{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e0f51511-48be-4871-b2e8-787b723aa5c1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mDEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621\u001b[0m\n",
      "Requirement already satisfied: pandas_datareader in /usr/local/lib/python3.9/site-packages (0.10.0)\n",
      "Requirement already satisfied: pandas>=0.23 in /usr/local/lib/python3.9/site-packages (from pandas_datareader) (1.3.4)\n",
      "Requirement already satisfied: lxml in /usr/local/lib/python3.9/site-packages (from pandas_datareader) (4.7.1)\n",
      "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.9/site-packages (from pandas_datareader) (2.26.0)\n",
      "Requirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.9/site-packages (from pandas>=0.23->pandas_datareader) (1.21.2)\n",
      "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.9/site-packages (from pandas>=0.23->pandas_datareader) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.9/site-packages (from pandas>=0.23->pandas_datareader) (2021.1)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/site-packages (from requests>=2.19.0->pandas_datareader) (1.26.7)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/site-packages (from requests>=2.19.0->pandas_datareader) (3.3)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/site-packages (from requests>=2.19.0->pandas_datareader) (2021.5.30)\n",
      "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/site-packages (from requests>=2.19.0->pandas_datareader) (2.0.7)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/site-packages (from python-dateutil>=2.7.3->pandas>=0.23->pandas_datareader) (1.16.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install pandas_datareader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "240712a7-02c3-45a5-afc7-9f485a3f5df4",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bbf04403-c61e-40bb-a517-b84b6edb5c2c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas_datareader as data\n",
    "import plotly.express as px\n",
    "import streamlit as st\n",
    "import requests\n",
    "from streamlit_lottie import st_lottie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d0839bc4-2d5d-42bd-a8e7-e9766b1dd32b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Today is:  2022-01-08\n",
      "Yesterday was:  2022-01-07\n"
     ]
    }
   ],
   "source": [
    "from datetime import date\n",
    "from datetime import timedelta\n",
    "today = date.today()\n",
    "print(\"Today is: \", today)\n",
    " \n",
    "# Yesterday date\n",
    "yesterday = today - timedelta(days = 1)\n",
    "print(\"Yesterday was: \", yesterday)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "25add0cc-c415-405d-9a46-8d1b7dc28aff",
   "metadata": {},
   "outputs": [
    {
     "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>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Open</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>Adj Close</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2007-12-31</th>\n",
       "      <td>7.160714</td>\n",
       "      <td>7.062500</td>\n",
       "      <td>7.125000</td>\n",
       "      <td>7.074286</td>\n",
       "      <td>5.393332e+08</td>\n",
       "      <td>6.065246</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-01-02</th>\n",
       "      <td>7.152143</td>\n",
       "      <td>6.876786</td>\n",
       "      <td>7.116786</td>\n",
       "      <td>6.958571</td>\n",
       "      <td>1.079179e+09</td>\n",
       "      <td>5.966034</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-01-03</th>\n",
       "      <td>7.049643</td>\n",
       "      <td>6.881786</td>\n",
       "      <td>6.978929</td>\n",
       "      <td>6.961786</td>\n",
       "      <td>8.420664e+08</td>\n",
       "      <td>5.968793</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-01-04</th>\n",
       "      <td>6.892857</td>\n",
       "      <td>6.388929</td>\n",
       "      <td>6.837500</td>\n",
       "      <td>6.430357</td>\n",
       "      <td>1.455832e+09</td>\n",
       "      <td>5.513163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008-01-07</th>\n",
       "      <td>6.557143</td>\n",
       "      <td>6.079643</td>\n",
       "      <td>6.473214</td>\n",
       "      <td>6.344286</td>\n",
       "      <td>2.072193e+09</td>\n",
       "      <td>5.439369</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-03</th>\n",
       "      <td>182.880005</td>\n",
       "      <td>177.710007</td>\n",
       "      <td>177.830002</td>\n",
       "      <td>182.009995</td>\n",
       "      <td>1.044879e+08</td>\n",
       "      <td>182.009995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-04</th>\n",
       "      <td>182.940002</td>\n",
       "      <td>179.119995</td>\n",
       "      <td>182.630005</td>\n",
       "      <td>179.699997</td>\n",
