y\")\n",
        "\n",
        "fpt['Date'] = fpt['Date'].apply(str_to_datetime)\n",
        "fpt['Date']"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 455
        },
        "id": "f2c_pi_zlDQu",
        "outputId": "2b94aa89-cfa8-40cc-b9c7-882353d435a9"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "summary": "{\n  \"name\": \"fpt\",\n  \"rows\": 499,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2018-12-25 00:00:00\",\n        \"max\": \"2020-12-22 00:00:00\",\n        \"num_unique_values\": 499,\n        \"samples\": [\n          \"2020-10-29 00:00:00\",\n          \"2019-04-17 00:00:00\",\n          \"2019-11-29 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Close\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.757144457245744,\n        \"min\": 30.44,\n        \"max\": 58.1,\n        \"num_unique_values\": 295,\n        \"samples\": [\n          51.7,\n          49.76,\n          38.95\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
              "type": "dataframe",
              "variable_name": "fpt"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-21715cdd-f31c-4b05-a064-7e2eaefa3029\" 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>Close</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Date</th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2018-12-25</th>\n",
              "      <td>30.66</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-12-26</th>\n",
              "      <td>30.89</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-12-27</th>\n",
              "      <td>31.19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018-12-28</th>\n",
              "      <td>31.49</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019-01-02</th>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-16</th>\n",
              "      <td>57.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-17</th>\n",
              "      <td>56.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-18</th>\n",
              "      <td>56.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-21</th>\n",
              "      <td>57.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2020-12-22</th>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>499 rows × 1 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-21715cdd-f31c-4b05-a064-7e2eaefa3029')\"\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-21715cdd-f31c-4b05-a064-7e2eaefa3029 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-21715cdd-f31c-4b05-a064-7e2eaefa3029');\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-990856ee-9811-4d81-9fa8-30914944dab5\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-990856ee-9811-4d81-9fa8-30914944dab5')\"\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-990856ee-9811-4d81-9fa8-30914944dab5 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_3cae47d8-8eb2-4131-bd3a-b60a3141276f\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('fpt')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_3cae47d8-8eb2-4131-bd3a-b60a3141276f button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('fpt');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "            Close\n",
              "Date             \n",
              "2018-12-25  30.66\n",
              "2018-12-26  30.89\n",
              "2018-12-27  31.19\n",
              "2018-12-28  31.49\n",
              "2019-01-02  30.74\n",
              "...           ...\n",
              "2020-12-16  57.10\n",
              "2020-12-17  56.50\n",
              "2020-12-18  56.90\n",
              "2020-12-21  57.50\n",
              "2020-12-22  58.10\n",
              "\n",
              "[499 rows x 1 columns]"
            ]
          },
          "execution_count": 344,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "fpt.index = fpt.pop('Date')\n",
        "fpt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "uEs172f97ybX",
        "outputId": "dd8504ed-7b79-4c14-98b7-8579a649e777"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "plt.plot(fpt.index, fpt['Close'])\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hIZsN2toA8hw"
      },
      "source": [
        "#2. Feature Engineering và Huấn luyện Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "O6fBzzRV9vwC",
