{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dotenv import load_dotenv\n",
    "import os \n",
    "from alpha_vantage.timeseries import TimeSeries\n",
    "import pandas as pd\n",
    "import hopsworks\n",
    "import re \n",
    "import modal \n",
    "#prepocessing\n",
    "import requests\n",
    "import pandas as pd\n",
    "import json\n",
    "import pandas_market_calendars as mcal\n",
    "import datetime\n",
    "import numpy as np\n",
    "from datetime import datetime, timedelta\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "            1. open  2. high    3. low  4. close    5. volume\n",
      "date                                                         \n",
      "2024-05-02   182.86   184.60  176.0200    180.01   89148041.0\n",
      "2024-05-01   182.00   185.86  179.0100    179.99   92829719.0\n",
      "2024-04-30   186.98   190.95  182.8401    183.28  127031787.0\n",
      "2024-04-29   188.42   198.87  184.5400    194.05  243869678.0\n",
      "2024-04-26   168.85   172.12  166.3700    168.29  109815725.0\n"
     ]
    }
   ],
   "source": [
    "load_dotenv()\n",
    "\n",
    "api_key = os.environ.get('stocks_api') # Replace this with your actual API key\n",
    "ts = TimeSeries(key=api_key, output_format='pandas')\n",
    "\n",
    "# Fetch daily adjusted stock prices; adjust the symbol as needed\n",
    "data, meta_data = ts.get_daily(symbol='TSLA', outputsize='full')\n",
    "\n",
    "print(data.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>1. open</th>\n",
       "      <th>2. high</th>\n",
       "      <th>3. low</th>\n",
       "      <th>4. close</th>\n",
       "      <th>5. volume</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</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>2024-05-02</th>\n",
       "      <td>182.86</td>\n",
       "      <td>184.6000</td>\n",
       "      <td>176.0200</td>\n",
       "      <td>180.01</td>\n",
       "      <td>89148041.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-01</th>\n",
       "      <td>182.00</td>\n",
       "      <td>185.8600</td>\n",
       "      <td>179.0100</td>\n",
       "      <td>179.99</td>\n",
       "      <td>92829719.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-30</th>\n",
       "      <td>186.98</td>\n",
       "      <td>190.9500</td>\n",
       "      <td>182.8401</td>\n",
       "      <td>183.28</td>\n",
       "      <td>127031787.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-29</th>\n",
       "      <td>188.42</td>\n",
       "      <td>198.8700</td>\n",
       "      <td>184.5400</td>\n",
       "      <td>194.05</td>\n",
       "      <td>243869678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-26</th>\n",
       "      <td>168.85</td>\n",
       "      <td>172.1200</td>\n",
       "      <td>166.3700</td>\n",
       "      <td>168.29</td>\n",
       "      <td>109815725.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-06</th>\n",
       "      <td>20.00</td>\n",
       "      <td>20.0000</td>\n",
       "      <td>15.8300</td>\n",
       "      <td>16.11</td>\n",
       "      <td>6866900.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-02</th>\n",
       "      <td>23.00</td>\n",
       "      <td>23.1000</td>\n",
       "      <td>18.7100</td>\n",
       "      <td>19.20</td>\n",
       "      <td>5139800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-07-01</th>\n",
       "      <td>25.00</td>\n",
       "      <td>25.9200</td>\n",
       "      <td>20.2700</td>\n",
       "      <td>21.96</td>\n",
       "      <td>8218800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-06-30</th>\n",
       "      <td>25.79</td>\n",
       "      <td>30.4192</td>\n",
       "      <td>23.3000</td>\n",
       "      <td>23.83</td>\n",
       "      <td>17187100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010-06-29</th>\n",
       "      <td>19.00</td>\n",
       "      <td>25.0000</td>\n",
       "      <td>17.5400</td>\n",
       "      <td>23.89</td>\n",
