{"id":54073,"date":"2025-08-12T21:49:56","date_gmt":"2025-08-12T13:49:56","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/54073.html"},"modified":"2025-08-12T21:49:56","modified_gmt":"2025-08-12T13:49:56","slug":"%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0-dbscan-2","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/54073.html","title":{"rendered":"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN"},"content":{"rendered":"<p>DBSCAN&#xff08;Density-Based Spatial Clustering of Applications with Noise&#xff09;\u662f\u4e00\u79cd\u57fa\u4e8e\u5bc6\u5ea6\u7684\u7ecf\u5178\u805a\u7c7b\u7b97\u6cd5&#xff0c;\u7531 Martin Ester \u7b49\u4eba\u4e8e 1996 \u5e74\u63d0\u51fa\u3002\u8be5\u7b97\u6cd5\u901a\u8fc7\u5b9a\u4e49\u4e24\u4e2a\u5173\u952e\u53c2\u6570&#xff08;\u90bb\u57df\u534a\u5f84 eps \u548c\u6700\u5c0f\u6837\u672c\u6570 minPts&#xff09;\u6765\u8bc6\u522b\u9ad8\u5bc6\u5ea6\u533a\u57df&#xff0c;\u80fd\u591f\u6709\u6548\u53d1\u73b0\u4efb\u610f\u5f62\u72b6\u7684\u7c07&#xff0c;\u5e76\u81ea\u52a8\u5c06\u7a00\u758f\u533a\u57df\u7684\u70b9\u6807\u8bb0\u4e3a\u566a\u58f0\u70b9&#xff08;\u79bb\u7fa4\u70b9&#xff09;\u3002<\/p>\n<p>\u4e0e\u57fa\u4e8e\u8ddd\u79bb\u7684 K-Means \u7b97\u6cd5\u76f8\u6bd4&#xff0c;DBSCAN \u5177\u6709\u4ee5\u4e0b\u663e\u8457\u4f18\u52bf&#xff1a;<\/p>\n<li>\u65e0\u9700\u9884\u5148\u6307\u5b9a\u7c07\u7684\u6570\u91cf&#xff0c;\u7b97\u6cd5\u53ef\u81ea\u52a8\u786e\u5b9a\u5408\u9002\u7684\u7c07\u6570<\/li>\n<li>\u80fd\u591f\u8bc6\u522b\u975e\u51f8\u5f62\u72b6\u7684\u7c07&#xff08;\u5982\u73af\u5f62\u3001\u6708\u7259\u5f62\u7b49&#xff09;<\/li>\n<li>\u5bf9\u566a\u58f0\u6570\u636e\u5177\u6709\u9c81\u68d2\u6027&#xff0c;\u80fd\u6709\u6548\u8fc7\u6ee4\u79bb\u7fa4\u70b9<\/li>\n<li>\u5bf9\u521d\u59cb\u503c\u4e0d\u654f\u611f&#xff0c;\u7ed3\u679c\u5177\u6709\u7a33\u5b9a\u6027<\/li>\n<p>\u4f8b\u5982\u5728\u7535\u5546\u7528\u6237\u5206\u6790\u4e2d&#xff0c;DBSCAN \u53ef\u4ee5\u57fa\u4e8e\u7528\u6237\u7684\u8d2d\u4e70\u9891\u7387\u548c\u6d88\u8d39\u91d1\u989d&#xff0c;\u81ea\u52a8\u8bc6\u522b\u51fa\u9ad8\u4ef7\u503c\u7528\u6237\u7fa4\u3001\u666e\u901a\u7528\u6237\u7fa4&#xff0c;\u5e76\u5c06\u5f02\u5e38\u6d88\u8d39\u884c\u4e3a\u7684\u7528\u6237\u6807\u8bb0\u4e3a\u9700\u8981\u7279\u522b\u5173\u6ce8\u7684\u79bb\u7fa4\u70b9\u3002<\/p>\n<h2>DBSCAN \u7b97\u6cd5\u8be6\u89e3<\/h2>\n<h3>\u6838\u5fc3\u6982\u5ff5<\/h3>\n<h4>&#xff08;1&#xff09;\u5173\u952e\u53c2\u6570<\/h4>\n<p>eps&#xff08;\u03b5&#xff09;&#xff1a;\u90bb\u57df\u534a\u5f84&#xff0c;\u51b3\u5b9a\u4e24\u4e2a\u6837\u672c\u662f\u5426\u5c5e\u4e8e\u540c\u4e00\u7c07\u3002\u8fd9\u4e2a\u53c2\u6570\u76f4\u63a5\u5f71\u54cd\u805a\u7c7b\u7ed3\u679c\u7684\u8303\u56f4\u548c\u7c92\u5ea6\u3002\u4f8b\u5982&#xff0c;\u5728\u4e8c\u7ef4\u7a7a\u95f4\u4e2d&#xff0c;\u5982\u679c\u8bbe\u7f6e eps&#061;0.5&#xff0c;\u610f\u5473\u7740\u4e24\u4e2a\u70b9\u8ddd\u79bb\u5c0f\u4e8e0.5\u5355\u4f4d\u65f6\u4f1a\u88ab\u89c6\u4e3a\u76f8\u90bb\u3002<\/p>\n<ul>\n<li>\u8f83\u5c0f\u503c\u53ef\u80fd\u5bfc\u81f4\u8fc7\u5ea6\u5206\u5272<\/li>\n<li>\u8f83\u5927\u503c\u53ef\u80fd\u5408\u5e76\u672c\u5e94\u5206\u5f00\u7684\u7c07<\/li>\n<\/ul>\n<p>min_samples&#xff1a;\u6838\u5fc3\u70b9&#xff08;Core