{"id":2520,"date":"2019-10-20T17:00:00","date_gmt":"2019-10-20T08:00:00","guid":{"rendered":"https:\/\/analysis-navi.com\/?p=2520"},"modified":"2025-06-12T18:45:14","modified_gmt":"2025-06-12T09:45:14","slug":"python%e3%81%ab%e3%82%88%e3%82%8bsvm%e3%82%b5%e3%83%9d%e3%83%bc%e3%83%88%e3%83%99%e3%82%af%e3%82%bf%e3%83%bc%e3%83%9e%e3%82%b7%e3%83%b3%e3%81%ae%e5%ae%9f%e8%a1%8c","status":"publish","type":"post","link":"https:\/\/analysis-navi.com\/?p=2520","title":{"rendered":"Python\u306b\u3088\u308bSVM(\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3)\u306e\u5b9f\u884c"},"content":{"rendered":"\n

Python\u3067\u6a5f\u68b0\u5b66\u7fd2\u306e\u3072\u3068\u3064SVM(\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3)<\/strong>\u3092\u5b9f\u884c\u3057\u3066\u307f\u307e\u3059\u3002
1963\u5e74\u306b\u57fa\u790e\u7406\u8ad6\u304c\u767a\u8868\u3055\u308c\u3066\u304b\u3089\u672a\u3060\u306b\u4f7f\u7528\u3055\u308c\u308b\u4e8b\u306e\u591a\u3044\u3001\u6a5f\u68b0\u5b66\u7fd2\u306e\u4ee3\u8868\u7684\u624b\u6cd5\u3067\u3059\u3002<\/p>\n\n\n\n

\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3\u3068\u306f<\/h2>\n\n\n\n

\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3001\u5ea7\u6a19\u5e73\u9762\u4e0a\u306b2\u7a2e\u985e\u306e\u30c7\u30fc\u30bf\u304c\u3042\u308b\u3068\u3057\u307e\u3059\u3002
\"\"<\/p>\n\n\n\n

\u3053\u308c\u3092\u76f4\u7dda\u3067\u3046\u307e\u3044\u5177\u5408\u306b\u5206\u5272\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002
\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u8272\u3005\u3068\u5b9f\u9a13\u3057\u3066\u307f\u307e\u3059\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n\n\n\n\n

\u771f\u3093\u4e2d\u306e\u56f3\u30822\u5206\u5272\u51fa\u6765\u3066\u3044\u307e\u3059\u304c\u3001\u7dda\u3068\u70b9\u304c\u30ae\u30ea\u30ae\u30ea\u3067\u3059\u3002
\u5de6\u306e\u56f3\u306f\u3001\u70b9\u3068\u7dda\u306e\u8ddd\u96e2\u306b\u4f59\u88d5\u304c\u3042\u308a\u3001\u771f\u3093\u4e2d\u306e\u56f3\u3088\u308a\u3082\u826f\u3044\u5206\u3051\u65b9\u306b\u898b\u3048\u307e\u3059\u3002<\/p>\n\n\n\n

\u3053\u306e\u3088\u3046\u306b\u3001\u3046\u307e\u304f\u30c7\u30fc\u30bf\u3092\u5206\u5272\u3059\u308b\u7dda\u306f\u3069\u3053\u304b\u3092\u8a08\u7b97\u3057\u3066\u304f\u308c\u308b\u6a5f\u68b0\u5b66\u7fd2\u624b\u6cd5\u304c\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3<\/span><\/strong>\u3067\u3059\u3002<\/p>\n\n\n\n

\u3053\u306e\u3088\u3046\u306b\u7dda\u3092\u5f15\u304f\u3053\u3068\u304c\u3067\u304d\u308c\u3070\u300c\u7dda\u3067\u5206\u3051\u305f\u3053\u3063\u3061\u5074\u304b\u3001\u3042\u3063\u3061\u5074\u304b\u300d<\/strong>\u3092\u898b\u308b\u3060\u3051\u3067\u672a\u77e5\u306e\u30c7\u30fc\u30bf\u304c\u30aa\u30ec\u30f3\u30b8\u8272\u306e\u30b0\u30eb\u30fc\u30d7\u306b\u5c5e\u3059\u308b\u304b\u9752\u8272\u306e\u30b0\u30eb\u30fc\u30d7\u306b\u5c5e\u3059\u308b\u304b\u3092\u63a8\u6e2c\u3059\u308b\u4e8b\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n