       "      <td>18766300.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3485 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            1. open   2. high    3. low  4. close    5. volume\n",
       "date                                                          \n",
       "2024-05-02   182.86  184.6000  176.0200    180.01   89148041.0\n",
       "2024-05-01   182.00  185.8600  179.0100    179.99   92829719.0\n",
       "2024-04-30   186.98  190.9500  182.8401    183.28  127031787.0\n",
       "2024-04-29   188.42  198.8700  184.5400    194.05  243869678.0\n",
       "2024-04-26   168.85  172.1200  166.3700    168.29  109815725.0\n",
       "...             ...       ...       ...       ...          ...\n",
       "2010-07-06    20.00   20.0000   15.8300     16.11    6866900.0\n",
       "2010-07-02    23.00   23.1000   18.7100     19.20    5139800.0\n",
       "2010-07-01    25.00   25.9200   20.2700     21.96    8218800.0\n",
       "2010-06-30    25.79   30.4192   23.3000     23.83   17187100.0\n",
       "2010-06-29    19.00   25.0000   17.5400     23.89   18766300.0\n",
       "\n",
       "[3485 rows x 5 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "DatetimeIndex: 3485 entries, 2024-05-02 to 2010-06-29\n",
      "Data columns (total 5 columns):\n",
      " #   Column     Non-Null Count  Dtype  \n",
      "---  ------     --------------  -----  \n",
      " 0   1. open    3485 non-null   float64\n",
      " 1   2. high    3485 non-null   float64\n",
      " 2   3. low     3485 non-null   float64\n",
      " 3   4. close   3485 non-null   float64\n",
      " 4   5. volume  3485 non-null   float64\n",
      "dtypes: float64(5)\n",
      "memory usage: 163.4 KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'1. Information': 'Daily Prices (open, high, low, close) and Volumes',\n",
       " '2. Symbol': 'TSLA',\n",
       " '3. Last Refreshed': '2024-05-02',\n",
       " '4. Output Size': 'Full size',\n",
       " '5. Time Zone': 'US/Eastern'}"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "meta_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Stock market:\n",
    "def today_is_a_business_day(today):\n",
    "    # Get the NYSE calendar\n",
    "    cal = mcal.get_calendar('NYSE')\n",
    "    schedule = cal.schedule(start_date=today, end_date=today) # Get the NYSE calendar's open and close times for the specified period\n",
    "    try:\n",
    "        isBusinessDay = schedule.market_open.dt.strftime('%Y-%m-%d')\n",
    "        return True\n",
    "    except:\n",
    "        print('Today {} is not a business day'.format(today))\n",
    "        return False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def next_business_day(today):\n",
    "    \n",
    "    # Real tomorrow\n",
    "    tomorrow = (today + timedelta(days=1)).strftime(\"%Y-%m-%d\")\n",
    "    \n",
    "    # Get the NYSE calendar\n",
    "    cal = mcal.get_calendar('NYSE')\n",
    "\n",
    "    found_next_business_day = False \n",
    "    while not found_next_business_day:\n",
    "        schedule = cal.schedule(start_date=tomorrow, end_date=tomorrow) # Get the NYSE calendar's open and close times for the specified period\n",
    "        try:\n",
    "            isBusinessDay = schedule.market_open.dt.strftime('%Y-%m-%d') # Only need a list of dates when it's open (not open and close times)\n",
    "            found_next_business_day = True\n",
    "        except:\n",
    "            print('The date {} is not a business day'.format(tomorrow))\n",
    "            tomorrow = (datetime.datetime.strptime(tomorrow,\"%Y-%m-%d\") + timedelta(days=1)).strftime(\"%Y-%m-%d\")\n",
    "            \n",
    "    return isBusinessDay.to_numpy()[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_business_day(start_date,end_date):\n",
    "    \"\"\"\n",
    "    Given a start_date and end_date.\n",
    "    \n",
    "    `Returns`:\n",
    "    \n",
    "    isBusinessDay: list of str (with all dates being business days)\n",