Point&#xff09;\u7684\u90bb\u57df\u5185\u6700\u5c11\u6837\u672c\u6570\u3002\u8fd9\u4e2a\u53c2\u6570\u51b3\u5b9a\u4e86\u4e00\u4e2a\u533a\u57df\u88ab\u8bc6\u522b\u4e3a\u5bc6\u96c6\u533a\u57df\u6240\u9700\u7684\u6700\u5c0f\u6570\u636e\u70b9\u6570\u91cf\u3002<\/p>\n<ul>\n<li>\u5e38\u89c1\u53d6\u503c\u8303\u56f4&#xff1a;3-10&#xff08;\u53d6\u51b3\u4e8e\u6570\u636e\u96c6\u5927\u5c0f&#xff09;<\/li>\n<li>\u8f83\u5927\u503c\u66f4\u9002\u5408\u566a\u58f0\u8f83\u591a\u7684\u6570\u636e\u96c6<\/li>\n<\/ul>\n<h4>&#xff08;2&#xff09;\u70b9\u7c7b\u578b<\/h4>\n<p>\u6838\u5fc3\u70b9&#xff08;Core Point&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u5728 eps \u90bb\u57df\u5185\u81f3\u5c11\u6709 min_samples \u4e2a\u6837\u672c\u7684\u70b9<\/li>\n<li>\u662f\u7c07\u5f62\u6210\u7684\u57fa\u7840<\/li>\n<li>\u793a\u4f8b&#xff1a;\u5728\u4e00\u4e2a\u4e8c\u7ef4\u6570\u636e\u96c6\u4e2d&#xff0c;\u67d0\u70b9\u5468\u56f4\u6709\u81f3\u5c115\u4e2a\u70b9&#xff08;min_samples&#061;5&#xff09;\u90fd\u5728\u534a\u5f840.3&#xff08;eps&#061;0.3&#xff09;\u8303\u56f4\u5185<\/li>\n<\/ul>\n<p>\u8fb9\u754c\u70b9&#xff08;Border Point&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u5c5e\u4e8e\u67d0\u4e2a\u6838\u5fc3\u70b9\u7684\u90bb\u57df&#xff0c;\u4f46\u81ea\u8eab\u90bb\u57df\u5185\u6837\u672c\u6570\u4e0d\u8db3 min_samples<\/li>\n<li>\u5904\u5728\u7c07\u7684\u8fb9\u7f18\u533a\u57df<\/li>\n<li>\u793a\u4f8b&#xff1a;\u67d0\u70b9\u5468\u56f4\u53ea\u67093\u4e2a\u90bb\u5c45&#xff08;min_samples&#061;5&#xff09;&#xff0c;\u4f46\u4f4d\u4e8e\u4e00\u4e2a\u6838\u5fc3\u70b9\u7684\u90bb\u57df\u5185<\/li>\n<\/ul>\n<p>\u566a\u58f0\u70b9&#xff08;Noise Point&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u65e2\u975e\u6838\u5fc3\u70b9\u4e5f\u975e\u8fb9\u754c\u70b9<\/li>\n<li>\u88ab\u7b97\u6cd5\u8bc6\u522b\u4e3a\u79bb\u7fa4\u503c<\/li>\n<li>\u793a\u4f8b&#xff1a;\u67d0\u70b9\u5468\u56f4\u6ca1\u6709\u8db3\u591f\u90bb\u5c45&#xff0c;\u4e5f\u4e0d\u5728\u4efb\u4f55\u6838\u5fc3\u70b9\u7684\u90bb\u57df\u5185<\/li>\n<\/ul>\n<h3>\u7b97\u6cd5\u6d41\u7a0b<\/h3>\n<h4>1. \u968f\u673a\u9009\u62e9\u4e00\u4e2a\u672a\u8bbf\u95ee\u7684\u70b9<\/h4>\n<ul>\n<li>\u4ece\u6570\u636e\u96c6\u4e2d\u968f\u673a\u9009\u53d6\u4e00\u4e2a\u672a\u88ab\u5904\u7406\u7684\u6570\u636e\u70b9<\/li>\n<li>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d&#xff0c;\u4e3a\u63d0\u9ad8\u53ef\u91cd\u590d\u6027&#xff0c;\u901a\u5e38\u4f1a\u8bbe\u7f6e\u968f\u673a\u79cd\u5b50<\/li>\n<\/ul>\n<h4>2. \u68c0\u67e5\u5176 eps \u90bb\u57df\u5185\u7684\u6837\u672c\u6570<\/h4>\n<ul>\n<li>\u8ba1\u7b97\u8be5\u70b9\u534a\u5f84eps\u8303\u56f4\u5185\u7684\u6240\u6709\u70b9<\/li>\n<li>\u6761\u4ef6\u5224\u65ad&#xff1a;\n<ul>\n<li>\u82e5\u90bb\u57df\u5185\u70b9\u6570 \u2265 