        "outputId": "5404dbd3-f135-4fbf-e3db-7010236d1987"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "summary": "{\n  \"name\": \"windowed_df\",\n  \"rows\": 496,\n  \"fields\": [\n    {\n      \"column\": \"Target Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2018-12-28 00:00:00\",\n        \"max\": \"2020-12-22 00:00:00\",\n        \"num_unique_values\": 496,\n        \"samples\": [\n          \"2020-10-29 00:00:00\",\n          \"2019-04-22 00:00:00\",\n          \"2019-12-04 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Target-3\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.6990334143717085,\n        \"min\": 30.44,\n        \"max\": 57.5,\n        \"num_unique_values\": 293,\n        \"samples\": [\n          38.95,\n          50.8,\n          35.29\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Target-2\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.695083997685947,\n        \"min\": 30.44,\n        \"max\": 57.5,\n        \"num_unique_values\": 294,\n        \"samples\": [\n          33.2,\n          31.71,\n          49.59\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Target-1\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.693982048521902,\n        \"min\": 30.44,\n        \"max\": 57.5,\n        \"num_unique_values\": 293,\n        \"samples\": [\n          38.65,\n          50.6,\n          34.99\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Target\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 6.696083670328434,\n        \"min\": 30.44,\n        \"max\": 58.1,\n        \"num_unique_values\": 294,\n        \"samples\": [\n          34.69,\n          31.93,\n          49.42\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
              "type": "dataframe",
              "variable_name": "windowed_df"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-51e6199c-47e8-4d12-b018-557f61410f82\" 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>Target Date</th>\n",
              "      <th>Target-3</th>\n",
              "      <th>Target-2</th>\n",
              "      <th>Target-1</th>\n",
              "      <th>Target</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2018-12-28</td>\n",
              "      <td>30.66</td>\n",
              "      <td>30.89</td>\n",
              "      <td>31.19</td>\n",
              "      <td>31.49</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2019-01-02</td>\n",
              "      <td>30.89</td>\n",
              "      <td>31.19</td>\n",
              "      <td>31.49</td>\n",
              "      <td>30.74</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2019-01-03</td>\n",
              "      <td>31.19</td>\n",
              "      <td>31.49</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.44</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2019-01-04</td>\n",
              "      <td>31.49</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.44</td>\n",
              "      <td>30.66</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2019-01-07</td>\n",
              "      <td>30.74</td>\n",
              "      <td>30.44</td>\n",
              "      <td>30.66</td>\n",
              "      <td>31.19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>491</th>\n",
              "      <td>2020-12-16</td>\n",
              "      <td>57.00</td>\n",
              "      <td>57.20</td>\n",
              "      <td>56.70</td>\n",
              "      <td>57.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>492</th>\n",
              "      <td>2020-12-17</td>\n",
              "      <td>57.20</td>\n",
              "      <td>56.70</td>\n",
              "      <td>57.10</td>\n",
              "      <td>56.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>493</th>\n",
              "      <td>2020-12-18</td>\n",
              "      <td>56.70</td>\n",
              "      <td>57.10</td>\n",
              "      <td>56.50</td>\n",
              "      <td>56.90</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>494</th>\n",
              "      <td>2020-12-21</td>\n",
              "      <td>57.10</td>\n",
              "      <td>56.50</td>\n",
              "      <td>56.90</td>\n",
              "      <td>57.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>495</th>\n",
              "      <td>2020-12-22</td>\n",
              "      <td>56.50</td>\n",
              "      <td>56.90</td>\n",
              "      <td>57.50</td>\n",
              "      <td>58.10</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>496 rows × 5 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-51e6199c-47e8-4d12-b018-557f61410f82')\"\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-51e6199c-47e8-4d12-b018-557f61410f82 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-51e6199c-47e8-4d12-b018-557f61410f82');\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-76ccaad7-d665-4b58-bce1-528a621da673\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-76ccaad7-d665-4b58-bce1-528a621da673')\"\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-76ccaad7-d665-4b58-bce1-528a621da673 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_92f4ed1c-efdb-4a41-8c26-15e84bb887c3\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('windowed_df')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_92f4ed1c-efdb-4a41-8c26-15e84bb887c3 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('windowed_df');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "    Target Date  Target-3  Target-2  Target-1  Target\n",