    "    is_open: boolean list\n",
    "        e.g is_open = [1,0,...,1] means that start_date = open, day after start_date = closed, and end_date = open\n",
    "    \"\"\"\n",
    "    \n",
    "    # Save for later\n",
    "    end_date_save = end_date\n",
    "    \n",
    "    # Get the NYSE calendar\n",
    "    cal = mcal.get_calendar('NYSE')\n",
    "\n",
    "    # Get the NYSE calendar's open and close times for the specified period\n",
    "    schedule = cal.schedule(start_date=start_date, end_date=end_date)\n",
    "    \n",
    "    # Only need a list of dates when it's open (not open and close times)\n",
    "    isBusinessDay = np.array(schedule.market_open.dt.strftime('%Y-%m-%d')) \n",
    "    \n",
    "    # Go over all days: \n",
    "    delta = datetime.timedelta(days=1)\n",
    "    start_date = datetime.datetime.strptime(start_date,\"%Y-%m-%d\") #datetime.date(2015, 7, 16)\n",
    "    end_date = datetime.datetime.strptime(end_date,\"%Y-%m-%d\") #datetime.date(2023, 1, 4)\n",
    "    \n",
    "    # Extract days from the timedelta object\n",
    "    num_days = (end_date - start_date).days + 1\n",
    "    \n",
    "    # Create boolean array for days being open (1) and closed (0) \n",
    "    is_open = np.zeros(num_days)\n",
    "    \n",
    "    # iterate over range of dates\n",
    "    current_BusinessDay = isBusinessDay[0]\n",
    "    count_dates = 0\n",
    "    next_BusinessDay = 0\n",
    "    \n",
    "    while (start_date <= end_date):\n",
    "    \n",
    "        if start_date.strftime('%Y-%m-%d') == current_BusinessDay:\n",
    "            is_open[count_dates] = True\n",
    "\n",
    "            if current_BusinessDay == end_date_save or current_BusinessDay==isBusinessDay[-1]:\n",
    "                break\n",
    "            else:\n",
    "                next_BusinessDay += 1\n",
    "                current_BusinessDay = isBusinessDay[next_BusinessDay]\n",
    "        else:\n",
    "            is_open[count_dates] = False\n",
    "\n",
    "        count_dates += 1   \n",
    "        start_date += delta\n",
    "        \n",
    "    print(np.shape(is_open))\n",
    "        \n",
    "    return isBusinessDay, is_open"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def clean_column_name(name):\n",
    "    # Remove all non-letter characters\n",
    "    cleaned_name = re.sub(r'[^a-zA-Z]', '', name)\n",
    "    return cleaned_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.columns = [clean_column_name(col) for col in data.columns]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2024-05-02</th>\n",
       "      <td>182.86</td>\n",
       "      <td>184.60</td>\n",
       "      <td>176.0200</td>\n",
       "      <td>180.01</td>\n",
       "      <td>89148041.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-05-01</th>\n",
       "      <td>182.00</td>\n",
       "      <td>185.86</td>\n",
       "      <td>179.0100</td>\n",
       "      <td>179.99</td>\n",
       "      <td>92829719.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-30</th>\n",
       "      <td>186.98</td>\n",
       "      <td>190.95</td>\n",
       "      <td>182.8401</td>\n",
       "      <td>183.28</td>\n",
       "      <td>127031787.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-29</th>\n",
       "      <td>188.42</td>\n",
       "      <td>198.87</td>\n",
       "      <td>184.5400</td>\n",
       "      <td>194.05</td>\n",
       "      <td>243869678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2024-04-26</th>\n",
       "      <td>168.85</td>\n",
       "      <td>172.12</td>\n",
       "      <td>166.3700</td>\n",
       "      <td>168.29</td>\n",
       "      <td>109815725.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              open    high       low   close       volume\n",
       "date                                                     \n",
       "2024-05-02  182.86  184.60  176.0200  180.01   89148041.0\n",
       "2024-05-01  182.00  185.86  179.0100  179.99   92829719.0\n",