min_samples&#xff1a;\n<ul>\n<li>\u6807\u8bb0\u8be5\u70b9\u4e3a\u6838\u5fc3\u70b9<\/li>\n<li>\u521b\u5efa\u65b0\u7c07<\/li>\n<li>\u5c06\u8be5\u70b9\u52a0\u5165\u5f53\u524d\u7c07<\/li>\n<\/ul>\n<\/li>\n<li>\u5426\u5219&#xff1a;\n<ul>\n<li>\u6682\u65f6\u6807\u8bb0\u4e3a\u566a\u58f0\u70b9&#xff08;\u53ef\u80fd\u5728\u540e\u7eed\u5904\u7406\u4e2d\u88ab\u91cd\u65b0\u5206\u7c7b&#xff09;<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4>3. \u6269\u5c55\u7c07<\/h4>\n<ul>\n<li>\u5bf9\u4e8e\u65b0\u53d1\u73b0\u7684\u6838\u5fc3\u70b9&#xff0c;\u9012\u5f52\u5904\u7406\u5176\u90bb\u57df\u5185\u7684\u6240\u6709\u70b9&#xff1a;\n<ul>\n<li>\u5c06\u90bb\u57df\u5185\u672a\u5206\u7c7b\u7684\u70b9\u52a0\u5165\u5f53\u524d\u7c07<\/li>\n<li>\u5982\u679c\u90bb\u57df\u5185\u6709\u65b0\u53d1\u73b0\u7684\u6838\u5fc3\u70b9&#xff0c;\u7ee7\u7eed\u6269\u5c55<\/li>\n<\/ul>\n<\/li>\n<li>\u4f7f\u7528\u6df1\u5ea6\u4f18\u5148\u641c\u7d22(DFS)\u6216\u5e7f\u5ea6\u4f18\u5148\u641c\u7d22(BFS)\u7b56\u7565\u8fdb\u884c\u6269\u5c55<\/li>\n<\/ul>\n<h4>4. \u91cd\u590d<\/h4>\n<ul>\n<li>\u8fd4\u56de\u6b65\u9aa41&#xff0c;\u9009\u62e9\u4e0b\u4e00\u4e2a\u672a\u8bbf\u95ee\u7684\u70b9<\/li>\n<li>\u76f4\u5230\u6240\u6709\u70b9\u90fd\u88ab\u8bbf\u95ee\u548c\u5206\u7c7b<\/li>\n<\/ul>\n<h3>\u4f18\u7f3a\u70b9<\/h3>\n<h4>\u4f18\u70b9<\/h4>\n<li>\n<p>\u65e0\u9700\u6307\u5b9a\u7c07\u6570\u91cf&#xff08;\u5bf9\u6bd4 K-Means&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u81ea\u52a8\u786e\u5b9a\u6570\u636e\u4e2d\u5b58\u5728\u7684\u7c07\u6570\u91cf<\/li>\n<li>\u9002\u5408\u4e8b\u5148\u4e0d\u77e5\u9053\u6570\u636e\u5206\u5e03\u7684\u60c5\u51b5<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u80fd\u53d1\u73b0\u4efb\u610f\u5f62\u72b6\u7684\u7c07&#xff08;\u5982\u73af\u5f62\u3001\u7ebf\u6027&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u57fa\u4e8e\u5bc6\u5ea6\u8fde\u63a5\u800c\u975e\u8ddd\u79bb\u8d28\u5fc3<\/li>\n<li>\u793a\u4f8b&#xff1a;\u80fd\u6b63\u786e\u8bc6\u522b\u73af\u5f62\u5206\u5e03\u7684\u6570\u636e&#xff08;K-Means\u4f1a\u5c06\u5176\u5206\u6210\u591a\u4e2a\u6247\u5f62&#xff09;<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u5bf9\u566a\u58f0\u9c81\u68d2&#xff08;\u81ea\u52a8\u8bc6\u522b\u79bb\u7fa4\u70b9&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u660e\u786e\u7684\u566a\u58f0\u8bc6\u522b\u673a\u5236<\/li>\n<li>\u793a\u4f8b&#xff1a;\u5728\u542b\u670910%\u968f\u673a\u566a\u58f0\u7684\u6570\u636e\u96c6\u4e2d\u4ecd\u80fd\u4fdd\u6301\u826f\u597d\u805a\u7c7b\u6548\u679c<\/li>\n<\/ul>\n<\/li>\n<h4>\u7f3a\u70b9<\/h4>\n<li>\n<p>\u5bf9\u53c2\u6570 eps \u548c min_samples \u654f\u611f&#xff1a;<\/p>\n<ul>\n<li>\u9700\u8981\u4ed4\u7ec6\u8c03\u6574\u53c2\u6570<\/li>\n<li>\u53ef\u80fd\u9700\u8981\u901a\u8fc7k-\u8ddd\u79bb\u56fe\u7b49\u65b9\u6cd5\u786e\u5b9a\u5408\u9002\u53c2\u6570<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u4e0d\u9002\u5408\u5bc6\u5ea6\u5dee\u5f02\u5927\u7684\u6570\u636e\u96c6&#xff08;\u5168\u5c40\u53c2\u6570\u96be\u4ee5\u9002\u5e94\u5c40\u90e8\u53d8\u5316&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u5355\u4e00eps\u503c\u65e0\u6cd5\u540c\u65f6\u9002\u5e94\u7a00\u758f\u548c\u5bc6\u96c6\u533a\u57df<\/li>\n<li>\u793a\u4f8b&#xff1a;\u6570\u636e\u96c6\u4