\u4e0a\u8a18\u306f\u300c2\u6b21\u5143\u5e73\u9762\u4e0a\u306b\u304a\u3044\u3066\u3001\u76f4\u7dda\u3092\u7528\u3044\u3066\u9818\u57df\u30922\u3064\u306b\u5206\u3051\u308b\u300d\u8a71\u3067\u3057\u305f\u304c\u3001\u3053\u308c\u3092\u62e1\u5f35\u3057\u3066\u300cn\u6b21\u5143\u306b\u304a\u3044\u3066\u3001\u66f2\u7dda\uff08\u66f2\u9762\uff09\u3092\u7528\u3044\u3066\u9818\u57df\u3092n\u500b\u306b\u5206\u3051\u308b\u300d\u3068\u3044\u3046\u554f\u984c\u3092\u89e3\u304f\u4e8b\u3082\u3067\u304d\u307e\u3059\u3002<\/span><\/strong><\/p>\n\n\n\n

\u3053\u306e\u3088\u3046\u306b\u3001SVM\u306f\u69d8\u3005\u306a\u5206\u985e\u554f\u984c\u3092\u89e3\u304f\u305f\u3081\u306e\u6a5f\u68b0\u5b66\u7fd2\u624b\u6cd5\u3068\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n

Python\u306b\u3088\u308b\u5b9f\u884c<\/h2>\n\n\n\n

python\u306esklearn\u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u7528\u3044\u308c\u3070\u3001\u6b21\u5143\u6570\u3084\u30af\u30e9\u30b9\u6570\u306a\u3069\u306f\u6df1\u304f\u6c17\u306b\u305b\u305a\u306bSVM\u3092\u5b9f\u884c\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002
\u65e9\u901f\u3084\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n\n

\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u8fbc\u307f<\/h3>\n\n\n\n

\u4eca\u56de\u306f\u3001scikit-learn\u306b\u30b5\u30f3\u30d7\u30eb\u30c7\u30fc\u30bf\u3068\u3057\u3066\u7528\u610f\u3055\u308c\u3066\u3044\u308b\u4e73\u304c\u3093\u60a3\u8005\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u7528\u3044\u3066\u307f\u307e\u3059\u3002
\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u8aad\u307f\u8fbc\u307f\u307e\u3059\u3002<\/p>\n\n\n\n

