feat: optim_backtestingpy_sma_optimization.ipynb

notebooks/optim_backtestingpy_sma_optimization.ipynb

@@ -0,0 +1,202 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab3bfd28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# filename: optim_backtestingpy_sma_optimization.ipynb\n",
+    "\n",
+    "# --- 1. Imports and Setup ---\n",
+    "import pandas as pd\n",
+    "import pandas_ta as ta  # We'll use pandas-ta for the indicator calculation inside the strategy\n",
+    "from backtesting import Backtest, Strategy\n",
+    "from backtesting.lib import crossover\n",
+    "from backtesting.test import EURUSD\n",
+    "\n",
+    "# --- 2. Load Sample Data ---\n",
+    "print(\"Loading built-in EURUSD sample data...\")\n",
+    "data = EURUSD.copy()\n",
+    "print(\"Data loaded successfully.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55d51b03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 3. The Parameterized Strategy Class ---\n",
+    "\n",
+    "class SmaCrossOptimize(Strategy):\n",
+    "    # --- Parameters for Optimization ---\n",
+    "    # These values will be replaced by the optimizer.\n",
+    "    # The values here are just defaults for a single run.\n",
+    "    fast_period = 10\n",
+    "    slow_period = 40\n",
+    "\n",
+    "    def init(self):\n",
+    "        # In init(), we define the indicators. Since the periods are dynamic,\n",
+    "        # we calculate them here. self.I() is smart and caches the results.\n",
+    "        # We use pandas_ta for its clean syntax.\n",
+    "        self.fast_sma = self.I(ta.sma, pd.Series(self.data.Close), length=self.fast_period)\n",
+    "        self.slow_sma = self.I(ta.sma, pd.Series(self.data.Close), length=self.slow_period)\n",
+    "\n",
+    "    def next(self):\n",
+    "        # The same trading logic as before\n",
+    "        if crossover(self.fast_sma, self.slow_sma):\n",
+    "            if not self.position:\n",
+    "                self.buy()\n",
+    "        elif crossover(self.slow_sma, self.fast_sma):\n",
+    "            self.position.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ad1f5d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 4. Running the Optimization ---\n",
+    "print(\"\\n--- Starting Grid Search Optimization ---\")\n",
+    "\n",
+    "bt = Backtest(data, SmaCrossOptimize, cash=10000, commission=.002)\n",
+    "\n",
+    "# The optimize method performs a grid search.\n",
+    "# We store the results, which include the heatmap data, in a variable.\n",
+    "# return_heatmap=True is the default, so we don't need to specify it, but it's good to be aware of.\n",
+    "stats, heatmap = bt.optimize(\n",
+    "    fast_period=range(10, 31, 5),\n",
+    "    slow_period=range(40, 81, 10),\n",
+    "    maximize='Sharpe Ratio',\n",
+    "    constraint=lambda p: p.fast_period < p.slow_period,\n",
+    "    return_heatmap=True  # Explicitly ask for the heatmap data\n",
+    ")\n",
+    "\n",
+    "print(\"\\n--- Optimization Results ---\")\n",
+    "print(\"Best stats found:\")\n",
+    "print(stats)\n",
+    "\n",
+    "print(\"\\nBest parameters found:\")\n",
+    "print(stats._strategy)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7257ef5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 5. Visualizing the Optimization Results ---\n",
+    "from backtesting.lib import plot_heatmaps\n",
+    "\n",
+    "print(\"\\n--- Plotting Optimization Heatmap ---\")\n",
+    "\n",
+    "# The plot_heatmaps function is imported directly from backtesting.lib\n",
+    "# and takes the heatmap data returned by the optimize() method.\n",
+    "plot_heatmaps(heatmap, agg='mean')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "84ddd2e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 6. Walk-Forward Analysis (WFA) ---\n",
+    "# This is a more robust way to test our strategy. We optimize on a training set\n",
+    "# and validate on an unseen testing set, moving this window through time.\n",
+    "\n",
+    "print(\"\\n--- Starting Walk-Forward Analysis ---\")\n",
+    "\n",
+    "# --- WFA Configuration ---\n",
+    "n_train_bars = 24 * 30 * 3  # Approx. 3 months\n",
+    "n_test_bars = 24 * 30 * 1   # Approx. 1 month\n",
+    "step = n_test_bars\n",
+    "\n",
+    "oos_results = []\n",
+    "\n",
+    "# The main loop for walking forward\n",
+    "for i in range(n_train_bars, len(data) - n_test_bars, step):\n",
+    "    train_data = data.iloc[i - n_train_bars : i]\n",
+    "    test_data = data.iloc[i : i + n_test_bars]\n",
+    "\n",
+    "    print(f\"\\nTraining on data from {train_data.index[0]} to {train_data.index[-1]}\")\n",
+    "    print(f\"Testing on data from {test_data.index[0]} to {test_data.index[-1]}\")\n",
+    "\n",
+    "    # --- In-Sample Optimization ---\n",
+    "    # For the training part, finalizing trades is less critical, but we can add it for consistency.\n",
+    "    bt_train = Backtest(train_data, SmaCrossOptimize, cash=10000, commission=.002, finalize_trades=True)\n",
+    "\n",
+    "    stats_train, _ = bt_train.optimize(\n",
+    "        fast_period=range(10, 31, 5),\n",
+    "        slow_period=range(40, 81, 10),\n",
+    "        maximize='Sharpe Ratio',\n",
+    "        constraint=lambda p: p.fast_period < p.slow_period,\n",
+    "        return_heatmap=True\n",
+    "    )\n",
+    "\n",
+    "    best_params = stats_train._strategy\n",
+    "    print(f\"Best params found in-sample: {best_params.fast_period}/{best_params.slow_period}\")\n",
+    "\n",
+    "    # --- Out-of-Sample Validation ---\n",
+    "    # CORRECTED: Add finalize_trades=True to get more accurate OOS stats.\n",
+    "    bt_test = Backtest(test_data, SmaCrossOptimize, cash=10000, commission=.002, finalize_trades=True)\n",
+    "\n",
+    "    stats_test = bt_test.run(\n",
+    "        fast_period=best_params.fast_period,\n",
+    "        slow_period=best_params.slow_period\n",
+    "    )\n",
+    "\n",
+    "    oos_results.append(stats_test)\n",
+    "\n",
+    "\n",
+    "# --- 7. Analyze WFA Results ---\n",
+    "print(\"\\n\\n--- Walk-Forward Analysis Final Results ---\")\n",
+    "\n",
+    "if oos_results:\n",
+    "    wfa_df = pd.concat([res.to_frame(f\"Period_{i}\") for i, res in enumerate(oos_results)], axis=1).T\n",
+    "\n",
+    "    print(\"Performance of each Out-of-Sample period:\")\n",
+    "    print(wfa_df[['Return [%]', 'Sharpe Ratio', 'Win Rate [%]', '# Trades']])\n",
+    "\n",
+    "    print(\"\\nAverage performance across all OOS periods:\")\n",
+    "    print(wfa_df[['Return [%]', 'Sharpe Ratio', 'Win Rate [%]']].mean())\n",
+    "else:\n",
+    "    print(\"No out-of-sample periods were successfully tested.\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "strategy-optimizer_env_bck",
+   "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
+}