              "0    2018-12-28     30.66     30.89     31.19   31.49\n",
              "1    2019-01-02     30.89     31.19     31.49   30.74\n",
              "2    2019-01-03     31.19     31.49     30.74   30.44\n",
              "3    2019-01-04     31.49     30.74     30.44   30.66\n",
              "4    2019-01-07     30.74     30.44     30.66   31.19\n",
              "..          ...       ...       ...       ...     ...\n",
              "491  2020-12-16     57.00     57.20     56.70   57.10\n",
              "492  2020-12-17     57.20     56.70     57.10   56.50\n",
              "493  2020-12-18     56.70     57.10     56.50   56.90\n",
              "494  2020-12-21     57.10     56.50     56.90   57.50\n",
              "495  2020-12-22     56.50     56.90     57.50   58.10\n",
              "\n",
              "[496 rows x 5 columns]"
            ]
          },
          "execution_count": 346,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Splitting Windowed\n",
        "def df_to_windowed_df(dataframe, first_date_str, last_date_str, n=3):\n",
        "  first_date = str_to_datetime(first_date_str)\n",
        "  last_date  = str_to_datetime(last_date_str)\n",
        "\n",
        "  target_date = first_date\n",
        "\n",
        "  dates = []\n",
        "  X, Y = [], []\n",
        "\n",
        "  last_time = False\n",
        "  while True:\n",
        "    df_subset = dataframe.loc[:target_date].tail(n+1)\n",
        "\n",
        "    if len(df_subset) != n+1:\n",
        "      print(f'Error: Window of size {n} is too large for date {target_date}')\n",
        "      return\n",
        "\n",
        "    values = df_subset['Close'].to_numpy()\n",
        "    x, y = values[:-1], values[-1]\n",
        "\n",
        "    dates.append(target_date)\n",
        "    X.append(x)\n",
        "    Y.append(y)\n",
        "\n",
        "    next_period = dataframe.loc[target_date:target_date+datetime.timedelta(days=10)]\n",
        "    next_datetime_str = str(next_period.head(2).tail(1).index.values[0])\n",
        "    next_date_str = next_datetime_str.split('T')[0]\n",
        "    year_month_day = next_date_str.split('-')\n",
        "    year, month, day = year_month_day\n",
        "    next_date = datetime.datetime(day=int(day), month=int(month), year=int(year))\n",
        "\n",
        "    if last_time:\n",
        "      break\n",
        "\n",
        "    target_date = next_date\n",
        "\n",
        "    if target_date == last_date:\n",
        "      last_time = True\n",
        "\n",
        "  ret_df = pd.DataFrame({})\n",
        "  ret_df['Target Date'] = dates\n",
        "\n",
        "  X = np.array(X)\n",
        "  for i in range(0, n):\n",
        "    X[:, i]\n",
        "    ret_df[f'Target-{n-i}'] = X[:, i]\n",
        "\n",
        "  ret_df['Target'] = Y\n",
        "\n",
        "  return ret_df\n",
        "\n",
        "windowed_df = df_to_windowed_df(fpt, '12/28/2018', '12/22/2020', n=3)\n",
        "windowed_df"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yOuAqNu79xUf",
        "outputId": "88d80ace-e952-4892-d16e-1475962b08ad"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "((496,), (496, 3, 1), (496,))"
            ]
          },
          "execution_count": 347,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "def windowed_df_to_date_X_y(windowed_dataframe):\n",
        "  df_as_np = windowed_dataframe.to_numpy()\n",
        "\n",
        "  dates = df_as_np[:, 0]\n",
        "\n",
        "  middle_matrix = df_as_np[:, 1:-1]\n",
        "  X = middle_matrix.reshape((len(dates), middle_matrix.shape[1], 1))\n",
        "\n",
        "  Y = df_as_np[:, -1]\n",
        "\n",
        "  return dates, X.astype(np.float32), Y.astype(np.float32)\n",
        "\n",
        "dates, X, y = windowed_df_to_date_X_y(windowed_df)\n",
        "\n",
        "dates.shape, X.shape, y.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "G7fHob-z9ywp",
        "outputId": "81ea0744-5941-4f7f-e1cc-1c6a1d83fb32"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Chia dữ liệu\n",
