{"id":468,"date":"2020-03-31T13:14:26","date_gmt":"2020-03-31T04:14:26","guid":{"rendered":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/?p=468"},"modified":"2020-06-24T14:53:39","modified_gmt":"2020-06-24T05:53:39","slug":"openrefine%e3%82%92%e4%bd%bf%e3%81%a3%e3%81%a6%e3%83%87%e3%83%bc%e3%82%bf%e3%82%92%e3%81%8d%e3%82%8c%e3%81%84%e3%81%ab%e3%81%99%e3%82%8b%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/?p=468","title":{"rendered":"OpenRefine\u3092\u4f7f\u3063\u3066\u30c7\u30fc\u30bf\u3092\u304d\u308c\u3044\u306b\u3059\u308b\u65b9\u6cd5"},"content":{"rendered":"\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p style=\"background-color:#fcf8e3;color:#8a6d3b\" class=\"has-text-color has-background\"><strong>Seth van Hooland, Ruben Verborgh, Max De Wilde<\/strong><\/p>\n\n\n\n<p style=\"background-color:#fcf8e3;color:#8a6d3b\" class=\"has-text-color has-background\">\u3053\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u306f\u3001\u7814\u7a76\u8005\u304c\u3069\u306e\u3088\u3046\u306b\u3057\u3066\u30c7\u30fc\u30bf\u306e\u6b63\u78ba\u6027\u3092\u8a3a\u65ad\u3057\u3001\u305d\u308c\u306b\u57fa\u3065\u3044\u3066\u884c\u52d5\u3059\u308b\u304b\u306b\u7126\u70b9\u3092\u5f53\u3066\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"contents\">\u76ee\u6b21<\/h2>\n\n\n\n<ul><li><a href=\"#lesson-goals\">\u30ec\u30c3\u30b9\u30f3\u306e\u76ee\u6a19<\/a><\/li><li><a href=\"#why-should-historians-care-about-data-quality\">\u6b74\u53f2\u7814\u7a76\u8005\u306f\u306a\u305c\u30c7\u30fc\u30bf\u306e\u8cea\u3092\u6c17\u306b\u3059\u308b\u3079\u304d\u306a\u306e\u304b<\/a><\/li><li><a href=\"#description-of-the-tool-openrefine\">OpenRefine\u306e\u6982\u8981<\/a><\/li><li><a href=\"#description-of-the-exercise-powerhouse-museum\">\u6f14\u7fd2\u306e\u6982\u8981: \u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0<\/a><ul><li><a href=\"#getting-started-installing-openrefine-and-importing-data\">\u306f\u3058\u3081\u306b: OpenRefine\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3068\u30c7\u30fc\u30bf\u306e\u30a4\u30f3\u30dd\u30fc\u30c8<\/a><\/li><li><a href=\"#get-to-know-your-data\">\u30c7\u30fc\u30bf\u3092\u77e5\u308d\u3046<\/a><\/li><li><a href=\"#remove-blank-rows\">\u7a7a\u767d\u306e\u884c\u3092\u524a\u9664<\/a><\/li><li><a href=\"#removing-duplicates\">\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u306e\u524a\u9664<\/a><\/li><li><a href=\"#atomization\">\u500b\u5225\u5316\uff08Atomization\uff09<\/a><\/li><li><a href=\"#facetting-and-clustering\">\u30d5\u30a1\u30bb\u30c3\u30c8\u3068\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0<\/a><\/li><li><a href=\"https:\/\/programminghistorian.org\/en\/lessons\/cleaning-data-with-openrefine#applying-ad-hoc-transformations-through-the-use-of-regular-expressions\">\u6b63\u898f\u8868\u73fe\u3092\u5229\u7528\u3057\u305f\u30a2\u30c9\u30db\u30c3\u30af<\/a><a href=\"#applying-ad-hoc-transformations-through-the-use-of-regular-expressions\">\u306a\u5909\u63db<\/a><\/li><li><a href=\"#exporting-your-cleaned-data\">\u6574\u5f62\u6e08\u307f\u30c7\u30fc\u30bf\u306e\u51fa\u529b<\/a><\/li><li><a href=\"#building-on-top-of-your-cleaned-data\">\u6574\u5f62\u6e08\u307f\u30c7\u30fc\u30bf\u306e\u6b21\u306e\u30b9\u30c6\u30c3\u30d7<\/a><\/li><\/ul><\/li><li><a href=\"#conclusions\">\u7d42\u308f\u308a\u306b<\/a><\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"lesson-goals\">\u30ec\u30c3\u30b9\u30f3\u306e\u76ee\u6a19<\/h2>\n\n\n\n<p> \u30c7\u30fc\u30bf\u3092\u984d\u9762\u901a\u308a\u53d7\u3051\u6b62\u3081\u3066\u306f\u3044\u3051\u307e\u305b\u3093\u3002\u3053\u308c\u304c\u3001\u7814\u7a76\u8005\u304c\u3069\u306e\u3088\u3046\u306b\u3057\u3066\u30c7\u30fc\u30bf\u306e\u6b63\u78ba\u6027\u3092\u8a3a\u65ad\u3057\u3001\u305d\u308c\u306b\u57fa\u3065\u3044\u3066\u884c\u52d5\u3059\u308b\u304b\u306b\u7126\u70b9\u3092\u5f53\u3066\u305f\u3053\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u30ad\u30fc\u30e1\u30c3\u30bb\u30fc\u30b8\u3067\u3059\u3002\u672c\u30ec\u30c3\u30b9\u30f3\u3067\u306f\u3001\u30c7\u30fc\u30bf\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u306e\u539f\u5247\u3084\u5b9f\u8df5\u306b\u3064\u3044\u3066\u5b66\u3073\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/openrefine.org\/\" target=\"_blank\"><em>OpenRefine<\/em><\/a>\u3092\u4f7f\u3063\u3066\u884c\u3048\u308b\u3001\u30c7\u30fc\u30bf\u306e\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u306b\u304a\u3044\u3066\u6b20\u304b\u305b\u306a\u3044\u4ee5\u4e0b\u306e4\u3064\u306e\u30bf\u30b9\u30af\u306b\u3064\u3044\u3066\u8aac\u660e\u3057\u307e\u3059:<\/p>\n\n\n\n<ol><li>\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u306e\u524a\u9664<\/li><li>\u540c\u4e00\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306e\u8907\u6570\u306e\u5024\u306e\u5206\u5272<\/li><li>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u5168\u4f53\u3067\u306e\u5024\u306e\u5206\u5e03\u306e\u5206\u6790<\/li><li>\u540c\u3058\u4e8b\u8c61\u306b\u5bfe\u3059\u308b\u5225\u8868\u73fe\u306e\u30b0\u30eb\u30fc\u30d4\u30f3\u30b0<\/li><\/ol>\n\n\n\n<p> \u3053\u308c\u3089\u306e\u30b9\u30c6\u30c3\u30d7\u306f\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/www.powerhousemuseum.com\/\" target=\"_blank\">\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0<\/a>\u304c\u63d0\u4f9b\u3057\u3066\u3044\u308b\u30e1\u30bf\u30c7\u30fc\u30bf\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306b\u57fa\u3065\u3044\u305f\u6f14\u7fd2\u306b\u6cbf\u3063\u3066\u89e3\u8aac\u3057\u3066\u304a\u308a\u3001\uff08\u534a\uff09\u81ea\u52d5\u5316\u3057\u305f\u65b9\u6cd5\u304c\u3069\u306e\u3088\u3046\u306b\u30c7\u30fc\u30bf\u5185\u306e\u30a8\u30e9\u30fc\u3092\u4fee\u6b63\u3067\u304d\u308b\u306e\u304b\u3092\u793a\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"why-should-historians-care-about-data-quality\">\u6b74\u53f2\u7814\u7a76\u8005\u306f\u306a\u305c\u30c7\u30fc\u30bf\u306e\u8cea\u3092\u6c17\u306b\u3059\u308b\u3079\u304d\u306a\u306e\u304b<\/h2>\n\n\n\n<p>\u91cd\u8907\u3057\u3066\u3044\u308b\u30ec\u30b3\u30fc\u30c9\u3084\u7a7a\u767d\u5024\u3001\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u306e\u4e0d\u7d71\u4e00\u306a\u3069\u306b\u5bfe\u3057\u3066\u306f\u3001\u904e\u53bb\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u6271\u3046\u969b\u306b\u5099\u3048\u3066\u3044\u306a\u3051\u308c\u3070\u306a\u308a\u307e\u305b\u3093\u3002\u672c\u30ec\u30c3\u30b9\u30f3\u3067\u306f\u3001\u30b9\u30d7\u30ec\u30c3\u30c9\u30b7\u30fc\u30c8\u3084\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u5185\u306b\u542b\u307e\u308c\u3066\u3044\u308b\u77db\u76fe\u3057\u305f\u30c7\u30fc\u30bf\u3092\u898b\u3064\u3051\u308b\u65b9\u6cd5\u3092\u89e3\u8aac\u3057\u307e\u3059\u3002\u30a6\u30a7\u30d6\u4e0a\u3067\u30c7\u30fc\u30bf\u3092\u5171\u6709\u3057\u305f\u308a\u96c6\u7d04\u3057\u305f\u308a\u518d\u5229\u7528\u3057\u305f\u308a\u3059\u308b\u3053\u3068\u304c\u5897\u3048\u3066\u3044\u308b\u4e2d\u3067\u3001\u6b74\u53f2\u7814\u7a76\u8005\u306f\u3001\u907f\u3051\u3066\u306f\u901a\u308c\u306a\u3044\u30c7\u30fc\u30bf\u54c1\u8cea\u306e\u554f\u984c\u306b\u5bfe\u51e6\u3057\u306a\u304f\u3066\u306f\u306a\u3089\u306a\u3044\u3067\u3057\u3087\u3046\u3002<em>OpenRefine<\/em>\u3068\u3044\u3046\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u4f7f\u3048\u3070\u3001\u7a7a\u767d\u30bb\u30eb\u3001\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3001\u8868\u8a18\u3086\u308c\u306a\u3069\u306e\u30b7\u30b9\u30c6\u30de\u30c6\u30a3\u30c3\u30af\u306a\u30a8\u30e9\u30fc\u3092\u7c21\u5358\u306b\u7279\u5b9a\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<em>OpenRefine<\/em>\u306f\u30c7\u30fc\u30bf\u306e\u7cbe\u5ea6\u306b\u3064\u3044\u3066\u7d20\u65e9\u304f\u8a3a\u65ad\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u3060\u3051\u3067\u306a\u304f\u3001\u51e6\u7406\u3092\u81ea\u52d5\u5316\u3059\u308b\u3053\u3068\u3067\u7279\u5b9a\u306e\u30a8\u30e9\u30fc\u306b\u5bfe\u5fdc\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u3066\u304f\u308c\u307e\u3059\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"description-of-the-tool-openrefine\">OpenRefine\u306e\u6982\u8981<\/h2>\n\n\n\n<p>\u3053\u308c\u307e\u3067\u6b74\u53f2\u7814\u7a76\u8005\u306f\u3001\u30c7\u30fc\u30bf\u306e\u8cea\u3092\u5224\u65ad\u3057\u30c7\u30fc\u30bf\u306e\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u3092\u5b9f\u65bd\u3059\u308b\u305f\u3081\u306b\u306f\u3001\u60c5\u5831\u6280\u8853\u306e\u5c02\u9580\u5bb6\u306b\u983c\u3089\u306a\u304f\u3066\u306f\u306a\u308a\u307e\u305b\u3093\u3067\u3057\u305f\u3002\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u898f\u6a21\u304c\u5927\u304d\u3051\u308c\u3070\u3001\u30ab\u30b9\u30bf\u30de\u30a4\u30ba\u3055\u308c\u305f\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u7528\u3044\u308b\u5fc5\u8981\u304c\u3042\u3063\u305f\u306e\u3067\u3059\u3002\u5e78\u904b\u306a\u3053\u3068\u306b\u3001\u30a4\u30f3\u30bf\u30e9\u30af\u30c6\u30a3\u30d6\u30fb\u30c7\u30fc\u30bf\u5909\u63db\uff08Interactive