(feat) add mean reversion notebook

quants_lab/research_notebooks/mean_reversion_strat.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2023-06-23T18:54:06.001204Z",
+     "start_time": "2023-06-23T18:54:05.418412Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import pandas_ta as ta\n",
+    "\n",
+    "from quants_lab.utils import data_management\n",
+    "from quants_lab.backtesting.backtesting import Backtesting\n",
+    "from quants_lab.backtesting.backtesting_analysis import BacktestingAnalysis\n",
+    "\n",
+    "df = data_management.get_dataframe(\n",
+    "    exchange='binance_perpetual',\n",
+    "    trading_pair='ETH-USDT',\n",
+    "    interval='3m',\n",
+    ")\n",
+    "\n",
+    "def bbands_strategy(df):\n",
+    "    df.ta.bbands(length=100, std=3, append=True)\n",
+    "    df[\"side\"] = 0\n",
+    "    long_condition = df[\"BBP_100_3.0\"] < 0.0\n",
+    "    short_condition = df[\"BBP_100_3.0\"] > 1.0\n",
+    "    df.loc[long_condition, \"side\"] = 1\n",
+    "    df.loc[short_condition, \"side\"] = -1\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "outputs": [],
+   "source": [
+    "backtesting = Backtesting(candles_df=df)\n",
+    "\n",
+    "positions = backtesting.run_backtesting(\n",
+    "    strategy=bbands_strategy,\n",
+    "    order_amount=50,\n",
+    "    leverage=20,\n",
+    "    initial_portfolio=100,\n",
+    "    take_profit_multiplier=0.5,\n",
+    "    stop_loss_multiplier=5.0,\n",
+    "    time_limit=60 * 60 * 1,\n",
+    "    std_span=None,\n",
+    ")\n",
+    "backtesting_report = BacktestingAnalysis(df, positions, extra_rows=1, show_volume=False)\n"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-06-23T18:54:08.381976Z",
+     "start_time": "2023-06-23T18:54:06.002029Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Strategy Performance Report:\n",
+      "    - Net Profit: -4.07 USD (-4.07%)\n",
+      "    - Total Positions: 978\n",
+      "    - Win Signals: 581\n",
+      "    - Loss Signals: 397\n",
+      "    - Accuracy: 0.59%\n",
+      "    - Profit Factor: 0.97\n",
+      "    - Max Drawdown: -13.85 USD | -13.85%\n",
+      "    - Sharpe Ratio: -0.01\n",
+      "    - Duration: 6,478.55 Hours\n",
+      "    - Average Trade Duration: 48.62 minutes\n",
+      "    \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(backtesting_report.text_report())"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2023-06-23T18:54:09.658773Z",
+     "start_time": "2023-06-23T18:54:09.628910Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Set the backend to Plotly\n",
+    "pd.options.plotting.backend = \"plotly\"\n",
+    "\n",
+    "positions[\"ret_usd\"].cumsum().plot()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "is_executing": true,
+    "ExecuteTime": {
+     "start_time": "2023-06-23T18:54:11.277722Z"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}