{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "66be0f9b-942f-421c-882b-5cf6a8d225ef",
   "metadata": {},
   "source": [
    "# Creating an AI Trading Bot using Machine Learning with help of AI"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f70ecd95-f883-40e1-a73d-1ade318c8783",
   "metadata": {},
   "source": [
    "## Used tools"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "314ddf94-059a-452a-8098-22b1ec78d5b1",
   "metadata": {},
   "source": [
    "- https://aistudio.google.com\n",
    "- https://alpaca.markets/\n",
    "- https://jupyter.org/\n",
    "- https://superai.pl/courses.html"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b8e5201-a668-4b6a-9be0-5172b5e67b95",
   "metadata": {},
   "source": [
    "## Creating AI Trading Bot with AI"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d07ca5d-c625-496a-bd5c-5efa72b3e404",
   "metadata": {},
   "source": [
    "### 1st Prompt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bccd6bdd-6e98-4f76-bd50-eb0f13f5636c",
   "metadata": {},
   "source": [
    "1. \"I would like to create a trading bot. It should be using machine learning to trade BTCUSD in one minute intervals and Alpaca Markets. Can you help me with that?\"\n",
    "\n",
    "(Remember: At the moment Alpaca uses different symbols for executing orders such as “BTC/USD” and checking portfolio positions such as “BTCUSD”.)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6cf0ec94-cdb3-47e5-918e-5ba2cfd6f16e",
   "metadata": {},
   "source": [
    "#### Keys to Alpaca"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7d232c4b-7f4a-4f9d-b557-1abe46047672",
   "metadata": {},
   "outputs": [],
   "source": [
    "KEY_ID = \"your API KEY\" #replace it with your own KEY_ID from Alpaca: https://alpaca.markets/\n",
    "SECRET_KEY = \"your SECRET KEY\" #replace it with your own SECRET_KEY from Alpaca"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea5c66d3-6c54-49a0-800e-7dd663fec83c",
   "metadata": {},
   "source": [
    "### 1st Attempt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "56fce22c-c529-40c1-ae46-3576bcb75475",
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86801639-ce2c-4bac-bf23-94ab71cf70b7",
   "metadata": {},
   "source": [
    "Step 1: Alpaca Setup & Python Environment\n",
    "\n",
    "    Sign up for an Alpaca account: https://alpaca.markets/\n",
    "\n",
    "        Get your API Key ID and Secret Key from your paper trading account dashboard.\n",
    "\n",
    "    Install necessary Python libraries:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91850edf-7220-407e-a577-7a8cf4ee6ca9",
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install alpaca-trade-api pandas scikit-learn xgboost numpy pandas-ta"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "41adbca4-5621-4491-8541-3dd4f52eed2b",
   "metadata": {},
   "source": [
    "Set up API credentials (environment variables are best):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bc5e6181-d205-476d-8c17-8cecda0c01ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import alpaca_trade_api as tradeapi\n",
    "import pandas as pd\n",
    "from datetime import datetime, timedelta\n",
    "import time\n",
    "\n",
    "# For Paper Trading\n",
    "os.environ['APCA_API_BASE_URL'] = 'https://paper-api.alpaca.markets'\n",
    "# Replace with your actual keys or set them as environment variables\n",
    "os.environ['APCA_API_KEY_ID'] = \"your API KEY\" #replace it with your own KEY_ID from Alpaca: https://alpaca.markets/\n",
    "os.environ['APCA_API_SECRET_KEY'] = \"your SECRET KEY\" #replace it with your own SECRET_KEY from Alpaca\n",
    "\n",
    "API_KEY = os.getenv('APCA_API_KEY_ID')\n",
    "API_SECRET = os.getenv('APCA_API_SECRET_KEY')\n",
    "BASE_URL = os.getenv('APCA_API_BASE_URL')\n",
    "\n",
    "api = tradeapi.REST(API_KEY, API_SECRET, BASE_URL, api_version='v2')\n",
    "\n",
    "print(\"Connected to Alpaca Paper Trading.\")\n",
    "# Check account\n",
    "# account = api.get_account()\n",