       "      <td>9.931040e+07</td>\n",
       "      <td>179.699997</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-05</th>\n",
       "      <td>180.169998</td>\n",
       "      <td>174.639999</td>\n",
       "      <td>179.610001</td>\n",
       "      <td>174.919998</td>\n",
       "      <td>9.453760e+07</td>\n",
       "      <td>174.919998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-06</th>\n",
       "      <td>175.300003</td>\n",
       "      <td>171.639999</td>\n",
       "      <td>172.699997</td>\n",
       "      <td>172.000000</td>\n",
       "      <td>9.690400e+07</td>\n",
       "      <td>172.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-01-07</th>\n",
       "      <td>174.139999</td>\n",
       "      <td>171.029999</td>\n",
       "      <td>172.889999</td>\n",
       "      <td>172.169998</td>\n",
       "      <td>8.658010e+07</td>\n",
       "      <td>172.169998</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3532 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  High         Low        Open       Close        Volume  \\\n",
       "Date                                                                       \n",
       "2007-12-31    7.160714    7.062500    7.125000    7.074286  5.393332e+08   \n",
       "2008-01-02    7.152143    6.876786    7.116786    6.958571  1.079179e+09   \n",
       "2008-01-03    7.049643    6.881786    6.978929    6.961786  8.420664e+08   \n",
       "2008-01-04    6.892857    6.388929    6.837500    6.430357  1.455832e+09   \n",
       "2008-01-07    6.557143    6.079643    6.473214    6.344286  2.072193e+09   \n",
       "...                ...         ...         ...         ...           ...   \n",
       "2022-01-03  182.880005  177.710007  177.830002  182.009995  1.044879e+08   \n",
       "2022-01-04  182.940002  179.119995  182.630005  179.699997  9.931040e+07   \n",
       "2022-01-05  180.169998  174.639999  179.610001  174.919998  9.453760e+07   \n",
       "2022-01-06  175.300003  171.639999  172.699997  172.000000  9.690400e+07   \n",
       "2022-01-07  174.139999  171.029999  172.889999  172.169998  8.658010e+07   \n",
       "\n",
       "             Adj Close  \n",
       "Date                    \n",
       "2007-12-31    6.065246  \n",
       "2008-01-02    5.966034  \n",
       "2008-01-03    5.968793  \n",
       "2008-01-04    5.513163  \n",
       "2008-01-07    5.439369  \n",
       "...                ...  \n",
       "2022-01-03  182.009995  \n",
       "2022-01-04  179.699997  \n",
       "2022-01-05  174.919998  \n",
       "2022-01-06  172.000000  \n",
       "2022-01-07  172.169998  \n",
       "\n",
       "[3532 rows x 6 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start='2008-01-01'\n",
    "end=yesterday;\n",
    "\n",
    "df=data.DataReader('AAPL','yahoo',start,end)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "371c3c87-c27d-4ed8-b8dc-96827621ec9e",
   "metadata": {},
   "outputs": [
    {
     "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",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Open</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>Adj Close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2007-12-31</td>\n",
       "      <td>7.160714</td>\n",
       "      <td>7.062500</td>\n",
       "      <td>7.125000</td>\n",
       "      <td>7.074286</td>\n",
       "      <td>5.393332e+08</td>\n",
       "      <td>6.065246</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>7.152143</td>\n",
       "      <td>6.876786</td>\n",
       "      <td>7.116786</td>\n",
       "      <td>6.958571</td>\n",
       "      <td>1.079179e+09</td>\n",
       "      <td>5.966034</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2008-01-03</td>\n",
       "      <td>7.049643</td>\n",
       "      <td>6.881786</td>\n",
       "      <td>6.978929</td>\n",
       "      <td>6.961786</td>\n",
       "      <td>8.420664e+08</td>\n",
       "      <td>5.968793</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008-01-04</td>\n",
       "      <td>6.892857</td>\n",
       "      <td>6.388929</td>\n",
       "      <td>6.837500</td>\n",
       "      <td>6.430357</td>\n",
       "      <td>1.455832e+09</td>\n",
       "      <td>5.513163</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2008-01-07</td>\n",
       "      <td>6.557143</td>\n",
       "      <td>6.079643</td>\n",
       "      <td>6.473214</td>\n",
       "      <td>6.344286</td>\n",
       "      <td>2.072193e+09</td>\n",
       "      <td>5.439369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Date      High       Low      Open     Close        Volume  Adj Close\n",
       "0 2007-12-31  7.160714  7.062500  7.125000  7.074286  5.393332e+08   6.065246\n",
       "1 2008-01-02  7.152143  6.876786  7.116786  6.958571  1.079179e+09   5.966034\n",