       "2024-04-30  186.98  190.95  182.8401  183.28  127031787.0\n",
       "2024-04-29  188.42  198.87  184.5400  194.05  243869678.0\n",
       "2024-04-26  168.85  172.12  166.3700  168.29  109815725.0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.reset_index(inplace=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-05-02</td>\n",
       "      <td>182.86</td>\n",
       "      <td>184.60</td>\n",
       "      <td>176.0200</td>\n",
       "      <td>180.01</td>\n",
       "      <td>89148041.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-05-01</td>\n",
       "      <td>182.00</td>\n",
       "      <td>185.86</td>\n",
       "      <td>179.0100</td>\n",
       "      <td>179.99</td>\n",
       "      <td>92829719.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-04-30</td>\n",
       "      <td>186.98</td>\n",
       "      <td>190.95</td>\n",
       "      <td>182.8401</td>\n",
       "      <td>183.28</td>\n",
       "      <td>127031787.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-04-29</td>\n",
       "      <td>188.42</td>\n",
       "      <td>198.87</td>\n",
       "      <td>184.5400</td>\n",
       "      <td>194.05</td>\n",
       "      <td>243869678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-04-26</td>\n",
       "      <td>168.85</td>\n",
       "      <td>172.12</td>\n",
       "      <td>166.3700</td>\n",
       "      <td>168.29</td>\n",
       "      <td>109815725.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        date    open    high       low   close       volume\n",
       "0 2024-05-02  182.86  184.60  176.0200  180.01   89148041.0\n",
       "1 2024-05-01  182.00  185.86  179.0100  179.99   92829719.0\n",
       "2 2024-04-30  186.98  190.95  182.8401  183.28  127031787.0\n",
       "3 2024-04-29  188.42  198.87  184.5400  194.05  243869678.0\n",
       "4 2024-04-26  168.85  172.12  166.3700  168.29  109815725.0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-05-02</td>\n",
       "      <td>182.86</td>\n",
       "      <td>184.6000</td>\n",
       "      <td>176.0200</td>\n",
       "      <td>180.01</td>\n",
       "      <td>89148041.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-05-01</td>\n",
       "      <td>182.00</td>\n",
       "      <td>185.8600</td>\n",
       "      <td>179.0100</td>\n",
       "      <td>179.99</td>\n",
       "      <td>92829719.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-04-30</td>\n",
       "      <td>186.98</td>\n",
       "      <td>190.9500</td>\n",
       "      <td>182.8401</td>\n",
       "      <td>183.28</td>\n",
       "      <td>127031787.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-04-29</td>\n",
       "      <td>188.42</td>\n",
       "      <td>198.8700</td>\n",
       "      <td>184.5400</td>\n",
       "      <td>194.05</td>\n",
       "      <td>243869678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-04-26</td>\n",
       "      <td>168.85</td>\n",
       "      <td>172.1200</td>\n",
       "      <td>166.3700</td>\n",
       "      <td>168.29</td>\n",
       "      <td>109815725.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3480</th>\n",
       "      <td>2010-07-06</td>\n",
       "      <td>20.00</td>\n",
       "      <td>20.0000</td>\n",
       "      <td>15.8300</td>\n",
       "      <td>16.11</td>\n",
       "      <td>6866900.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3481</th>\n",
       "      <td>2010-07-02</td>\n",
       "      <td>23.00</td>\n",
       "      <td>23.1000</td>\n",
       "      <td>18.7100</td>\n",
       "      <td>19.20</td>\n",
       "      <td>5139800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3482</th>\n",
       "      <td>2010-07-01</td>\n",
       "      <td>25.00</td>\n",
       "      <td>25.9200</td>\n",
       "      <td>20.2700</td>\n",
       "      <td>21.96</td>\n",
       "      <td>8218800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3483</th>\n",
       "      <td>2010-06-30</td>\n",
