{"id":4681,"date":"2024-03-04T09:17:35","date_gmt":"2024-03-04T00:17:35","guid":{"rendered":"https:\/\/blog.since2020.jp\/?p=4681"},"modified":"2024-03-04T09:17:35","modified_gmt":"2024-03-04T00:17:35","slug":"labelencoder_vs_ordinalencoder","status":"publish","type":"post","link":"https:\/\/since2020.jp\/media\/labelencoder_vs_ordinalencoder\/","title":{"rendered":"Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306e\u9055\u3044\u306f\uff1f\u6709\u52b9\u306a\u6d3b\u7528\u5834\u9762\u3067\u6839\u62e0\u3092\u6301\u3063\u3066\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3057\u3088\u3046"},"content":{"rendered":"\n

\u3053\u3053\u3067\u306fLabel\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306e\u57fa\u672c\u7684\u306a\u9055\u3044\u3068\u3001\u305d\u308c\u305e\u308c\u304c\u3069\u306e\u3088\u3046\u306a\u30c7\u30fc\u30bf\u51e6\u7406\u5834\u9762\u3067\u6709\u52b9\u306b\u6d3b\u7528\u3067\u304d\u308b\u306e\u304b\u3092\u8a73\u3057\u304f\u89e3\u8aac\u3057\u307e\u3059\u3002\u307e\u305f\u3001LightGBM\u306eCategoryFuture\u3092\u4f7f\u7528\u3059\u308b\u5834\u5408\u306b\u3064\u3044\u3066\u3082\u5c11\u3057\u89e6\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n

\u306f\u3058\u3081\u306b<\/h2>\n

LightGBM\u3067\u30e2\u30c7\u30eb\u3092\u5b9f\u88c5\u3057\u305f\u969b\u306b\u30ab\u30c6\u30b4\u30ea\u5909\u6570\u3092One-Hot\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3059\u308b\u3064\u3082\u308a\u306f\u306a\u304f\u3001Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3059\u308b\u3079\u304d\u304bOrdinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3059\u308b\u3079\u304d\u304b\u8ff7\u3063\u305f\u306e\u3067\u3001\u3053\u3053\u3067\u306fLabel\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306e\u57fa\u672c\u7684\u306a\u9055\u3044\u3068\u3001\u305d\u308c\u305e\u308c\u304c\u3069\u306e\u3088\u3046\u306a\u30c7\u30fc\u30bf\u51e6\u7406\u5834\u9762\u3067\u6709\u52b9\u306b\u6d3b\u7528\u3067\u304d\u308b\u306e\u304b\u3092\u8a73\u3057\u304f\u89e3\u8aac\u3057\u307e\u3059\u3002<\/p>\n\n

Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068\u306f\u4f55\u304b\uff1f<\/h2>\n

Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30c7\u30fc\u30bf\u306e\u5404\u30ab\u30c6\u30b4\u30ea\u306b\u4e00\u610f\u306e\u6574\u6570\u3092\u5272\u308a\u5f53\u3066\u308b\u624b\u6cd5\u3067\u3059\u3002\u4e3b\u306b\u540d\u7fa9\u5c3a\u5ea6\u306e\u5909\u6570\u306b\u9069\u7528\u3055\u308c\u307e\u3059\u3002<\/p>\r\n

\u4f8b\u3048\u3070\u3001\u8272\u306e\u30ab\u30c6\u30b4\u30ea\u300c\u8d64\u300d\u300c\u9752\u300d\u300c\u7dd1\u300d\u304c\u3042\u3063\u305f\u5834\u5408\u3001\u3053\u308c\u3089\u306b\u305d\u308c\u305e\u308c\u300c0\u300d\u300c1\u300d\u300c2\u300d\u3068\u3044\u3046\u30e9\u30d9\u30eb\u3092\u5272\u308a\u5f53\u3066\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\r\n

\u3053\u306e\u65b9\u6cd5\u306e\u4e3b\u306a\u7279\u5fb4\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u9593\u306e\u9806\u5e8f\u3084\u5927\u5c0f\u95a2\u4fc2\u3092\u8003\u616e\u3057\u306a\u3044\u70b9\u306b\u3042\u308a\u307e\u3059\u3002<\/p>\r\n

