feat: optim_supertrend_vectorbt.ipynb

notebooks/optim_supertrend_vectorbt.ipynb

@@ -0,0 +1,229 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7e5f72c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# filename: optim_supertrend_vectorbt.ipynb\n",
+    "\n",
+    "# --- 1. Imports and Setup ---\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import pandas_ta as ta\n",
+    "import vectorbt as vbt\n",
+    "\n",
+    "print(\"Libraries imported.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d38122d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 2. Configuration ---\n",
+    "# This is the control panel for the optimization.\n",
+    "# Change the parameters here to analyze different datasets or strategy settings.\n",
+    "\n",
+    "# --- Data Input ---\n",
+    "# Assumes the file is in the project's 'data/parquet/' directory\n",
+    "DATA_FILENAME = \"EURUSD_M15_2024-09-14_to_2025-09-14.parquet\"\n",
+    "# The frequency of the data is crucial for correct performance calculation.\n",
+    "# Examples: '15min', '1H', '4H', 'D'\n",
+    "FREQ = '15min'\n",
+    "\n",
+    "# --- Optimization Parameters for Supertrend ---\n",
+    "# We define the ranges for the grid search here.\n",
+    "supert_period_range = np.arange(7, 22, 2)    # Test periods from 7 to 21\n",
+    "supert_multiplier_range = np.arange(2.0, 5.1, 0.5) # Test multipliers from 2.0 to 5.0\n",
+    "\n",
+    "# --- Backtest Settings ---\n",
+    "INIT_CASH = 10000\n",
+    "FEES = 0.0001      # 0.01% fee per trade\n",
+    "SLIPPAGE = 0.0001  # 0.01% slippage per trade\n",
+    "\n",
+    "# --- Analysis Settings ---\n",
+    "# The metric to sort the results by\n",
+    "OPTIMIZE_FOR = 'Sharpe Ratio'\n",
+    "# How many top results to display\n",
+    "N_TOP_RESULTS = 10\n",
+    "\n",
+    "# --- Path Construction ---\n",
+    "project_root = os.path.abspath(os.path.join(os.getcwd(), \"..\"))\n",
+    "file_path = os.path.join(project_root, \"data\", \"parquet\", DATA_FILENAME)\n",
+    "\n",
+    "print(\"Configuration loaded.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c17eeb09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 3. Data Loading and Indicator Calculation ---\n",
+    "print(f\"Loading data from: {file_path}\")\n",
+    "try:\n",
+    "    price_data = pd.read_parquet(file_path)\n",
+    "    price_data.set_index('Time', inplace=True)\n",
+    "    print(f\"Data loaded successfully: {len(price_data)} bars.\")\n",
+    "except Exception as e:\n",
+    "    print(f\"Error loading data: {e}\")\n",
+    "    exit()\n",
+    "\n",
+    "# --- CORRECTED APPROACH: Create a custom wrapper for pandas-ta ---\n",
+    "# This wrapper function will call pandas-ta and return only the main supertrend line.\n",
+    "# This solves the problem of dynamically named output columns.\n",
+    "def pta_supertrend_wrapper(high, low, close, length, multiplier):\n",
+    "    # Calculate the supertrend using pandas-ta\n",
+    "    st = ta.supertrend(high=high, low=low, close=close, length=length, multiplier=multiplier)\n",
+    "\n",
+    "    # pandas-ta returns a DataFrame. The first column is the main supertrend line.\n",
+    "    # We return only this column (as a Series).\n",
+    "    return st.iloc[:, 0]\n",
+    "\n",
+    "\n",
+    "# Now, create an indicator factory from our OWN wrapper function\n",
+    "Supertrend = vbt.IndicatorFactory(\n",
+    "    input_names=['high', 'low', 'close'],\n",
+    "    param_names=['length', 'multiplier'],\n",
+    "    output_names=['supertrend'] # We can name the output whatever we want here\n",
+    ").from_apply_func(\n",
+    "    pta_supertrend_wrapper,\n",
+    "    # Important settings for functions that expect pandas Series:\n",