Data Transformation; IDT\uff09\u30c4\u30fc\u30eb\u306e\u51fa\u73fe\u306b\u3088\u308a\u3001\u6df1\u3044\u30b9\u30ad\u30eb\u3092\u3082\u305f\u306a\u3044\u5c02\u9580\u5bb6\u3067\u3082\u5927\u91cf\u306e\u30c7\u30fc\u30bf\u3092\u9ad8\u901f\u304b\u3064\u5b89\u4fa1\u306b\u64cd\u4f5c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u3063\u305f\u306e\u3067\u3059\u3002<\/p>\n\n\n\n<p>IDT\u306f\u3001\u79c1\u305f\u3061\u304c\u3088\u304f\u77e5\u3063\u3066\u3044\u308b\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u7248\u306e\u8868\u8a08\u7b97\u30bd\u30d5\u30c8\u306b\u4f3c\u3066\u3044\u3066\u3001\u6a5f\u80fd\u3082\u5171\u901a\u3057\u3066\u3044\u308b\u90e8\u5206\u304c\u3042\u308a\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001\u30de\u30a4\u30af\u30ed\u30bd\u30d5\u30c8\u306eExcel\u306a\u3069\u306e\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u3067\u306f\u3001\u6570\u5024\u3001\u30a2\u30eb\u30d5\u30a1\u30d9\u30c3\u30c8\u3001\u307e\u305f\u306f\u72ec\u81ea\u30d5\u30a3\u30eb\u30bf\u30fc\u306b\u3088\u3063\u3066\u30c7\u30fc\u30bf\u3092\u4e26\u3079\u66ff\u3048\u3066\u3001\u5bb9\u6613\u306b\u30a8\u30e9\u30fc\u3092\u898b\u3064\u3051\u51fa\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3057\u304b\u3057\u3001\u3053\u306e\u3088\u3046\u306a\u30d5\u30a3\u30eb\u30bf\u30fc\u6a5f\u80fd\u306f\u4e8c\u6b21\u7684\u306a\u3082\u306e\u306a\u306e\u3067\u3001\u305d\u306e\u8a2d\u5b9a\u3092\u8868\u8a08\u7b97\u3067\u884c\u3046\u306e\u306f\u9762\u5012\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u3002\u3082\u3063\u3068\u4e00\u822c\u7684\u306a\u30ec\u30d9\u30eb\u3067\u8a00\u3046\u3068\u3001\u8868\u8a08\u7b97\u306f\u500b\u5225\u306e\u884c\u3084\u30bb\u30eb\u3092\u6271\u3046\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u3066\u3044\u308b\u306e\u306b\u5bfe\u3057\u3001IDT\u306f\u4e00\u5ea6\u306b\u5927\u91cf\u306e\u30c7\u30fc\u30bf\u3092\u6271\u3046\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u3066\u3044\u308b\u3068\u8a00\u3048\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u300c\u30b9\u30c6\u30ed\u30a4\u30c9\u4e0a\u306e\u30b9\u30d7\u30ec\u30c3\u30c9\u30b7\u30fc\u30c8\u300d\u306f\u3001\u4f7f\u3044\u3084\u3059\u3044\u7d71\u5408\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u63d0\u4f9b\u3057\u3001\u30a8\u30f3\u30c9\u30e6\u30fc\u30b6\u30fc\u304c\u30a8\u30e9\u30fc\u3092\u898b\u3064\u3051\u51fa\u3057\u3066\u4fee\u6b63\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p>\u8fd1\u5e74\u3001IDT\u306e\u305f\u3081\u306e\u6c4e\u7528\u30c4\u30fc\u30eb\u304c\u958b\u767a\u3055\u308c\u3066\u304a\u308a\u3001\u4f8b\u3048\u3070 &nbsp;<a rel=\"noreferrer noopener\" href=\"http:\/\/control.cs.berkeley.edu\/abc\/\" target=\"_blank\"><em>Potter\u2019s Wheel ABC<\/em><\/a>&nbsp;\u3084&nbsp;<a rel=\"noreferrer noopener\" href=\"http:\/\/vis.stanford.edu\/papers\/wrangler\/\" target=\"_blank\"><em>Wrangler<\/em><\/a> \u306a\u3069\u304c\u3042\u308a\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u7279\u306b <a rel=\"noreferrer noopener\" href=\"http:\/\/openrefine.org\/\" target=\"_blank\"><em>OpenRefine<\/em><\/a>&nbsp;\uff08\u4ee5\u524d\u306fFreebase Gridworks\u3084Google Refine\u3068\u547c\u3070\u308c\u3066\u3044\u305f\u3082\u306e\uff09\u306b\u6ce8\u76ee\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u3053\u308c\u306f\u3001\u30d6\u30e9\u30a6\u30b6\u30d9\u30fc\u30b9\u306e\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u901a\u3058\u3066\u3001\u5927\u91cf\u306e\u30c7\u30fc\u30bf\u3092\u52b9\u7387\u7684\u306b\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u30c4\u30fc\u30eb\u3068\u3057\u3066\u3001\u6700\u3082\u4f7f\u3044\u3084\u3059\u3044\u3082\u306e\u3067\u3042\u308b\u3068\u8003\u3048\u3066\u3044\u308b\u304b\u3089\u3067\u3059\u3002<\/p>\n\n\n\n<p><a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Data_profiling\" target=\"_blank\">\u30c7\u30fc\u30bf\u30d7\u30ed\u30d5\u30a1\u30a4\u30ea\u30f3\u30b0<\/a>\u3068\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u64cd\u4f5c\u306b\u52a0\u3048\u3001<em>OpenRefine<\/em>\u306e\u62e1\u5f35\u6a5f\u80fd\u3092\u4f7f\u3046\u3053\u3068\u3067\u3001\u975e\u69cb\u9020\u5316\u30c6\u30ad\u30b9\u30c8\u306b\u304a\u3051\u308b\u6982\u5ff5\u3092\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Named-entity_recognition\" target=\"_blank\">\u56fa\u6709\u8868\u73fe\u62bd\u51fa<\/a> \uff08named-entity recognition; NER\uff09\u3068\u547c\u3070\u308c\u308b\u51e6\u7406\u3092\u901a\u3058\u3066\u7279\u5b9a\u3057\u3001\u65e2\u5b58\u306e\u77e5\u8b58\u30d9\u30fc\u30b9\u3068\u81ea\u5206\u306e\u30c7\u30fc\u30bf\u3092\u7167\u5408\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002\u305d\u3046\u3059\u308b\u3053\u3068\u3067\u3001<em>OpenRefine<\/em>\u306f\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/www.loc.gov\/index.html\" target=\"_blank\">\u7c73\u56fd\u8b70\u4f1a\u56f3\u66f8\u9928<\/a>\u3084<a rel=\"noreferrer noopener\" href=\"http:\/\/www.oclc.org\/home.en.html\" target=\"_blank\">OCLC<\/a>\u306a\u3069\u306e\u6a5f\u95a2\u306b\u3088\u3063\u3066\u30a6\u30a7\u30d6\u4e0a\u3067\u65e2\u306b\u5ba3\u8a00\u3055\u308c\u3066\u3044\u308b\u6982\u5ff5\u3084\u5178\u62e0\u60c5\u5831\u306b\u5bfe\u3057\u3001\u30c7\u30fc\u30bf\u3092\u7d10\u3065\u3051\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u5b9f\u8df5\u7684\u306a\u30c4\u30fc\u30eb\u3068\u3057\u3066\u6a5f\u80fd\u3059\u308b\u306e\u3067\u3059\u3002\u30c7\u30fc\u30bf\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u306f\u305d\u308c\u3089\u306e\u30b9\u30c6\u30c3\u30d7\u306e\u305f\u3081\u524d\u63d0\u3067\u3042\u308a\u3001NER\u306e\u6210\u529f\u7387\u3068\u3042\u306a\u305f\u306e\u30c7\u30fc\u30bf\u3068\u5916\u90e8\u5178\u62e0\u30c7\u30fc\u30bf\u3068\u306e\u9593\u306e\u30de\u30c3\u30c1\u30f3\u30b0\u6210\u529f\u7387\u306f\u3001\u30c7\u30fc\u30bf\u3092\u9996\u5c3e\u4e00\u8cab\u3057\u305f\u3082\u306e\u306b\u3067\u304d\u308b\u304b\u3069\u3046\u304b\u306b\u304b\u304b\u3063\u3066\u3044\u307e\u3059\u3002 <\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"description-of-the-exercise-powerhouse-museum\">\u6f14\u7fd2\u306e\u6982\u8981: \u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0<\/h2>\n\n\n\n<p>\u30b7\u30c9\u30cb\u30fc\u306e\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u306f\u3001\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306b\u95a2\u3059\u308b\u81ea\u7531\u5229\u7528\u53ef\u80fd\u306a\u30e1\u30bf\u30c7\u30fc\u30bf\u3092<a rel=\"noreferrer