#\u30c7\u30fc\u30bf\u306e\u8aad\u307f\u8fbc\u307f\nfrom sklearn.datasets import load_breast_cancer\ndataset = load_breast_cancer()\nX, y = dataset.data, dataset.target<\/pre>\n\n\n\n
\u8aad\u307f\u8fbc\u3093\u3060\u5f8c\u306b\u3001\u8aac\u660e\u5909\u6570\u3067\u3042\u308b\u300cX\u300d\u3068\u76ee\u7684\u5909\u6570\u3067\u3042\u308b\u300cy\u300d\u3092\u305d\u308c\u305e\u308c\u53d6\u5f97\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
SVM\u306e\u5b9f\u884c<\/h3>\n\n\n\n
SVM\u306e\u6027\u80fd\u3092\u78ba\u8a8d\u3059\u308b\u305f\u3081\u3001\u300c\u5b66\u7fd2\u30c7\u30fc\u30bf\u300d\u3068\u300c\u8a55\u4fa1\u30c7\u30fc\u30bf\u300d\u306b\u5206\u5272\u3057\u307e\u3059\u3002
\u300c\u5b66\u7fd2\u30c7\u30fc\u30bf\u300d\u3067\u5ea7\u6a19\u4e0a\u306b\u826f\u3044\u611f\u3058\u306e\u7dda\u3092\u5f15\u304d\u3001\u300c\u8a55\u4fa1\u30c7\u30fc\u30bf\u300d\u3067\u305d\u306e\u7dda\u304c\u3069\u308c\u307b\u3069\u6b63\u3057\u3044\u306e\u304b\u3092\u78ba\u304b\u3081\u307e\u3059\u3002
\u4eba\u70ba\u7684\u306b\u5206\u5272\u3057\u3066\u3082\u826f\u3044\u306e\u3067\u3059\u304c\u3001sklearn\u306b\u306f\u300ctrain_test_split\u300d<\/strong>\u3068\u3044\u3046\u5927\u5909\u4fbf\u5229\u306a\u30d1\u30c3\u30b1\u30fc\u30b8\u304c\u3042\u308b\u306e\u3067\u3001\u305d\u308c\u3092\u4f7f\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
# \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5b66\u7fd2\u7528\u3068\u691c\u8a3c\u7528\u306b\u5206\u5272\u3059\u308b\nfrom sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=True, random_state=0, stratify=y)<\/pre>\n\n\n\n
\u300ctest_size\u300d<\/strong>\u306f\u300c\u8a55\u4fa1\u30c7\u30fc\u30bf\u300d\u306e\u6bd4\u7387\u3067\u3059\u3002\u4eca\u56de\u306f0.2\u3092\u6307\u5b9a\u3057\u305f\u306e\u3067\u3001\u5168\u30c7\u30fc\u30bf\u306e2\u5272\u304c\u300c\u8a55\u4fa1\u30c7\u30fc\u30bf\u300d\u306b\u632f\u308a\u5206\u3051\u3089\u308c\u307e\u3059\u3002
\u300cshuffle\u300d<\/strong>\u306f\u30c7\u30fc\u30bf\u306e\u9806\u756a\u3092\u30e9\u30f3\u30c0\u30e0\u306b\u3059\u308b\u30aa\u30d7\u30b7\u30e7\u30f3\u3067\u3059\u3002\u4eca\u56de\u3067\u8a00\u3048\u3070\u3001\u300c2\u5272\u300d\u3092\u4e0a\u304b\u3089\u9806\u756a\u306b\u53d6\u308b\u306e\u3067\u306f\u306a\u304f\u3001\u30e9\u30f3\u30c0\u30e0\u306b\u30d4\u30c3\u30af\u30a2\u30c3\u30d7\u3057\u307e\u3059\u3002\u30c7\u30fc\u30bf\u304c\u56fa\u307e\u3063\u3066\u3044\u308b\u3068\u5206\u5272\u3057\u305f2\u30c7\u30fc\u30bf\u306e\u50be\u5411\u304c\u7570\u306a\u3063\u3066\u3057\u307e\u3046\u53ef\u80fd\u6027\u3082\u3042\u308b\u306e\u3067\u3001\u57fa\u672c\u7684\u306b\u6307\u5b9a\u3057\u305f\u307b\u3046\u304c\u826f\u3044\u304b\u3068\u601d\u3044\u307e\u3059\u3002
\u300crandom_state\u300d<\/strong>\u306f\u4e71\u6570\u30b7\u30fc\u30c9\u306e\u6307\u5b9a\u3067\u3001\u6570\u5024\u3092\u6307\u5b9a\u3059\u308c\u3070\u6bce\u56de\u56fa\u5b9a\u306e\u4e71\u6570\u304c\u4f7f\u308f\u308c\u3001\u3057\u306a\u3051\u308c\u3070\u6bce\u56de\u4e71\u6570\u3092\u767a\u751f\u3055\u305b\u3066\u5b9f\u884c\u306e\u305f\u3073\u306b\u9055\u3046\u7d50\u679c\u304c\u5f97\u3089\u308c\u307e\u3059\u3002
