{"id":807,"date":"2024-08-13T16:37:26","date_gmt":"2024-08-13T08:37:26","guid":{"rendered":"https:\/\/blog.alltick.co\/?p=807"},"modified":"2025-04-28T15:44:02","modified_gmt":"2025-04-28T07:44:02","slug":"python-backtest","status":"publish","type":"post","link":"https:\/\/blog.alltick.co\/zh-CN\/python-backtest\/","title":{"rendered":"\u5982\u4f55\u7528Python\u642d\u5efa\u56de\u6d4b\u6846\u67b6"},"content":{"rendered":"\n<p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u5c1d\u8bd5\u7528Python\u521b\u5efa\u4e00\u4e2a\u56de\u6d4b\u6846\u67b6\uff0c\u9700\u8981\u5305\u542b\u4ee5\u4e0b\u529f\u80fd\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u6a21\u5757\u5316<\/strong> \u2013 \u6211\u4eec\u5e0c\u671b\u628a\u5b83\u505a\u6210\u6a21\u5757\u5316\u7684\uff0c\u53ef\u4ee5\u968f\u610f\u7ec4\u5408\u3001\u66ff\u6362\u3002<\/li>\n\n\n\n<li><strong>\u53ef\u6269\u5c55\u6027<\/strong> \u2013 \u4ee3\u7801\u5e94\u6613\u4e8e\u6269\u5c55\u3002<\/li>\n\n\n\n<li><strong>\u652f\u6301\u5355\u8d44\u4ea7\u548c\u591a\u8d44\u4ea7\u7b56\u7565<\/strong><\/li>\n\n\n\n<li><strong>\u8bbf\u95ee\u5386\u53f2\u80a1\u6743\u6570\u636e\u548c\u591a\u4e2a\u6570\u636e\u63d0\u4f9b\u5546<\/strong><\/li>\n\n\n\n<li><strong>\u5305\u542b\u4ea4\u6613\u8d39\u7528\u548c\u4f63\u91d1<\/strong><\/li>\n\n\n\n<li><strong>\u5177\u6709\u6027\u80fd\u6307\u6807<\/strong><\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<p>\u4e3a\u4e86\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\uff0c\u6211\u4eec\u9700\u8981\u51e0\u4e2a\u5173\u952e\u7ec4\u4ef6\uff0c\u5305\u62ec\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u6570\u636e\u7ba1\u7406<\/strong>: \u8d1f\u8d23OHLCV\u6570\u636e\u7684\u5bfc\u5165\u3001\u5b58\u50a8\u548c\u68c0\u7d22\uff0c\u4ee5\u53ca\u4efb\u4f55\u7528\u4e8e\u751f\u6210\u4fe1\u53f7\u7684\u66ff\u4ee3\u6570\u636e\u6e90\u3002<\/li>\n\n\n\n<li><strong>\u4fe1\u53f7\u751f\u6210<\/strong>: \u5305\u542b\u7528\u4e8e\u5206\u6790\u6570\u636e\u5e76\u57fa\u4e8e\u9884\u5b9a\u4e49\u7b56\u7565\u6216\u6307\u6807\u751f\u6210\u4e70\u5356\u4fe1\u53f7\u7684\u903b\u8f91\u3002<\/li>\n\n\n\n<li><strong>\u6267\u884c\u5f15\u64ce<\/strong>: \u6a21\u62df\u57fa\u4e8e\u4fe1\u53f7\u7684\u4ea4\u6613\u6267\u884c\uff0c\u8003\u8651\u4f63\u91d1\u3001\u6ed1\u70b9\uff0c\u5e76\u53ef\u9009\u5730\u8003\u8651\u4e70\u5356\u4ef7\u5dee\u3002<\/li>\n\n\n\n<li><strong>\u6027\u80fd\u8bc4\u4f30<\/strong>: \u8ba1\u7b97\u5173\u952e\u6027\u80fd\u6307\u6807\uff0c\u5982\u56de\u62a5\u7387\u3001\u6ce2\u52a8\u7387\u3001\u590f\u666e\u6bd4\u7387\u3001\u56de\u64a4\u7b49\uff0c\u4ee5\u8bc4\u4f30\u7b56\u7565\u7684\u6709\u6548\u6027\u3002<\/li>\n\n\n\n<li><strong>\u5b9e\u7528\u5de5\u5177<\/strong>: \u5305\u62ec\u65e5\u5fd7\u8bb0\u5f55\u3001\u914d\u7f6e\u7ba1\u7406\u4ee5\u53ca\u5176\u4ed6\u652f\u6301\u529f\u80fd\u3002<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<p>\u4e0b\u9762\u662f\u6211\u4eec\u5c06\u7528\u5230\u7684Python\u5e93\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Poetry<\/strong><\/li>\n\n\n\n<li><strong>OpenBB Platform<\/strong> \u2013 \u8fd9\u5c06\u4e3a\u6211\u4eec\u63d0\u4f9b\u65e0\u7f1d\u8bbf\u95ee\u591a\u4e2a\u6570\u636e\u63d0\u4f9b\u5546\u7684\u5e02\u573a\u6570\u636e\u3002\u4f60\u53ef\u4ee5\u5728\u8fd9\u91cc\u9605\u8bfb\u66f4\u591a\u4fe1\u606f\u3002<\/li>\n\n\n\n<li><strong>Pandas<\/strong><\/li>\n\n\n\n<li><strong>Numpy<\/strong><\/li>\n\n\n\n<li><strong>Matplotlib<\/strong><\/li>\n\n\n\n<li><strong>Ruff, Black, MyPy<\/strong> \u2013 \u6211\u4e2a\u4eba\u504f\u597d\u7684\u4ee3\u7801\u68c0\u67e5\u5de5\u5177\uff08\u53ef\u9009\uff09\u3002\u4f60\u53ef\u4ee5\u5728\u8fd9\u91cc\u9605\u8bfb\u66f4\u591a\u76f8\u5173\u4fe1\u606f\u3002<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u4f7f\u7528OpenBB\u521b\u5efa\u6570\u636e\u5904\u7406\u5668<\/strong><\/h2>\n\n\n\n<p>\u5728OpenBB\u5e73\u53f0\u4e0a\u521b\u5efa\u6570\u636e\u5904\u7406\u5668\u975e\u5e38\u7b80\u5355\u3002\u5e73\u53f0\u5e2e\u6211\u4eec\u5904\u7406\u4e86\u4e0d\u540cAPI\u89c4\u8303\u3001\u5404\u7c7b\u6570\u636e\u63d0\u4f9b\u5546\u3001\u6742\u4e71\u65e0\u7ae0\u7684\u8f93\u51fa\u548c\u6570