        "q_80 = int(len(dates) * .8)\n",
        "q_90 = int(len(dates) * .9)\n",
        "\n",
        "dates_train, X_train, y_train = dates[:q_80], X[:q_80], y[:q_80]\n",
        "\n",
        "dates_val, X_val, y_val = dates[q_80:q_90], X[q_80:q_90], y[q_80:q_90]\n",
        "dates_test, X_test, y_test = dates[q_90:], X[q_90:], y[q_90:]\n",
        "\n",
        "plt.plot(dates_train, y_train)\n",
        "plt.plot(dates_val, y_val)\n",
        "plt.plot(dates_test, y_test)\n",
        "\n",
        "plt.legend(['Train', 'Validation', 'Test'])\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ycC3IY0a907V",
        "outputId": "cf32d92b-006a-43a7-b879-a02d6cc214c0"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 44ms/step - loss: 1826.9546 - mean_absolute_error: 42.3328 - val_loss: 2277.1443 - val_mean_absolute_error: 47.6953\n",
            "Epoch 2/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1686.6083 - mean_absolute_error: 40.6291 - val_loss: 2145.2256 - val_mean_absolute_error: 46.2914\n",
            "Epoch 3/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1551.0599 - mean_absolute_error: 38.9021 - val_loss: 1935.1127 - val_mean_absolute_error: 43.9627\n",
            "Epoch 4/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1331.0194 - mean_absolute_error: 35.9273 - val_loss: 1567.9448 - val_mean_absolute_error: 39.5654\n",
            "Epoch 5/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 983.1359 - mean_absolute_error: 30.6064 - val_loss: 967.6005 - val_mean_absolute_error: 31.0632\n",
            "Epoch 6/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 482.5534 - mean_absolute_error: 20.8436 - val_loss: 360.6814 - val_mean_absolute_error: 18.9220\n",
            "Epoch 7/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 127.5964 - mean_absolute_error: 9.6049 - val_loss: 43.4516 - val_mean_absolute_error: 6.3846\n",
            "Epoch 8/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 47.1447 - mean_absolute_error: 5.7078 - val_loss: 20.4875 - val_mean_absolute_error: 4.2441\n",
            "Epoch 9/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 45.9288 - mean_absolute_error: 5.6951 - val_loss: 55.8143 - val_mean_absolute_error: 7.3093\n",
            "Epoch 10/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 35.4736 - mean_absolute_error: 5.4121 - val_loss: 60.5718 - val_mean_absolute_error: 7.6360\n",
            "Epoch 11/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 35.4904 - mean_absolute_error: 5.4613 - val_loss: 44.0883 - val_mean_absolute_error: 6.4764\n",
            "Epoch 12/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 30.1175 - mean_absolute_error: 4.8924 - val_loss: 40.6005 - val_mean_absolute_error: 6.2275\n",
            "Epoch 13/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 25.7774 - mean_absolute_error: 4.6101 - val_loss: 29.1030 - val_mean_absolute_error: 5.2358\n",
            "Epoch 14/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 20.0498 - mean_absolute_error: 3.9867 - val_loss: 23.2661 - val_mean_absolute_error: 4.6699\n",
            "Epoch 15/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 14.6531 - mean_absolute_error: 3.3956 - val_loss: 13.3126 - val_mean_absolute_error: 3.4552\n",
            "Epoch 16/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 10.7823 - mean_absolute_error: 2.8033 - val_loss: 11.8593 - val_mean_absolute_error: 3.2927\n",
            "Epoch 17/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 6.7938 - mean_absolute_error: 2.2452 - val_loss: 6.5078 - val_mean_absolute_error: 2.3545\n",
            "Epoch 18/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 3.4150 - mean_absolute_error: 1.5483 - val_loss: 2.8682 - val_mean_absolute_error: 1.4405\n",
            "Epoch 19/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 1.3991 - mean_absolute_error: 0.9376 - val_loss: 1.8251 - val_mean_absolute_error: 1.1416\n",
            "Epoch 20/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 0.8024 - mean_absolute_error: 0.6368 - val_loss: 1.1763 - val_mean_absolute_error: 0.9257\n",
            "Epoch 21/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 0.6621 - mean_absolute_error: 0.5825 - val_loss: 0.7514 - val_mean_absolute_error: 0.7357\n",
            "Epoch 22/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6445 - mean_absolute_error: 0.5664 - val_loss: 1.0177 - val_mean_absolute_error: 0.8640\n",
            "Epoch 23/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6832 - mean_absolute_error: 0.6041 - val_loss: 0.9282 - val_mean_absolute_error: 0.8235\n",
