Tesla_Stock_Price_Prediction_LSTM.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyONSFuvcqPDuvRsK05QEi8r",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/yashlad27/LSTM_basics/blob/main/tuning_hyperparameters_with_XGBOOST.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "metadata": {
        "id": "3ZHztOTZalgK"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.svm import SVC\n",
        "from xgboost import XGBClassifier\n",
        "from sklearn import metrics\n",
        "\n",
        "from sklearn import linear_model\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "import keras.backend as K\n",
        "from keras.callbacks import EarlyStopping\n",
        "\n",
        "from keras.optimizers import Adam\n",
        "from keras.models import load_model\n",
        "from keras.layers import LSTM\n",
        "from keras.utils.vis_utils import plot_model\n",
        "\n",
        "import tensorflow as tf\n",
        "import datetime as dt\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from sklearn.metrics import mean_squared_error\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Dense, LSTM, Dropout\n",
        "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import files\n",
        "uploaded = files.upload()\n",
        "\n",
        "import io\n",
        "df = pd.read_csv(io.BytesIO(uploaded['TSLA.csv']))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "wx9dfqUhb0C-",
        "outputId": "dd7d290b-38d2-4b10-979a-47aa0ee0d48e"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-0d9acbc8-1961-4eae-9c13-05da1c9dd60b\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-0d9acbc8-1961-4eae-9c13-05da1c9dd60b\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving TSLA.csv to TSLA (2).csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "O0cNmzGhchDQ",
        "outputId": "24d3002d-3a18-4987-f10a-568d6aad9269"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Date        Open        High         Low       Close   Adj Close  \\\n",
              "0     2010-06-29   19.000000   25.000000   17.540001   23.889999   23.889999   \n",
              "1     2010-06-30   25.790001   30.420000   23.299999   23.830000   23.830000   \n",
              "2     2010-07-01   25.000000   25.920000   20.270000   21.959999   21.959999   \n",
              "3     2010-07-02   23.000000   23.100000   18.709999   19.200001   19.200001   \n",
              "4     2010-07-06   20.000000   20.000000   15.830000   16.110001   16.110001   \n",
              "...          ...         ...         ...         ...         ...         ...   \n",
              "2411  2020-01-28  568.489990  576.809998  558.080017  566.900024  566.900024   \n",
              "2412  2020-01-29  575.690002  589.799988  567.429993  580.989990  580.989990   \n",
              "2413  2020-01-30  632.419983  650.880005  618.000000  640.809998  640.809998   \n",
              "2414  2020-01-31  640.000000  653.000000  632.520020  650.570007  650.570007   \n",
              "2415  2020-02-03  673.690002  786.140015  673.520020  780.000000  780.000000   \n",
              "\n",
              "        Volume  \n",
              "0     18766300  \n",
              "1     17187100  \n",
              "2      8218800  \n",
              "3      5139800  \n",
              "4      6866900  \n",
              "...        ...  \n",
              "2411  11788500  \n",
              "2412  17801500  \n",
              "2413  29005700  \n",
              "2414  15719300  \n",
              "2415  47065000  \n",
              "\n",
              "[2416 rows x 7 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f2c6284d-7758-4d75-b47d-ed3638877c4e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Date</th>\n",
              "      <th>Open</th>\n",
              "      <th>High</th>\n",
              "      <th>Low</th>\n",
              "      <th>Close</th>\n",
              "      <th>Adj Close</th>\n",
              "      <th>Volume</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2010-06-29</td>\n",
              "      <td>19.000000</td>\n",
              "      <td>25.000000</td>\n",
              "      <td>17.540001</td>\n",
              "      <td>23.889999</td>\n",
              "      <td>23.889999</td>\n",
              "      <td>18766300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2010-06-30</td>\n",
              "      <td>25.790001</td>\n",
              "      <td>30.420000</td>\n",
              "      <td>23.299999</td>\n",
              "      <td>23.830000</td>\n",
              "      <td>23.830000</td>\n",
              "      <td>17187100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2010-07-01</td>\n",
              "      <td>25.000000</td>\n",