\u636e\u9a8c\u8bc1\u7b49\u96be\u9898\u3002<\/p>\n\n\n\n<p>\u8fd9\u6837\u4e00\u6765\uff0c\u6211\u4eec\u5c31\u4e0d\u518d\u9700\u8981\u4e3a\u6570\u636e\u9a8c\u8bc1\u548c\u5904\u7406\u521b\u5efa\u81ea\u5b9a\u4e49\u7c7b\u3002\u4f60\u53ef\u4ee5\u8f7b\u677e\u8bbf\u95ee\u591a\u4e2a\u6570\u636e\u63d0\u4f9b\u5546\u3001\u4e0a\u767e\u4e2a\u6570\u636e\u70b9\u3001\u4e0d\u540c\u8d44\u4ea7\u7c7b\u522b\u7b49\u3002\u5e73\u53f0\u8fd8\u786e\u4fdd\u4e86\u8fd4\u56de\u7684\u6570\u636e\u7b26\u5408\u6807\u51c6\uff0c\u8d28\u91cf\u6709\u4fdd\u969c\u3002<\/p>\n\n\n\n<p>\u5728\u8fd9\u91cc\uff0c\u6211\u4f1a\u4e13\u6ce8\u4e8e\u80a1\u7968\u8d44\u4ea7\uff0c\u5e76\u5c06\u6570\u636e\u9650\u5b9a\u4e3a\u65e5K\u7ebf\u3002\u5f53\u7136\uff0c\u4f60\u53ef\u4ee5\u6839\u636e\u9700\u8981\u6269\u5c55\u548c\u4fee\u6539\u8fd9\u4e9b\u8bbe\u7f6e\u3002\u6211\u8fd8\u4f1a\u5141\u8bb8\u7528\u6237\u66f4\u6539\u6570\u636e\u63d0\u4f9b\u5546\u3001\u4ea4\u6613\u4ee3\u7801\u4ee5\u53ca\u6570\u636e\u7684\u5f00\u59cb\u548c\u7ed3\u675f\u65e5\u671f\u3002<\/p>\n\n\n\n<p>\u6211\u7279\u522b\u559c\u6b22OpenBB\u5e73\u53f0\u7684\u4e00\u70b9\u662f\uff0c\u5b83\u7684\u67d0\u4e9b\u7aef\u70b9\u5141\u8bb8\u4f20\u9012\u591a\u4e2a\u80a1\u7968\u4ee3\u7801\u3002\u8fd9\u610f\u5473\u7740\u6211\u4eec\u5df2\u7ecf\u5728\u652f\u6301\u591a\u8d44\u4ea7\u4ea4\u6613\u7684\u9053\u8def\u4e0a\u8fc8\u51fa\u4e86\u91cd\u8981\u7684\u4e00\u6b65\uff0c\u53ea\u9700\u4f20\u9012\u4e00\u4e2a\u7528\u9017\u53f7\u5206\u9694\u7684\u7b26\u53f7\u5217\u8868\u5373\u53ef\u3002<\/p>\n\n\n\n<p>\u4e0b\u9762\u662f\u4ee3\u7801\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">\"\"\"\u7528\u4e8e\u52a0\u8f7d\u548c\u5904\u7406\u6570\u636e\u7684\u6570\u636e\u5904\u7406\u6a21\u5757\u3002\"\"\"\n\nfrom typing import Optional\n\nimport pandas as pd\nfrom openbb import obb\n\n\nclass DataHandler:\n    \"\"\"\u7528\u4e8e\u52a0\u8f7d\u548c\u5904\u7406\u6570\u636e\u7684\u6570\u636e\u5904\u7406\u7c7b\u3002\"\"\"\n\n    def __init__(\n        self,\n        symbol: str,\n        start_date: Optional[str] = None,\n        end_date: Optional[str] = None,\n        provider: str = \"fmp\",\n    ):\n        \"\"\"\u521d\u59cb\u5316\u6570\u636e\u5904\u7406\u5668\u3002\"\"\"\n        self.symbol = symbol.upper()\n        self.start_date = start_date\n        self.end_date = end_date\n        self.provider = provider\n\n    def load_data(self) -> pd.DataFrame | dict[str, pd.DataFrame]:\n        \"\"\"\u52a0\u8f7d\u80a1\u7968\u6570\u636e\u3002\"\"\"\n        data = obb.equity.price.historical(\n            symbol=self.symbol,\n            start_date=self.start_date,\n            end_date=self.end_date,\n            provider=self.provider,\n        ).to_df()\n\n        if \",\" in self.symbol:\n            data = data.reset_index().set_index(\"symbol\")\n            return {symbol: data.loc[symbol] for symbol in self.symbol.split(\",\")}\n\n        return data\n\n    def load_data_from_csv(self, file_path) -> pd.DataFrame:\n        \"\"\"\u4eceCSV\u6587\u4ef6\u52a0\u8f7d\u6570\u636e\u3002\"\"\"\n        return pd.read_csv(file_path, index_col=\"date\", parse_dates=True)\n<\/pre>\n\n\n\n<p>\u6ce8\u610f\uff0c\u5f53\u4f20\u9012\u591a\u4e2a\u4ea4\u6613\u4ee3\u7801\u65f6\uff0c\u5b83\u4f1a\u8fd4\u56de\u4e00\u4e2a\u5305\u542bPandas\u6570\u636e\u6846\u7684\u5b57\u5178\u3002\u6211\u8fd8\u6dfb\u52a0\u4e86\u4e00\u4e2a\u51fd\u6570\uff0c\u53ef\u4ee5\u4ece\u81ea\u5b9a\u4e49\u7684CSV\u6587\u4ef6\u4e2d\u52a0\u8f7d\u6570\u636e\uff0c\u5e76\u4f7f\u7528\u65e5\u671f\u5217\u4f5c\u4e3a\u7d22\u5f15\u3002\u4f60\u53ef\u4ee5\u6839\u636e\u81ea\u5df1\u7684\u9700\u6c42\u8fdb\u4e00\u6b65\u6269\u5c55\u548c\u4fee\u6539\u8fd9\u4e2a\u529f\u80fd\u3002<\/p>\n\n\n\n<p>\u8981\u83b7\u53d6\u4e00\u4e9b\u6570\u636e\uff0c\u6211\u4eec\u53ea\u9700\u8981\u521d\u59cb\u5316\u8fd9\u4e2a\u7c7b\uff0c\u7136\u540e\u50cf\u8fd9\u6837\u8c03\u7528<code>load_data<\/code>\u65b9\u6cd5\u5373\u53ef\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">data = DataHandler(\"AAPL\").load_data()\ndata.head()<\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u521b\u5efa\u7b56\u7565\u5904\u7406\u5668<\/strong><\/h2>\n\n\n\n<p>\u4e0b\u4e00\u6b65\u662f\u521b\u5efa\u4e00\u4e2a\u7528\u4e8e\u5904\u7406\u7b56\u7565\u7684\u6a21\u5757\u3002\u6211\u7684\u610f\u601d\u662f\uff0c\u6784\u5efa\u4e00\u4e2a\u80fd\u591f\u6839\u636e\u7b56\u7565\u9700\u6c42\u751f\u6210\u4fe1\u53f7\u5e76\u5c06\u5176\u9644\u52a0\u5230\u6570\u636e\u4e0a\u7684\u6a21\u5757\uff0c\u8fd9\u6837\u6267\u884c\u5668\u5c31\u53ef\u4ee5\u5728\u56de\u6d4b\u4e2d\u4f7f\u7528\u8fd9\u4e9b\u4fe1\u53f7\u3002<\/p>\n\n\n\n<p>\u6211\u60f3\u8981\u5b9e\u73b0\u7684\u662f\u4e00\u4e2a\u7c7b\u4f3c\u4e8e\u7b56\u7565\u57fa\u7c7b\u7684\u4e1c\u897f\uff0c\u5f00\u53d1\u8005\u53ef\u4ee5\u7ee7\u627f\u5b83\u3001\u4fee\u6539\u5b83\uff0c\u6216\u8005\u6784\u5efa\u81ea\u5df1\u7684\u81ea\u5b9a\u4e49\u7b56\u7565\u3002\u6211\u8fd8\u5e0c\u671b\u5b83\u5728\u5904\u7406\u591a\u8d44\u4ea7\u65f6\u80fd\u65e0\u7f1d\u5de5\u4f5c\uff0c\u80fd\u591f\u5bf9\u591a\u4e2a\u8d44\u4ea7\u5e94\u7528\u76f8\u540c\u7684\u4fe1\u53f7\u903b\u8f91\u3002<\/p>\n\n\n\n<p>\u4ee5\u4e0b\u662f\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">class Strategy:\n\n    def __init__(self, indicators: dict, signal_logic: Any):\n        \"\"\"\u4f7f\u7528\u6307\u6807\u548c\u4fe1\u53f7\u903b\u8f91\u521d\u59cb\u5316\u7b56\u7565\u3002\"\"\"\n        self.indicators = indicators\n        self.signal_logic = signal_logic\n\n    def generate_signals(\n        self, data: pd.DataFrame | dict[str, pd.DataFrame]\n    ) -> pd.DataFrame | dict[str, pd.DataFrame]:\n        \"\"\"\u6839\u636e\u7b56\u7565\u7684\u6307\u6807\u548c\u4fe1\u53f7\u903b\u8f91\u751f\u6210\u4ea4\u6613\u4fe1\u53f7\u3002\"\"\"\n        if isinstance(data, dict):\n            for _, asset_data in data.items():\n                self._apply_strategy(asset_data)\n        else:\n            self._apply_strategy(data)\n        return data\n\n    def _apply_strategy(self, df: pd.DataFrame) -> None:\n        \"\"\"\u5c06\u7b56\u7565\u5e94\u7528\u4e8e\u5355\u4e2a\u6570\u636e\u6846\u3002\"\"\"\n        for name, indicator in self.indicators.items():\n            df[name] = indicator(df)\n\n        df[\"signal\"] = df.apply(lambda row: self.signal_logic(row), axis=1)\n        df[\"positions\"] = df[\"signal\"].diff().fillna(0)\n<\/pre>\n\n\n\n<p>\u5b83\u7684\u539f\u7406\u662f\u63a5\u53d7\u4e00\u4e2a\u9700\u8981\u8ba1\u7b97\u7684\u6307\u6807\u5b57\u5178\uff0c\u4ee5\u53ca\u751f\u6210\u4fe1\u53f7\u7684\u903b\u8f91\uff0c\u8fd9\u4e9b\u4fe1\u53f7\u53ef\u4ee5\u662f -1 \u8868\u793a\u5356\u51fa\uff0c+1 \u8868\u793a\u4e70\u5165\u3002\u5b83\u8fd8\u8ddf\u8e2a\u6211\u4eec\u5f53\u524d\u7684\u6301\u4ed3\u72b6\u6001\u3002<\/p>\n\n\n\n<p>\u76ee\u524d\u7684\u7f16\u7801\u65b9\u5f0f\u662f\uff0c\u6211\u4eec\u4f20\u9012\u7ed9\u5b83\u7684 Lambda \u51fd\u6570\u5c06\u5e94\u7528\u4e8e\u6570\u636e\u6846\u3002<\/p>\n\n\n\n<p>\u793a\u4f8b\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">strategy = Strategy(\n    indicators={\n        \"sma_20\": lambda row: row[\"close\"].rolling(window=20).mean(),\n        \"sma_60\": lambda row: row[\"close\"].rolling(window=60).mean(),\n    },\n    signal_logic=lambda row: 1 if row[\"sma_20\"] > row[\"sma_60\"] else -1,\n)\ndata = strategy.generate_signals(data)\ndata.tail()<\/pre>\n\n\n\n<p>\u5728\u4e0a\u9762\u7684\u4f8b\u5b50\u4e2d\uff0c\u6211\u521b\u5efa\u4e86\u4e00\u4e2a\u6162\u901f\u548c\u4e00\u4e2a\u5feb\u901f\u79fb\u52a8\u5e73\u5747\u7ebf\uff0c\u5e76\u5728\u6b64\u57fa\u7840\u4e0a\u5b9a\u4e49\u4e86\u6211\u7684\u4ea4\u6613\u903b\u8f91\uff1a\u5f53\u5feb\u901f\u79fb\u52a8\u5e73\u5747\u7ebf\u7a81\u7834\u6162\u901f\u79fb\u52a8\u5e73\u5747\u7ebf\u65f6\u505a\u591a\uff0c\u53cd\u4e4b\u5219\u505a\u7a7a\u3002<\/p>\n\n\n\n<p>\u73b0\u5728\u6211\u4eec\u5df2\u7ecf\u6709\u4e86\u83b7\u53d6\u6570\u636e\u548c\u751f\u6210\u4ea4\u6613\u4fe1\u53f7\u7684\u65b9\u6cd5\uff0c\u53ea\u7f3a\u5c11\u4e00\u4e2a\u5b9e\u9645\u8fd0\u884c\u56de\u6d4b\u7684\u65b9\u6cd5\u3002\u8fd9\u662f\u6700\u590d\u6742\u7684\u90e8\u5206\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u521b\u5efa\u4e3b\u8981\u56de\u6d4b\u903b\u8f91<\/strong><\/h2>\n\n\n\n<p>\u4e3b\u8981