<\/p>\r\n

\u5b9f\u969b\u306b\u3084\u3063\u3066\u307f\u308b<\/strong><\/p>\r\n

\r\n
from sklearn.preprocessing import LabelBinarizer\r\nfrom sklearn import preprocessing\r\nimport pandas as pd\r\nimport numpy as np\r\n\r\n# \u30c7\u30fc\u30bf\u306e\u7528\u610f\r\ndf = pd.DataFrame(\r\ndata={'\u6027\u5225': np.array(['male', 'female', 'male', 'female', 'male']),\r\n'\u8840\u6db2\u578b': np.array(['A', 'B', 'O', 'AB', 'O'])})\r\n\r\n# \u30e9\u30d9\u30eb\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0(LabelEncoder)\r\nfrom sklearn.preprocessing import LabelEncoder\r\n\r\nle = LabelEncoder()\r\nencoded = le.fit_transform(df['\u8840\u6db2\u578b'].values)\r\ndf['re_\u8840\u6db2\u578b'] = encoded<\/code><\/pre>\r\n
\"\"
\r\n\u7d50\u679c\u300cA\u21920\u300d\u300cB\u21922\u300d\u300cO\u21923\u300d\u300cAB\u21921\u300d\u306b\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\r\n
\u3053\u3053\u3067\u3084\u3084\u3053\u3057\u3044\u306e\u304c\u3001\u8907\u6570\u884c\u306b\u5bfe\u3057\u3066\u4e00\u62ec\u30e9\u30d9\u30eb\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3059\u308b\u3068\u304d\u306fOrdinal Encoder\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002<\/p>\r\n
\r\n
# \u30e9\u30d9\u30eb\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\uff08OrdinalEncoder\uff09\r\nfrom sklearn.preprocessing import OrdinalEncoder\r\n\r\noe = preprocessing.OrdinalEncoder()\r\nencoded = oe.fit_transform(df[['\u6027\u5225', '\u8840\u6db2\u578b']].values)\r\nencoded = pd.DataFrame(encoded, columns=['encode\u6027\u5225', 'encode\u8840\u6db2\u578b'])\r\n\r\ndf = pd.concat([df, encoded], axis=1)\r\ndf<\/code><\/pre>\r\n
\"\"<\/p>\r\n
\u7d50\u679c\u300cmale\u21921\u300d\u300cfemale\u21920\u300d\u306b\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\r\n<\/div>\r\n
<\/p>\r\n<\/div>\n\n
Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068\u306f\u4f55\u304b\uff1f<\/h2>\n
\u4e00\u65b9\u3001Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u306b\u9806\u5e8f\u95a2\u4fc2\u304c\u5b58\u5728\u3059\u308b\u5834\u5408\u306b\u9069\u7528\u3055\u308c\u308b\u624b\u6cd5\u3067\u3059\u3002\u305f\u3068\u3048\u3070\u3001\u300c\u5c0f\u300d\u300c\u4e2d\u300d\u300c\u5927\u300d\u3068\u3044\u3046\u30b5\u30a4\u30ba\u30ab\u30c6\u30b4\u30ea\u306b\u5bfe\u3057\u3066\u3001Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3092\u7528\u3044\u308b\u3068\u300c0\u300d\u300c1\u300d\u300c2\u300d\u306e\u3088\u3046\u306b\u3001\u81ea\u7136\u306a\u9806\u5e8f\u3092\u53cd\u6620\u3057\u305f\u6570\u5024\u3092\u5272\u308a\u5f53\u3066\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\r\n
\u3053\u306e\u624b\u6cd5\u3067\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u9593\u306e\u9806\u5e8f\u304c\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306b\u3088\u3063\u3066\u4fdd\u6301\u3055\u308c\u308b\u305f\u3081\u3001\u30e2\u30c7\u30eb\u304c\u3053\u306e\u60c5\u5831\u3092\u5b66\u7fd2\u306b\u6d3b\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\r\n
\u5b9f\u969b\u306b\u3084\u3063\u3066\u307f\u308b<\/strong><\/p>\r\n
\r\n
# \u30c7\u30fc\u30bf\u306e\u7528\u610f\r\ndf = pd.DataFrame(\r\ndata={\r\n'\u30e6\u30fc\u30b6\u30fc': np.array(['A', 'B', 'C', 'D', 'E']),\r\n'\u8a55\u4fa1': np.array(['\u975e\u5e38\u306b\u60aa\u3044','\u60aa\u3044', '\u666e\u901a', '\u826f\u3044', '\u975e\u5e38\u306b\u826f\u3044', np.nan])\r\n})\r\ndf<\/code><\/pre>\r\n
\"\"<\/p>\r\n
\r\n
