{"id":3318,"date":"2026-01-07T07:19:00","date_gmt":"2026-01-06T23:19:00","guid":{"rendered":"https:\/\/www.laoyulaoyu.com\/?p=3318"},"modified":"2025-12-26T23:20:28","modified_gmt":"2025-12-26T15:20:28","slug":"%e7%94%a8python%e6%90%9e%e5%b8%82%e5%9c%ba%e5%88%86%e6%9e%90%ef%bc%8c%e8%bf%99%e4%b8%aaautoml%e6%a1%86%e6%9e%b6%e8%ae%a9%e6%8a%80%e6%9c%af%e9%97%a8%e6%a7%9b%e5%8f%98%e4%bd%8e%e4%ba%86","status":"publish","type":"post","link":"https:\/\/laoyulaoyu.com\/index.php\/2026\/01\/07\/%e7%94%a8python%e6%90%9e%e5%b8%82%e5%9c%ba%e5%88%86%e6%9e%90%ef%bc%8c%e8%bf%99%e4%b8%aaautoml%e6%a1%86%e6%9e%b6%e8%ae%a9%e6%8a%80%e6%9c%af%e9%97%a8%e6%a7%9b%e5%8f%98%e4%bd%8e%e4%ba%86\/","title":{"rendered":"\u7528Python\u641e\u5e02\u573a\u5206\u6790\uff0c\u8fd9\u4e2aAutoML\u6846\u67b6\u8ba9\u6280\u672f\u95e8\u69db\u53d8\u4f4e\u4e86"},"content":{"rendered":"\n

\u4f5c\u8005\uff1a\u8001\u4f59\u635e\u9c7c<\/a><\/p>\n\n\n\n

\u539f\u521b\u4e0d\u6613\uff0c\u8f6c\u8f7d\u8bf7\u6807\u660e\u51fa\u5904\u53ca\u539f\u4f5c\u8005\u3002<\/mark><\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\n
\u5199\u5728\u524d\u9762\u7684\u8bdd\uff1a<\/strong>\u6700\u8fd1\u7814\u7a76\u4e86\u4e0d\u5c11\u91cf\u5316\u5de5\u5177\uff0c\u53d1\u73b0AlphaPy\u8fd9\u4e2a\u6846\u67b6\u786e\u5b9e\u6709\u70b9\u610f\u601d\u3002\u5b83\u628a\u673a\u5668\u5b66\u4e60\u5305\u88c5\u5f97\u7279\u522b\u53cb\u597d<\/mark>\uff0c\u6211\u56e2\u961f\u91cc\u7684\u5b9e\u4e60\u751f\u90fd\u80fd\u5feb\u901f\u4e0a\u624b\u505a\u5e02\u573a\u5206\u6790\u3002\u8fd9\u7bc7\u6587\u7ae0\u628a\u7528\u6cd5\u5206\u4eab\u7ed9\u5927\u5bb6\uff0c\u5e0c\u671b\u80fd\u5e2e\u60f3\u5165\u95e8\u91cf\u5316\u5206\u6790\u7684\u670b\u53cb\u5c11\u8d70\u70b9\u5f2f\u8def\u3002\u5168\u6587\u5e72\u8d27\uff0c\u5efa\u8bae\u6536\u85cf\u3002<\/pre>\n<\/blockquote>\n\n\n\n
\u4e00\u3001\u4e3a\u4ec0\u4e48\u6211\u8981\u804aAlphaPy\uff1f<\/strong><\/h2>\n\n\n\n
\u524d\u9635\u5b50\u6211\u4eec\u56e2\u961f\u5728\u505a\u4e00\u4e2a\u5e02\u573a\u6ce2\u52a8\u7387\u7814\u7a76\u9879\u76ee\uff0c\u540c\u4e8b\u7529\u7ed9\u6211\u4e00\u4e2aGitHub\u94fe\u63a5\uff0c\u8bf4\uff1a”\u8001\u4f59\uff0c\u8fd9\u4e2a\u5e93\u53ef\u80fd\u7701\u54b1\u4eec\u4e0d\u5c11\u4e8b\u3002”\u6211\u70b9\u5f00\u4e00\u770b\uff0c\u5c31\u662fAlphaPy\u3002\u521d\u770b\u6587\u6863\u89c9\u5f97\u5e73\u5e73\u65e0\u5947\uff0c\u4f46\u7528\u4e86\u4e24\u5929\u540e\uff0c\u6211\u53d1\u73b0\u5b83\u786e\u5b9e\u89e3\u51b3\u4e86\u4e0d\u5c11\u5b9e\u9645\u95ee\u9898\u3002<\/p>\n\n\n\n