\u300cstratify\u300d<\/strong>\u306f\u5b66\u7fd2\u30c7\u30fc\u30bf\u3068\u8a55\u4fa1\u30c7\u30fc\u30bf\u306by\u304c\u5747\u7b49\u306b\u632f\u308a\u5206\u3051\u3089\u308c\u308b\u3088\u3046\u306b\u3059\u308b\u30aa\u30d7\u30b7\u30e7\u30f3\u3067\u3059\u3002\u5b66\u7fd2\u30c7\u30fc\u30bf\u306b\u300c\u60aa\u6027\u300d\u3070\u304b\u308a\u56fa\u307e\u3063\u305f\u308a\u3059\u308b\u4e8b\u304c\u7121\u304f\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
\u3067\u306f\u3001\u3053\u306e\u5b66\u7fd2\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066SVM\u3092\u5b9f\u884c\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002
\u305d\u308c\u306b\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
# \u5b66\u7fd2\nfrom sklearn.svm import SVC\nsvc = SVC(kernel='linear', random_state=0)\nsvc.fit(X_train, y_train)<\/pre>\n\n\n\n
\u300ckernel\u300d<\/strong>\u306b\u306f\u5206\u5272\u306b\u4f7f\u3046\u7dda\u3092\u6307\u5b9a\u3057\u307e\u3059\u304c\u3001\u4eca\u56de\u306f\u30b7\u30f3\u30d7\u30eb\u306b\u76f4\u7dda(\u5e73\u9762)\u3067\u5206\u5272\u3057\u3066\u307f\u307e\u3059\u306e\u3067\u300clinear\u300d<\/strong>\u3092\u6307\u5b9a\u3057\u3066\u3044\u307e\u3059\u3002
\u3061\u306a\u307f\u306b\u3001\u4f55\u3082\u6307\u5b9a\u3057\u306a\u3044\u3068\u3001\u300cRBF\u30ab\u30fc\u30cd\u30eb\u300d\u3068\u3044\u3046\u65b9\u6cd5\u3067\u5206\u985e\u304c\u884c\u308f\u308c\u307e\u3059\u3002<\/p>\n\n\n\n
\u6027\u80fd\u8a55\u4fa1<\/h3>\n\n\n\n
\u300c\u5b66\u7fd2\u30c7\u30fc\u30bf\u300d\u300c\u8a55\u4fa1\u30c7\u30fc\u30bf\u300d\u305d\u308c\u305e\u308c\u306b\u3064\u3044\u3066\u3001\u3069\u308c\u307b\u3069\u306e\u5224\u5225\u7cbe\u5ea6\u304c\u51fa\u3066\u3044\u308b\u304b\u898b\u3066\u307f\u307e\u3059\u3002<\/p>\n\n\n\n
# \u8a55\u4fa1\nfrom sklearn.metrics import accuracy_score\n\ny_train_pred = svc.predict(X_train)\ntrain_acc = accuracy_score(y_train, y_train_pred)\nprint('train score :',train_acc)\n\ny_test_pred = svc.predict(X_test)\ntest_acc = accuracy_score(y_test, y_test_pred)\nprint('test score :',test_acc)<\/pre>\n\n\n\n
\u7d50\u679c\u3092\u898b\u3066\u307f\u308b\u3068\u3002\u3002\u3002<\/p>\n\n\n\n
train score : 0.9692307692307692\ntest score : 0.956140350877193<\/pre>\n\n\n\n
\u5b66\u7fd2\u30c7\u30fc\u30bf\u3067\u306f\u7d0496.9%\u306e\u6b63\u89e3\u7387\u3001\u8a55\u4fa1\u30c7\u30fc\u30bf\u3067\u306f\u7d0495.6%\u306e\u6b63\u89e3\u7387<\/span><\/strong>\u3067\u3001\u975e\u5e38\u306b\u826f\u3044\u5206\u985e\u7cbe\u5ea6\u304c\u51fa\u3066\u3044\u308b\u3088\u3046\u3067\u3059\u3002<\/p>\n\n\n\n
\u7d50\u679c\u306e\u56f3\u793a<\/h3>\n\n\n\n
\u7d50\u679c\u3092\u56f3\u306b\u3057\u3066\u307f\u307e\u3059\u3002
\u65b9\u6cd5\u306f\u8272\u3005\u3068\u3042\u308a\u307e\u3059\u304c\u3001\u4e3b\u6210\u5206\u5206\u6790<\/a>\u306b\u3088\u308a\u6b21\u5143\u6570\u30922\u306b\u843d\u3068\u3057\u3001\u826f\u6027\u304b\u60aa\u6027\u304b\u3092\u8272\u5206\u3051\u3057\u3066\u8868\u793a\u3057\u3066\u307f\u307e\u3059\u3002<\/p>\n\n\n\n
from sklearn.decomposition import PCA\nimport matplotlib.pyplot as plt\npca = PCA(n_components=2)\n\nvecs_train = pca.fit_transform(X_train)\nplt.scatter(vecs_train[:,0], vecs_train[:,1],s=4, c=y_train, cmap='jet')\nplt.show()\n\nvecs_test = pca.fit_transform(X_test)\nplt.scatter(vecs_test[:,0], vecs_test[:,1],s=4, c=y_test, cmap='jet')\nplt.show()<\/pre>\n\n\n\n
\"\"<\/figure>\n\n\n\n\n\n\n\n