from sklearn.preprocessing import OrdinalEncoder\r\n\r\n# \u30ab\u30c6\u30b4\u30ea\u30fc\u306e\u9806\u5e8f\u3092\u6c7a\u3081\u308b(\u5de6\u304b\u30890, 1...\u3068\u306a\u308b)\r\ncategories = [['\u975e\u5e38\u306b\u60aa\u3044','\u60aa\u3044','\u666e\u901a', '\u826f\u3044', '\u975e\u5e38\u306b\u826f\u3044']]\r\n\r\n# \u30aa\u30fc\u30c7\u30a3\u30ca\u30eb\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\uff08OrdinalEncoder\uff09\r\noe = OrdinalEncoder(categories=categories, handle_unknown='use_encoded_value', unknown_value=5)\r\ndf['encode\u8a55\u4fa1'] = oe.fit_transform(df[['\u8a55\u4fa1']])\r\n\r\ndf<\/code><\/pre>\r\n
\"\"<\/p>\r\n
\u8a55\u4fa1\u306f\u60aa\u3044\u304b\u3089\u826f\u3044\u3078\u306e\u7bc4\u56f2\u30670\u304b\u3089\u30a8\u30f3\u30b3\u30fc\u30c9\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3055\u3089\u306b\u3001handle_unknown<\/span>\u3067\u30ab\u30c6\u30b4\u30ea\u30fc\u306b\u306a\u3044\u30c7\u30fc\u30bf\u306e\u51e6\u7406\u65b9\u6cd5\u3092\u6307\u5b9a\u3059\u308b\u3053\u3068\u3082\u53ef\u80fd\u3067\u3059\u3002\u3053\u306e\u4f8b\u3067\u306f\u30015\u3064\u306e\u8a55\u4fa1\u4ee5\u5916\u306e\u30c7\u30fc\u30bf\u304c\u3042\u308b\u5834\u5408\u30015\u3092\u8fd4\u3059\u3088\u3046\u6307\u5b9a\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\r\n<\/div>\r\n<\/div>\r\n
<\/p>\n\n
\u4e3b\u306a\u9055\u3044<\/h2>\n
Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306e\u4e3b\u306a\u9055\u3044\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u9593\u306e\u300c\u9806\u5e8f\u300d\u3092\u8003\u616e\u3059\u308b\u304b\u3069\u3046\u304b\u306b\u3042\u308a\u307e\u3059\u3002Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u9806\u5e8f\u3092\u8003\u616e\u3057\u307e\u305b\u3093\u304c\u3001Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u30ab\u30c6\u30b4\u30ea\u9593\u306e\u81ea\u7136\u306a\u9806\u5e8f\u3092\u6570\u5024\u306b\u53cd\u6620\u3055\u305b\u307e\u3059\u3002\u3053\u306e\u305f\u3081\u3001Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u9806\u5e8f\u304c\u610f\u5473\u3092\u6301\u3064\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30c7\u30fc\u30bf\u306b\u5bfe\u3057\u3066\u7279\u306b\u6709\u52b9\u3067\u3059\u3002<\/p>\n\n
LightGBM\u306eCategory Future\u3092\u4f7f\u7528\u3059\u308b\u3068\u304d<\/h2>\n
\u6c7a\u5b9a\u6728\u30d9\u30fc\u30b9\u306eLightGBM\u306eCategory Future\u3067\u9806\u5e8f\u3092\u53cd\u6620\u3055\u305b\u305f\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3057\u305f\u30ab\u30e9\u30e0\u3092\u6307\u5b9a\u3059\u308b\u3068\u610f\u5473\u306e\u306a\u3044\u3082\u306e\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\r\n
Light GBM\u306eCategory Future\u306f\u3001\u6570\u5024\u3068\u3057\u3066\u306e\u5927\u5c0f\u95a2\u4fc2\u3092\u76f4\u63a5\u5229\u7528\u3059\u308b\u306e\u3067\u306f\u306a\u304f\u3001\u30ab\u30c6\u30b4\u30ea\u9593\u306e\u5206\u5272\u3092\u6700\u9069\u5316\u3059\u308b\u305f\u3081\u306b\u4f7f\u7528\u3055\u308c\u307e\u3059\u3002\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u7279\u5fb4\u3092\u5185\u90e8\u3067\u6700\u9069\u306a\u5206\u5272\u70b9\u3092\u898b\u3064\u3051\u308b\u305f\u3081\u306b\u4f7f\u7528\u3057\u3001\u305d\u308c\u306b\u3088\u3063\u3066\u30ce\u30fc\u30c9\u3092\u5206\u5272\u3057\u307e\u3059\u3002\u3053\u306e\u30d7\u30ed\u30bb\u30b9\u306f\u3001\u7279\u5fb4\u306e\u5024\u304c\u6570\u5024\u3068\u3057\u3066\u306e\u5927\u5c0f\u95a2\u4fc2\u3092\u6301\u3063\u3066\u3044\u308b\u304b\u3069\u3046\u304b\u306b\u4f9d\u5b58\u3057\u307e\u305b\u3093\u3002<\/p>\r\n
\u3057\u305f\u304c\u3063\u3066\u3001Ordinal Encoder\u3067\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3055\u308c\u305f\u30ab\u30e9\u30e0\u3092LightGBM\u306e\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30d5\u30a3\u30fc\u30c1\u30e3\u30fc\u3068\u3057\u3066\u6307\u5b9a\u3057\u305f\u5834\u5408\u3001\u305d\u306e\u9806\u5e8f\u6027\u306f\u76f4\u63a5\u7684\u306a\u610f\u5473\u3092\u6301\u305f\u306a\u304f\u306a\u308a\u307e\u3059\u3002<\/p>\r\n
<\/p>\n\n