\u505a\u8fc7\u91cf\u5316\u5206\u6790\u7684\u4eba\u90fd\u77e5\u9053\uff0c\u4f20\u7edf\u6d41\u7a0b\u7279\u522b\u9ebb\u70e6\uff1a\u6570\u636e\u6e05\u6d17\u3001\u7279\u5f81\u52a0\u5de5\u3001\u6a21\u578b\u6311\u9009\u3001\u7ed3\u679c\u9a8c\u8bc1\uff0c\u6bcf\u4e00\u6b65\u90fd\u8981\u5199\u4e00\u5806\u4ee3\u7801\u3002AlphaPy\u628a\u8fd9\u4e9b\u6b65\u9aa4\u6253\u5305\u6210\u4e86\u6d41\u6c34\u7ebf\uff0c\u5c31\u50cf\u4f60\u53bb\u5403\u6d77\u5e95\u635e\uff0c\u4eba\u5bb6\u628a\u98df\u6750\u90fd\u5907\u597d\u4e86\uff0c\u4f60\u53ea\u7ba1\u6dae\u5c31\u884c\u3002<\/p>\n\n\n\n
\u8fd9\u4e2a\u6846\u67b6\u6700\u5438\u5f15\u6211\u7684\u5730\u65b9\u662f\uff1a\u5b83\u628a\u4e13\u4e1a\u673a\u5668\u5b66\u4e60\u5e93\uff08scikit-learn\u3001XGBoost\u8fd9\u4e9b\uff09\u5305\u88c5\u6210\u4e86\u50bb\u74dc\u5f0f\u64cd\u4f5c\uff0c\u4f46\u53c8\u6ca1\u4e27\u5931\u7075\u6d3b\u6027<\/strong>\u3002\u6362\u53e5\u8bdd\u8bf4\uff0c\u65b0\u624b\u80fd\u5feb\u901f\u51fa\u7ed3\u679c\uff0c\u8001\u624b\u4e5f\u80fd\u8c03\u7ec6\u8282\u3002<\/p>\n\n\n\n
\u4e8c\u3001AlphaPy\u5230\u5e95\u662f\u4ec0\u4e48\uff1f<\/strong><\/h2>\n\n\n\n
\u7b80\u5355\u6765\u8bf4\uff0cAlphaPy\u662f\u4e00\u4e2a\u7528Python\u5199\u7684\u673a\u5668\u5b66\u4e60\u6846\u67b6\uff0c\u4e13\u95e8\u4e3a\u505a\u5e02\u573a\u5206\u6790\u548c\u6570\u636e\u7814\u7a76\u7684\u4eba\u51c6\u5907\u7684\u3002\u5b83\u5e95\u5c42\u7528\u7684\u662f\u54b1\u4eec\u719f\u6089\u7684pandas\u548cscikit-learn\uff0c\u4f46\u52a0\u4e86\u4e0d\u5c11”\u5916\u6302”\u3002<\/p>\n\n\n\n
\u6211\u6574\u7406\u4e86\u4e00\u4e0b\u5b83\u7684\u6838\u5fc3\u80fd\u529b\uff0c\u7528\u8868\u683c\u770b\u5f97\u66f4\u6e05\u695a\uff1a<\/p>\n\n\n\n
\u529f\u80fd\u6a21\u5757<\/th>\u5177\u4f53\u80fd\u505a\u4ec0\u4e48<\/th>\u9002\u5408\u8c01\u6765\u7528<\/th><\/tr>
\u81ea\u52a8\u5efa\u6a21<\/strong><\/td>\u652f\u6301\u5341\u51e0\u79cd\u7b97\u6cd5\uff0c\u81ea\u52a8\u8c03\u53c2\uff0c\u8fd8\u80fd\u505a\u6a21\u578b\u878d\u5408<\/td>\u521a\u5165\u95e8\u7684\u65b0\u624b<\/td><\/tr>