\u7684\u56de\u6d4b\u5668\u903b\u8f91\u5c06\u7531\u51e0\u4e2a\u90e8\u5206\u7ec4\u6210\u3002\u6211\u4eec\u9700\u8981\u5305\u542b\u7684\u4e3b\u8981\u90e8\u5206\u5982\u4e0b\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u4ea4\u6613\u6267\u884c\u5668<\/li>\n\n\n\n<li>\u4f63\u91d1\u8ba1\u7b97\u5668<\/li>\n\n\n\n<li>\u6027\u80fd\u6307\u6807\u8ba1\u7b97\u5668<\/li>\n\n\n\n<li>\u6295\u8d44\u7ec4\u5408\u7ba1\u7406\u5668<\/li>\n\n\n\n<li>\u5c06\u6240\u6709\u8fd9\u4e9b\u90e8\u5206\u8054\u7cfb\u5728\u4e00\u8d77\u7684\u7ebd\u5e26<\/li>\n<\/ul>\n\n\n\n<p>\u6211\u4eec\u9996\u5148\u5b9a\u4e49\u7c7b\u5e76\u8bbe\u7f6e\u4e00\u4e9b\u6211\u4eec\u5e0c\u671b\u5176\u5904\u7406\u7684\u57fa\u672c\u53d8\u91cf\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">class Backtester:\n\n    def __init__(\n        self,\n        initial_capital: float = 10000.0,\n        commission_pct: float = 0.001,\n        commission_fixed: float = 1.0,\n    ):\n        \"\"\"Initialize the backtester with initial capital and commission fees.\"\"\"\n        self.initial_capital: float = initial_capital\n        self.commission_pct: float = commission_pct\n        self.commission_fixed: float = commission_fixed\n        self.assets_data: Dict = {}\n        self.portfolio_history: Dict = {}\n        self.daily_portfolio_values: List[float] = []<\/pre>\n\n\n\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u5c06\u5b9a\u4e49\u4ea4\u6613\u6267\u884c\u5668\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\"> def execute_trade(self, asset: str, signal: int, price: float) -> None:\n    if signal > 0 and self.assets_data[asset][\"cash\"] > 0:  # Buy\n        trade_value = self.assets_data[asset][\"cash\"]\n        commission = self.calculate_commission(trade_value)\n        shares_to_buy = (trade_value - commission) \/ price\n        self.assets_data[asset][\"positions\"] += shares_to_buy\n        self.assets_data[asset][\"cash\"] -= trade_value\n    elif signal &lt; 0 and self.assets_data[asset][\"positions\"] > 0:  # Sell\n        trade_value = self.assets_data[asset][\"positions\"] * price\n        commission = self.calculate_commission(trade_value)\n        self.assets_data[asset][\"cash\"] += trade_value - commission\n        self.assets_data[asset][\"positions\"] = 0<\/pre>\n\n\n\n<p>\u4ea4\u6613\u6267\u884c\u5668\u5c06\u5728\u4fe1\u53f7\u5927\u4e8e0\u65f6\u8d2d\u4e70\u8d44\u4ea7\uff0c\u5728\u4fe1\u53f7\u5c0f\u4e8e0\u65f6\u5356\u51fa\u8d44\u4ea7\u3002\u5b83\u8fd8\u4f1a\u786e\u4fdd\u6211\u4eec\u6709\u8db3\u591f\u7684\u73b0\u91d1\u7528\u4e8e\u8d2d\u4e70\uff0c\u5e76\u4e14\u6211\u4eec\u5904\u4e8e\u80fd\u591f\u5356\u51fa\u7684\u4ed3\u4f4d\u3002\u6b64\u5916\uff0c\u5b83\u8fd8\u5c06\u8ba1\u7b97\u6211\u4eec\u53ef\u4ee5\u8d2d\u4e70\u7684\u80a1\u7968\u6570\u91cf\u5e76\u8003\u8651\u4ea4\u6613\u4f63\u91d1\u3002<\/p>\n\n\n\n<p>\u8981\u8ba1\u7b97\u4f63\u91d1\uff0c\u6211\u4eec\u9700\u8981\u6267\u884c\u4ee5\u4e0b\u6b65\u9aa4\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">def calculate_commission(self, trade_value: float) -> float:\n    return max(trade_value * self.commission_pct, self.commission_fixed)<\/pre>\n\n\n\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u9700\u8981\u8ddf\u8e2a\u6211\u4eec\u4ea4\u6613\u7684\u8d44\u4ea7\u7684\u6301\u4ed3\u3001\u5176\u4ef7\u503c\u4ee5\u53ca\u5386\u53f2\u8bb0\u5f55\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">def update_portfolio(self, asset: str, price: float) -> None:\n    self.assets_data[asset][\"position_value\"] = (\n        self.assets_data[asset][\"positions\"] * price\n    )\n    self.assets_data[asset][\"total_value\"] = (\n        self.assets_data[asset][\"cash\"] + self.assets_data[asset][\"position_value\"]\n    )\n    self.portfolio_history[asset].append(self.assets_data[asset][\"total_value\"])<\/pre>\n\n\n\n<p>\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u8fd9\u4e9b\u65b9\u6cd5\u6765\u8fd0\u884c\u56de\u6d4b\u5668\uff0c\u5982\u4e0b\u6240\u793a\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">def backtest(self, data: pd.DataFrame | dict[str, pd.DataFrame]):\n    