       "2 2008-01-03  7.049643  6.881786  6.978929  6.961786  8.420664e+08   5.968793\n",
       "3 2008-01-04  6.892857  6.388929  6.837500  6.430357  1.455832e+09   5.513163\n",
       "4 2008-01-07  6.557143  6.079643  6.473214  6.344286  2.072193e+09   5.439369"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=df.reset_index()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5fb45485-41d7-482d-9fb3-61a0500979f6",
   "metadata": {},
   "outputs": [
    {
     "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>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Open</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.160714</td>\n",
       "      <td>7.062500</td>\n",
       "      <td>7.125000</td>\n",
       "      <td>7.074286</td>\n",
       "      <td>5.393332e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7.152143</td>\n",
       "      <td>6.876786</td>\n",
       "      <td>7.116786</td>\n",
       "      <td>6.958571</td>\n",
       "      <td>1.079179e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.049643</td>\n",
       "      <td>6.881786</td>\n",
       "      <td>6.978929</td>\n",
       "      <td>6.961786</td>\n",
       "      <td>8.420664e+08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.892857</td>\n",
       "      <td>6.388929</td>\n",
       "      <td>6.837500</td>\n",
       "      <td>6.430357</td>\n",
       "      <td>1.455832e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.557143</td>\n",
       "      <td>6.079643</td>\n",
       "      <td>6.473214</td>\n",
       "      <td>6.344286</td>\n",
       "      <td>2.072193e+09</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       High       Low      Open     Close        Volume\n",
       "0  7.160714  7.062500  7.125000  7.074286  5.393332e+08\n",
       "1  7.152143  6.876786  7.116786  6.958571  1.079179e+09\n",
       "2  7.049643  6.881786  6.978929  6.961786  8.420664e+08\n",
       "3  6.892857  6.388929  6.837500  6.430357  1.455832e+09\n",
       "4  6.557143  6.079643  6.473214  6.344286  2.072193e+09"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "date=df['Date']\n",
    "df=df.drop(['Date','Adj Close'],axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3f54e6c9-51e2-4204-b546-3c3507934a21",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0            NaN\n",
       "1            NaN\n",
       "2            NaN\n",
       "3            NaN\n",
       "4            NaN\n",
       "          ...   \n",
       "3527    155.0014\n",
       "3528    155.3095\n",
       "3529    155.5677\n",
       "3530    155.7765\n",
       "3531    155.9963\n",
       "Name: Close, Length: 3532, dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "average100=df['Close'].rolling(100).mean()\n",
    "average100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3e94f473-3437-46ee-8645-b10a4107c89d",
   "metadata": {},
   "outputs": [],
   "source": [
    "average30=df['Close'].rolling(100).mean()\n",
    "#average365=df['Close'].rolling(365).mean()\n",
    "#average30"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4f6261c1-babd-4af4-b4d2-bfff78205834",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,6))\n",
    "plt.plot(date,df['Close'],label=\"Every day\")\n",
    "plt.plot(date,average100,color='red',label=\"Every 100 days\")\n",
    "plt.plot(date,average30,color='green',label=\"Every 30 days\")\n",
    "#plt.plot(average365,color='pink',label=\"Every year\")\n",
    "plt.title(\"Stock Prices\")\n",
    "plt.xlabel(\"Time\")\n",
    "plt.ylabel(\"Price\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9f4407aa-1503-4390-bcc6-c4db487207e1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3532, 5)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "51c98989-8d04-4ea3-97b3-1aadb79858da",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2472, 1)\n",
      "(1060, 1)\n"
     ]
    }
   ],
   "source": [
    "#Splitting data into training and testing\n",
    "\n",
    "data_training= pd.DataFrame(df['Close'][0:int(len(df)*0.7)])\n",
    "data_testing= pd.DataFrame(df['Close'][int(len(df)*0.7):int(len(df))])\n",
    "ydate= date[int(len(df)*0.7):int(len(df))]\n",
    "print(data_training.shape)\n",
    "print(data_testing.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a28f8a36-4203-45ce-ba03-5c9f4bf09996",
   "metadata": {},
   "outputs": [
    {
     "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>Close</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.074286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.958571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6.961786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.430357</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.344286</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Close\n",
       "0  7.074286\n",
       "1  6.958571\n",
       "2  6.961786\n",
       "3  6.430357\n",