    "# print(f\"Account status: {account.status}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45682be7-b549-422b-8a7d-1d9dbd8f2672",
   "metadata": {},
   "source": [
    "Step 2: Data Acquisition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "923fea7c-910e-45cb-b19f-3b7a3002322c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def fetch_data(symbol, timeframe, start_date_str, end_date_str=None):\n",
    "    \"\"\"Fetches historical crypto data from Alpaca.\"\"\"\n",
    "    if end_date_str is None:\n",
    "        end_date_str = datetime.now().strftime('%Y-%m-%d')\n",
    "\n",
    "    # Alpaca API expects ISO 8601 format for start/end times\n",
    "    # And it has a limit on how many bars can be fetched per request (e.g., 10000 for crypto)\n",
    "    # So we may need to fetch in chunks if requesting a long period.\n",
    "\n",
    "    all_bars = []\n",
    "    start_dt = pd.to_datetime(start_date_str, utc=True)\n",
    "    end_dt = pd.to_datetime(end_date_str, utc=True)\n",
    "\n",
    "    # Fetch data in chunks to avoid hitting API limits for very long periods\n",
    "    # For 1-minute data, 10000 bars is about 7 days.\n",
    "    # Let's fetch data in smaller chunks, e.g., 5 days at a time.\n",
    "    current_start = start_dt\n",
    "    while current_start < end_dt:\n",
    "        chunk_end = min(current_start + timedelta(days=5), end_dt) # Adjust chunk size as needed\n",
    "        print(f\"Fetching data from {current_start.isoformat()} to {chunk_end.isoformat()}\")\n",
    "\n",
    "        # Alpaca's get_crypto_bars expects start and end in ISO format\n",
    "        bars = api.get_crypto_bars(\n",
    "            symbol,\n",
    "            timeframe,\n",
    "            start=current_start.isoformat(),\n",
    "            end=chunk_end.isoformat(),\n",
    "            limit=10000 # Max limit per request\n",
    "        ).df\n",
    "\n",
    "        if bars.empty:\n",
    "            print(f\"No data found for chunk starting {current_start.isoformat()}\")\n",
    "            if current_start + timedelta(days=5) > end_dt and not all_bars: # if first chunk and no data\n",
    "                 break\n",
    "            current_start += timedelta(days=5) # Move to next chunk period\n",
    "            time.sleep(1) # Be nice to the API\n",
    "            continue\n",
    "\n",
    "        all_bars.append(bars)\n",
    "        # Update current_start to the timestamp of the last bar fetched + 1 minute\n",
    "        # to avoid overlap and to ensure we move forward.\n",
    "        if not bars.index.empty:\n",
    "            current_start = bars.index[-1] + pd.Timedelta(minutes=1)\n",
    "        else: # Should not happen if bars is not empty, but as a safeguard\n",
    "            current_start += timedelta(days=5)\n",
    "\n",
    "        time.sleep(1) # Respect API rate limits\n",
    "\n",
    "    if not all_bars:\n",
    "        print(\"No data fetched. Check your date range or symbol.\")\n",
    "        return pd.DataFrame()\n",
    "\n",
    "    df = pd.concat(all_bars)\n",
    "    df = df[~df.index.duplicated(keep='first')] # Remove potential duplicates from chunking\n",
    "    df = df.sort_index() # Ensure chronological order\n",
    "    df = df[df.index <= end_dt] # Ensure we don't go past the requested end_dt\n",
    "    return df\n",
    "\n",
    "# Example usage:\n",
    "symbol = \"BTC/USD\" # Alpaca uses \"BTC/USD\" for crypto pairs\n",
    "timeframe = tradeapi. টাইমফ্রেম.মিনিট # or \"1Min\" for older SDK versions\n",
    "# Fetch last 30 days of data for example\n",
    "start_date = (datetime.now() - timedelta(days=30)).strftime('%Y-%m-%d')\n",
    "# end_date = datetime.now().strftime('%Y-%m-%d') # Fetches up to now\n",
    "\n",
    "btc_data = fetch_data(symbol, timeframe, start_date)\n",
    "if not btc_data.empty:\n",
    "    print(f\"Fetched {len(btc_data)} rows of {symbol} data.\")\n",
    "    print(btc_data.head())\n",
    "    print(btc_data.tail())\n",
    "else:\n",
    "    print(\"Failed to fetch data.\")"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}