e2d\u540c\u65f6\u5b58\u5728\u975e\u5e38\u5bc6\u96c6\u548c\u975e\u5e38\u7a00\u758f\u7684\u533a\u57df<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u9ad8\u7ef4\u6570\u636e\u6027\u80fd\u4e0b\u964d&#xff08;&#034;\u7ef4\u5ea6\u707e\u96be&#034;&#xff09;&#xff1a;<\/p>\n<ul>\n<li>\u5728\u9ad8\u7ef4\u7a7a\u95f4\u4e2d\u8ddd\u79bb\u5ea6\u91cf\u53d8\u5f97\u4e0d\u53ef\u9760<\/li>\n<li>\u901a\u5e38\u9700\u8981\u964d\u7ef4\u9884\u5904\u7406<\/li>\n<li>\u793a\u4f8b&#xff1a;\u5728100\u7ef4\u4ee5\u4e0a\u7684\u6570\u636e\u96c6\u4e2d\u6548\u679c\u663e\u8457\u4e0b\u964d<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u8ba1\u7b97\u590d\u6742\u5ea6&#xff1a;<\/p>\n<ul>\n<li>\u9700\u8981\u8ba1\u7b97\u6240\u6709\u70b9\u5bf9\u4e4b\u95f4\u7684\u8ddd\u79bb<\/li>\n<li>\u65f6\u95f4\u590d\u6742\u5ea6\u7ea6\u4e3aO(n\u00b2)&#xff0c;\u5bf9\u4e8e\u5927\u6570\u636e\u96c6\u53ef\u80fd\u8f83\u6162<\/li>\n<li>\u53ef\u901a\u8fc7\u7a7a\u95f4\u7d22\u5f15\u6280\u672f&#xff08;\u5982KD-tree&#xff09;\u4f18\u5316<\/li>\n<\/ul>\n<\/li>\n<h2>Python\u5b9e\u6218<\/h2>\n<p>class sklearn.cluster.DBSCAN( eps&#061;0.5, # \u90bb\u57df\u534a\u5f84 min_samples&#061;5, # \u6838\u5fc3\u70b9\u7684\u6700\u5c0f\u90bb\u57df\u6837\u672c\u6570 metric&#061;&#039;euclidean&#039;, # \u8ddd\u79bb\u5ea6\u91cf metric_params&#061;None, algorithm&#061;&#039;auto&#039;, # \u90bb\u57df\u8ba1\u7b97\u7b97\u6cd5 (&#039;auto&#039;, &#039;ball_tree&#039;, &#039;kd_tree&#039;, &#039;brute&#039;) leaf_size&#061;30, # \u6811\u7c7b\u7b97\u6cd5\u7684\u53f6\u5b50\u5927\u5c0f p&#061;None, # \u95f5\u53ef\u592b\u65af\u57fa\u8ddd\u79bb\u7684p\u503c&#xff08;p&#061;2\u4e3a\u6b27\u6c0f\u8ddd\u79bb&#xff09; n_jobs&#061;None # \u5e76\u884c\u8ba1\u7b97\u6570 )<\/p>\n<h3>2. \u6838\u5fc3\u53c2\u6570\u200b\u200b<\/h3>\n<table>\n<tr>\n<p>\u53c2\u6570<\/p>\n<p>\u7c7b\u578b<\/p>\n<p>\u9ed8\u8ba4\u503c<\/p>\n<p>\u8bf4\u660e<\/p>\n<\/tr>\n<tbody>\n<tr>\n<td>\n<p>\u200b\u200beps\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>float<\/p>\n<\/td>\n<td>\n<p>0.5<\/p>\n<\/td>\n<td>\n<p>\u90bb\u57df\u534a\u5f84&#xff0c;\u51b3\u5b9a\u6837\u672c\u662f\u5426\u5c5e\u4e8e\u540c\u4e00\u7c07\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bmin_samples\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>int<\/p>\n<\/td>\n<td>\n<p>5<\/p>\n<\/td>\n<td>\n<p>\u6838\u5fc3\u70b9\u7684\u90bb\u57df\u5185\u6700\u5c11\u6837\u672c\u6570\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bmetric\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>str or callable<\/p>\n<\/td>\n<td>\n<p>&#039;euclidean&#039;<\/p>\n<\/td>\n<td>\n<p>\u8ddd\u79bb\u5ea6\u91cf&#xff0c;\u652f\u6301\u00a0&#039;euclidean&#039;,\u00a0&#039;manhattan&#039;,\u00a0&#039;cosine&#039;\u7b49&#xff0c;\u6216\u81ea\u5b9a\u4e49\u51fd\u6570\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200balgorithm\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>str<\/p>\n<\/td>\n<td>\n<p>&#039;auto&#039;<\/p>\n<\/td>\n<td>\n<p>\u90bb\u57df\u641c\u7d22\u7b97\u6cd5&#xff1a;&#039;ball_tree&#039;,\u00a0&#