noopener\" href=\"http:\/\/www.powerhousemuseum.com\/collection\/database\/download.php\" target=\"_blank\">\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8<\/a>\u4e0a\u3067\u63d0\u4f9b\u3057\u3066\u3044\u307e\u3059\u3002\u540c\u535a\u7269\u9928\u306f\u4e16\u754c\u3067\u3082\u6700\u5927\u898f\u6a21\u306e\u79d1\u5b66\u6280\u8853\u535a\u7269\u9928\u3067\u3042\u308a\u3001\u84b8\u6c17\u6a5f\u95a2\u304b\u3089\u30ac\u30e9\u30b9\u7d30\u5de5\u54c1\u3084\u30aa\u30fc\u30c8\u30af\u30c1\u30e5\u30fc\u30eb\u54c1\u3001\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30c1\u30c3\u30d7\u307e\u3067\u300190,000\u70b9\u3092\u8d85\u3048\u308b\u8cc7\u6599\u3078\u306e\u30a2\u30af\u30bb\u30b9\u3092\u63d0\u4f9b\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p>\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u306f\u3001\u305d\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e\u30aa\u30f3\u30e9\u30a4\u30f3\u516c\u958b\u3092\u975e\u5e38\u306b\u7a4d\u6975\u7684\u306b\u884c\u3063\u3066\u304a\u308a\u3001\u30c7\u30fc\u30bf\u306e\u307b\u3068\u3093\u3069\u3092\u81ea\u7531\u306b\u5229\u7528\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u3066\u3044\u307e\u3059\u3002\u535a\u7269\u9928\u306e\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8\u304b\u3089\u306f\u3001\u30d5\u30a1\u30a4\u30eb\u540d\u304c<em>phm-collection.tsv<\/em>\u3068\u306a\u3063\u3066\u3044\u308b\u30bf\u30d6\u533a\u5207\u308a\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3067\u304d\u3001\u8868\u8a08\u7b97\u30bd\u30d5\u30c8\u3067\u958b\u304f\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u89e3\u51cd\u5f8c\u306e\u30d5\u30a1\u30a4\u30eb\uff0858MB\uff09 \u306b\u306f75,823\u70b9\u3082\u306e\u8cc7\u6599\u306b\u95a2\u3059\u308b\u57fa\u672c\u7684\u306a\u30e1\u30bf\u30c7\u30fc\u30bf\uff0817\u30d5\u30a3\u30fc\u30eb\u30c9\uff09\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/creativecommons.org\/licenses\/by-nc\/2.5\/au\/\" target=\"_blank\">Creative Commons Attribution Share Alike (CCASA) \u30e9\u30a4\u30bb\u30f3\u30b9<\/a>\u306e\u4e0b\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u672c\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u306f\u3001\u7b46\u8005\u3089\u304c\u4fdd\u5b58\u3057\u3066\uff08\u3053\u306e\u5f8c\u3059\u3050\u306b\uff09\u3042\u306a\u305f\u304c\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u305f\u30c7\u30fc\u30bf\u306e\u30b3\u30d4\u30fc\u3092\u4f7f\u3044\u307e\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u304c\u30c7\u30fc\u30bf\u3092\u66f4\u65b0\u3057\u3066\u3082\u3001\u30ec\u30c3\u30b9\u30f3\u306b\u6cbf\u3063\u3066\u5b66\u7fd2\u3092\u9032\u3081\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<p>\u30c7\u30fc\u30bf\u30d7\u30ed\u30d5\u30a1\u30a4\u30ea\u30f3\u30b0\u3084\u30c7\u30fc\u30bf\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u306e\u30d7\u30ed\u30bb\u30b9\u3092\u901a\u3058\u3066\u3001\u672c\u30b1\u30fc\u30b9\u30b9\u30bf\u30c7\u30a3\u3067\u306f\u3001\u7279\u306b\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u306e\u8cc7\u6599\u540d\u30b7\u30bd\u30fc\u30e9\u30b9\uff08Powerhouse Museum Object Names Thesaurus; PONT\uff09\u306e\u7528\u8a9e\u304c\u4f7f\u308f\u308c\u3066\u3044\u308b <code><font style=\"color:#ff0000\" class=\"has-text-color\">Categories<\/font><\/code>\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u6ce8\u76ee\u3057\u307e\u3059\u3002PONT\u306f\u30aa\u30fc\u30b9\u30c8\u30e9\u30ea\u30a2\u82f1\u8a9e\u7279\u6709\u306e\u8a00\u8449\u9063\u3044\u3084\u7db4\u308a\u3092\u8a8d\u8b58\u3057\u3001\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e\u5f37\u307f\u3092\u975e\u5e38\u306b\u76f4\u63a5\u7684\u306b\u53cd\u6620\u3057\u3066\u3044\u307e\u3059\u3002\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306f\u3001\u793e\u4f1a\u53f2\u3084\u88c5\u98fe\u7f8e\u8853\u3092\u3088\u308a\u3088\u304f\u8868\u3057\u3066\u304a\u308a\u3001\u4e00\u65b9\u3067\u7f8e\u8853\u3084\u81ea\u7136\u53f2\u306b\u95a2\u9023\u3059\u308b\u8cc7\u6599\u540d\u306f\u6bd4\u8f03\u7684\u5c11\u306a\u304f\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p>Categories\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306e\u7528\u8a9e\u306f\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Controlled_vocabulary\" target=\"_blank\">\u7d71\u5236\u8a9e\u5f59<\/a>\u3068\u547c\u3070\u308c\u308b\u3082\u306e\u3092\u69cb\u6210\u3057\u3066\u3044\u307e\u3059\u3002\u7d71\u5236\u8a9e\u5f59\u3068\u306f\u3001\u9650\u3089\u308c\u305f\u6570\u306e\u7528\u8a9e\u3092\u7528\u3044\u3066\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e\u5185\u5bb9\u3092\u8a18\u8ff0\u3059\u308b\u30ad\u30fc\u30ef\u30fc\u30c9\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3082\u306e\u3067\u3001\u56f3\u66f8\u9928\u3084\u6587\u66f8\u9928\u3001\u535a\u7269\u9928\u3067\u3001\u6b74\u53f2\u7814\u7a76\u8005\u304c\u89e6\u308c\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3078\u306e\u91cd\u8981\u306a\u5165\u308a\u53e3\u3068\u306a\u3063\u3066\u3044\u308b\u3053\u3068\u304c\u591a\u3044\u3067\u3059\u3002\u300cCategories\u300d\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u6ce8\u76ee\u3057\u3066\u3044\u308b\u306e\u306f\u3053\u306e\u305f\u3081\u3067\u3059\u3002\u4e00\u65e6\u30c7\u30fc\u30bf\u306e\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u304c\u5b8c\u4e86\u3059\u308b\u3068\u3001\u7d71\u5236\u8a9e\u5f59\u306e\u7528\u8a9e\u3092\u518d\u5229\u7528\u3057\u3066\u3001\u30aa\u30f3\u30e9\u30a4\u30f3\u3067\u7528\u8a9e\u306b\u95a2\u3059\u308b\u8ffd\u52a0\u60c5\u5831\u3092\u898b\u3064\u3051\u308b\u3053\u3068\u304c\u53ef\u80fd\u3068\u306a\u308a\u307e\u3059\u3002\u3053\u308c\u306f<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Linked_data\" target=\"_blank\">Linked Data<\/a>\u306e\u4f5c\u6210\u3068\u3057\u3066\u77e5\u3089\u308c\u3066\u3044\u308b\u3082\u306e\u3067\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"getting-started-installing-openrefine-and-importing-data\">\u306f\u3058\u3081\u306b: OpenRefine\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3068\u30c7\u30fc\u30bf\u306e\u30a4\u30f3\u30dd\u30fc\u30c8<\/h3>\n\n\n\n<p><a rel=\"noreferrer noopener\" href=\"http:\/\/openrefine.org\/#download_openrefine\" target=\"_blank\">OpenRefine\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9<\/a>\u3057\u3001\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u624b\u9806\u306b\u5f93\u3063\u3066\u304f\u3060\u3055\u3044\u3002OpenRefine\u306f\u3001Windows\u3001Mac\u3001Linux\u306e\u3059\u3079\u3066\u306e\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0\u3067\u52d5\u4f5c\u3057\u307e\u3059\u3002OpenRefine\u306f\u30d6\u30e9\u30a6\u30b6\u30fc\u3067\u958b\u304d\u307e\u3059\u304c\u3001\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306f\u30ed\u30fc\u30ab\u30eb\u3067\u5b9f\u884c\u3055\u308c\u3001\u30c7\u30fc\u30bf\u306f\u30aa\u30f3\u30e9\u30a4\u30f3\u3067\u4fdd\u5b58\u3055\u308c\u306a\u3044\u3053\u3068\u3092\u899a\u3048\u3066\u304d\u307e\u3057\u3087\u3046\u3002\u30c7\u30fc\u30bf\u30d5\u30a1\u30a4\u30eb\u306f\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/data.freeyourmetadata.org\/powerhouse-museum\/\" target=\"_blank\">FreeYourMetadata\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8<\/a>\u304b\u3089\u5165\u624b\u53ef\u80fd\u3067\u3001\u672c\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u901a\u3058\u3066\u6d3b\u7528\u3057\u3066\u3044\u304d\u307e\u3059\u3002\u6b21\u3078\u9032\u3080\u524d\u306b<em>phm-collection.tsv<\/em>\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u3066\u304a\u3044\u3066\u4e0b\u3055\u3044\uff08the Programming Historian\u30b5\u30a4\u30c8\u4e0a\u3067\u3082<a href=\"https:\/\/programminghistorian.org\/assets\/phm-collection.tsv\">phm-collection<\/a>\u3068\u3057\u3066\u4fdd\u5b58\u3057\u3066\u3044\u307e\u3059\u3002\uff09\u3002<\/p>\n\n\n\n<p>OpenRefine\u306e\u30b9\u30bf\u30fc\u30c8\u30da\u30fc\u30b8\u3067\u3001\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u305f\u30c7\u30fc\u30bf\u3092\u4f7f\u7528\u3057\u3066\u3001\u65b0\u898f\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u4f5c\u6210\u3057\u3001<strong>\u300c\u6b21\u3078\u300d<\/strong>\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u4e0b\u3055\u3044\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u3067\u306f\u3001\u6700\u521d\u306e\u884c\u306f\u30ab\u30e9\u30e0\u540d\u3068\u3057\u3066\u6b63\u3057\u304f\u89e3\u6790\u3055\u308c\u307e\u3059\u304c\u3001\u30d5\u30a1\u30a4\u30eb\u5185\u306e\u5f15\u7528\u7b26\u306fOpenRefine\u306b\u3068\u3063\u3066\u4f55\u306e\u610f\u5473\u3082\u306a\u3044\u305f\u3081\u3001<strong>\u300c\u6587\u5b57 \u201d \u3067\u30bb\u30eb\u3092\u56f2\u3080\u300d<\/strong>\u306e\u30c1\u30a7\u30c3\u30af\u30dc\u30c3\u30af\u30b9\u3092\u5916\u3059\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u3055\u3089\u306b\u3001<strong>\u300c\u30bb\u30eb\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u89e3\u6790 \u6570\u5b57, \u65e5\u4ed8\u2026\u300d<\/strong>\u306e\u30c1\u30a7\u30c3\u30af\u30dc\u30c3\u30af\u30b9\u3092\u9078\u629e\u3059\u308b\u3068\u3001OpenRefine\u304c\u81ea\u52d5\u3067\u6570\u5024\u3092\u691c\u51fa\u3059\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002\u3053\u3053\u3067<strong>\u300c\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u4f5c\u6210\u300d<\/strong>\u3092\u30af\u30ea\u30c3\u30af\u3057\u307e\u3059\u3002\u3059\u3079\u3066\u3046\u307e\u304f\u3044\u3051\u3070\u300175,814\u884c\u304c\u78ba\u8a8d\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002\u307e\u305f\u3001<a rel=\"noreferrer noopener\" href=\"http:\/\/data.freeyourmetadata.org\/powerhouse-museum\/phm-collection.google-refine.tar.gz\" target=\"_blank\">\u521d\u671f\u306eOpenRefine\u30d7\u30ed\u30b8\u30a7\u30af\u30c8<\/a>\u3092\u76f4\u63a5\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<p>\u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306f\u3001\u30bf\u30a4\u30c8\u30eb\u3001\u5185\u5bb9\u8a18\u8ff0\u3001\u30a2\u30a4\u30c6\u30e0\u304c\u5c5e\u3059\u308b\u8907\u6570\u306e\u30ab\u30c6\u30b4\u30ea\u30fc\u3001\u51fa\u6240\u60c5\u5831\u3001\u535a\u7269\u9928\u306e\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8\u4e0a\u306e\u8cc7\u6599\u3078\u306e\u6c38\u7d9a\u7684\u306a\u30ea\u30f3\u30af\u3092\u542b\u3080\u3001\u3059\u3079\u3066\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u8cc7\u6599\u306b\u95a2\u3059\u308b\u8a73\u7d30\u306a\u30e1\u30bf\u30c7\u30fc\u30bf\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u30e1\u30bf\u30c7\u30fc\u30bf\u304c\u3069\u306e\u8cc7\u6599\u306b\u5bfe\u5fdc\u3057\u3066\u3044\u308b\u304b\u3092\u77e5\u308b\u306b\u306f\u3001\u6c38\u7d9a\u7684\u306a\u30ea\u30f3\u30af\u3092\u30af\u30ea\u30c3\u30af\u3059\u308c\u3070\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8\u304c\u958b\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/programminghistorian.org\/images\/cleaning-data-with-openrefine\/powerhouseScreenshot.png\" alt=\"Figure 1: Screenshot of a Sample Object on the Powerhouse Museum Website\"\/><figcaption> \u56f31: \u30d1\u30ef\u30fc\u30cf\u30a6\u30b9\u30df\u30e5\u30fc\u30b8\u30a2\u30e0\u306e\u30a6\u30a7\u30d6\u30b5\u30a4\u30c8\u306b\u63b2\u8f09\u3055\u308c\u3066\u3044\u308b\u30b5\u30f3\u30d7\u30eb\u306e\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 <\/figcaption><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"get-to-know-your-data\">\u30c7\u30fc\u30bf\u3092\u77e5\u308d\u3046<\/h3>\n\n\n\n<p>\u307e\u305a\u306f\u3001\u30c7\u30fc\u30bf\u3092\u773a\u3081\u3001\u6163\u308c\u89aa\u3057\u3080\u3053\u3068\u3067\u3059\u3002\u300c\u30d5\u30a1\u30bb\u30c3\u30c8\u300d\u3067\u8868\u793a\u3059\u308b\u3053\u3068\u3067\u69d8\u3005\u306a\u30c7\u30fc\u30bf\u5024\u3092\u78ba\u8a8d\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Faceted_search\" target=\"_blank\">\u30d5\u30a1\u30bb\u30c3\u30c8<\/a>\u306f\u3001\u9078\u629e\u3057\u305f\u57fa\u6e96\u306b\u57fa\u3065\u3044\u3066\u30c7\u30fc\u30bf\u306e\u7279\u5b9a\u306e\u30b5\u30d6\u30bb\u30c3\u30c8\u3092\u898b\u308b\u30ec\u30f3\u30ba\u306e\u3088\u3046\u306a\u3082\u306e\u3068\u8003\u3048\u3066\u304f\u3060\u3055\u3044\u3002\u30ab\u30e9\u30e0\u540d\u306e\u524d\u306e\u4e09\u89d2\u5f62\u3092\u30af\u30ea\u30c3\u30af\u3057\u3001\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9078\u629e\u3057\u3066\u4f5c\u6210\u3057\u307e\u3059\u3002\u4f8b\u3048\u3070\u3001\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u542b\u307e\u308c\u3066\u3044\u308b\u5024\u306e\u6027\u8cea\u306b\u3082\u3088\u308a\u307e\u3059\u304c\u3001\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30bb\u30c3\u30c8\u3084\u6570\u5024\u30d5\u30a1\u30bb\u30c3\u30c8\u306a\u3069\u3092\u8a66\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\uff08\u6570\u5024\u306f\u7dd1\u8272\u3067\u8868\u793a\u3055\u308c\u307e\u3059\uff09\u3002\u305f\u3060\u3057\u3001\u30c6\u30ad\u30b9\u30c8\u578b\u306e\u30d5\u30a1\u30bb\u30c3\u30c8\u306f\u3001\u5197\u9577\u306a\u5024\u304c\u3042\u308b\u30d5\u30a3\u30fc\u30eb\u30c9\uff08\u4f8b\u3048\u3070\u30ab\u30c6\u30b4\u30ea\u30fc\uff09\u306b\u6700\u9069\u3067\u3042\u308b\u3053\u3068\u306b\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002<strong>\u300c\u9078\u629e\u80a2\u304c\u591a\u3059\u304e\u3001\u8868\u793a\u3067\u304d\u307e\u305b\u3093\u300d<\/strong>\u3068\u3044\u3046\u30a8\u30e9\u30fc\u304c\u51fa\u305f\u3089\u3001\u9078\u629e\u80a2\u306e\u4e0a\u9650\u3092\u30c7\u30d5\u30a9\u30eb\u30c8\u306e2,000\u4ef6\u3088\u308a\u5897\u3084\u3059\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u304c\u3001\u591a\u3059\u304e\u308b\u3068\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306e\u52d5\u4f5c\u304c\u9045\u304f\u306a\u3063\u3066\u3057\u307e\u3044\u307e\u3059\uff08\u901a\u5e38\u306f5,000\u304f\u3089\u3044\u3067\u3088\u3044\u3067\u3057\u3087\u3046\uff09\u3002\u6570\u5024\u578b\u306e\u30d5\u30a1\u30bb\u30c3\u30c8\u306b\u306f\u3053\u306e\u3088\u3046\u306a\u5236\u9650\u306f\u3042\u308a\u307e\u305b\u3093\u3002\u3055\u3089\u306b\u591a\u304f\u306e\u30aa\u30d7\u30b7\u30e7\u30f3\u3092\u4f7f\u3044\u305f\u3044\u5834\u5408\u306f<strong>\u300c\u30ab\u30b9\u30bf\u30e0\u30d5\u30a1\u30bb\u30c3\u30c8\u300d<\/strong>\u3092\u4f7f\u3063\u3066\u304f\u3060\u3055\u3044\u3002\u4f8b\u3048\u3070\u3001\u7a7a\u767d\u306b\u3088\u308b\u30d5\u30a1\u30bb\u30c3\u30c8\u306f\u3001\u5404\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u5024\u304c\u3044\u304f\u3064\u3042\u308b\u306e\u304b\u78ba\u8a8d\u3057\u305f\u3044\u5834\u5408\u306a\u3069\u306b\u4fbf\u5229\u3067\u3059\u3002\u4ee5\u4e0b\u306e\u6f14\u7fd2\u3092\u901a\u3058\u3066\u3053\u308c\u3089\u306e\u30d5\u30a1\u30bb\u30c3\u30c8\u306b\u3055\u3089\u306b\u8a73\u3057\u304f\u89e6\u308c\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"remove-blank-rows\">\u7a7a\u767d\u306e\u884c\u3092\u524a\u9664<\/h3>\n\n\n\n<p>\u30ec\u30b3\u30fc\u30c9ID\u5217\u7528\u306b\u6570\u5024\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u4f5c\u6210\u3057\u305f\u969b\u306b\u6c17\u304c\u4ed8\u3044\u305f\u3068\u601d\u3044\u307e\u3059\u304c\u3001\u7a7a\u767d\u306e\u884c\u304c3\u884c\u3042\u308a\u307e\u3059[\u8a33\u6ce8\uff1aRecordID\u3067\u6570\u5024\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9078\u629e\u3057\u305f\u969b\u306b\u201dNon-numeric\u201d\u3068\u3057\u3066\u8868\u793a\u3055\u308c\u308b3\u4ef6\u306e\u3053\u3068]\u3002\u300c\u6570\u5b57\u300d\u306e\u30c1\u30a7\u30c3\u30af\u30dc\u30c3\u30af\u30b9\u3092\u5916\u3057\u3001\u975e\u6570\u5024\u578b\u306e\u5024\u306e\u307f\u3092\u6b8b\u3059\u3053\u3068\u3067\u898b\u3064\u3051\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u5b9f\u306f\u3001\u3053\u308c\u3089\u306e\u5024\u306f\u7a7a\u767d\u3067\u306f\u306a\u304f\u30b9\u30da\u30fc\u30b91\u500b\u5206\u306e\u6587\u5b57\u3092\u542b\u3093\u3067\u304a\u308a\u3001\u5024\u304c\u3042\u308b\u306f\u305a\u306e\u3068\u3053\u308d\u3078\u30ab\u30fc\u30bd\u30eb\u3092\u79fb\u52d5\u3055\u305b\u308b\u3068\u73fe\u308c\u308b\u300c<strong>edit<\/strong>\u300d\uff08\u7de8\u96c6\uff09\u30dc\u30bf\u30f3\u3092\u30af\u30ea\u30c3\u30af\u3059\u308b\u3053\u3068\u3067\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u884c\u3092\u524a\u9664\u3059\u308b\u305f\u3081\u306b\u306f\u3001\u6700