       "4  6.344286"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_training.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e969567d-9485-4c0e-be6b-7e4fb61a88ef",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mDEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621\u001b[0m\n",
      "Requirement already satisfied: sklearn in /usr/local/lib/python3.9/site-packages (0.0)\n",
      "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.9/site-packages (from sklearn) (1.0.2)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.9/site-packages (from scikit-learn->sklearn) (3.0.0)\n",
      "Requirement already satisfied: scipy>=1.1.0 in /usr/local/lib/python3.9/site-packages (from scikit-learn->sklearn) (1.7.3)\n",
      "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.9/site-packages (from scikit-learn->sklearn) (1.1.0)\n",
      "Requirement already satisfied: numpy>=1.14.6 in /usr/local/lib/python3.9/site-packages (from scikit-learn->sklearn) (1.21.2)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "1a271bda-3d66-480d-ac85-9c1ecc105fb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "scaler=MinMaxScaler(feature_range=(0,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "8502118b-4b3b-4bd4-a71e-9c8629dfdf7b",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_train = scaler.fit_transform(data_training)\n",
    "dataset_test = scaler.transform(data_testing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d1a28f19-8f0e-42fb-bc3b-6d6cd25fc870",
   "metadata": {},
   "outputs": [],
   "source": [
    "def create_dataset(df):\n",
    "    x = []\n",
    "    y = []\n",
    "    for i in range(50, df.shape[0]):\n",
    "        x.append(df[i-50:i, 0])\n",
    "        y.append(df[i, 0])\n",
    "    x = np.array(x)\n",
    "    y = np.array(y)\n",
    "    return x,y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "878020b2-c0df-411b-8d84-784fee507265",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, y_train = create_dataset(dataset_train)\n",
    "x_test, y_test = create_dataset(dataset_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "11f88168-b4e7-4036-ba72-2f894dac9cbc",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
    "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "deb18a6a-37aa-446b-aa74-667b2bd47a8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#ML MODEL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "38c69363-1165-4304-98f8-72184a11b887",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mDEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621\u001b[0m\n",
      "Requirement already satisfied: keras in /usr/local/lib/python3.9/site-packages (2.7.0)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install keras"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "7d137174-27c0-4d4d-9411-92c5068485ce",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mDEPRECATION: Configuring installation scheme with distutils config files is deprecated and will no longer work in the near future. If you are using a Homebrew or Linuxbrew Python, please see discussion at https://github.com/Homebrew/homebrew-core/issues/76621\u001b[0m\n",
      "Requirement already satisfied: tensorflow in /usr/local/lib/python3.9/site-packages (2.7.0)\n",
      "Requirement already satisfied: keras<2.8,>=2.7.0rc0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (2.7.0)\n",
      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.21.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (0.23.1)\n",
      "Requirement already satisfied: tensorboard~=2.6 in /usr/local/lib/python3.9/site-packages (from tensorflow) (2.7.0)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.9/site-packages (from tensorflow) (3.3.0)\n",
      "Requirement already satisfied: wheel<1.0,>=0.32.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (0.37.0)\n",
      "Requirement already satisfied: flatbuffers<3.0,>=1.12 in /usr/local/lib/python3.9/site-packages (from tensorflow) (2.0)\n",
      "Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.1.2)\n",
      "Requirement already satisfied: tensorflow-estimator<2.8,~=2.7.0rc0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (2.7.0)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.1.0)\n",
      "Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.9/site-packages (from tensorflow) (12.0.0)\n",
      "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.13.3)\n",
      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.43.0)\n",
      "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.9/site-packages (from tensorflow) (4.0.1)\n",
      "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.6.3)\n",
      "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (3.6.0)\n",
      "Requirement already satisfied: numpy>=1.14.5 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.21.2)\n",