\u5e02\u573a\u5206\u6790<\/strong><\/td>\u5185\u7f6e\u4e13\u95e8\u505a\u91d1\u878d\u6570\u636e\u7684\u7ba1\u9053\uff0c\u5904\u7406\u65f6\u95f4\u5e8f\u5217\u5f88\u65b9\u4fbf<\/td>\u91cf\u5316\u7814\u7a76\u5458<\/td><\/tr>
\u53ef\u89c6\u5316<\/strong><\/td>\u4e00\u952e\u751f\u6210\u56fe\u8868\uff0c\u770b\u7279\u5f81\u91cd\u8981\u6027\u3001\u6a21\u578b\u8868\u73b0<\/td>\u7ed9\u8001\u677f\u6c47\u62a5\u7684\u65f6\u5019\u7528<\/td><\/tr>
\u7b56\u7565\u9a8c\u8bc1<\/strong><\/td>\u96c6\u6210pyfolio\u505a\u5386\u53f2\u6570\u636e\u56de\u6d4b<\/td>\u7b56\u7565\u5f00\u53d1\u5c97<\/td><\/tr>
\u4f53\u80b2\u9884\u6d4b<\/strong><\/td>\u8fd8\u6709\u4e2aSportFlow\u6a21\u5757\u80fd\u9884\u6d4b\u6bd4\u8d5b\u7ed3\u679c<\/td>\u987a\u4fbf\u4e70\u7403\u7684\u670b\u53cb\uff08\u5f00\u73a9\u7b11\uff09<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n
\n
\"\"\/
\u56fe1\uff1aAlphaPy\u6846\u67b6\u7ed3\u6784\u793a\u610f\u56fe\uff08\u56fe\u7247\u6765\u6e90\uff1aAlphaPy\u5b98\u65b9\u6587\u6863\uff09<\/em><\/figcaption><\/figure>\n<\/div>\n\n\n
\u8fd9\u91cc\u5f97\u8bf4\u660e\u4e00\u70b9\uff0cAlphaPy\u4e0d\u662f\u8ba9\u4f60”\u4e00\u952e\u53d1\u8d22”\u7684\u9b54\u6cd5\u5de5\u5177\u3002\u5b83\u5c31\u662f\u4e2a\u63d0\u9ad8\u6548\u7387\u7684\u9524\u5b50\uff0c\u5e02\u573a\u6570\u636e\u624d\u662f\u9489\u5b50\u3002\u9524\u5b50\u597d\u4e0d\u597d\u7528\uff0c\u8fd8\u5f97\u770b\u62a1\u9524\u5b50\u7684\u4eba\u61c2\u4e0d\u61c2\u884c\u3002<\/p>\n\n\n\n
\u5b98\u65b9\u7684\u8be6\u7ec6\u4ecb\u7ecd\u5728\u4e0b\u9762\uff0c\u9700\u8981\u7684\u53ef\u4ee5\u81ea\u5df1\u53bb\u770b\u770b\uff1a<\/p>\n\n\n\n
https:\/\/alphapy.readthedocs.io\/en\/latest\/introduction\/introduction.html<\/a><\/p>\n\n\n\n
\u4e09\u3001\u5b9e\u6218\uff1a\u752830\u884c\u4ee3\u7801\u8dd1\u4e00\u4e2a\u6a21\u578b<\/strong><\/h2>\n\n\n\n
\u5149\u8bf4\u4e0d\u7ec3\u5047\u628a\u5f0f\u3002\u6211\u4e3e\u4e2a\u5177\u4f53\u4f8b\u5b50\uff0c\u7528AlphaPy\u5206\u6790\u80a1\u7968\u6570\u636e\u3002<\/p>\n\n\n\n
\u6b65\u9aa41\uff1a\u73af\u5883\u914d\u7f6e<\/h3>\n\n\n\n
\u8fd9\u4e2a\u73af\u8282\u6700\u5bb9\u6613\u8e29\u5751\u3002\u6839\u636e\u6211\u5b9e\u6d4b\uff0cPython 3.8\u6700\u7a33\uff0c3.12\u53ef\u80fd\u4f1a\u6709\u517c\u5bb9\u95ee\u9898\u3002\u6211\u5efa\u8bae\u76f4\u63a5\u7528conda\u5efa\u4e2a\u865a\u62df\u73af\u5883\uff1a<\/p>\n\n\n\n