039;kd_tree&#039;,\u00a0&#039;brute&#039;,\u00a0&#039;auto&#039;\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bleaf_size\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>int<\/p>\n<\/td>\n<td>\n<p>30<\/p>\n<\/td>\n<td>\n<p>\u6811\u7c7b\u7b97\u6cd5&#xff08;BallTree\/KDTree&#xff09;\u7684\u53f6\u5b50\u5927\u5c0f\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bp\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>float<\/p>\n<\/td>\n<td>\n<p>None<\/p>\n<\/td>\n<td>\n<p>\u95f5\u53ef\u592b\u65af\u57fa\u8ddd\u79bb\u7684\u5e42\u53c2\u6570&#xff08;p&#061;1&#xff1a;\u66fc\u54c8\u987f&#xff1b;p&#061;2&#xff1a;\u6b27\u6c0f&#xff09;\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bn_jobs\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>int<\/p>\n<\/td>\n<td>\n<p>None<\/p>\n<\/td>\n<td>\n<p>\u5e76\u884c\u8ba1\u7b97\u6570&#xff08;-1\u4f7f\u7528\u6240\u6709CPU&#xff09;\u3002<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>\u200b\u200b3. \u5c5e\u6027\u200b\u200b<\/h3>\n<table>\n<tr>\n<p>\u5c5e\u6027<\/p>\n<p>\u7c7b\u578b<\/p>\n<p>\u8bf4\u660e<\/p>\n<\/tr>\n<tbody>\n<tr>\n<td>\n<p>\u200b\u200bcore_sample_indices_\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>ndarray<\/p>\n<\/td>\n<td>\n<p>\u6838\u5fc3\u70b9\u7684\u7d22\u5f15\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200bcomponents_\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>ndarray<\/p>\n<\/td>\n<td>\n<p>\u6838\u5fc3\u70b9\u7684\u5750\u6807&#xff08;\u5f62\u72b6&#xff1a;[n_core_samples, n_features]&#xff09;\u3002<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p>\u200b\u200blabels_\u200b\u200b<\/p>\n<\/td>\n<td>\n<p>ndarray<\/p>\n<\/td>\n<td>\n<p>\u6bcf\u4e2a\u6837\u672c\u7684\u7c07\u6807\u7b7e&#xff08;-1\u8868\u793a\u566a\u58f0&#xff09;\u3002<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h3>\u200b\u200b4. \u65b9\u6cd5\u200b\u200b<\/h3>\n<h4>\u200b\u200b&#xff08;1&#xff09;fit(X)\u200b\u200b<\/h4>\n<ul>\n<li>\n<p>\u200b\u200b\u529f\u80fd\u200b\u200b&#xff1a;\u62df\u5408\u6a21\u578b\u5e76\u8fd4\u56de\u7c07\u6807\u7b7e\u3002<\/p>\n<\/li>\n<li>\n<p>\u200b\u200b\u53c2\u6570\u200b\u200b&#xff1a;<\/p>\n<ul>\n<li>\n<p>X&#xff1a;\u8f93\u5165\u6570\u636e&#xff0c;\u5f62\u72b6\u00a0[n_samples, n_features]\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<li>\n<p>\u200b\u200b\u8fd4\u56de\u200b\u200b&#xff1a;<\/p>\n<ul>\n<li>\n<p>self&#xff1a;\u62df\u5408\u540e\u7684\u6a21\u578b\u5b9e\u4f8b\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4>\u200b\u200b&#xff08;2&#xff09;fit_predict(X)\u200b\u200b<\/h4>\n<ul>\n<li>\n<p>\u200b\u200b\u529f\u80fd\u200b\u200b&#xff1a;\u62df\u5408\u6a21\u578b\u5e76\u76f4\u63a5\u8fd4\u56de\u7c07\u6807\u7b7e\u3002<\/p>\n<\/li>\n<li>\n<p>\u200b\u200b\u8fd4\u56de\u200b\u200b&#xff1a;<\/p>\n<ul>\n<li>\n<p>labels&#xff1a;\u5f62\u72b6\u00a0[n_samples]&#xff0c;\u7c07\u6807\u7b7e&#xff08;\u566a\u58f0\u70b9\u4e3a\u00a0-1&#xff09;\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>\u5b9e\u4f8b<\/p>\n<p>import pandas as pd<br \/>\nfrom sklearn.cluster