if isinstance(data, pd.DataFrame):  # Single asset\n        data = {\n            \"SINGLE_ASSET\": data\n        }  \n    for asset in data:\n        self.assets_data[asset] = {\n            \"cash\": self.initial_capital \/ len(data),\n            \"positions\": 0,\n            \"position_value\": 0,\n            \"total_value\": 0,\n        }\n        self.portfolio_history[asset] = []\n\n        for date, row in data[asset].iterrows():\n            self.execute_trade(asset, row[\"signal\"], row[\"close\"])\n            self.update_portfolio(asset, row[\"close\"])\n            if len(self.daily_portfolio_values) &lt; len(data[asset]):\n                self.daily_portfolio_values.append(\n                    self.assets_data[asset][\"total_value\"]\n                )\n            else:\n                self.daily_portfolio_values[\n                    len(self.portfolio_history[asset]) - 1\n                ] += self.assets_data[asset][\"total_value\"]<\/pre>\n\n\n\n<p>\u73b0\u5728\uff0c\u6211\u5c06\u6dfb\u52a0\u4e00\u4e2a\u65b9\u6cd5\u6765\u8ba1\u7b97\u4e00\u4e9b\u6307\u6807\uff0c\u5e76\u4e14\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u7b49\u6765\u6269\u5c55\u8fd9\u4e9b\u529f\u80fd\u3002\u6211\u8fd8\u4f1a\u5bf9\u7ed8\u56fe\u529f\u80fd\u505a\u540c\u6837\u7684\u5904\u7406\u3002\u5177\u4f53\u7684\u4ee3\u7801\u53ef\u4ee5\u5728\u4ee3\u7801\u5e93\u4e2d\u67e5\u770b\u3002<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">def calculate_performance(self, plot: bool = True) -> None:\n    if not self.daily_portfolio_values:\n        print(\"No portfolio history to calculate performance.\")\n        return\n\n    portfolio_values = pd.Series(self.daily_portfolio_values)\n    daily_returns = portfolio_values.pct_change().dropna()\n\n    total_return = calculate_total_return(\n        portfolio_values.iloc[-1], self.initial_capital\n    )\n    annualized_return = calculate_annualized_return(\n        total_return, len(portfolio_values)\n    )\n    annualized_volatility = calculate_annualized_volatility(daily_returns)\n    sharpe_ratio = calculate_sharpe_ratio(annualized_return, annualized_volatility)\n    sortino_ratio = calculate_sortino_ratio(daily_returns, annualized_return)\n    max_drawdown = calculate_maximum_drawdown(portfolio_values)\n\n    print(f\"Final Portfolio Value: {portfolio_values.iloc[-1]:.2f}\")\n    print(f\"Total Return: {total_return * 100:.2f}%\")\n    print(f\"Annualized Return: {annualized_return * 100:.2f}%\")\n    print(f\"Annualized Volatility: {annualized_volatility * 100:.2f}%\")\n    print(f\"Sharpe Ratio: {sharpe_ratio:.2f}\")\n    print(f\"Sortino Ratio: {sortino_ratio:.2f}\")\n    print(f\"Maximum Drawdown: {max_drawdown * 100:.2f}%\")\n\n    if plot:\n        self.plot_performance(portfolio_values, daily_returns)\n\ndef plot_performance(self, portfolio_values: Dict, daily_returns: pd.DataFrame):\n    plt.figure(figsize=(10, 6))\n\n    plt.subplot(2, 1, 1)\n    plt.plot(portfolio_values, label=\"Portfolio Value\")\n    plt.title(\"Portfolio Value Over Time\")\n    plt.legend()\n\n    plt.subplot(2, 1, 2)\n    plt.plot(daily_returns, label=\"Daily Returns\", color=\"orange\")\n    plt.title(\"Daily Returns Over Time\")\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show()<\/pre>\n\n\n\n<p>Final Portfolio Value: \u6700\u7ec8\u6295\u8d44\u7ec4\u5408\u4ef7\u503c<br>Total Return: \u603b\u56de\u62a5<br>Annualized Return: \u5e74\u5316\u56de\u62a5<br>Annualized Volatility: \u5e74\u5316\u6ce2\u52a8\u7387<br>Sharpe Ratio: \u590f\u666e\u6bd4\u7387<br>Sortino Ratio: \u7d22\u63d0\u8bfa\u6bd4\u7387<br>Maximum Drawdown: \u6700\u5927\u56de\u64a4<\/p>\n\n\n\n<p>\u65e2\u7136\u56de\u6d4b\u5668\u5df2\u7ecf\u51c6\u5907\u597d\u4e86\uff0c\u8ba9\u6211\u4eec\u7528\u51e0\u79cd\u4e0d\u540c\u7684\u7b56\u7565\u6765\u8bd5\u4e00\u8bd5\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u5982\u4f55\u4f7f\u7528 Python \u56de\u6d4b\u4e00\u4e2a\u4ea4\u53c9\u7b56\u7565\uff1f<\/strong><\/h2>\n\n\n\n<p>\u8be5\u7b56\u7565\u7684\u76ee\u6807\u662f\u521b\u5efa\u4e00\u4e2a\u975e\u5e38\u57fa\u672c\u7684\u4ea4\u53c9\u7b56\u7565\uff0c\u5176\u4e2d\u6211\u4eec\u4f7f\u7528\u4e00\u4e2a\u5feb\u901f\u79fb\u52a8\u7b80\u5355\u79fb\u52a8\u5e73\u5747\u7ebf\uff08SMA\uff09\u548c\u4e00\u4e2a\u6162\u901f\u79fb\u52a8\u7b80\u5355\u79fb\u52a8\u5e73\u5747\u7ebf\u3002\u5f53\u5feb\u901f\u7ebf\u8d85\u8fc7\u6162\u901f\u7ebf\u65f6\u4e70\u5165\uff0c\u53cd\u4e4b\u5356\u51fa\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u53ef\u4ee5\u7528\u82f9\u679c\u80a1\u7968\u8dd1\u4e00\u4e0b\u3002\u4ee5\u4e0b\u662f\u5177\u4f53\u64cd\u4f5c\u65b9\u6cd5\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">from backtester.data_handler import DataHandler\nfrom backtester.backtester import Backtester\nfrom backtester.strategies import Strategy\n\nsymbol = \"AAPL,MSFT\"\nstart_date = \"2023-01-01\"\nend_date = \"2023-12-31\"\n\ndata = DataHandler(\n        symbol=symbol, start_date=start_date, end_date=end_date\n    ).load_data()\n\nstrategy = Strategy(\n    indicators={\n        \"sma_20\": lambda row: row[\"close\"].rolling(window=20).mean(),\n        \"sma_60\": lambda row: row[\"close\"].rolling(window=60).mean(),\n    },\n    signal_logic=lambda row: 1 if row[\"sma_20\"] > row[\"sma_60\"] else -1,\n)\ndata = strategy.generate_signals(data)\n\nbacktester = Backtester()\nbacktester.backtest(data)\nbacktester.calculate_performance()<\/pre>\n\n\n\n<p>\u8f93\u51fa\u7ed3\u679c\uff1a<\/p>\n\n\n\n<p class=\"has-background\" style=\"background-color:#f4f4f4\">\u6700\u7ec8\u6295\u8d44\u7ec4\u5408\u4ef7\u503c\uff1a11804.58<br>\u603b\u56de\u62a5\uff1a18.05%<br>\u5e74\u5316\u56de\u62a5\uff1a18.20%<br>\u5e74\u5316\u6ce2\u52a8\u7387\uff1a13.06%<br>\u590f\u666e\u6bd4\u7387\uff1a1.39<br>\u7d22\u63d0\u8bfa\u6bd4\u7387\uff1a2.06<br>\u6700\u5927\u56de\u64a4\uff1a-12.07%<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" fetchpriority=\"high\" decoding=\"async\" width=\"731\" height=\"198\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image.png?resize=731%2C198&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-809\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image.png?w=731&amp;ssl=1 731w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image.png?resize=300%2C81&amp;ssl=1 300w\" sizes=\"(max-width: 731px) 100vw, 731px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" decoding=\"async\" width=\"727\" height=\"201\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image-1.png?resize=727%2C201&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-810\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-1.png?w=727&amp;ssl=1 727w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-1.png?resize=300%2C83&amp;ssl=1 300w\" sizes=\"(max-width: 727px) 100vw, 727px\" \/><\/figure>\n\n\n\n<p>\u770b\u8d77\u6765\u8fd8\u884c\uff01<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u5982\u4f55\u4f7f\u7528 Python \u56de\u6d4b\u5747\u503c\u56de\u5f52\u7b56\u7565\uff1f<\/strong><\/h2>\n\n\n\n<p>\u9996\u5148\uff0c\u8ba9\u6211\u4eec\u89c4\u5212\u7b56\u7565\u903b\u8f91\uff1a<\/p>\n\n\n\n<p>\u8be5\u7b56\u7565\u7684\u76ee\u6807\u662f\uff1a\u5f53\u8d44\u4ea7\u7684\u4ea4\u6613\u4ef7\u683c\u8d85\u8fc7\u6eda\u52a8\u5e73\u5747\u503c\u4e09\u4e2a\u6807\u51c6\u5dee\u65f6\u5356\u51fa\u8be5\u8d44\u4ea7\uff1b\u5f53\u8d44\u4ea7\u7684\u4ea4\u6613\u4ef7\u683c\u4f4e\u4e8e\u6eda\u52a8\u5e73\u5747\u503c\u4e09\u4e2a\u6807\u51c6\u5dee\u65f6\u4e70\u5165\u8be5\u8d44\u4ea7\u3002<\/p>\n\n\n\n<p>\u8981\u4f7f\u5176\u6b63\u5e38\u5de5\u4f5c\uff0c\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9700\u8981\u6709\u4e00\u4e2a\u6eda\u52a8\u5e73\u5747\u503c<\/li>\n\n\n\n<li>\u9700\u8981\u4ece\u6eda\u52a8\u5e73\u5747\u503c\u4e2d\u8ba1\u7b97\u6807\u51c6\u5dee<\/li>\n\n\n\n<li>\u9700\u8981\u8ba1\u7b97\u4e0a\u4e0b\u754c<\/li>\n<\/ul>\n\n\n\n<p>\u7531\u4e8e\u6211\u4eec\u7684\u7b56\u7565\u7c7b\u6309\u7ed9\u5b9a\u987a\u5e8f\u5e94\u7528\u8ba1\u7b97\uff0c\u6211\u4eec\u53ef\u4ee5\u6309\u7167\u903b\u8f91\u987a\u5e8f\u8f7b\u677e\u5730\u5c06\u8fd9\u4e9b\u8ba1\u7b97\u8fde\u63a5\u8d77\u6765\uff0c\u5e76\u57fa\u4e8e\u8fd9\u4e9b\u8ba1\u7b97\u521b\u5efa\u4fe1\u53f7\u3002<\/p>\n\n\n\n<p>\u8ba9\u6211\u4eec\u4ece\u5b9a\u4e49\u57fa\u672c\u56de\u6d4b\u53c2\u6570\u5f00\u59cb\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">symbol = \"HE\"\nstart_date = \"2022-01-01\"\nend_date = \"2022-12-31\"<\/pre>\n\n\n\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u9700\u8981\u83b7\u53d6\u6570\u636e\uff0c\u5c06\u64cd\u4f5c\u94fe\u63a5\u5728\u4e00\u8d77\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">data = DataHandler(symbol=symbol, start_date=start_date, end_date=end_date).load_data()\n\nstrategy = Strategy(\n    indicators={\n        \"sma_50\": lambda row: row[\"close\"].rolling(window=50).mean(),\n        \"std_3\": lambda row: row[\"close\"].rolling(window=50).std() * 3,\n        \"std_3_upper\": lambda row: row[\"sma_50\"] + row[\"std_3\"],\n        \"std_3_lower\": lambda row: row[\"sma_50\"] - row[\"std_3\"],\n    },\n    signal_logic=lambda row: (\n        1\n        if row[\"close\"] &lt; row[\"std_3_lower\"]\n        else -1 if row[\"close\"] > row[\"std_3_upper\"] else 0\n    ),\n)\ndata = strategy.generate_signals(data)\n\nbacktester = Backtester()\nbacktester.backtest(data)\nbacktester.calculate_performance()<\/pre>\n\n\n\n<p class=\"has-background\" style=\"background-color:#f4f4f4\">\u6700\u7ec8\u6295\u8d44\u7ec4\u5408\u4ef7\u503c\uff1a10725.54<br>\u603b\u56de\u62a5\uff1a7.26%<br>\u5e74\u5316\u56de\u62a5\uff1a7.29%<br>\u5e74\u5316\u6ce2\u52a8\u7387\uff1a18.32%<br>\u590f\u666e\u6bd4\u7387\uff1a0.40<br>\u7d22\u63d0\u8bfa\u6bd4\u7387\uff1a0.53<br>\u6700\u5927\u56de\u64a4\uff1a-23.37%<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" decoding=\"async\" width=\"733\" height=\"198\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image-2.png?resize=733%2C198&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-811\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-2.png?w=733&amp;ssl=1 733w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-2.png?resize=300%2C81&amp;ssl=1 300w\" sizes=\"(max-width: 733px) 100vw, 733px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" loading=\"lazy\" decoding=\"async\" width=\"727\" height=\"201\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image-3.png?resize=727%2C201&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-812\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-3.png?w=727&amp;ssl=1 727w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-3.png?resize=300%2C83&amp;ssl=1 300w\" sizes=\"(max-width: 727px) 100vw, 727px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>\u5982\u4f55\u4f7f\u7528 Python \u56de\u6d4b\u914d\u5bf9\u4ea4\u6613\u7b56\u7565\uff1f<\/strong><\/h2>\n\n\n\n<p>\u7528 Python \u56de\u6d4b\u914d\u5bf9\u4ea4\u6613\u7b56\u7565\u662f\u4e00\u4e2a\u66f4\u590d\u6742\u7684\u4f8b\u5b50\uff0c\u4f46\u6211\u4eec\u7684\u56de\u6d4b\u5668\u5e94\u8be5\u80fd\u591f\u6267\u884c\u8fd9\u4e00\u7b56\u7565\u3002\u590d\u6742\u4e4b\u5904\u5728\u4e8e\u6211\u4eec\u9700\u8981\u5c06\u4e24\u4e2a\u8d44\u4ea7\u7684\u6570\u636e\u653e\u5728\u540c\u4e00\u4e2a\u6570\u636e\u6846\u4e2d\u3002\u9996\u5148\uff0c\u8ba9\u6211\u4eec\u5b9a\u4e49\u4e00\u4e0b\u8fd9\u4e2a\u7b56\u7565\u3002<\/p>\n\n\n\n<p>\u6211\u4eec\u8981\u4ea4\u6613\u7684\u8d44\u4ea7\u662f Roku (ROKU) \u548c Netflix (NFLX)\uff0c\u56e0\u4e3a\u6839\u636e\u6211\u4eec\u4e4b\u524d\u7684\u6587\u7ae0\u548c\u5206\u6790\uff0c\u5b83\u4eec\u5177\u6709\u534f\u6574\u5173\u7cfb\u3002<\/p>\n\n\n\n<p>\u5982\u679c\u4e00\u53ea\u80a1\u7968\u5728\u8fc7\u53bb\u4e94\u5929\u5185\u76f8\u5bf9\u4e8e\u53e6\u4e00\u53ea\u80a1\u7968\u7684\u6da8\u5e45\u8fbe\u5230\u6216\u8d85\u8fc7 5%\uff0c\u6211\u4eec\u5c31\u4f1a\u8fdb\u5165\u4ed3\u4f4d\uff08\u4e70\u5165\uff09\u3002\u6211\u4eec\u5c06\u5356\u51fa\u4ef7\u683c\u8f83\u9ad8\u7684\u90a3\u53ea\uff0c\u4e70\u5165\u4ef7\u683c\u8f83\u4f4e\u7684\u90a3\u53ea\uff0c\u76f4\u5230\u4ef7\u5dee\u53cd\u8f6c\u3002\u8ba9\u6211\u4eec\u5f00\u59cb\u8bbe\u7f6e\u5e76\u5feb\u901f\u5904\u7406\u6570\u636e\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">import pandas as pd\n\nsymbol = \"NFLX,ROKU\"\nstart_date = \"2023-01-01\"\n\ndata = DataHandler(\n    symbol=symbol,\n    start_date=start_date,\n).load_data()\n\ndata = pd.merge(\n    data[\"NFLX\"].reset_index(),\n    data[\"ROKU\"].reset_index(),\n    left_index=True,\n    right_index=True,\n    suffixes=(\"_NFLX\", \"_ROKU\"),\n)\n\ndata = data.rename(columns={\"close_ROKU\": \"close\"})\ndata.head()<\/pre>\n\n\n\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u53ea\u9700\u5236\u5b9a\u4ea4\u6613\u903b\u8f91\uff0c\u5c31\u53ef\u4ee5\u8fd0\u884c\u56de\u6d4b\u5668\u4e86\uff1a<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\" data-enlighter-language=\"python\" data-enlighter-theme=\"\" data-enlighter-highlight=\"\" data-enlighter-linenumbers=\"\" data-enlighter-lineoffset=\"\" data-enlighter-title=\"\" data-enlighter-group=\"\">strategy = Strategy(\n    indicators={\n        \"day_5_lookback_NFLX\": lambda row: row[\"close_NFLX\"].shift(5),\n        \"day_5_lookback_ROKU\": lambda row: row[\"close\"].shift(5),\n    },\n    signal_logic=lambda row: (\n        1\n        if row[\"close_NFLX\"] > row[\"day_5_lookback_NFLX\"] * 1.05\n        else -1 if row[\"close_NFLX\"] &lt; row[\"day_5_lookback_NFLX\"] * 0.95 else 0\n    ),\n)\ndata = strategy.generate_signals(data)\n\nbacktester = Backtester()\nbacktester.backtest(data)\nbacktester.calculate_performance()<\/pre>\n\n\n\n<p class=\"has-background\" style=\"background-color:#f4f4f4\">\u6700\u7ec8\u6295\u8d44\u7ec4\u5408\u4ef7\u503c\uff1a14387.50<br>\u603b\u56de\u62a5\uff1a43.88%<br>\u5e74\u5316\u56de\u62a5\uff1a34.80%<br>\u5e74\u5316\u6ce2\u52a8\u7387\uff1a55.77%<br>\u590f\u666e\u6bd4\u7387\uff1a0.62<br>\u7d22\u63d0\u8bfa\u6bd4\u7387\uff1a0.74<br>\u6700\u5927\u56de\u64a4\uff1a-39.86%<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" loading=\"lazy\" decoding=\"async\" width=\"735\" height=\"193\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image-4.png?resize=735%2C193&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-813\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-4.png?w=735&amp;ssl=1 735w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-4.png?resize=300%2C79&amp;ssl=1 300w\" sizes=\"(max-width: 735px) 100vw, 735px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" loading=\"lazy\" decoding=\"async\" width=\"721\" height=\"197\" src=\"https:\/\/i0.wp.com\/blog.alltick.co\/wp-content\/uploads\/2024\/08\/image-5.png?resize=721%2C197&#038;ssl=1\" alt=\"ALT\" class=\"wp-image-814\" srcset=\"https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-5.png?w=721&amp;ssl=1 721w, https:\/\/i0.wp.com\/blog.alltick.co\/zh-CN\/wp-content\/uploads\/2024\/08\/image-5.png?resize=300%2C82&amp;ssl=1 300w\" sizes=\"(max-width: 721px) 100vw, 721px\" \/><\/figure>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u5c1d\u8bd5\u7528Python\u521b\u5efa\u4e00\u4e2a\u56de\u6d4b\u6846\u67b6\uff0c\u9700\u8981\u5305\u542b\u4ee5\u4e0b\u529f\u80fd\uff1a \u4e3a\u4e86\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\uff0c\u6211\u4eec\u9700\u8981\u51e0\u4e2a\u5173\u952e\u7ec4\u4ef6&#8230;<\/p>\n","protected":false},"author":1,"featured_media":817,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[8],"tags":[],"class_list":["post-807","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tick-data-wiki"],"acf":[],"_links":{"self":[{"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/posts\/807","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/comments?post=807"}],"version-history":[{"count":5,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/posts\/807\/revisions"}],"predecessor-version":[{"id":10428,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/posts\/807\/revisions\/10428"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/media\/817"}],"wp:attachment":[{"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/media?parent=807"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/categories?post=807"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.alltick.co\/zh-CN\/wp-json\/wp\/v2\/tags?post=807"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}