\u521d\u306e\u5217<strong>\u300c\u5168\u3066\u300d<\/strong>\u306b\u3042\u308b\u4e09\u89d2\u5f62\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u3001\u300c<strong>\u884c\u3092\u7de8\u96c6<\/strong>\u300d\u3092\u9078\u629e\u3057\u3001\u300c<strong>\u30de\u30c3\u30c1\u3057\u305f\u884c\u3092\u524a\u9664<\/strong>\u300d\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u6570\u5024\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9589\u3058\u308b\u3068\u3001\u6b8b\u308a\u306e75,811\u884c\u304c\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"removing-duplicates\">\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u306e\u524a\u9664<\/h3>\n\n\n\n<p>\u7b2c2\u306e\u30b9\u30c6\u30c3\u30d7\u306f\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3092\u898b\u3064\u3051\u3060\u3057\u524a\u9664\u3059\u308b\u3053\u3068\u3067\u3059\u3002\u3053\u308c\u3089\u306f\u56fa\u6709\u5024\u3001\u4f8b\u3048\u3070\u30ec\u30b3\u30fc\u30c9ID\uff08\u3053\u3053\u3067\u306f\u5404\u30a8\u30f3\u30c8\u30ea\u30fc\u306b\u5bfe\u3057\u3066\u30ec\u30b3\u30fc\u30c9ID\u304c\u5b9f\u969b\u306b\u56fa\u6709\u3067\u3042\u308b\u3068\u4eee\u5b9a\u3057\u3066\u3044\u307e\u3059\uff09\u306a\u3069\u3067\u30bd\u30fc\u30c8\u3059\u308b\u3053\u3068\u3067\u6d17\u3044\u51fa\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u306e\u4f5c\u696d\u306f\u30ec\u30b3\u30fc\u30c9ID\u306e\u5de6\u96a3\u306b\u3042\u308b\u4e09\u89d2\u5f62\u3092\u30af\u30ea\u30c3\u30af\u3057\u3001\u300c<strong>\u30bd\u30fc\u30c8\u2026<\/strong>\u300d\u3092\u9078\u629e\u3057\u305f\u306e\u3061\u3001\u300c<strong>\u6570\u5b57<\/strong>\u300d\u3092\u9078\u629e\u3059\u308b\u3053\u3068\u3067\u5b9f\u65bd\u3067\u304d\u307e\u3059\u3002OpenRefine\u3067\u306f\u3001\u4e26\u3073\u66ff\u3048\u3092\u6c38\u7d9a\u7684\u306b\u4fdd\u5b58\u3057\u306a\u3044\u9650\u308a\u3001\u4e26\u3073\u66ff\u3048\u306f\u898b\u3084\u3059\u304f\u3059\u308b\u305f\u3081\u306e\u3082\u306e\u3067\u3057\u304b\u3042\u308a\u307e\u305b\u3093\u3002\u3053\u308c\u3092\u884c\u3046\u306b\u306f\u3001\u4e0a\u90e8\u306b\u73fe\u308c\u305f\u300c<strong>\u30bd\u30fc\u30c8<\/strong>\u300d\u30e1\u30cb\u30e5\u30fc\u3092\u30af\u30ea\u30c3\u30af\u3057\u3001\u300c<strong>\u884c\u3092\u6c38\u7d9a\u7684\u306b\u4e26\u3073\u66ff\u3048\u308b<\/strong>\u300d\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u3053\u308c\u3092\u5fd8\u308c\u308b\u3068\u3001\u672c\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u5f8c\u534a\u3067\u4e88\u671f\u3057\u306a\u304b\u3063\u305f\u7d50\u679c\u306b\u306a\u3063\u3066\u3057\u307e\u3046\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<p>\u3053\u308c\u3067\u540c\u3058\u884c\u304c\u96a3\u63a5\u3059\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002\u6b21\u306b\u3001\u4e0a\u306e\u884c\u3068\u540c\u3058\u30ec\u30b3\u30fc\u30c9ID\u3092\u3082\u3064\u884c\u306e\u30ec\u30b3\u30fc\u30c9ID\u3092\u7a7a\u767d\u306b\u3057\u3066\u3001\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3068\u3057\u3066\u30de\u30fc\u30af\u3057\u307e\u3059\u3002\u305d\u306e\u305f\u3081\u306b\u3001\u30ec\u30b3\u30fc\u30c9ID\u306e\u4e09\u89d2\u5f62\u3092\u30af\u30ea\u30c3\u30af\u3057\u3001\u300c<strong>\u30bb\u30eb\u7de8\u96c6<\/strong> &gt;<strong>\u4e0b\u65b9\u5411\u306b\u7a7a\u767d\u306b\u3059\u308b<\/strong>\u300d&nbsp;\u3068\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u30b9\u30c6\u30fc\u30bf\u30b9\u30e1\u30c3\u30bb\u30fc\u30b8\u306b\u306f\u300184\u5217\u304c\u7de8\u96c6\u3055\u308c\u305f\u3053\u3068\u304c\u8868\u793a\u3055\u308c\u307e\u3059\uff08\u884c\u306e\u4e26\u3073\u66ff\u3048\u3092\u6052\u4e45\u5316\u3059\u308b\u3053\u3068\u3092\u5fd8\u308c\u305f\u5834\u5408\u306f19\u884c\u3057\u304b\u8868\u793a\u3055\u308c\u307e\u305b\u3093\u3002\u305d\u306e\u5834\u5408\u306f\u300c<strong>\u53d6\u308a\u6d88\u3059\uff0f\u3084\u308a\u76f4\u3059<\/strong>\u300d\u30bf\u30d6\u3067\u30d6\u30e9\u30f3\u30af\u30c0\u30a6\u30f3\u306e\u64cd\u4f5c\u3092\u5143\u306b\u623b\u3057\u3001\u524d\u306e\u6bb5\u843d\u3078\u623b\u3063\u3066\u3001\u884c\u304c\u4e26\u3079\u66ff\u3048\u3089\u308c\u305f\u3060\u3051\u3067\u306f\u306a\u3044\u3053\u3068\u3092\u78ba\u8a8d\u3057\u3066\u304f\u3060\u3055\u3044\uff09\u3002\u30ec\u30b3\u30fc\u30c9ID\u5217\u3067\u300c<strong>\u7a7a\u767d\u30bb\u30eb<\/strong>\u300d\u306e\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u4f5c\u6210\u3057\uff08\u300c\u30d5\u30a1\u30bb\u30c3\u30c8 &gt; \u30ab\u30b9\u30bf\u30e0\u30d5\u30a1\u30bb\u30c3\u30c8 &gt; \u7a7a\u767d\u30d5\u30a1\u30bb\u30c3\u30c8\uff08null\/\u7a7a\uff09\uff09\u3001\u300c<strong>true<\/strong>\u300d\u3092\u30af\u30ea\u30c3\u30af\u3059\u308b\u3053\u3068\u306784\u884c\u306e\u7a7a\u767d\u884c\u3092\u9078\u629e\u3057\u3001\u300c<strong>\u5168\u3066<\/strong>\u300d\u306e\u4e09\u89d2\u5f62\u3092\u62bc\u3057\u3066\u3053\u308c\u3089\u306e\u884c\u3092\u524a\u9664\u3057\u3066\u304f\u3060\u3055\u3044\uff08<strong>\u884c\u3092\u7de8\u96c6\u3000&gt; \u30de\u30c3\u30c1\u3057\u305f\u884c\u3092\u524a\u9664<\/strong>\uff09\u3002\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9589\u3058\u308b\u3068\u300175,727\u884c\u306e\u30e6\u30cb\u30fc\u30af\u884c\u3092\u78ba\u8a8d\u3067\u304d\u308b\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<p>\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3092\u524a\u9664\u3059\u308b\u3068\u304d\u306f\u7279\u306b\u6ce8\u610f\u304c\u5fc5\u8981\u3067\u3059\u3002\u4e0a\u8a18\u306e\u30b9\u30c6\u30c3\u30d7\u3067\u306f\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u30e6\u30cb\u30fc\u30af\u306a\u5024\u3092\u6301\u3064\u30d5\u30a3\u30fc\u30eb\u30c9\u304c\u3042\u308b\u3068\u4eee\u5b9a\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u3053\u308c\u306f\u884c\u5168\u4f53\u304c\u91cd\u8907\u3057\u3066\u3044\u308b\u3053\u3068\u3092\u524d\u63d0\u306b\u3057\u3066\u3044\u307e\u3059\u3002\u3053\u308c\u306f\u5fc5\u305a\u3057\u3082\u305d\u3046\u3068\u306f\u9650\u3089\u306a\u3044\u306e\u3067\u3001\u6df1\u304f\u6ce8\u610f\u3092\u6255\u3044\u3064\u3064\u3001\u884c\u5168\u4f53\u304c\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3067\u3042\u308b\u304b\u3069\u3046\u304b\u3092\u624b\u52d5\u3067\u78ba\u8a8d\u3059\u3079\u304d\u3067\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"atomization\">\u500b\u5225\u5316\uff08Atomization\uff09<\/h3>\n\n\n\n<p>\u91cd\u8907\u30ec\u30b3\u30fc\u30c9\u3092\u524a\u9664\u3057\u305f\u306e\u3067\u3001<em>Categories<\/em>\u306e\u30d5\u30a3\u30fc\u30eb\u30c9\u3092\u8a73\u3057\u304f\u898b\u3066\u3044\u304f\u3053\u3068\u304c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002 \u5e73\u5747\u3057\u3066\u3001\u5404\u8cc7\u6599\u306b\u306f2.25\u500b\u306e\u30ab\u30c6\u30b4\u30ea\u30fc\u304c\u7d10\u3065\u3044\u3066\u3044\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u30ab\u30c6\u30b4\u30ea\u30fc\u306f\u3001\u30d1\u30a4\u30d7\u6587\u5b57\u300c|\u300d\u3067\u533a\u5207\u3089\u308c\u305f\u3001\u540c\u3058\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306b\u542b\u307e\u308c\u3066\u3044\u307e\u3059\u3002\u4f8b\u3048\u3070Record 9\u306b\u306f\u3001\u300cMineral samples|Specimens|Mineral