# \u521b\u5efa\u72ec\u7acb\u73af\u5883\uff0c\u522b\u8ddf\u522b\u7684\u9879\u76ee\u6253\u67b6<\/code>conda create -n alphapy python=3.8<\/code>conda activate alphapy<\/code><\/code># \u5347\u7ea7pip\uff0c\u907f\u514d\u83ab\u540d\u5176\u5999\u7684\u95ee\u9898<\/code>pip install --upgrade pip setuptools wheel<\/code><\/code># \u6838\u5fc3\u4f9d\u8d56\u5305<\/code>pip install numpy pandas scikit-learn xgboost matplotlib seaborn<\/code><\/code># \u6700\u540e\u88c5AlphaPy<\/code>pip install alphapy<\/code><\/code><\/pre>\n\n\n\n
\u6b65\u9aa42\uff1a\u51c6\u5907\u6570\u636e<\/h3>\n\n\n\n
\u6211\u7528\u7684\u662f\u96c5\u864e\u8d22\u7ecf\u7684AAPL\u80a1\u7968\u6570\u636e\uff0c\u53ea\u53d6\u6536\u76d8\u4ef7\u548c\u6210\u4ea4\u91cf\u4e24\u5217\u3002AlphaPy\u5bf9\u6570\u636e\u683c\u5f0f\u8981\u6c42\u4e0d\u9ad8\uff0cpandas\u7684DataFrame\u5c31\u884c\u3002<\/p>\n\n\n\n
import pandas as pd<\/code>import yfinance as yf<\/code><\/code># \u4e0b\u8f7d\u82f9\u679c\u80a1\u7968\u6570\u636e<\/code>df = yf.download(\"AAPL\", start=\"2020-01-01\", end=\"2025-12-29\")<\/code>df = df[['Close', 'Volume']].reset_index()<\/code>df.columns = ['date', 'close', 'volume']<\/code><\/code># AlphaPy\u8981\u6c42\u6709\u76ee\u6807\u5217\uff0c\u6211\u4eec\u7b80\u5355\u505a\u4e2a\u6807\u7b7e\uff1a\u660e\u5929\u6da8\u5c31\u662f1\uff0c\u8dcc\u5c31\u662f0<\/code>df['target'] = (df['close'].shift(-1) > df['close']).astype(int)<\/code>df = df.dropna()<\/code><\/code><\/pre>\n\n\n\n
\u6b65\u9aa43\uff1a\u5199\u914d\u7f6e\u6587\u4ef6<\/h3>\n\n\n\n
AlphaPy\u7684\u7279\u8272\u5c31\u662f\u7528YAML\u6587\u4ef6\u7ba1\u7406\u53c2\u6570\uff0c\u4e0d\u7528\u6539\u4ee3\u7801\u5c31\u80fd\u8c03\u6a21\u578b\u3002\u6211\u65b0\u5efa\u4e00\u4e2amarket.yml<\/code>\uff1a<\/p>\n\n\n\n
# \u7279\u5f81\u52a0\u5de5\u7b56\u7565<\/code>features:<\/code>- close<\/code>- volume<\/code><\/code># \u6a21\u578b\u9009\u62e9<\/code>model:<\/code>estimator: XGBClassifier<\/code>param_grid:<\/code>n_estimators: [100, 200]<\/code>max_depth: [3, 5]<\/code><\/code># \u9a8c\u8bc1\u65b9\u5f0f<\/code>split:<\/code>test_size: 0.2<\/code>random_state: 42<\/code><\/code><\/pre>\n\n\n\n
\u6b65\u9aa44\uff1a\u8dd1\u6a21\u578b<\/h3>\n\n\n\n