\u5404\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u304c\u6709\u52b9\u306a\u6d3b\u7528\u5834\u9762<\/h2>\n
<\/h1>\r\n
    \r\n\t
  • Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0<\/strong>: \u9806\u5e8f\u95a2\u4fc2\u306e\u306a\u3044\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30c7\u30fc\u30bf\u306b\u9069\u3057\u3066\u3044\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001\u56fd\u540d\u3084\u6027\u5225\u3001\u8840\u6db2\u578b\u306a\u3069\u3001\u9806\u5e8f\u3092\u8003\u616e\u3059\u308b\u5fc5\u8981\u306e\u306a\u3044\u30ab\u30c6\u30b4\u30ea\u306b\u6700\u9069\u3067\u3059\u3002<\/li>\r\n\t
  • Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0<\/strong>: \u9806\u5e8f\u95a2\u4fc2\u304c\u660e\u78ba\u306b\u5b58\u5728\u3059\u308b\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30c7\u30fc\u30bf\u306b\u6709\u52b9\u3067\u3059\u3002\u4f8b\u3048\u3070\u3001\u5b66\u6b74\uff08\u9ad8\u5352\u3001\u5c02\u9580\u5352\u3001\u5927\u5352\u3001\u5927\u5b66\u9662\u5352\uff09\u3084\u8a55\u4fa1\uff08\u60aa\u3044\u3001\u666e\u901a\u3001\u826f\u3044\u3001\u975e\u5e38\u306b\u826f\u3044\uff09\u306a\u3069\u3001\u81ea\u7136\u306a\u9806\u5e8f\u304c\u5b58\u5728\u3059\u308b\u5834\u5408\u306b\u9069\u7528\u3057\u307e\u3059\u3002<\/li>\r\n<\/ul>\r\n
    <\/p>\n\n
    \u307e\u3068\u3081<\/h2>\n
    Label\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u3001\u30ab\u30c6\u30b4\u30ea\u30ab\u30eb\u30c7\u30fc\u30bf\u3092\u6570\u5024\u30c7\u30fc\u30bf\u306b\u5909\u63db\u3059\u308b\u305f\u3081\u306e\u6709\u52b9\u306a\u624b\u6cd5\u3067\u3059\u304c\u3001\u305d\u308c\u305e\u308c\u304c\u6709\u52b9\u306a\u5834\u9762\u306f\u7570\u306a\u308a\u307e\u3059\u3002\u30c7\u30fc\u30bf\u306e\u6027\u8cea\u3092\u6b63\u78ba\u306b\u7406\u89e3\u3057\u3001\u76ee\u7684\u3084\u30e2\u30c7\u30eb\u306b\u5fdc\u3058\u3066\u9069\u5207\u306a\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u624b\u6cd5\u3092\u9078\u629e\u3059\u308b\u3053\u3068\u304c\u4e0d\u53ef\u6b20\u3067\u3059\u3002<\/p>","protected":false},"excerpt":{"rendered":"
    \u3053\u3053\u3067\u306fLabel\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3068Ordinal\u30a8\u30f3\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306e\u57fa\u672c\u7684\u306a\u9055\u3044\u3068\u3001\u305d\u308c\u305e\u308c\u304c\u3069\u306e\u3088\u3046\u306a\u30c7\u30fc\u30bf\u51e6\u7406\u5834\u9762\u3067\u6709\u52b9\u306b\u6d3b\u7528\u3067\u304d\u308b\u306e\u304b\u3092\u8a73\u3057\u304f\u89e3\u8aac\u3057\u307e\u3059\u3002\u307e\u305f\u3001LightGBM\u306eCategoryFuture\u3092\u4f7f\u7528\u3059 […]<\/p>\n","protected":false},"author":62,"featured_media":3651,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","swell_btn_cv_data":"","footnotes":"","_wp_rev_ctl_limit":""},"categories":[1246],"tags":[569,359,570,39],"class_list":["post-4681","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-infrastructure","tag-label-encoder","tag-lightgbm","tag-ordinalencoder","tag-39"],"_links":{"self":[{"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/posts\/4681","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/users\/62"}],"replies":[{"embeddable":true,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/comments?post=4681"}],"version-history":[{"count":0,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/posts\/4681\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/media\/3651"}],"wp:attachment":[{"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/media?parent=4681"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/categories?post=4681"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/since2020.jp\/media\/wp-json\/wp\/v2\/tags?post=4681"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}