      "Requirement already satisfied: absl-py>=0.4.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.0.0)\n",
      "Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.9/site-packages (from tensorflow) (3.19.1)\n",
      "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.9/site-packages (from tensorflow) (0.2.0)\n",
      "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.9/site-packages (from tensorflow) (1.16.0)\n",
      "Requirement already satisfied: gast<0.5.0,>=0.2.1 in /usr/local/lib/python3.9/site-packages (from tensorflow) (0.4.0)\n",
      "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (1.8.1)\n",
      "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (57.4.0)\n",
      "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (2.0.2)\n",
      "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (3.3.6)\n",
      "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (2.3.3)\n",
      "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (0.6.1)\n",
      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (0.4.6)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.9/site-packages (from tensorboard~=2.6->tensorflow) (2.26.0)\n",
      "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow) (0.2.8)\n",
      "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow) (4.2.4)\n",
      "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow) (4.8)\n",
      "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.9/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow) (1.3.0)\n",
      "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.9/site-packages (from markdown>=2.6.8->tensorboard~=2.6->tensorflow) (4.10.0)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (2021.5.30)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (3.3)\n",
      "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (2.0.7)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (1.26.7)\n",
      "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard~=2.6->tensorflow) (3.7.0)\n",
      "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.9/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow) (0.4.8)\n",
      "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.9/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow) (3.1.1)\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install tensorflow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "364ba039-0f19-492e-8e17-9643e1265859",
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.layers import Dense, Dropout, LSTM\n",
    "from keras.models import Sequential"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "208077ec-f088-4ef9-ae93-8e275927f011",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "model.add(LSTM(units=96, return_sequences=True, input_shape=(x_train.shape[1], 1)))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(units=96,return_sequences=True))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(units=96,return_sequences=True))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(LSTM(units=96))\n",
    "model.add(Dropout(0.2))\n",
    "model.add(Dense(units=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "01fc5e62-1de0-40fe-9294-1f015373adbb",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))\n",
    "x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "ab95f2f0-b743-4012-9725-ccb1126df77c",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(loss='mean_squared_error', optimizer='adam')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "ec207a32-d66d-4526-ae07-07cf006112ce",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50\n",
      "76/76 [==============================] - 15s 123ms/step - loss: 0.0162\n",
      "Epoch 2/50\n",
      "76/76 [==============================] - 10s 129ms/step - loss: 0.0026\n",
      "Epoch 3/50\n",
      "76/76 [==============================] - 10s 136ms/step - loss: 0.0020\n",
      "Epoch 4/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 0.0022\n",
      "Epoch 5/50\n",
      "76/76 [==============================] - 11s 141ms/step - loss: 0.0019\n",
      "Epoch 6/50\n",
      "76/76 [==============================] - 11s 145ms/step - loss: 0.0021\n",
      "Epoch 7/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 0.0021\n",
      "Epoch 8/50\n",
      "76/76 [==============================] - 11s 150ms/step - loss: 0.0017\n",
      "Epoch 9/50\n",
      "76/76 [==============================] - 11s 147ms/step - loss: 0.0016\n",
      "Epoch 10/50\n",
      "76/76 [==============================] - 11s 146ms/step - loss: 0.0021\n",
      "Epoch 11/50\n",
      "76/76 [==============================] - 11s 148ms/step - loss: 0.0019\n",
      "Epoch 12/50\n",
      "76/76 [==============================] - 11s 150ms/step - loss: 0.0016\n",
      "Epoch 13/50\n",
      "76/76 [==============================] - 12s 158ms/step - loss: 0.0014\n",