              "      <td>25.920000</td>\n",
              "      <td>20.270000</td>\n",
              "      <td>21.959999</td>\n",
              "      <td>21.959999</td>\n",
              "      <td>8218800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2010-07-02</td>\n",
              "      <td>23.000000</td>\n",
              "      <td>23.100000</td>\n",
              "      <td>18.709999</td>\n",
              "      <td>19.200001</td>\n",
              "      <td>19.200001</td>\n",
              "      <td>5139800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2010-07-06</td>\n",
              "      <td>20.000000</td>\n",
              "      <td>20.000000</td>\n",
              "      <td>15.830000</td>\n",
              "      <td>16.110001</td>\n",
              "      <td>16.110001</td>\n",
              "      <td>6866900</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2411</th>\n",
              "      <td>2020-01-28</td>\n",
              "      <td>568.489990</td>\n",
              "      <td>576.809998</td>\n",
              "      <td>558.080017</td>\n",
              "      <td>566.900024</td>\n",
              "      <td>566.900024</td>\n",
              "      <td>11788500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2412</th>\n",
              "      <td>2020-01-29</td>\n",
              "      <td>575.690002</td>\n",
              "      <td>589.799988</td>\n",
              "      <td>567.429993</td>\n",
              "      <td>580.989990</td>\n",
              "      <td>580.989990</td>\n",
              "      <td>17801500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2413</th>\n",
              "      <td>2020-01-30</td>\n",
              "      <td>632.419983</td>\n",
              "      <td>650.880005</td>\n",
              "      <td>618.000000</td>\n",
              "      <td>640.809998</td>\n",
              "      <td>640.809998</td>\n",
              "      <td>29005700</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2414</th>\n",
              "      <td>2020-01-31</td>\n",
              "      <td>640.000000</td>\n",
              "      <td>653.000000</td>\n",
              "      <td>632.520020</td>\n",
              "      <td>650.570007</td>\n",
              "      <td>650.570007</td>\n",
              "      <td>15719300</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2415</th>\n",
              "      <td>2020-02-03</td>\n",
              "      <td>673.690002</td>\n",
              "      <td>786.140015</td>\n",
              "      <td>673.520020</td>\n",
              "      <td>780.000000</td>\n",
              "      <td>780.000000</td>\n",
              "      <td>47065000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2416 rows × 7 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f2c6284d-7758-4d75-b47d-ed3638877c4e')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-f2c6284d-7758-4d75-b47d-ed3638877c4e 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-f2c6284d-7758-4d75-b47d-ed3638877c4e');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def check_df(dataframe,head=5):\n",
        "  print(\"######################### Head #########################\")\n",
        "  print(dataframe.head(head))\n",
        "  print(\"######################### Tail #########################\")\n",
        "  print(dataframe.tail(head))\n",
        "  print(\"######################### Shape #########################\")\n",
        "  print(dataframe.shape)\n",
        "  print(\"######################### Types #########################\")\n",
        "  print(dataframe.dtypes)\n",
        "  print(\"######################### NA #########################\")\n",
        "  print(dataframe.isnull().sum())\n",
        "  print(\"######################### Qurtiles #########################\")\n",
        "  print(dataframe.describe([0, 0.05, 0.50, 0.95, 0.99, 1]).T)"
      ],
      "metadata": {
        "id": "KDh4r-4PcHnp"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "check_df(df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ck62FdHucs9b",
        "outputId": "d01ad1c0-bc07-4fd8-aef1-94c46af2b460"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "######################### Head #########################\n",
            "         Date       Open   High        Low      Close  Adj Close    Volume\n",
            "0  2010-06-29  19.000000  25.00  17.540001  23.889999  23.889999  18766300\n",
            "1  2010-06-30  25.790001  30.42  23.299999  23.830000  23.830000  17187100\n",
            "2  2010-07-01  25.000000  25.92  20.270000  21.959999  21.959999   8218800\n",
            "3  2010-07-02  23.000000  23.10  18.709999  19.200001  19.200001   5139800\n",