+    "    keep_pd=True,\n",
+    "    to_2d=False\n",
+    ")\n",
+    "\n",
+    "print(\"\\nCalculating Supertrend for all parameter combinations...\")\n",
+    "supertrend_indicator = Supertrend.run(\n",
+    "    price_data['High'],\n",
+    "    price_data['Low'],\n",
+    "    price_data['Close'],\n",
+    "    length=supert_period_range,\n",
+    "    multiplier=supert_multiplier_range,\n",
+    "    param_product=True\n",
+    ")\n",
+    "print(\"Indicator calculation complete.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aafe29ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 4. Signal Generation and Backtest Execution ---\n",
+    "print(\"\\nGenerating signals and running backtest...\")\n",
+    "\n",
+    "# Now we can access the output via the name we defined: .supertrend\n",
+    "entries = price_data['Close'].vbt.crossed_above(supertrend_indicator.supertrend)\n",
+    "exits = price_data['Close'].vbt.crossed_below(supertrend_indicator.supertrend)\n",
+    "\n",
+    "# Run the portfolio simulation\n",
+    "portfolio = vbt.Portfolio.from_signals(\n",
+    "    price_data['Close'],\n",
+    "    entries,\n",
+    "    exits,\n",
+    "    freq=FREQ,\n",
+    "    init_cash=INIT_CASH,\n",
+    "    fees=FEES,\n",
+    "    slippage=SLIPPAGE\n",
+    ")\n",
+    "print(\"Backtest complete.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74f45bc0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 5. Numerical Analysis of Results (FINAL, DEFINITIVE VERSION 4) ---\n",
+    "print(f\"\\n--- Optimization Results ---\")\n",
+    "\n",
+    "if portfolio.trades.count().sum() == 0:\n",
+    "    print(\"No trades were executed for any parameter combination.\")\n",
+    "else:\n",
+    "    # --- Top N Results ---\n",
+    "    print(f\"\\nTop {N_TOP_RESULTS} parameter combinations sorted by '{OPTIMIZE_FOR}':\")\n",
+    "\n",
+    "    # Build the results DataFrame manually from individual metric Series.\n",
+    "\n",
+    "    total_return = portfolio.total_return()\n",
+    "    sharpe_ratio = portfolio.sharpe_ratio()\n",
+    "    max_drawdown = portfolio.max_drawdown()\n",
+    "    win_rate = portfolio.trades.win_rate()\n",
+    "\n",
+    "    # CORRECTED: profit_factor is also an attribute of the `trades` accessor\n",
+    "    profit_factor = portfolio.trades.profit_factor()\n",
+    "\n",
+    "    total_trades = portfolio.trades.count()\n",
+    "\n",
+    "    # Combine these Series into a single DataFrame.\n",
+    "    results_df = pd.concat([\n",
+    "        total_return,\n",
+    "        sharpe_ratio,\n",
+    "        max_drawdown,\n",
+    "        win_rate,\n",
+    "        profit_factor,\n",
+    "        total_trades\n",
+    "    ], axis=1, keys=[\n",
+    "        'Total Return [%]',\n",
+    "        'Sharpe Ratio',\n",
+    "        'Max Drawdown [%]',\n",
+    "        'Win Rate [%]',\n",
+    "        'Profit Factor',\n",
+    "        'Total Trades'\n",
+    "    ])\n",
+    "\n",
+    "    # Sort this new DataFrame by the desired metric.\n",
+    "    top_stats = results_df.sort_values(by=OPTIMIZE_FOR, ascending=False).head(N_TOP_RESULTS)\n",
+    "\n",
+    "    print(top_stats)\n",
+    "\n",
+    "    # --- Best Result In-Depth ---\n",
+    "    best_params_idx = top_stats.index[0]\n",
+    "    best_portfolio_run = portfolio[best_params_idx]\n",
+    "    best_stats = best_portfolio_run.stats()\n",
+    "\n",
+    "    print(f\"\\n--- Detailed Stats for the Best Combination: {best_params_idx} ---\")\n",
+    "    print(best_stats)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "strategy-optimizer_env",
+   "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": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}