      "Epoch 14/50\n",
      "76/76 [==============================] - 12s 153ms/step - loss: 0.0014\n",
      "Epoch 15/50\n",
      "76/76 [==============================] - 11s 151ms/step - loss: 0.0014\n",
      "Epoch 16/50\n",
      "76/76 [==============================] - 11s 147ms/step - loss: 0.0012\n",
      "Epoch 17/50\n",
      "76/76 [==============================] - 11s 150ms/step - loss: 0.0014\n",
      "Epoch 18/50\n",
      "76/76 [==============================] - 11s 151ms/step - loss: 0.0012\n",
      "Epoch 19/50\n",
      "76/76 [==============================] - 11s 149ms/step - loss: 0.0012\n",
      "Epoch 20/50\n",
      "76/76 [==============================] - 11s 151ms/step - loss: 0.0012\n",
      "Epoch 21/50\n",
      "76/76 [==============================] - 12s 163ms/step - loss: 0.0012\n",
      "Epoch 22/50\n",
      "76/76 [==============================] - 22s 287ms/step - loss: 0.0011\n",
      "Epoch 23/50\n",
      "76/76 [==============================] - 15s 195ms/step - loss: 0.0013\n",
      "Epoch 24/50\n",
      "76/76 [==============================] - 15s 202ms/step - loss: 0.0011\n",
      "Epoch 25/50\n",
      "76/76 [==============================] - 11s 151ms/step - loss: 0.0010\n",
      "Epoch 26/50\n",
      "76/76 [==============================] - 11s 148ms/step - loss: 0.0011\n",
      "Epoch 27/50\n",
      "76/76 [==============================] - 11s 150ms/step - loss: 0.0010\n",
      "Epoch 28/50\n",
      "76/76 [==============================] - 11s 145ms/step - loss: 9.9985e-04\n",
      "Epoch 29/50\n",
      "76/76 [==============================] - 11s 148ms/step - loss: 9.6926e-04\n",
      "Epoch 30/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 9.1884e-04\n",
      "Epoch 31/50\n",
      "76/76 [==============================] - 11s 146ms/step - loss: 9.6590e-04\n",
      "Epoch 32/50\n",
      "76/76 [==============================] - 11s 146ms/step - loss: 8.9258e-04\n",
      "Epoch 33/50\n",
      "76/76 [==============================] - 11s 145ms/step - loss: 8.9413e-04\n",
      "Epoch 34/50\n",
      "76/76 [==============================] - 12s 155ms/step - loss: 9.2726e-04\n",
      "Epoch 35/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 8.7176e-04\n",
      "Epoch 36/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 8.6551e-04\n",
      "Epoch 37/50\n",
      "76/76 [==============================] - 11s 143ms/step - loss: 8.3855e-04\n",
      "Epoch 38/50\n",
      "76/76 [==============================] - 11s 149ms/step - loss: 9.2502e-04\n",
      "Epoch 39/50\n",
      "76/76 [==============================] - 11s 149ms/step - loss: 8.1635e-04\n",
      "Epoch 40/50\n",
      "76/76 [==============================] - 11s 143ms/step - loss: 8.1621e-04\n",
      "Epoch 41/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 8.2319e-04\n",
      "Epoch 42/50\n",
      "76/76 [==============================] - 11s 141ms/step - loss: 8.8733e-04\n",
      "Epoch 43/50\n",
      "76/76 [==============================] - 11s 143ms/step - loss: 8.6521e-04\n",
      "Epoch 44/50\n",
      "76/76 [==============================] - 11s 140ms/step - loss: 7.7094e-04\n",
      "Epoch 45/50\n",
      "76/76 [==============================] - 11s 148ms/step - loss: 7.1819e-04\n",
      "Epoch 46/50\n",
      "76/76 [==============================] - 11s 143ms/step - loss: 7.8392e-04\n",
      "Epoch 47/50\n",
      "76/76 [==============================] - 11s 144ms/step - loss: 8.4255e-04\n",
      "Epoch 48/50\n",
      "76/76 [==============================] - 11s 143ms/step - loss: 7.7680e-04\n",
      "Epoch 49/50\n",
      "76/76 [==============================] - 11s 147ms/step - loss: 0.0010\n",
      "Epoch 50/50\n",
      "76/76 [==============================] - 13s 167ms/step - loss: 7.5341e-04\n"
     ]
    }
   ],
   "source": [
    "model.fit(x_train, y_train, epochs=50, batch_size=32)\n",
    "model.save('stock_prediction.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "2e167d0b-7b35-40ac-8726-1e427e58648e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x137b2abb0>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "predictions = model.predict(x_test)\n",
    "predictions = scaler.inverse_transform(predictions)\n",
    "y_test_scaled = scaler.inverse_transform(y_test.reshape(-1, 1))\n",
    "\n",
    "cydate=ydate[50:]\n",
    "fig, ax = plt.subplots(figsize=(16,8))\n",
    "ax.set_facecolor('#000041')\n",
    "ax.plot(cydate,y_test_scaled, color='red', label='Original price')\n",
    "plt.plot(cydate,predictions, color='cyan', label='Predicted price')\n",
    "plt.xlabel(\"Date\")\n",
    "plt.ylabel(\"Price\")\n",
    "plt.title(\"Stocks\")\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fbdfc51e-b24f-42e2-9a4b-ec709bcf7f1a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}