            "Epoch 24/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5720 - mean_absolute_error: 0.5506 - val_loss: 0.7116 - val_mean_absolute_error: 0.7116\n",
            "Epoch 25/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6361 - mean_absolute_error: 0.5665 - val_loss: 0.7714 - val_mean_absolute_error: 0.7465\n",
            "Epoch 26/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 0.5847 - mean_absolute_error: 0.5369 - val_loss: 0.5103 - val_mean_absolute_error: 0.5884\n",
            "Epoch 27/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6564 - mean_absolute_error: 0.5908 - val_loss: 0.5769 - val_mean_absolute_error: 0.6330\n",
            "Epoch 28/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6827 - mean_absolute_error: 0.5871 - val_loss: 0.8369 - val_mean_absolute_error: 0.7866\n",
            "Epoch 29/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6932 - mean_absolute_error: 0.6026 - val_loss: 0.7643 - val_mean_absolute_error: 0.7470\n",
            "Epoch 30/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6539 - mean_absolute_error: 0.5571 - val_loss: 0.4457 - val_mean_absolute_error: 0.5427\n",
            "Epoch 31/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5822 - mean_absolute_error: 0.5289 - val_loss: 0.7662 - val_mean_absolute_error: 0.7494\n",
            "Epoch 32/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5698 - mean_absolute_error: 0.5523 - val_loss: 0.6407 - val_mean_absolute_error: 0.6745\n",
            "Epoch 33/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5892 - mean_absolute_error: 0.5262 - val_loss: 0.5213 - val_mean_absolute_error: 0.5961\n",
            "Epoch 34/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 0.4857 - mean_absolute_error: 0.4920 - val_loss: 0.5411 - val_mean_absolute_error: 0.6104\n",
            "Epoch 35/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5921 - mean_absolute_error: 0.5449 - val_loss: 0.3991 - val_mean_absolute_error: 0.5086\n",
            "Epoch 36/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5240 - mean_absolute_error: 0.5148 - val_loss: 0.7368 - val_mean_absolute_error: 0.7346\n",
            "Epoch 37/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7130 - mean_absolute_error: 0.6122 - val_loss: 0.4686 - val_mean_absolute_error: 0.5566\n",
            "Epoch 38/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5091 - mean_absolute_error: 0.5073 - val_loss: 0.5420 - val_mean_absolute_error: 0.6109\n",
            "Epoch 39/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6001 - mean_absolute_error: 0.5497 - val_loss: 0.5421 - val_mean_absolute_error: 0.6108\n",
            "Epoch 40/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5932 - mean_absolute_error: 0.5368 - val_loss: 0.3590 - val_mean_absolute_error: 0.4786\n",
            "Epoch 41/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7631 - mean_absolute_error: 0.5900 - val_loss: 0.4257 - val_mean_absolute_error: 0.5258\n",
            "Epoch 42/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5220 - mean_absolute_error: 0.5104 - val_loss: 0.6927 - val_mean_absolute_error: 0.7075\n",
            "Epoch 43/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.5535 - mean_absolute_error: 0.5397 - val_loss: 0.3780 - val_mean_absolute_error: 0.4900\n",
            "Epoch 44/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.6640 - mean_absolute_error: 0.5570 - val_loss: 0.3806 - val_mean_absolute_error: 0.4918\n",
            "Epoch 45/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5805 - mean_absolute_error: 0.5285 - val_loss: 0.5250 - val_mean_absolute_error: 0.5977\n",
            "Epoch 46/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.5335 - mean_absolute_error: 0.5135 - val_loss: 0.4293 - val_mean_absolute_error: 0.5278\n",
            "Epoch 47/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5731 - mean_absolute_error: 0.5138 - val_loss: 0.4606 - val_mean_absolute_error: 0.5501\n",
            "Epoch 48/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6459 - mean_absolute_error: 0.5616 - val_loss: 0.6045 - val_mean_absolute_error: 0.6519\n",
            "Epoch 49/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6402 - mean_absolute_error: 0.5895 - val_loss: 0.4914 - val_mean_absolute_error: 0.5727\n",
            "Epoch 50/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5707 - mean_absolute_error: 0.5515 - val_loss: 0.3076 - val_mean_absolute_error: 0.4455\n",
            "Epoch 51/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6362 - mean_absolute_error: 0.6185 - val_loss: 0.3434 - val_mean_absolute_error: 0.4640\n",