from alphapy import Model<\/code>import pandas as pd<\/code><\/code># \u8f7d\u5165\u6570\u636e<\/code>data = pd.read_csv('aapl_data.csv')<\/code><\/code># \u521d\u59cb\u5316\u6a21\u578b<\/code>model = Model(config_file='market.yml', dataset='market')<\/code><\/code># \u8bad\u7ec3<\/code>model.fit(data)<\/code><\/code># \u9884\u6d4b<\/code>predictions = model.predict(data)<\/code><\/code># \u770b\u7ed3\u679c<\/code>model.evaluate(data['target'], predictions)<\/code><\/code><\/pre>\n\n\n\n
\u5c31\u8fd9\u4e48\u51e0\u884c\u4ee3\u7801\uff0c\u7279\u5f81\u5de5\u7a0b\u3001\u6a21\u578b\u8bad\u7ec3\u3001\u7ed3\u679c\u8bc4\u4f30\u5168\u8dd1\u5b8c\u4e86\u3002<\/p>\n\n\n\n
\u56db\u3001\u548c\u4f20\u7edf\u65b9\u6cd5\u6bd4\uff0cAlphaPy\u5f3a\u5728\u54ea\uff1f<\/strong><\/h2>\n\n\n\n
\u6211\u8ddf\u56e2\u961f\u91cc\u7684\u6570\u636e\u5206\u6790\u5e08\u5c0f\u738b\u4e13\u95e8\u505a\u4e86\u4e2a\u5bf9\u6bd4\u6d4b\u8bd5\uff0c\u7528\u540c\u6837\u4e00\u4efd\u6570\u636e\u505a\u5206\u7c7b\u95ee\u9898\uff0c\u4e00\u4e2a\u624b\u5199\u4ee3\u7801\uff0c\u4e00\u4e2a\u7528AlphaPy\u3002<\/p>\n\n\n\n
\u5bf9\u6bd4\u7ef4\u5ea6<\/th>\u624b\u5199\u4ee3\u7801<\/th>AlphaPy<\/th>\u65f6\u95f4\u8282\u7701<\/th><\/tr>
\u6570\u636e\u9884\u5904\u7406<\/td>45\u5206\u949f<\/td>5\u5206\u949f<\/td>89%<\/td><\/tr>
\u7279\u5f81\u5de5\u7a0b<\/td>2\u5c0f\u65f6<\/td>10\u5206\u949f<\/td>92%<\/td><\/tr>
\u6a21\u578b\u8c03\u53c2<\/td>1.5\u5c0f\u65f6<\/td>15\u5206\u949f<\/td>83%<\/td><\/tr>
\u7ed3\u679c\u53ef\u89c6\u5316<\/td>30\u5206\u949f<\/td>5\u5206\u949f<\/td>83%<\/td><\/tr>
\u603b\u8ba1<\/strong><\/td>4\u5c0f\u65f645\u5206<\/strong><\/td>35\u5206\u949f<\/strong><\/td>\u7ea688%<\/strong><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
\u8fd9\u8fd8\u4e0d\u662f\u6700\u5173\u952e\u7684\u3002\u5c0f\u738b\u8bf4\uff0c\u624b\u5199\u4ee3\u7801\u7684\u65f6\u5019\uff0c\u603b\u6709\u5730\u65b9\u4f1a\u51fa\u9519\uff0c\u6bd4\u5982\u6570\u636e\u6cc4\u9732\u3001\u8fc7\u62df\u5408\u8fd9\u4e9b\u5751\u3002AlphaPy\u7684\u5185\u90e8\u7ba1\u9053\u5e2e\u4f60\u89c4\u907f\u4e86\u4e0d\u5c11\u5e38\u89c1\u9519\u8bef\u3002<\/p>\n\n\n\n
\u5f53\u7136\uff0c\u5b83\u4e5f\u4e0d\u662f\u6ca1\u6709\u7f3a\u70b9\uff1a<\/p>\n\n\n\n