            "4  2010-07-06  20.000000  20.00  15.830000  16.110001  16.110001   6866900\n",
            "######################### Tail #########################\n",
            "            Date        Open        High         Low       Close   Adj Close  \\\n",
            "2411  2020-01-28  568.489990  576.809998  558.080017  566.900024  566.900024   \n",
            "2412  2020-01-29  575.690002  589.799988  567.429993  580.989990  580.989990   \n",
            "2413  2020-01-30  632.419983  650.880005  618.000000  640.809998  640.809998   \n",
            "2414  2020-01-31  640.000000  653.000000  632.520020  650.570007  650.570007   \n",
            "2415  2020-02-03  673.690002  786.140015  673.520020  780.000000  780.000000   \n",
            "\n",
            "        Volume  \n",
            "2411  11788500  \n",
            "2412  17801500  \n",
            "2413  29005700  \n",
            "2414  15719300  \n",
            "2415  47065000  \n",
            "######################### Shape #########################\n",
            "(2416, 7)\n",
            "######################### Types #########################\n",
            "Date          object\n",
            "Open         float64\n",
            "High         float64\n",
            "Low          float64\n",
            "Close        float64\n",
            "Adj Close    float64\n",
            "Volume         int64\n",
            "dtype: object\n",
            "######################### NA #########################\n",
            "Date         0\n",
            "Open         0\n",
            "High         0\n",
            "Low          0\n",
            "Close        0\n",
            "Adj Close    0\n",
            "Volume       0\n",
            "dtype: int64\n",
            "######################### Qurtiles #########################\n",
            "            count          mean           std            min             0%  \\\n",
            "Open       2416.0  1.862711e+02  1.187402e+02      16.139999      16.139999   \n",
            "High       2416.0  1.895782e+02  1.208923e+02      16.629999      16.629999   \n",
            "Low        2416.0  1.829166e+02  1.168576e+02      14.980000      14.980000   \n",
            "Close      2416.0  1.864037e+02  1.191360e+02      15.800000      15.800000   \n",
            "Adj Close  2416.0  1.864037e+02  1.191360e+02      15.800000      15.800000   \n",
            "Volume     2416.0  5.572722e+06  4.987809e+06  118500.000000  118500.000000   \n",
            "\n",
            "                      5%           50%           95%           99%  \\\n",
            "Open           23.384999  2.130350e+02  3.519100e+02  4.235790e+02   \n",
            "High           24.022501  2.167450e+02  3.567500e+02  4.284705e+02   \n",
            "Low            22.867499  2.088700e+02  3.460250e+02  4.122865e+02   \n",
            "Close          23.565000  2.129600e+02  3.511675e+02  4.243455e+02   \n",
            "Adj Close      23.565000  2.129600e+02  3.511675e+02  4.243455e+02   \n",
            "Volume     633825.000000  4.578400e+06  1.476090e+07  2.459959e+07   \n",
            "\n",
            "                   100%           max  \n",
            "Open       6.736900e+02  6.736900e+02  \n",
            "High       7.861400e+02  7.861400e+02  \n",
            "Low        6.735200e+02  6.735200e+02  \n",
            "Close      7.800000e+02  7.800000e+02  \n",
            "Adj Close  7.800000e+02  7.800000e+02  \n",
            "Volume     4.706500e+07  4.706500e+07  \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df[\"Date\"] = pd.to_datetime(df[\"Date\"])\n",
        "tesla_df = df[[\"Date\", \"Close\"]]\n",
        "tesla_df.index = tesla_df[\"Date\"]\n",
        "tesla_df.drop(\"Date\", axis=1, inplace=True)\n",
        "tesla_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 324
        },
        "id": "vAgXK0VucwDJ",
        "outputId": "8dc1b722-287d-4f55-c80d-d7995c95e2ef"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.8/dist-packages/pandas/core/frame.py:4906: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame\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",
            "  return super().drop(\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                Close\n",
              "Date                 \n",
              "2010-06-29  23.889999\n",
              "2010-06-30  23.830000\n",
              "2010-07-01  21.959999\n",
              "2010-07-02  19.200001\n",
              "2010-07-06  16.110001"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-87df92d6-d4f5-4eb4-b304-8758d42f3de9\">\n",
              "    <div 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>2010-06-29</th>\n",