            "Epoch 52/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6642 - mean_absolute_error: 0.5804 - val_loss: 0.9177 - val_mean_absolute_error: 0.8438\n",
            "Epoch 53/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5930 - mean_absolute_error: 0.5753 - val_loss: 0.6036 - val_mean_absolute_error: 0.6491\n",
            "Epoch 54/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6085 - mean_absolute_error: 0.5760 - val_loss: 0.5270 - val_mean_absolute_error: 0.5989\n",
            "Epoch 55/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.5661 - mean_absolute_error: 0.5181 - val_loss: 0.4258 - val_mean_absolute_error: 0.5245\n",
            "Epoch 56/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5637 - mean_absolute_error: 0.5425 - val_loss: 0.5974 - val_mean_absolute_error: 0.6462\n",
            "Epoch 57/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6853 - mean_absolute_error: 0.6384 - val_loss: 1.1036 - val_mean_absolute_error: 0.9474\n",
            "Epoch 58/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 0.6705 - mean_absolute_error: 0.6212 - val_loss: 0.3613 - val_mean_absolute_error: 0.4772\n",
            "Epoch 59/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6880 - mean_absolute_error: 0.6325 - val_loss: 0.3643 - val_mean_absolute_error: 0.4800\n",
            "Epoch 60/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5821 - mean_absolute_error: 0.5656 - val_loss: 0.5445 - val_mean_absolute_error: 0.6107\n",
            "Epoch 61/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5278 - mean_absolute_error: 0.5076 - val_loss: 0.3924 - val_mean_absolute_error: 0.5001\n",
            "Epoch 62/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5279 - mean_absolute_error: 0.5016 - val_loss: 0.3411 - val_mean_absolute_error: 0.4622\n",
            "Epoch 63/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6373 - mean_absolute_error: 0.5820 - val_loss: 0.4362 - val_mean_absolute_error: 0.5311\n",
            "Epoch 64/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5536 - mean_absolute_error: 0.5294 - val_loss: 0.9335 - val_mean_absolute_error: 0.8563\n",
            "Epoch 65/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7646 - mean_absolute_error: 0.6294 - val_loss: 0.5024 - val_mean_absolute_error: 0.5802\n",
            "Epoch 66/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5789 - mean_absolute_error: 0.5225 - val_loss: 0.4208 - val_mean_absolute_error: 0.5201\n",
            "Epoch 67/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 0.5770 - mean_absolute_error: 0.5500 - val_loss: 0.5366 - val_mean_absolute_error: 0.6036\n",
            "Epoch 68/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 0.5658 - mean_absolute_error: 0.5243 - val_loss: 0.5908 - val_mean_absolute_error: 0.6398\n",
            "Epoch 69/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 0.5671 - mean_absolute_error: 0.5454 - val_loss: 0.3242 - val_mean_absolute_error: 0.4493\n",
            "Epoch 70/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 0.6070 - mean_absolute_error: 0.5773 - val_loss: 0.3713 - val_mean_absolute_error: 0.4822\n",
            "Epoch 71/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 0.6576 - mean_absolute_error: 0.6014 - val_loss: 0.3607 - val_mean_absolute_error: 0.4740\n",
            "Epoch 72/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 0.5775 - mean_absolute_error: 0.5155 - val_loss: 0.3785 - val_mean_absolute_error: 0.4869\n",
            "Epoch 73/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 0.5516 - mean_absolute_error: 0.5252 - val_loss: 0.4155 - val_mean_absolute_error: 0.5155\n",
            "Epoch 74/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 0.5887 - mean_absolute_error: 0.5495 - val_loss: 0.3936 - val_mean_absolute_error: 0.4984\n",
            "Epoch 75/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 0.4689 - mean_absolute_error: 0.4935 - val_loss: 0.4544 - val_mean_absolute_error: 0.5435\n",
            "Epoch 76/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 0.6161 - mean_absolute_error: 0.5461 - val_loss: 0.5330 - val_mean_absolute_error: 0.6001\n",
            "Epoch 77/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 0.5293 - mean_absolute_error: 0.5016 - val_loss: 0.3327 - val_mean_absolute_error: 0.4519\n",
            "Epoch 78/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 0.6693 - mean_absolute_error: 0.5828 - val_loss: 0.3048 - val_mean_absolute_error: 0.4366\n",
            "Epoch 79/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 0.5316 - mean_absolute_error: 0.5032 - val_loss: 0.4089 - val_mean_absolute_error: 0.5094\n",