import DBSCAN<br \/>\nfrom sklearn.preprocessing import StandardScaler<br \/>\nfrom sklearn.metrics import silhouette_score  # \u65e0\u76d1\u7763\u805a\u7c7b\u8bc4\u4f30\u6307\u6807<\/p>\n<p># \u6570\u636e\u52a0\u8f7d\u4e0e\u9884\u5904\u7406<br \/>\ndata &#061; pd.read_csv(&#039;datingTestSet2.txt&#039;,sep&#061;&#039;\\\\t&#039;)<br \/>\nx_scaled &#061; StandardScaler().fit_transform(data)  # \u6807\u51c6\u5316\u6570\u636e<br \/>\nepsd &#061;[0.3,0.5,0.6,0.7,0.8,0.9]<br \/>\nmin_samples &#061;[2,3,4,5,6,7]<br \/>\nbest &#061; []<br \/>\nscores&#061; 0<\/p>\n<p># DBSCAN\u805a\u7c7b&#xff08;\u8c03\u6574\u53c2\u6570&#xff09;<br \/>\nfor i in epsd:<br \/>\n    for j in min_samples:<br \/>\n        db &#061; DBSCAN(eps&#061;i, min_samples&#061;j)  # \u66f4\u5408\u7406\u7684\u9ed8\u8ba4\u53c2\u6570<br \/>\n        labels &#061; db.fit_predict(x_scaled)<br \/>\n        score &#061; silhouette_score(x_scaled, labels)<br \/>\n        if score &gt; scores:<br \/>\n            scores &#061; score<br \/>\n            best &#061; [i,j]<\/p>\n<p>print(best)<br \/>\ndb &#061; DBSCAN(eps&#061;best[0], min_samples&#061;best[1])<br \/>\nlabels &#061; db.fit_predict(x_scaled)<br \/>\n# \u8bc4\u4f30\u805a\u7c7b\u6548\u679c&#xff08;\u65e0\u76d1\u7763\u6307\u6807&#xff09;<br \/>\nprint(&#034;\u8f6e\u5ed3\u7cfb\u6570:&#034;, silhouette_score(x_scaled, labels))  # \u503c\u8d8a\u63a5\u8fd11\u8d8a\u597d<br \/>\nprint(&#034;\u566a\u58f0\u70b9\u6bd4\u4f8b:&#034;, sum(labels &#061;&#061; -1) \/ len(labels))  # \u566a\u58f0\u5360\u6bd4<br \/>\nprint(&#034;\u7c07\u6570\u91cf:&#034;, len(set(labels)) &#8211; (1 if -1 in labels else 0))<\/p>\n<p>import pandas as pd<br \/>\nimport numpy as np<br \/>\nfrom sklearn.cluster import DBSCAN<br \/>\nfrom sklearn.preprocessing import StandardScaler<br \/>\nfrom sklearn.metrics import silhouette_score<br \/>\nimport matplotlib.pyplot as plt<br \/>\nfrom sklearn.neighbors import NearestNeighbors<\/p>\n<p># \u6570\u636e\u52a0\u8f7d\u4e0e\u6807\u51c6\u5316<br \/>\ndata &#061; pd.read_csv(&#039;datingTestSet2.txt&#039;, sep&#061;&#039;\\\\t&#039;)<br \/>\nx_scaled &#061; StandardScaler().fit_transform(data)<\/p>\n<p># 1. \u901a\u8fc7k-\u8ddd\u79bb\u56fe\u786e\u5b9aeps\u8303\u56f4&#xff08;k&#061;min_samples\u7684\u5019\u9009\u503c&#xff09;<br \/>\ndef plot_k_distance(X, k&#061;4):<br \/>\n    neighbors &#061; NearestNeighbors(n_neighbors&#061;k).fit(X)<br \/>\n    distances, _ &#061; neighbors.kneighbors(X)<br \/>\n    k_distances &#061; np.sort(distances[:, -1])<br \/>\n    plt.plot(k_distances)<br \/>\n    plt.xlabel(&#039;Points sorted by distance&#039;)<br \/>\n    plt.ylabel(f&#039;{k}-th nearest neighbor distance&#039;)<br \/>\n    plt.title(&#039;k-Distance Graph for Eps Selection&#039;)<br \/>\n    plt.show()<\/p>\n<p>plot_k_distance(x_scaled, k&#061;4)  # \u89c2\u5bdf\u62d0\u70b9\u4f4d\u7f6e\u4f5c\u4e3aeps\u53c2\u8003\u503c<\/p>\n<p># 2. \u53c2\u6570\u8c03\u4f18&#xff08;\u57fa\u4e8ek-\u8ddd\u79bb\u56fe\u7ed3\u679c\u8c03\u6574\u8303\u56f4&#xff09;<br \/>\neps_candidates &#061; np.linspace(0.3, 1.0, 8)  # \u6839\u636e\u62d0\u70b9\u8c03\u6574\u8303\u56f4<br \/>\nmin_samples_candidates &#061; [3, 5, 7, 10]    # \u81f3\u5c11\u4e3a\u7ef4\u5ea6&#043;1<\/p>\n<p>best_score &#061; -1<br \/>\nbest_params &#061; {}<\/p>\n<p>for eps in eps_candidates:<br \/>\n    for min_samples in min_samples_candidates:<br \/>\n        db &#061; DBSCAN(eps&#061;eps, min_samples&#061;min_samples)<br \/>\n        labels &#061; db.fit_predict(x_scaled)<br \/>\n        if len(set(labels)) &gt; 1:  # \u81f3\u5c11\u4e24\u4e2a\u7c07\u624d\u80fd\u8ba1\u7b97\u8f6e\u5ed3\u7cfb\u6570<br \/>\n            score &#061; silhouette_score(x_scaled, labels)<br \/>\n            if score &gt; best_score:<br \/>\n                best_score &#061; score<br \/>\n                best_params &#061; {&#039;eps&#039;: eps, &#039;min_samples&#039;: min_samples}<\/p>\n<p># 3. \u4f7f\u7528\u6700\u4f73\u53c2\u6570\u805a\u7c7b<br \/>\ndb &#061; DBSCAN(**best_params)<br \/>\nlabels &#061; db.fit_predict(x_scaled)<\/p>\n<p># 4. \u8bc4\u4f30\u4e0e\u53ef\u89c6\u5316<br \/>\nprint(&#034;\u6700\u4f73\u53c2\u6570:&#034;, best_params)<br \/>\nprint(&#034;\u8f6e\u5ed3\u7cfb\u6570:&#034;, silhouette_score(x_scaled, labels))<br \/>\nprint(&#034;\u566a\u58f0\u70b9\u6bd4\u4f8b:&#034;, sum(labels &#061;&#061; -1) \/ len(labels))<br \/>\nprint(&#034;\u7c07\u6570\u91cf:&#034;, len(set(labels)) &#8211; (1 if -1 in labels else 0))<\/p>\n<p># \u53ef\u89c6\u5316\u805a\u7c7b\u7ed3\u679c&#xff08;\u5047\u8bbe\u6570\u636e\u4e3a\u4e8c\u7ef4&#xff09;<br \/>\nplt.scatter(x_scaled[:, 0], x_scaled[:, 1], c&#061;labels, cmap&#061;&#039;viridis&#039;, alpha&#061;0.6)<br \/>\nplt.title(&#039;DBSCAN Clustering Results&#039;)<br \/>\nplt.show()<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb197\u6b21\u3002DBSCAN\uff08Density-Based Spatial Clustering of Applications with Noise\uff09\u662f\u4e00\u79cd\u57fa\u4e8e\u5bc6\u5ea6\u7684\u7ecf\u5178\u805a\u7c7b\u7b97\u6cd5\uff0c\u7531 Martin Ester \u7b49\u4eba\u4e8e 1996 \u5e74\u63d0\u51fa\u3002\u8be5\u7b97\u6cd5\u901a\u8fc7\u5b9a\u4e49\u4e24\u4e2a\u5173\u952e\u53c2\u6570\uff08\u90bb\u57df\u534a\u5f84 eps \u548c\u6700\u5c0f\u6837\u672c\u6570 minPts\uff09\u6765\u8bc6\u522b\u9ad8\u5bc6\u5ea6\u533a\u57df\uff0c\u80fd\u591f\u6709\u6548\u53d1\u73b0\u4efb\u610f\u5f62\u72b6\u7684\u7c07\uff0c\u5e76\u81ea\u52a8\u5c06\u7a00\u758f\u533a\u57df\u7684\u70b9\u6807\u8bb0\u4e3a\u566a\u58f0\u70b9\uff08\u79bb\u7fa4\u70b9\uff09\u3002<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[50,207],"topic":[],"class_list":["post-54073","post","type-post","status-publish","format-standard","hentry","category-server","tag-50","tag-207"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/54073.