              "      <td>23.889999</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-06-30</th>\n",
              "      <td>23.830000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-07-01</th>\n",
              "      <td>21.959999</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-07-02</th>\n",
              "      <td>19.200001</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2010-07-06</th>\n",
              "      <td>16.110001</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-87df92d6-d4f5-4eb4-b304-8758d42f3de9')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-87df92d6-d4f5-4eb4-b304-8758d42f3de9 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-87df92d6-d4f5-4eb4-b304-8758d42f3de9');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "result_df = tesla_df.copy()\n",
        "tesla_df = tesla_df.values\n",
        "tesla_df = tesla_df.astype(\"float32\")\n",
        "tesla_df[0:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ICH1dHWqc5Kq",
        "outputId": "90ae4b7a-0446-428c-cea2-ab49c074c9c7"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[23.89],\n",
              "       [23.83],\n",
              "       [21.96],\n",
              "       [19.2 ],\n",
              "       [16.11]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(12,6))\n",
        "plt.plot(result_df[\"Close\"], color=\"blue\")\n",
        "plt.ylabel(\"Stock Price\")\n",
        "plt.xlabel(\"Time\")\n",
        "plt.title(\"Tesla Stock Price\")\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 404
        },
        "id": "kcN_TAKmc7ib",
        "outputId": "af62aab5-55d1-4b67-81c2-8a9096bd4828"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def split_data(dataframe, test_size):\n",
        "  position = int(round(len(dataframe) * (1-test_size)))\n",
        "  train = dataframe[:position]\n",
        "  test = dataframe[position:]\n",
        "  return train, test, position"
      ],
      "metadata": {
        "id": "kQKEpY9fc9Sh"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "train, test, position = split_data(tesla_df, 0.20)\n",
        "print(\"Train shape:\", train.shape, \" Test shape:\", test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KG1YnnIgdCse",
        "outputId": "b6d2fc82-b827-4e84-d632-4dfca5f7011a"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train shape: (1933, 1)  Test shape: (483, 1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def encoding_scaling(train, test):\n",
        "  scaler_train = MinMaxScaler(feature_range=(0,1))\n",
        "  train = scaler_train.fit_transform(train)\n",
        "  scaler_test = MinMaxScaler(feature_range=(0,1))\n",
        "  test = scaler_test.fit_transform(test)\n",
        "  return scaler_train, train, scaler_test, test"
      ],
      "metadata": {
        "id": "hXmzIHd0dESK"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "scaler_train, train, scaler_test, test = encoding_scaling(train, test)"
      ],
      "metadata": {
        "id": "CNS2aGKodGFn"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def create_features(data, lookback):\n",
        "  X, Y = [], []\n",
        "  for i in range(lookback, len(data)):\n",
        "    X.append(data[i-lookback:i,0])\n",
        "    Y.append(data[i,0])\n",
        "  return np.array(X), np.array(Y)"
      ],
      "metadata": {
        "id": "oRUg1tGydHYH"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "lookback=20\n",
        "X_train, y_train = create_features(train, lookback)\n",
        "X_test, y_test = create_features(test, lookback)\n",
        "print(\"X_train shape:\", X_train.shape, \" y_train shape:\", y_train.shape, \"\\nX_test shape:\", X_test.shape, \" y_test shape: \", y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qlNBI9U6dQFD",
        "outputId": "055a3bb4-72c0-4614-97ae-b3cb6df637ad"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "X_train shape: (1913, 20)  y_train shape: (1913,) \n",
            "X_test shape: (463, 20)  y_test shape:  (463,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))\n",
        "X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))\n",
        "y_train = y_train.reshape(-1,1)\n",
        "y_test = y_test.reshape(-1,1)\n",
        "print(\"X_train shape:\", X_train.shape, \" y_train shape:\", y_train.shape, \"\\nX_test shape:\", X_test.shape, \" y_test shape: \", y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WgmmWo8GdSDg",
        "outputId": "c8968d38-744f-4931-fa21-b8c5fed6c1a4"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "X_train shape: (1913, 1, 20)  y_train shape: (1913, 1) \n",
            "X_test shape: (463, 1, 20)  y_test shape:  (463, 1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def LSTM_create_and_fit_model(X_train,y_train, X_test, y_test, lookback=20, epochs=100, summary=True, fit=True):\n",