            "Epoch 80/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 0.5166 - mean_absolute_error: 0.5048 - val_loss: 0.3921 - val_mean_absolute_error: 0.4966\n",
            "Epoch 81/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5555 - mean_absolute_error: 0.5224 - val_loss: 0.6226 - val_mean_absolute_error: 0.6611\n",
            "Epoch 82/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5475 - mean_absolute_error: 0.5525 - val_loss: 0.6088 - val_mean_absolute_error: 0.6520\n",
            "Epoch 83/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5389 - mean_absolute_error: 0.5254 - val_loss: 0.2907 - val_mean_absolute_error: 0.4260\n",
            "Epoch 84/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5841 - mean_absolute_error: 0.5390 - val_loss: 0.5694 - val_mean_absolute_error: 0.6254\n",
            "Epoch 85/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6726 - mean_absolute_error: 0.5660 - val_loss: 0.4454 - val_mean_absolute_error: 0.5357\n",
            "Epoch 86/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5209 - mean_absolute_error: 0.5127 - val_loss: 0.5798 - val_mean_absolute_error: 0.6320\n",
            "Epoch 87/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 0.5987 - mean_absolute_error: 0.5512 - val_loss: 0.3702 - val_mean_absolute_error: 0.4792\n",
            "Epoch 88/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5712 - mean_absolute_error: 0.5309 - val_loss: 0.3510 - val_mean_absolute_error: 0.4644\n",
            "Epoch 89/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6050 - mean_absolute_error: 0.5272 - val_loss: 0.4528 - val_mean_absolute_error: 0.5409\n",
            "Epoch 90/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.5413 - mean_absolute_error: 0.5134 - val_loss: 0.5191 - val_mean_absolute_error: 0.5884\n",
            "Epoch 91/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5654 - mean_absolute_error: 0.5292 - val_loss: 0.2937 - val_mean_absolute_error: 0.4267\n",
            "Epoch 92/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5536 - mean_absolute_error: 0.5411 - val_loss: 0.3192 - val_mean_absolute_error: 0.4424\n",
            "Epoch 93/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.4861 - mean_absolute_error: 0.4982 - val_loss: 0.3682 - val_mean_absolute_error: 0.4772\n",
            "Epoch 94/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.5065 - mean_absolute_error: 0.5087 - val_loss: 0.5086 - val_mean_absolute_error: 0.5802\n",
            "Epoch 95/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.5389 - mean_absolute_error: 0.5388 - val_loss: 0.2937 - val_mean_absolute_error: 0.4267\n",
            "Epoch 96/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.5669 - mean_absolute_error: 0.5273 - val_loss: 0.3176 - val_mean_absolute_error: 0.4408\n",
            "Epoch 97/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.5857 - mean_absolute_error: 0.5234 - val_loss: 0.3697 - val_mean_absolute_error: 0.4782\n",
            "Epoch 98/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.5534 - mean_absolute_error: 0.5139 - val_loss: 0.3682 - val_mean_absolute_error: 0.4768\n",
            "Epoch 99/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.4614 - mean_absolute_error: 0.4774 - val_loss: 0.4391 - val_mean_absolute_error: 0.5295\n",
            "Epoch 100/100\n",
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6476 - mean_absolute_error: 0.5765 - val_loss: 0.8653 - val_mean_absolute_error: 0.8213\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x7c91162b6ed0>"
            ]
          },
          "execution_count": 349,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "from tensorflow.keras import layers\n",
        "\n",
        "model = Sequential([layers.Input((3, 1)),\n",
        "                    layers.LSTM(64),\n",
        "                    layers.Dense(32, activation='relu'),\n",
        "                    layers.Dense(32, activation='relu'),\n",
        "                    layers.Dense(1)])\n",
        "\n",
        "model.compile(loss='mse',\n",
        "              optimizer=Adam(learning_rate=0.001),\n",
        "              metrics=['mean_absolute_error'])\n",
        "\n",
        "model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=100)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J9tuKHDHBU9Q"
      },
      "source": [
        "#3. Đánh giá Model Trực quan hóa"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 505
        },
        "id": "tYeIpNOo92np",
        "outputId": "cdd0e160-7896-49ff-cbe9-9608c8603796"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\u001b[1m13/13\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step\n"