       "      <td>25.79</td>\n",
       "      <td>30.4192</td>\n",
       "      <td>23.3000</td>\n",
       "      <td>23.83</td>\n",
       "      <td>17187100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3484</th>\n",
       "      <td>2010-06-29</td>\n",
       "      <td>19.00</td>\n",
       "      <td>25.0000</td>\n",
       "      <td>17.5400</td>\n",
       "      <td>23.89</td>\n",
       "      <td>18766300.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3485 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           date    open      high       low   close       volume\n",
       "0    2024-05-02  182.86  184.6000  176.0200  180.01   89148041.0\n",
       "1    2024-05-01  182.00  185.8600  179.0100  179.99   92829719.0\n",
       "2    2024-04-30  186.98  190.9500  182.8401  183.28  127031787.0\n",
       "3    2024-04-29  188.42  198.8700  184.5400  194.05  243869678.0\n",
       "4    2024-04-26  168.85  172.1200  166.3700  168.29  109815725.0\n",
       "...         ...     ...       ...       ...     ...          ...\n",
       "3480 2010-07-06   20.00   20.0000   15.8300   16.11    6866900.0\n",
       "3481 2010-07-02   23.00   23.1000   18.7100   19.20    5139800.0\n",
       "3482 2010-07-01   25.00   25.9200   20.2700   21.96    8218800.0\n",
       "3483 2010-06-30   25.79   30.4192   23.3000   23.83   17187100.0\n",
       "3484 2010-06-29   19.00   25.0000   17.5400   23.89   18766300.0\n",
       "\n",
       "[3485 rows x 6 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the date range you're interested in\n",
    "yesterday =datetime.now()-timedelta(days=1)\n",
    "two_years_back = yesterday - timedelta(days=684)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Filter the DataFrame to this range\n",
    "filtered_df = data[(data['date'] >= two_years_back) & (data['date'] <= yesterday)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "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>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-05-02</td>\n",
       "      <td>182.86</td>\n",
       "      <td>184.60</td>\n",
       "      <td>176.0200</td>\n",
       "      <td>180.01</td>\n",
       "      <td>89148041.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-05-01</td>\n",
       "      <td>182.00</td>\n",
       "      <td>185.86</td>\n",
       "      <td>179.0100</td>\n",
       "      <td>179.99</td>\n",
       "      <td>92829719.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-04-30</td>\n",
       "      <td>186.98</td>\n",
       "      <td>190.95</td>\n",
       "      <td>182.8401</td>\n",
       "      <td>183.28</td>\n",
       "      <td>127031787.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-04-29</td>\n",
       "      <td>188.42</td>\n",
       "      <td>198.87</td>\n",
       "      <td>184.5400</td>\n",
       "      <td>194.05</td>\n",
       "      <td>243869678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-04-26</td>\n",
       "      <td>168.85</td>\n",
       "      <td>172.12</td>\n",
       "      <td>166.3700</td>\n",
       "      <td>168.29</td>\n",
       "      <td>109815725.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        date    open    high       low   close       volume\n",
       "0 2024-05-02  182.86  184.60  176.0200  180.01   89148041.0\n",
       "1 2024-05-01  182.00  185.86  179.0100  179.99   92829719.0\n",
       "2 2024-04-30  186.98  190.95  182.8401  183.28  127031787.0\n",
       "3 2024-04-29  188.42  198.87  184.5400  194.05  243869678.0\n",
       "4 2024-04-26  168.85  172.12  166.3700  168.29  109815725.0"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2022-06-21 00:00:00\n",
      "2024-05-02 00:00:00\n"
     ]
    }
   ],
   "source": [
    "print(filtered_df['date'].min())\n",
    "print(filtered_df['date'].max())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(470, 6)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.4"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}