        "  model = Sequential()\n",
        "  model.add(LSTM(units=50, activation=\"relu\", input_shape=(X_train.shape[1], lookback)))\n",
        "  model.add(Dropout(0.2))\n",
        "  model.add(Dense(1))\n",
        "\n",
        "  model.compile(loss=\"mean_squared_error\", optimizer=\"adam\")\n",
        "  callbacks = [EarlyStopping(monitor=\"val_loss\", patience=3, verbose=1, mode=\"min\"), \n",
        "              ModelCheckpoint(filepath=\"mymodel.h5\", monitor=\"val_loss\", mode=\"min\", save_best_only=True, save_weights_only=False, verbose=1)]\n",
        "  \n",
        "  if summary:\n",
        "    model.summary()\n",
        "  \n",
        "  if fit:\n",
        "    history = model.fit(x=X_train, y=y_train, epochs=epochs, batch_size=20, \n",
        "                      validation_data=(X_test, y_test), callbacks=callbacks, shuffle=False)\n",
        "  \n",
        "  return model, history"
      ],
      "metadata": {
        "id": "djuZcQICdT7R"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model, history = LSTM_create_and_fit_model(X_train,y_train, X_test, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1OtNMCxcdVgS",
        "outputId": "b2e809d2-4501-4aa5-84ce-e66e1f815eee"
      },
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_1\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " lstm_1 (LSTM)               (None, 50)                14200     \n",
            "                                                                 \n",
            " dropout (Dropout)           (None, 50)                0         \n",
            "                                                                 \n",
            " dense (Dense)               (None, 1)                 51        \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 14,251\n",
            "Trainable params: 14,251\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n",
            "Epoch 1/100\n",
            "92/96 [===========================>..] - ETA: 0s - loss: 0.0096\n",
            "Epoch 1: val_loss improved from inf to 0.00385, saving model to mymodel.h5\n",
            "96/96 [==============================] - 3s 7ms/step - loss: 0.0097 - val_loss: 0.0039\n",
            "Epoch 2/100\n",
            "80/96 [========================>.....] - ETA: 0s - loss: 0.0061\n",
            "Epoch 2: val_loss improved from 0.00385 to 0.00340, saving model to mymodel.h5\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0075 - val_loss: 0.0034\n",
            "Epoch 3/100\n",
            "96/96 [==============================] - ETA: 0s - loss: 0.0062\n",
            "Epoch 3: val_loss improved from 0.00340 to 0.00315, saving model to mymodel.h5\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0062 - val_loss: 0.0032\n",
            "Epoch 4/100\n",
            "77/96 [=======================>......] - ETA: 0s - loss: 0.0046\n",
            "Epoch 4: val_loss improved from 0.00315 to 0.00298, saving model to mymodel.h5\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0061 - val_loss: 0.0030\n",
            "Epoch 5/100\n",
            "77/96 [=======================>......] - ETA: 0s - loss: 0.0035\n",
            "Epoch 5: val_loss improved from 0.00298 to 0.00259, saving model to mymodel.h5\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0051 - val_loss: 0.0026\n",
            "Epoch 6/100\n",
            "77/96 [=======================>......] - ETA: 0s - loss: 0.0035\n",
            "Epoch 6: val_loss did not improve from 0.00259\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0051 - val_loss: 0.0029\n",
            "Epoch 7/100\n",
            "94/96 [============================>.] - ETA: 0s - loss: 0.0047\n",
            "Epoch 7: val_loss did not improve from 0.00259\n",
            "96/96 [==============================] - 0s 3ms/step - loss: 0.0049 - val_loss: 0.0026\n",
            "Epoch 8/100\n",
            "77/96 [=======================>......] - ETA: 0s - loss: 0.0031\n",
            "Epoch 8: val_loss did not improve from 0.00259\n",
            "96/96 [==============================] - 0s 4ms/step - loss: 0.0047 - val_loss: 0.0029\n",
            "Epoch 8: early stopping\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def LSTM_model_evaluate(model):\n",
        "  loss = model.evaluate(X_test, y_test, batch_size=20)\n",
        "  print(\"Test Loss: %.2f\" % (100 * loss))\n",
        "  plt.figure(figsize=(10,5))\n",
        "  plt.plot(history.history[\"loss\"], color=\"r\", label=\"Training Loss\")\n",
        "  plt.plot(history.history[\"val_loss\"], color=\"b\", label=\"Validation Loss\")\n",
        "  plt.legend(loc=\"upper right\")\n",