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb197\u6b21\u3002DBSCAN\uff08Density-Based Spatial Clustering of Applications with Noise\uff09\u662f\u4e00\u79cd\u57fa\u4e8e\u5bc6\u5ea6\u7684\u7ecf\u5178\u805a\u7c7b\u7b97\u6cd5\uff0c\u7531 Martin Ester \u7b49\u4eba\u4e8e 1996 \u5e74\u63d0\u51fa\u3002\u8be5\u7b97\u6cd5\u901a\u8fc7\u5b9a\u4e49\u4e24\u4e2a\u5173\u952e\u53c2\u6570\uff08\u90bb\u57df\u534a\u5f84 eps \u548c\u6700\u5c0f\u6837\u672c\u6570 minPts\uff09\u6765\u8bc6\u522b\u9ad8\u5bc6\u5ea6\u533a\u57df\uff0c\u80fd\u591f\u6709\u6548\u53d1\u73b0\u4efb\u610f\u5f62\u72b6\u7684\u7c07\uff0c\u5e76\u81ea\u52a8\u5c06\u7a00\u758f\u533a\u57df\u7684\u70b9\u6807\u8bb0\u4e3a\u566a\u58f0\u70b9\uff08\u79bb\u7fa4\u70b9\uff09\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/54073.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2025-08-12T13:49:56+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/54073.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/54073.html\",\"name\":\"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2025-08-12T13:49:56+00:00\",\"dateModified\":\"2025-08-12T13:49:56+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/54073.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/54073.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/54073.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/54073.html","og_locale":"zh_CN","og_type":"article","og_title":"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb197\u6b21\u3002DBSCAN\uff08Density-Based Spatial Clustering of Applications with Noise\uff09\u662f\u4e00\u79cd\u57fa\u4e8e\u5bc6\u5ea6\u7684\u7ecf\u5178\u805a\u7c7b\u7b97\u6cd5\uff0c\u7531 Martin Ester \u7b49\u4eba\u4e8e 1996 \u5e74\u63d0\u51fa\u3002\u8be5\u7b97\u6cd5\u901a\u8fc7\u5b9a\u4e49\u4e24\u4e2a\u5173\u952e\u53c2\u6570\uff08\u90bb\u57df\u534a\u5f84 eps \u548c\u6700\u5c0f\u6837\u672c\u6570 minPts\uff09\u6765\u8bc6\u522b\u9ad8\u5bc6\u5ea6\u533a\u57df\uff0c\u80fd\u591f\u6709\u6548\u53d1\u73b0\u4efb\u610f\u5f62\u72b6\u7684\u7c07\uff0c\u5e76\u81ea\u52a8\u5c06\u7a00\u758f\u533a\u57df\u7684\u70b9\u6807\u8bb0\u4e3a\u566a\u58f0\u70b9\uff08\u79bb\u7fa4\u70b9\uff09\u3002","og_url":"https:\/\/www.wsisp.com\/helps\/54073.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2025-08-12T13:49:56+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/54073.html","url":"https:\/\/www.wsisp.com\/helps\/54073.html","name":"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2025-08-12T13:49:56+00:00","dateModified":"2025-08-12T13:49:56+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/54073.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/54073.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/54073.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u673a\u5668\u5b66\u4e60\u2014\u2014DBSCAN"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/54073","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=54073"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/54073\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=54073"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=54073"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=54073"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=54073"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}