feat: optim_walk_forward_analysis_sma.ipynb

notebooks/optim_walk_forward_analysis_sma.ipynb

@@ -0,0 +1,186 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5ae2f039",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# filename: optim_walk_forward_analysis_sma.ipynb\n",
+    "\n",
+    "# --- 1. Imports and Setup ---\n",
+    "# --- Matplotlib Setup for Pandas Plots ---\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import pandas_ta as ta\n",
+    "from backtesting import Backtest, Strategy\n",
+    "from backtesting.lib import crossover\n",
+    "from backtesting.test import EURUSD\n",
+    "\n",
+    "%matplotlib inline\n",
+    "# This magic command tells Jupyter to render plots directly in the output cell.\n",
+    "plt.style.use('dark_background') # Optional: Set a dark theme consistent with other plots\n",
+    "\n",
+    "# --- 2. Load Sample Data ---\n",
+    "print(\"Loading built-in EURUSD sample data...\")\n",
+    "data = EURUSD.copy()\n",
+    "print(f\"Data loaded. Contains {len(data)} bars from {data.index[0]} to {data.index[-1]}.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "367c50d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 3. The Parameterized Strategy Class ---\n",
+    "# This is the same strategy we optimized in the previous notebook.\n",
+    "\n",
+    "class SmaCrossSLTP(Strategy):\n",
+    "    fast_period = 10\n",
+    "    slow_period = 40\n",
+    "    sl_percent = 1.5\n",
+    "    tp_percent = 3.0\n",
+    "\n",
+    "    def init(self):\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",
+    "        sl_price = self.data.Close[-1] * (1 - self.sl_percent / 100)\n",
+    "        tp_price = self.data.Close[-1] * (1 + self.tp_percent / 100)\n",
+    "\n",
+    "        if crossover(self.fast_sma, self.slow_sma):\n",
+    "            if not self.position:\n",
+    "                self.buy(sl=sl_price, tp=tp_price)\n",
+    "        elif crossover(self.slow_sma, self.fast_sma):\n",
+    "            self.position.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3a932019",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 4. Walk-Forward Analysis Implementation ---\n",
+    "print(\"\\n--- Starting Walk-Forward Analysis ---\")\n",
+    "\n",
+    "# --- WFA Configuration ---\n",
+    "# Using integer indices for slicing the DataFrame\n",
+    "total_bars = len(data)\n",
+    "# ~6 months of training data, ~2 months of validation data (4-hour bars)\n",
+    "n_train_bars = int(total_bars * 0.25) # Use 25% of data for the first training\n",
+    "n_test_bars = int(n_train_bars / 3)   # Test period is 1/3 of the training period\n",
+    "step = n_test_bars                    # Slide the window forward by the test period size\n",
+    "\n",
+    "# List to store the results from each out-of-sample (OOS) run\n",
+    "oos_results = []\n",
+    "\n",
+    "# The main loop for walking forward\n",
+    "for i in range(n_train_bars, total_bars - n_test_bars, step):\n",
+    "    # Define the training and testing data slices\n",
+    "    train_data = data.iloc[i - n_train_bars : i]\n",
+    "    test_data = data.iloc[i : i + n_test_bars]\n",
+    "\n",
+    "    print(\"-\" * 50)\n",
+    "    print(f\"Training on: {train_data.index[0]} -> {train_data.index[-1]} ({len(train_data)} bars)\")\n",
+    "    print(f\"Testing on:  {test_data.index[0]} -> {test_data.index[-1]} ({len(test_data)} bars)\")\n",
+    "\n",
+    "    # --- In-Sample Optimization ---\n",
+    "    bt_train = Backtest(train_data, SmaCrossSLTP, cash=10000, commission=.002, finalize_trades=True)\n",
+    "\n",
+    "    # Using a smaller parameter grid for faster WFA execution\n",
+    "    stats_train, _ = bt_train.optimize(\n",
+    "        fast_period=[10, 20],\n",
+    "        slow_period=[40, 50],\n",
+    "        sl_percent=[1.0, 1.5],\n",
+    "        tp_percent=[2.0, 3.0],\n",
+    "        maximize='SQN',\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: fast={best_params.fast_period}, slow={best_params.slow_period}, sl={best_params.sl_percent}%, tp={best_params.tp_percent}%\")\n",
+    "\n",
+    "    # --- Out-of-Sample Validation ---\n",
+    "    bt_test = Backtest(test_data, SmaCrossSLTP, 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",
+    "        sl_percent=best_params.sl_percent,\n",
+    "        tp_percent=best_params.tp_percent\n",
+    "    )\n",
+    "\n",
+    "    oos_results.append(stats_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b1d250d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %%\n",
+    "# --- 5. Analyze WFA Results ---\n",
+    "print(\"\\n\\n\" + \"=\"*50)\n",
+    "print(\"--- Walk-Forward Analysis Final Results ---\")\n",
+    "\n",
+    "if oos_results:\n",
+    "    # Create a DataFrame from the list of Series 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(\"\\nPerformance of each Out-of-Sample period:\")\n",
+    "    print(wfa_df[['Return [%]', 'Sharpe Ratio', 'Win Rate [%]', '# Trades', 'Profit Factor']])\n",
+    "\n",
+    "    print(\"\\nAverage performance across all OOS periods:\")\n",
+    "    print(wfa_df[['Return [%]', 'Sharpe Ratio', 'Win Rate [%]']].mean())\n",
+    "\n",
+    "    # Plot the equity curve of each OOS period\n",
+    "    print(\"\\nPlotting cumulative equity of OOS periods...\")\n",
+    "    # This plot will now render correctly thanks to the setup in the first cell\n",
+    "    wfa_df['Equity Final [$]'].plot(\n",
+    "        kind='bar',\n",
+    "        title='Final Equity per Out-of-Sample Period',\n",
+    "        xlabel='WFA Period',\n",
+    "        ylabel='Final Equity [$]',\n",
+    "        figsize=(10, 6), # Optional: make the plot bigger\n",
+    "        grid=True\n",
+    "    )\n",
+    "    plt.show() # Explicitly showing the plot is the most robust way\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
+}