          ]
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "train_predictions = model.predict(X_train).flatten()\n",
        "\n",
        "plt.plot(dates_train, train_predictions)\n",
        "plt.plot(dates_train, y_train)\n",
        "plt.legend(['Training Predictions', 'Training Observations'])\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 505
        },
        "id": "_cIEUiOF93sE",
        "outputId": "1a694090-9098-423a-f3ad-2933fdcb1061"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step\n"
          ]
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "val_predictions = model.predict(X_val).flatten()\n",
        "\n",
        "plt.plot(dates_val, val_predictions)\n",
        "plt.plot(dates_val, y_val)\n",
        "plt.legend(['Validation Predictions', 'Validation Observations'])\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 505
        },
        "id": "_Nf2E8dw947M",
        "outputId": "9583c4d0-586f-4c6d-d9a0-07f64e8ffbe0"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step\n"
          ]
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "test_predictions = model.predict(X_test).flatten()\n",
        "\n",
        "plt.plot(dates_test, test_predictions)\n",
        "plt.plot(dates_test, y_test)\n",
        "plt.legend(['Testing Predictions', 'Testing Observations'])\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "OZtCslyZ959H",
        "outputId": "e26ec9b6-fe8e-43e9-ba37-323140527a87"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "plt.plot(dates_train, train_predictions)\n",
        "plt.plot(dates_train, y_train)\n",
        "plt.plot(dates_val, val_predictions)\n",
        "plt.plot(dates_val, y_val)\n",
        "plt.plot(dates_test, test_predictions)\n",
        "plt.plot(dates_test, y_test)\n",
        "plt.legend(['Training Predictions',\n",
        "            'Training Observations',\n",
        "            'Validation Predictions',\n",
        "            'Validation Observations',\n",
        "            'Testing Predictions',\n",
        "            'Testing Observations'])\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xAyLFqB-99-6",
        "outputId": "bcc0ab7d-56f3-42ee-89bd-a546935380f7"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 61ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 89ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 77ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 73ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 66ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 57ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 73ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 67ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 72ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 64ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 74ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 60ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 45ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 49ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 46ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 44ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n"
          ]
        }
      ],
      "source": [
        "from copy import deepcopy\n",
        "\n",
        "recursive_predictions = []\n",
        "recursive_dates = np.concatenate([dates_val, dates_test])\n",
        "\n",
        "for target_date in recursive_dates:\n",
        "  last_window = deepcopy(X_train[-1])\n",
        "  next_prediction = model.predict(np.array([last_window])).flatten()\n",
        "  recursive_predictions.append(next_prediction)\n",
        "  last_window[-1] = next_prediction"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "dnbWB4389_N_",
        "outputId": "80b2eba1-f5ed-454f-de7a-0d5a67d55fbf"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "plt.plot(dates_train, train_predictions)\n",
        "plt.plot(dates_train, y_train)\n",
        "plt.plot(dates_val, val_predictions)\n",
        "plt.plot(dates_val, y_val)\n",
        "plt.plot(dates_test, test_predictions)\n",
        "plt.plot(dates_test, y_test)\n",
        "plt.plot(recursive_dates, recursive_predictions)\n",
        "plt.legend(['Training Predictions',\n",
        "            'Training Observations',\n",
        "            'Validation Predictions',\n",
        "            'Validation Observations',\n",
        "            'Testing Predictions',\n",
        "            'Testing Observations',\n",
        "            'Recursive Predictions'])\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}