\u5b66\u7fd2\u30c7\u30fc\u30bf(\u4e0a\u56f3)\u3082\u8a55\u4fa1\u30c7\u30fc\u30bf(\u4e0b\u56f3)\u3082\u3001\u9752\u8272(\u826f\u6027)\u3068\u8d64\u8272(\u60aa\u6027)\u306e\u4f4d\u7f6e\u305d\u3053\u305d\u3053\u56fa\u307e\u3063\u3066\u304a\u308a\u3001\u3084\u306f\u308a\u826f\u3044\u5206\u985e\u304c\u51fa\u6765\u3066\u3044\u305d\u3046\u3067\u3059\u3002<\/p>\n\n\n\n
\u3061\u306a\u307f\u306b\u3001\u65b0\u898f\u306e\u30c7\u30fc\u30bf\u306b\u5bfe\u3057\u3066\u3001\u4e73\u304c\u3093\u304b\u3069\u3046\u304b\u4e88\u6e2c\u3059\u308b\u306b\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306bpredict\u30e1\u30bd\u30c3\u30c9\u306b\u8aac\u660e\u5909\u6570\u3092\u30ea\u30b9\u30c8\u3067\u4e0e\u3048\u308c\u3070OK\u3067\u3059\u3002<\/p>\n\n\n\n
#\u4e88\u6e2c\u3057\u305f\u3044\u3068\u304d\npred = svc.predict([[1.0,2.0,9.0,5.0,1.0,1.0,1.0,6.0,2.0,7.0,4.0,1.0,2.0,3.0,9.0,\n                     3.0,3.0,1.0,2.0,6.0,1.0,3.0,1.0,7.0,1.0,3.0,3.0,1.0,3.0,1.0]])\nprint(pred)<\/pre>\n\n\n\n
[1]<\/pre>\n\n\n\n
\u300c\u30af\u30e9\u30b91\u300d\u3001\u3064\u307e\u308a\u826f\u6027\u3067\u3042\u308b\u3068\u63a8\u5b9a\u3055\u308c\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
\u7d42\u308f\u308a\u306b<\/h2>\n\n\n\n
\u4ee5\u4e0a\u304cPython\u306b\u304a\u3051\u308bSVM(\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3)\u306e\u5b9f\u884c\u65b9\u6cd5\u3067\u3057\u305f\u3002
\u975e\u5e38\u306b\u5b9f\u884c\u3082\u7c21\u5358\u3067\u6027\u80fd\u304c\u51fa\u308b\u3053\u3068\u306e\u591a\u3044\u6a5f\u68b0\u5b66\u7fd2\u624b\u6cd5\u3067\u3059\u306e\u3067\u3001\u5206\u985e\u30bf\u30b9\u30af\u3092\u89e3\u304f\u969b\u306b\u306f\u6d3b\u7528\u3092\u691c\u8a0e\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
Python\u3067\u6a5f\u68b0\u5b66\u7fd2\u306e\u3072\u3068\u3064SVM(\u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3)\u3092\u5b9f\u884c\u3057\u3066\u307f\u307e\u3059\u30021963\u5e74\u306b\u57fa\u790e\u7406\u8ad6\u304c\u767a\u8868\u3055\u308c\u3066\u304b\u3089\u672a\u3060\u306b\u4f7f\u7528\u3055\u308c\u308b\u4e8b\u306e\u591a\u3044\u3001\u6a5f\u68b0\u5b66\u7fd2\u306e\u4ee3\u8868\u7684\u624b\u6cd5\u3067\u3059\u3002 \u30b5\u30dd\u30fc\u30c8\u30d9\u30af\u30bf\u30fc\u30de\u30b7\u30f3\u3068\u306f \u4ee5\u4e0b\u306e\u3088\u3046\u306b\u3001\u5ea7\u6a19\u5e73\u9762 […]<\/p>\n","protected":false},"author":1,"featured_media":5033,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"swell_btn_cv_data":"","vkexunit_cta_each_option":"","footnotes":""},"categories":[129],"tags":[101,134],"class_list":["post-2520","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-study","tag-ml","tag-python"],"_links":{"self":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/2520","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2520"}],"version-history":[{"count":15,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/2520\/revisions"}],"predecessor-version":[{"id":5149,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/posts\/2520\/revisions\/5149"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=\/wp\/v2\/media\/5033"}],"wp:attachment":[{"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2520"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2520"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/analysis-navi.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2520"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}