        "  plt.xlabel(\"Epoch\", fontsize=16)\n",
        "  plt.ylabel(\"Loss\", fontsize=16)\n",
        "  plt.ylim([0, max(plt.ylim())])\n",
        "  plt.title(\"Training and Validation Loss\", fontsize=16);"
      ],
      "metadata": {
        "id": "aGxSSQx9dXQn"
      },
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "LSTM_model_evaluate(model)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 392
        },
        "id": "uDhtqAL6g63Y",
        "outputId": "9be5042e-3637-4406-c535-597b80cb2a87"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "24/24 [==============================] - 0s 2ms/step - loss: 0.0029\n",
            "Test Loss: 0.29\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 720x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def show_prediction(model, dataframe, X_train, X_test, y_train, y_test, lookback=20, plot=True):\n",
        "  train_predict = model.predict(X_train)\n",
        "  test_predict = model.predict(X_test)\n",
        "  train_predict = scaler_train.inverse_transform(train_predict)\n",
        "  test_predict = scaler_test.inverse_transform(test_predict) \n",
        "  y_train = scaler_train.inverse_transform(y_train)\n",
        "  y_test = scaler_test.inverse_transform(y_test)\n",
        "  RMSE_train = np.sqrt(mean_squared_error(y_train, train_predict))\n",
        "  RMSE_test = np.sqrt(mean_squared_error(y_test, test_predict))\n",
        "  print(\"############### Loss ###############\")\n",
        "  print(\"RMSE Train: \", RMSE_train, \"\\nRMSE Test: \", RMSE_test)\n",
        "\n",
        "  train_prediction_df = dataframe[lookback:position]\n",
        "  train_prediction_df[\"Predicted\"] = train_predict\n",
        "  print(\"############### Train Predictoion Head ###############\")\n",
        "  print(train_prediction_df.head())\n",
        "\n",
        "  test_prediction_df = dataframe[position+lookback:]\n",
        "  test_prediction_df[\"Predicted\"] = test_predict\n",
        "  print(\"############### Test Predictoion Head ###############\")\n",
        "  print(test_prediction_df.head())\n",
        "\n",
        "  if plot:\n",
        "    plt.figure(figsize=(14,5))\n",
        "    plt.plot(dataframe, label=\"Real Number of Passengers\")\n",
        "    plt.plot(train_prediction_df[\"Predicted\"], color=\"blue\", label=\"Train Predicted Stock Price\")\n",
        "    plt.plot(test_prediction_df[\"Predicted\"], color=\"red\", label=\"Test Predicted Stock Price\")\n",
        "    plt.title(\"Tesla Stock Price Prediction\")\n",
        "    plt.xlabel(\"Time\")\n",
        "    plt.ylabel(\"Stock Price\")\n",
        "    plt.legend()\n",
        "    plt.show()"
      ],
      "metadata": {
        "id": "UZ3jW6XYhBuM"
      },
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "show_prediction(model, result_df, X_train, X_test, y_train, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 923
        },
        "id": "vvGxwSzRhHU4",
        "outputId": "f2313032-cafe-42aa-f50e-7e5ac8ac1b41"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "60/60 [==============================] - 1s 5ms/step\n",
            "15/15 [==============================] - 0s 3ms/step\n",
            "############### Loss ###############\n",
            "RMSE Train:  20.371078 \n",
            "RMSE Test:  32.412537\n",
            "############### Train Predictoion Head ###############\n",
            "                Close  Predicted\n",
            "Date                            \n",
            "2010-07-28  20.719999  31.770124\n",
            "2010-07-29  20.350000  31.752583\n",
            "2010-07-30  19.940001  31.739342\n",
            "2010-08-02  20.920000  31.735056\n",
            "2010-08-03  21.950001  31.737738\n",
            "############### Test Predictoion Head ###############\n",
            "                 Close   Predicted\n",
            "Date                              \n",
            "2018-04-03  267.529999  294.364777\n",
            "2018-04-04  286.940002  291.490448\n",
            "2018-04-05  305.720001  288.877045\n",
            "2018-04-06  299.299988  288.430389\n",
            "2018-04-09  289.660004  287.613800\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-34-c5f201cb9f3b>:14: 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",
            "  train_prediction_df[\"Predicted\"] = train_predict\n",
            "<ipython-input-34-c5f201cb9f3b>:19: 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",
            "  test_prediction_df[\"Predicted\"] = test_predict\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1008x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "SmNOxECshJB-"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}