Samples-Geological\u300d\u3068\u3044\u30463\u3064\u306e\u5024\u304c\u542b\u307e\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u30ad\u30fc\u30ef\u30fc\u30c9\u306e\u4f7f\u7528\u3092\u8a73\u7d30\u306b\u5206\u6790\u3059\u308b\u305f\u3081\u306b\u306f\u3001Categories\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306e\u5024\u3092\u3001\u30d1\u30a4\u30d7\u306e\u4f4d\u7f6e\u3067\u500b\u5225\u306e\u30bb\u30eb\u306b\u5206\u5272\u3057\u3066\u3044\u304f\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u300175,727\u500b\u3042\u308b\u30ec\u30b3\u30fc\u30c9\u306f170,167\u884c\u306b\u62e1\u5927\u3057\u307e\u3059\u3002\uff08Categories\u306b\u3042\u308b\u4e09\u89d2\u5f62\u304b\u3089\uff09\u300c<strong>\u30bb\u30eb\u7de8\u96c6\uff1e\u591a\u5024\u306e\u30bb\u30eb\u3092\u5206\u5272<\/strong>\u300d\u3092\u9078\u629e\u3057\u3001\uff08\u300c\u6587\u5b57\u3067\u5206\u5272\u300d\u306e\uff09\u300c\u533a\u5207\u308a\u6587\u5b57\u300d\u306b\u300c<strong>|<\/strong>\u300d\u3092\u5165\u529b\u3057\u307e\u3059\u3002\u3053\u308c\u3067170,167\u884c\u3068\u306a\u3063\u305f\u3053\u3068\u304cOpenRefine\u304b\u3089\u901a\u77e5\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n<p>\u884c\/\u30ec\u30b3\u30fc\u30c9\u306e\u30d1\u30e9\u30c0\u30a4\u30e0\u3092\u3088\u304f\u7406\u89e3\u3057\u3066\u304a\u304f\u3053\u3068\u306f\u91cd\u8981\u3067\u3059\u3002\u30ec\u30b3\u30fc\u30c9ID\u5217\u3092\u8868\u793a\u3055\u305b\u3001\u4f55\u304c\u8d77\u304d\u3066\u3044\u308b\u304b\u3092\u898b\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u5217\u306e\u30d8\u30c3\u30c0\u30fc\u306e\u4e0a\u306b\u3042\u308b\u30e9\u30d9\u30eb\u306e\u30ea\u30f3\u30af\u3092\u30af\u30ea\u30c3\u30af\u3059\u308b\u3053\u3068\u3067\u3001\u300c\u884c\u300d\u3068\u300c\u30ec\u30b3\u30fc\u30c9\u300d\u306e\u8868\u793a\u3092\u5207\u308a\u66ff\u3048\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u300c\u884c\u30d3\u30e5\u30fc\u300d\u3067\u306f\u3001\u5404\u884c\u304c2\uff5e3\u306e\u30ec\u30b3\u30fc\u30c9ID\u304c\u30011\u3064\u306e\u30ab\u30c6\u30b4\u30ea\u30fc\u3092\u8868\u3057\u3066\u304a\u308a\u3001\u305d\u308c\u305e\u308c\u3092\u500b\u5225\u306b\u64cd\u4f5c\u3067\u304d\u307e\u3059\u3002\u300c\u30ec\u30b3\u30fc\u30c9\u30d3\u30e5\u30fc\u300d\u306b\u306f\u30ec\u30b3\u30fc\u30c9ID\u3054\u3068\u306b\u30a8\u30f3\u30c8\u30ea\u30fc\u304c\u3042\u308a\u3001\u884c\u3054\u3068\u306b\u7570\u306a\u308b\u30ab\u30c6\u30b4\u30ea\u30fc\uff08\u30b0\u30ec\u30fc\u307e\u305f\u306f\u767d\u3067\u30b0\u30eb\u30fc\u30d7\u5316\uff09\u3092\u6301\u3064\u3053\u3068\u304c\u51fa\u6765\u307e\u3059\u304c\u3001\u5404\u30ec\u30b3\u30fc\u30c9\u306f\u5168\u4f53\u3068\u3057\u3066\u64cd\u4f5c\u3055\u308c\u307e\u3059\u3002\u5177\u4f53\u7684\u306b\u306f\u3001\u73fe\u5728170,167\u500b\u306e\u30ab\u30c6\u30b4\u30ea\u30fc\u306e\u5272\u308a\u5f53\u3066\uff08\u884c\uff09\u304c\u3042\u308a\u300175,736\u500b\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u30a2\u30a4\u30c6\u30e0\uff08\u30ec\u30b3\u30fc\u30c9\uff09\u306b\u307e\u305f\u304c\u3063\u3066\u3044\u307e\u3059\u3002\u5143\u306e75,727\u4ef6\u306e\u30ec\u30b3\u30fc\u30c9\u3068\u6bd4\u30799\u4ef6\u5897\u3048\u3066\u3044\u308b\u3053\u3068\u306b\u6c17\u304c\u4ed8\u3044\u305f\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u304c\u3001\u3053\u306e\u5c0f\u3055\u306a\u9055\u3044\u306b\u3064\u3044\u3066\u306f\u5f8c\u3067\u89e6\u308c\u308b\u306e\u3067\u3001\u4eca\u306f\u6c17\u306b\u3057\u306a\u3044\u3067\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"facetting-and-clustering\">\u30d5\u30a1\u30bb\u30c3\u30c8\u3068\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0<\/h3>\n\n\n\n<p>\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306e\u5185\u5bb9\u3092\u9069\u5207\u306b\u500b\u5225\u5316\u3059\u308b\u3068\u3001\u30d5\u30a3\u30eb\u30bf\u30fc\u3084\u30d5\u30a1\u30bb\u30c3\u30c8\u3001\u30af\u30e9\u30b9\u30bf\u30fc\u3092\u5229\u7528\u3057\u3066\u3001\u30e1\u30bf\u30c7\u30fc\u30bf\u306e\u53e4\u5178\u7684\u306a\u554f\u984c\u3092\u8fc5\u901f\u304b\u3064\u7c21\u5358\u306b\u6982\u89b3\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\uff08Categories\u306e\u4e09\u89d2\u5f62\u304b\u3089\uff09\u300c<strong>\u30ab\u30b9\u30bf\u30e0\u30d5\u30a1\u30bb\u30c3\u30c8<\/strong>\uff1e<strong>\u7a7a\u767d\u30d5\u30a1\u30bb\u30c3\u30c8<\/strong>\u300d\u3092\u9069\u7528\u3059\u308b\u3053\u3068\u3067\u3001461\u4ef6\u306e\u30ec\u30b3\u30fc\u30c9\u306b\u306f\u30ab\u30c6\u30b4\u30ea\u30fc\u304c\u5272\u308a\u5f53\u3066\u3089\u308c\u3066\u304a\u3089\u305a\u3001\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e0.6%\u3092\u5360\u3081\u3066\u3044\u308b\u3053\u3068\u304c\u3059\u3050\u306b\u5206\u304b\u308b\u3067\u3057\u3087\u3046\u3002\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u30c6\u30ad\u30b9\u30c8\u578b\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9069\u7528\u3059\u308b\u3068\u3001\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306b\u7528\u3044\u3089\u308c\u3066\u3044\u308b4,934\u500b\u306e\u7570\u306a\u308b\u30ab\u30c6\u30b4\u30ea\u30fc\u306e\u6982\u8981\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\uff08\u30c7\u30d5\u30a9\u30eb\u30c8\u306e\u30ea\u30df\u30c3\u30c8\u306f2,000\u500b\u306a\u306e\u3067\u3001\u300c<strong>\u30ab\u30a6\u30f3\u30bf\u3092\u5236\u9650\u3057\u3066\u304f\u3060\u3055\u3044<\/strong>\u300d\u3092\u30af\u30ea\u30c3\u30af\u3057\u30665,000\u307e\u3067\u4e0a\u3052\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\uff09\u3002\u898b\u51fa\u3057\u306f\u30a2\u30eb\u30d5\u30a1\u30d9\u30c3\u30c8\u9806\u307e\u305f\u306f\u30ab\u30a6\u30f3\u30c8\uff08\u983b\u5ea6\uff09\u9806\u306b\u4e26\u3073\u5909\u3048\u3001\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e\u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u5316\u3092\u884c\u3046\u305f\u3081\u306b\u6700\u3082\u983b\u7e41\u306b\u4f7f\u308f\u308c\u3066\u3044\u308b\u7528\u8a9e\u306e\u4e00\u89a7\u3092\u5f97\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\uff08\u30ab\u30a6\u30f3\u30c8\u9806\u306b\u4e26\u3079\u305f\u5834\u5408\uff09\u898b\u51fa\u3057\u306e\u4e0a\u4f4d3\u3064\u306f\u300cNumismatics\u300d\uff088,041\uff09\u3001\u300cCeramics\u300d\uff087,390\uff09\u3001\u300cClothing and dress\u300d\uff087,279\uff09\u3067\u3059\u3002<\/p>\n\n\n\n<p>\u30d5\u30a1\u30bb\u30c3\u30c8\u3092\u9069\u7528\u3059\u308b\u3068\u3001OpenRefine\u306f\u69d8\u3005\u306a\u985e\u4f3c\u6027\u306b\u3088\u3063\u3066\u30d5\u30a1\u30bb\u30c3\u30c8\u306e\u9078\u629e\u80a2\u3092\u30af\u30e9\u30b9\u30bf\u30fc\u3068\u3057\u3066\u307e\u3068\u3081\u308b\u3053\u3068\u3092\u63d0\u6848\u3057\u3066\u304d\u307e\u3059\uff3b\u8a33\u6ce8\uff1aCategories\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30bb\u30c3\u30c8\u306b\u300c\u30af\u30e9\u30b9\u30bf\u300d\u3068\u8868\u793a\u3055\u308c\u305f\u30dc\u30bf\u30f3\u304c\u767b\u5834\u3059\u308b\u306e\u3067\u3001\u305d\u308c\u3092\u30af\u30ea\u30c3\u30af\u3059\u308b\uff3d\u3002\u56f32\u304c\u793a\u3057\u3066\u3044\u308b\u3088\u3046\u306b\u3001\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u306b\u3088\u308a\u5927\u6587\u5b57\u5c0f\u6587\u5b57\u306e\u4e0d\u4e00\u81f4\u3084\u5358\u6570\u5f62\u3068\u8907\u6570\u5f62\u306e\u3070\u3089\u3070\u3089\u306a\u4f7f\u3044\u65b9\u3001\u5358\u7d14\u306a\u30b9\u30da\u30eb\u30df\u30b9\u306a\u3069\u306e\u554f\u984c\u306b\u5bfe\u5fdc\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002OpenRefine\u306f\u95a2\u9023\u3059\u308b\u5024\u3092\u8868\u793a\u3057\u3001\u6700\u3082\u983b\u5ea6\u306e\u9ad8\u3044\u5024\u3078\u3068\u30de\u30fc\u30b8\u3059\u308b\u3088\u3046\u306b\u63d0\u6848\u3057\u3066\u304f\u308c\u307e\u3059\u3002\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3057\u305f\u3044\u5024\u306e\u30dc\u30c3\u30af\u30b9\u3092\u500b\u5225\u306b\u9078\u629e\u3059\u308b\u304b\u3001\u6700\u4e0b\u90e8\u306e\u300c\u5168\u9078\u629e\u300d\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u9078\u629e\u3057\u3001\u300c<strong>\u30de\u30fc\u30b8\u3057\u518d\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0<\/strong>\u300d\u3092\u9078\u629e\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/programminghistorian.org\/images\/cleaning-data-with-openrefine\/overviewOfSomeClusters.png\" alt=\"Figure 2 : Overview of some clusters\"\/><figcaption> \u56f32 : \u30af\u30e9\u30b9\u30bf\u30fc\u306e\u6982\u89b3 <\/figcaption><\/figure>\n\n\n\n<p>\u30c7\u30d5\u30a9\u30eb\u30c8\u306e\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u65b9\u6cd5\u306f\u3042\u307e\u308a\u8907\u96d1\u3067\u306f\u306a\u3044\u305f\u3081\u3001\u5168\u3066\u306e\u30af\u30e9\u30b9\u30bf\u30fc\u3092\u898b\u3064\u3051\u5207\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u69d8\u3005\u306a\u65b9\u6cd5\u3092\u8a66\u3057\u3066\u307f\u3066\u3001\u3069\u306e\u3088\u3046\u306a\u7d50\u679c\u304c\u5f97\u3089\u308c\u308b\u304b\u78ba\u8a8d\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u305f\u3060\u3057\u3001\u65b9\u6cd5\u306e\u4e2d\u306b\u306f\u30a2\u30b0\u30ec\u30c3\u30b7\u30d6\u3059\u304e\u308b\u3082\u306e\u3082\u3042\u308b\u305f\u3081\u3001\u4e00\u7dd2\u306b\u5c5e\u3057\u3066\u3044\u306a\u3044\u5024\u3092\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3057\u3066\u3057\u307e\u3046\u304b\u3082\u3057\u308c\u306a\u3044\u306e\u3067\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u5024\u304c\u500b\u5225\u306b\u30af\u30e9\u30b9\u30bf\u30ea\u30f3\u30b0\u3055\u308c\u305f\u306e\u3067\u3001\u305d\u308c\u3089\u3092\u4e00\u3064\u306e\u30bb\u30eb\u306b\u623b\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002Categories\u306e\u4e09\u89d2\u5f62\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u300c<strong>\u30bb\u30eb\u7de8\u96c6\uff1e\u591a\u5024\u306e\u30bb\u30eb\u3092\u7d50\u5408<\/strong>\u300d\u3068\u9078\u629e\u3057\u3066OK\u3068\u62bc\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u533a\u5207\u308a\u306b\u306f\u30d1\u30a4\u30d7\u6587\u5b57\uff08|\uff09\u3092\u9078\u629e\u3057\u307e\u3059\u3002\u3053\u308c\u3067\u884c\u306f\u4ee5\u524d\u306e\u3088\u3046\u306b\u306a\u308a\u3001Categories\u30d5\u30a3\u30fc\u30eb\u30c9\u306b\u8907\u6570\u306e\u5024\u304c\u542b\u307e\u308c\u3066\u3044\u308b\u3053\u3068\u3067\u3057\u3087\u3046\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"applying-ad-hoc-transformations-through-the-use-of-regular-expressions\">\u6b63\u898f\u8868\u73fe\u3092\u5229\u7528\u3057\u305f\u30a2\u30c9\u30db\u30c3\u30af\u306a\u5909\u63db<\/h3>\n\n\n\n<p>\u5206\u5272\u51e6\u7406\u306e\u5f8c\u306b\u30ec\u30b3\u30fc\u30c9\u306e\u6570\u304c\u5897\u3048\u305f\u3053\u3068\u3092\u899a\u3048\u3066\u3044\u308b\u3067\u3057\u3087\u3046\u304b\u3002\u3069\u3053\u304b\u3089\u3068\u3082\u306a\u304f\u30ec\u30b3\u30fc\u30c9\u304c9\u3064\u73fe\u308c\u307e\u3057\u305f\u3002\u3053\u306e\u5dee\u7570\u306e\u539f\u56e0\u3092\u898b\u3064\u3051\u308b\u305f\u3081\u306b\u306f\u3001\u6642\u9593\u3092\u5dfb\u304d\u623b\u3057\u3066\u30ab\u30c6\u30b4\u30ea\u30fc\u3092\u5225\u3005\u306e\u884c\u3078\u3068\u5206\u5272\u3059\u308b\u524d\u307e\u3067\u9061\u3089\u306a\u304f\u3066\u306f\u3044\u3051\u307e\u305b\u3093\u3002\u305d\u306e\u305f\u3081\u306b\u3001\uff08\u753b\u9762\u5de6\u4e0a\u90e8\u306b\u3042\u308b\uff09<strong>\u300c\u30d5\u30a1\u30bb\u30c3\u30c8\uff0f\u30d5\u30a3\u30eb\u30bf\u30fc\u300d<\/strong>\u30bf\u30d6\u306e\u53f3\u96a3\u306b\u3042\u308b\u300c<strong>\u53d6\u308a\u6d88\u3059\uff0f\u3084\u308a\u76f4\u3059<\/strong>\u300d\u30bf\u30d6\u3092\u62bc\u3059\u3068\u3001\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u4f5c\u6210\u3057\u3066\u4ee5\u6765\u3042\u306a\u305f\u304c\u884c\u3063\u3066\u304d\u305f\u64cd\u4f5c\u5c65\u6b74\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002\u300cSplit multi-valued cells in column Categories\u300d\u3088\u308a\u76f4\u524d\u306e\u30b9\u30c6\u30c3\u30d7\u3092\u9078\u629e\u3057\uff08\u7b46\u8005\u306e\u4f8b\u306b\u5f93\u3063\u3066\u304d\u305f\u306e\u3067\u3042\u308c\u3070\u3001\u300cRemove 84 rows\u300d\u306e\u306f\u305a\u3067\u3059\uff09\u3001<strong>\u300c\u30d5\u30a1\u30bb\u30c3\u30c8\uff0f\u30d5\u30a3\u30eb\u30bf\u30fc\u300d<\/strong>\u30bf\u30d6\u306b\u623b\u3063\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<p>\u3053\u306e\u554f\u984c\u306f\u30d1\u30a4\u30d7\u6587\u5b57\u306e\u5206\u5272\u51e6\u7406\u4e2d\u306b\u767a\u751f\u3057\u305f\u306e\u3067\u3001\u3053\u3053\u3067\u8d77\u304d\u305f\u554f\u984c\u306f\u3053\u306e\u6587\u5b57\u3068\u95a2\u9023\u3057\u3066\u3044\u308b\u306e\u3067\u306f\u306a\u3044\u3067\u3057\u3087\u3046\u304b\u3002Categories\u30ab\u30e9\u30e0\u306b\u5bfe\u3057\u3066\u3001\u30e1\u30cb\u30e5\u30fc\u304b\u3089\u300c<strong>\u30c6\u30ad\u30b9\u30c8\u30d5\u30a3\u30eb\u30bf\u30fc<\/strong>\u300d\u3092\u9078\u629e\u3057\u9069\u7528\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u307e\u305a\u306f\u5de6\u306e\u30d5\u30a3\u30fc\u30eb\u30c9\u306b|\u3068\u5165\u529b\u3057\u3066\u304f\u3060\u3055\u3044\u300275,727\u4ef6\u3042\u308b\u30ec\u30b3\u30fc\u30c9\u306e\u3046\u3061\u300171,064\u4ef6\u304c\u4e00\u81f4\uff08\u3064\u307e\u308a\u3001\u30d1\u30a4\u30d7\u6587\u5b57\u3092\u542b\u3080\u30ec\u30b3\u30fc\u30c9\uff09\u3057\u3066\u3044\u308b\u3053\u3068\u3092<em>OpenRefine<\/em>\u304c\u6559\u3048\u3066\u304f\u308c\u308b\u3067\u3057\u3087\u3046\u3002\u30d1\u30a4\u30d7\u6587\u5b57\u3092\u542b\u307e\u306a\u3044\u30bb\u30eb\u306f\u3001\u7a7a\u767d\u30bb\u30eb\u304b\u3001\u30ec\u30b3\u30fc\u30c9#29\u306e\u3088\u3046\u306b\u300cScientific instruments\u300d\u3057\u304b\u542b\u3093\u3067\u3044\u306a\u3044\u3088\u3046\u306a\u3001\u533a\u5207\u308a\u304c\u306a\u304f\u30ab\u30c6\u30b4\u30ea\u30fc\u304c1\u3064\u3057\u304b\u306a\u3044\u30bb\u30eb\u306a\u306e\u3067\u3059\u3002<\/p>\n\n\n\n<p>\u6700\u521d\u306b\u5165\u529b\u3057\u305f\u30d1\u30a4\u30d7\u6587\u5b57\u306b\u7d9a\u304d|\u3092\u5165\u529b\u3057\u3001||\uff08\u30c0\u30d6\u30eb\u30d1\u30a4\u30d7\uff09\u306b\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u3053\u306e\u30d1\u30bf\u30fc\u30f3\u306b\u4e00\u81f4\u3059\u308b\u30ec\u30b3\u30fc\u30c9\u304c9\u4ef6\u3042\u308b\u3053\u3068\u304c\u5206\u304b\u308b\u3067\u3057\u3087\u3046\u3002\u3053\u306e9\u4ef6\u306e\u30ec\u30b3\u30fc\u30c9\u304c\u4e0d\u4e00\u81f4\u306e\u539f\u56e0\u306a\u306e\u3067\u306f\u306a\u3044\u3067\u3057\u3087\u3046\u304b\u3002<em>OpenRefine<\/em>\u304c\u3053\u308c\u3089\u306e\u30ec\u30b3\u30fc\u30c9\u3092\u5206\u5272\u3057\u305f\u969b\u3001\u30c0\u30d6\u30eb\u30d1\u30a4\u30d7\u3092\u610f\u5473\u306e\u306a\u3044\u30c0\u30d6\u30eb\u533a\u5207\u308a\u3067\u306f\u306a\u304f2\u4ef6\u306e\u30ec\u30b3\u30fc\u30c9\u306e\u9593\u306b\u304a\u3051\u308b\u533a\u5207\u308a\u3068\u3057\u3066\u89e3\u91c8\u3057\u3066\u3057\u307e\u3063\u305f\u306e\u3067\u3057\u3087\u3046\u3002\u3053\u308c\u3089\u306e\u5024\u306f\u3069\u306e\u3088\u3046\u306b\u4fee\u6b63\u3059\u308c\u3070\u3088\u3044\u3067\u3057\u3087\u3046\u304b\uff1f\u300cCategories\u300d\u30d5\u30a3\u30fc\u30eb\u30c9\u306e\u30e1\u30cb\u30e5\u30fc\u304b\u3089<strong>\u300c\u30bb\u30eb\u7de8\u96c6 &gt; \u5909\u63db\u2026\u300d<\/strong>\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u30ab\u30b9\u30bf\u30e0\u30c6\u30ad\u30b9\u30c8\u306b\u3088\u308b\u5909\u63db\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\uff08\u8a33\u6ce8\uff1a<strong>\u300c\u5f0f\u306b\u3088\u308b\u5024\u306e\u5909\u63db\u300d<\/strong>\uff09\u3078\u3088\u3046\u3053\u305d\u3002\u3053\u308c\u306f\u3001<em>OpenRefine<\/em>&nbsp;&nbsp;Expression Language\uff08GREL\uff09\u3092\u4f7f\u3063\u305f<em>OpenRefine<\/em>\u306e\u5f37\u529b\u306a\u6a5f\u80fd\u3067\u3059\u3002<\/p>\n\n\n\n<p>\u4ee5\u4e0b\u306b\u898b\u3048\u308b\u901a\u308a\u3001\u30c6\u30ad\u30b9\u30c8\u30d5\u30a3\u30fc\u30eb\u30c9\u5185\u306e\u201dvalue\u201d\u3068\u3044\u3046\u5358\u8a9e\u306f\u3001\u5404\u30bb\u30eb\u306e\u73fe\u5728\u306e\u5024\u3092\u8868\u3057\u3066\u3044\u307e\u3059\u3002\u3053\u306e\u5024\u306b\u95a2\u6570\u3092\u9069\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u5024\u3092\u4fee\u6b63\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\uff08\u6a5f\u80fd\u4e00\u89a7\u306f<a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/OpenRefine\/OpenRefine\/wiki\/GREL-Functions\" target=\"_blank\">GREL\u30c9\u30ad\u30e5\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\uff08\u82f1\u8a9e\uff09<\/a>\u3092\u53c2\u7167\u3057\u3066\u304f\u3060\u3055\u3044\uff09\u3002\u3053\u3053\u3067\u306f\u3001\u30c0\u30d6\u30eb\u30d1\u30a4\u30d7\u3092\u30b7\u30f3\u30b0\u30eb\u30d1\u30a4\u30d7\u306b\u7f6e\u63db\u3057\u305f\u3044\u306e\u3067\u3059\u3002\u3053\u308c\u306f\u4ee5\u4e0b\u306e<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Regular_expression\" target=\"_blank\">\u6b63\u898f\u8868\u73fe<\/a>\u3092\u4f7f\u3048\u3070\u5b9f\u73fe\u3067\u304d\u307e\u3059\uff08\u5f15\u7528\u7b26\u3092\u5fd8\u308c\u306a\u3044\u3067\u304f\u3060\u3055\u3044\uff09\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>value.replace('||', '|')\n<\/code><\/pre>\n\n\n\n<p>\u300cExpression\u300d\u30c6\u30ad\u30b9\u30c8\u30d5\u30a3\u30fc\u30eb\u30c9\u306e\u4e0b\u3067\u3001\u30c0\u30d6\u30eb\u30d1\u30a4\u30d7\u3092\u524a\u9664\u3057\u3066\u4fee\u6b63\u3057\u305f\u5024\u306e\u30d7\u30ec\u30d3\u30e5\u30fc\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<strong>OK<\/strong>\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u304b\u3089\u3001\uff08Categories\u306e\uff09\u300c<strong>\u30bb\u30eb\u7de8\u96c6 &gt; \u591a\u5024\u306e\u30bb\u30eb\u3092\u5206\u5272<\/strong>\u2026\u300d\u304b\u3089\u30ab\u30c6\u30b4\u30ea\u30fc\u3092\u5206\u5272\u3057\u3066\u307f\u308b\u3068\u3001\u4eca\u5ea6\u306f\u30ec\u30b3\u30fc\u30c9\u306e\u6570\u304c75,727\u306e\u307e\u307e\u306b\u306a\u3063\u3066\u3044\u308b\u3067\u3057\u3087\u3046\uff08\u518d\u78ba\u8a8d\u3059\u308b\u305f\u3081\u306b\u3001\u300c<strong>\u30ec\u30b3\u30fc\u30c9\u30d3\u30e5\u30fc<\/strong>\u300d\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\uff09\u3002<\/p>\n\n\n\n<p>* * *GREL\u3067\u89e3\u6c7a\u3067\u304d\u308b\u3082\u30461\u3064\u306e\u554f\u984c\u304c\u3001\u540c\u3058\u30ab\u30c6\u30b4\u30ea\u30fc\u304c2\u56de\u8a18\u8ff0\u3055\u308c\u3066\u3044\u308b\u30ec\u30b3\u30fc\u30c9\u306e\u554f\u984c\u3067\u3059\u3002\u4f8b\u3048\u3070\u30ec\u30b3\u30fc\u30c9#41\u3092\u898b\u308b\u3068\u3001\u300cModels|Botanical specimens|Botanical Specimens|Didactic Displays|Models\u300d\u3068\u3044\u3063\u305f\u30ab\u30c6\u30b4\u30ea\u30fc\u304c\u3042\u308a\u307e\u3059\u3002\u300cModels\u300d\u30ab\u30c6\u30b4\u30ea\u30fc\u306f\u7279\u306b\u7406\u7531\u3082\u306a\u304f2\u56de\u8a18\u8ff0\u3055\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u91cd\u8907\u3057\u3066\u3044\u308b\u5206\u3092\u524a\u9664\u3057\u305f\u3044\u3068\u3053\u308d\u3067\u3059\u3002Categories\u306e\u25bd\u3092\u30af\u30ea\u30c3\u30af\u3057\u3001\u300c<strong>\u30bb\u30eb\u7de8\u96c6\u3000\uff1e\u591a\u5024\u306e\u30bb\u30eb\u3092\u7d50\u5408\u2026<\/strong>\u300d\u3092\u9078\u629e\u3057\u3001OK\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u533a\u5207\u308a\u306b\u306f\u30d1\u30a4\u30d7\u6587\u5b57\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u3053\u308c\u3067\u5148\u307b\u3069\u3068\u540c\u3058\u3088\u3046\u306b\u30ab\u30c6\u30b4\u30ea\u30fc\u304c\u4e00\u89a7\u8868\u793a\u3055\u308c\u307e\u3057\u305f\u3002\u6b21\u306b\u3001Categories\u304b\u3089\u300c<strong>\u30bb\u30eb\u7de8\u96c6\u3000&gt; \u5909\u63db<\/strong>\u300d\u3068\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\u3002GREL\u3092\u4f7f\u3063\u3066\u30d1\u30a4\u30d7\u6587\u5b57\u3067\u30ab\u30c6\u30b4\u30ea\u30fc\u30921\u3064\u305a\u3064\u5206\u5272\u3057\u3001\u30e6\u30cb\u30fc\u30af\u306a\u30ab\u30c6\u30b4\u30ea\u30fc\u3092\u898b\u3064\u3051\u3066\u7d50\u5408\u3057\u306a\u304a\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u306e\u305f\u3081\u306b\u306f\u3001\u4ee5\u4e0b\u306e\u901a\u308a\u5165\u529b\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>value.split('|').uniques().join('|')\n<\/code><\/pre>\n\n\n\n<p>\u30bb\u30eb\u304c33,008\u500b\u3001\u3064\u307e\u308a\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u306e\u534a\u5206\u4ee5\u4e0a\u304c\u5f71\u97ff\u3092\u53d7\u3051\u305f\u3053\u3068\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"exporting-your-cleaned-data\">\u6574\u5f62\u6e08\u307f\u30c7\u30fc\u30bf\u306e\u51fa\u529b<\/h3>\n\n\n\n<p><em>OpenRefine<\/em>\u306b\u30c7\u30fc\u30bf\u3092\u6700\u521d\u306b\u30ed\u30fc\u30c9\u3057\u3066\u4ee5\u6765\u3001\u5168\u3066\u306e\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u64cd\u4f5c\u306f\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u306e\u30e1\u30e2\u30ea\u5185\u3067\u5b9f\u884c\u3055\u308c\u3001\u5143\u306e\u30c7\u30fc\u30bf\u306f\u305d\u306e\u307e\u307e\u6b8b\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u6e08\u307f\u306e\u30c7\u30fc\u30bf\u3092\u4fdd\u5b58\u3057\u305f\u3044\u5834\u5408\u306f\u3001\u753b\u9762\u53f3\u4e0a\u306e\u300c<strong>\u51fa\u529b<\/strong>\u300d\u30e1\u30cb\u30e5\u30fc\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u51fa\u529b\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<em>OpenRefine<\/em>\u3067\u306f<a rel=\"noreferrer noopener\" href=\"http:\/\/en.wikipedia.org\/wiki\/Comma-separated_values\" target=\"_blank\">CSV<\/a>\u3084HTML\u3001Excel\u3068\u3044\u3063\u305f\u69d8\u3005\u306a\u30d5\u30a1\u30a4\u30eb\u5f62\u5f0f\u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u308b\u306e\u3067\u3001\u3042\u306a\u305f\u306e\u30cb\u30fc\u30ba\u306b\u5408\u3063\u305f\u5f62\u5f0f\u3092\u9078\u629e\u3059\u308b\u304b\u3001\u300c<strong>\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u2026<\/strong>\u300d\u3092\u30af\u30ea\u30c3\u30af\u3057\u3066\u72ec\u81ea\u306e\u30a8\u30af\u30b9\u30dd\u30fc\u30c8\u7528\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u3092\u8ffd\u52a0\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002\u307e\u305f\u3001\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u4ed6\u306e\u4eba\u3068\u5171\u6709\u3059\u308b\u305f\u3081\u306b\u3001\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092OpenRefine\u306e\u5185\u90e8\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3067\u51fa\u529b\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"building-on-top-of-your-cleaned-data\">\u6574\u5f62\u6e08\u307f\u30c7\u30fc\u30bf\u306e\u6b21\u306e\u30b9\u30c6\u30c3\u30d7<\/h3>\n\n\n\n<p>\u4e00\u65e6\u30c7\u30fc\u30bf\u304c\u304d\u308c\u3044\u306b\u306a\u3063\u305f\u3089\u3001\u6b21\u306e\u30b9\u30c6\u30c3\u30d7\u3078\u9032\u307f<em>OpenRefine<\/em>\u306e\u4ed6\u306e\u30a8\u30ad\u30b5\u30a4\u30c6\u30a3\u30f3\u30b0\u306a\u6a5f\u80fd\u3092\u63a2\u7d22\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002<em>OpenRefine<\/em>\u306e\u30e6\u30fc\u30b6\u30fc\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306f\u7279\u306b2\u3064\u306e\u8208\u5473\u6df1\u3044\u62e1\u5f35\u6a5f\u80fd\u3092\u958b\u767a\u3057\u307e\u3057\u305f\u3002\u305d\u308c\u306b\u3088\u3063\u3066\u65e2\u306bWeb\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u30c7\u30fc\u30bf\u3068\u3042\u306a\u305f\u306e\u30c7\u30fc\u30bf\u3092\u30ea\u30f3\u30af\u3055\u305b\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002<a rel=\"noreferrer noopener\" href=\"http:\/\/web.archive.org\/web\/20180113121435\/http:\/refine.deri.ie\/docs\" target=\"_blank\">RDF Refine\u62e1\u5f35\u6a5f\u80fd<\/a>\u306f\u30d7\u30ec\u30fc\u30f3\u30c6\u30ad\u30b9\u30c8\u306e\u30ad\u30fc\u30ef\u30fc\u30c9\u3092URL\u3078\u5909\u63db\u3057\u3066\u304f\u308c\u307e\u3059\u3002\u307e\u305f\u3001<a rel=\"noreferrer noopener\" href=\"https:\/\/github.com\/RubenVerborgh\/Refine-NER-Extension\" target=\"_blank\">NER\u62e1\u5f35\u6a5f\u80fd<\/a>\u306f\u56fa\u6709\u8868\u73fe\u62bd\u51fa\uff08NER\uff09\u3092\u9069\u7528\u3057\u3001\u30c6\u30ad\u30b9\u30c8\u304b\u3089\u30ad\u30fc\u30ef\u30fc\u30c9\u3092\u7279\u5b9a\u3057\u305d\u308c\u306bURL\u3092\u4e0e\u3048\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"conclusions\">\u7d42\u308f\u308a\u306b<\/h2>\n\n\n\n<p>\u672c\u30ec\u30c3\u30b9\u30f3\u3067\u899a\u3048\u3066\u304a\u304f\u3079\u304d\u3053\u3068\u304c\u3042\u308b\u3068\u3059\u308c\u3070\u3001\u305d\u308c\u306f\u6b21\u306e\u3053\u3068\u3067\u3059\u3002\u3059\u306a\u308f\u3061\u3001<em>\u5168\u3066\u306e\u30c7\u30fc\u30bf\u306f\u6c5a\u3044\u3082\u306e\u306e\u3001\u5bfe\u5fdc\u3059\u308b\u3053\u3068\u306f\u3067\u304d\u308b<\/em>\u3068\u3044\u3046\u3053\u3068\u3067\u3059\u3002\u3053\u3053\u3067\u793a\u3057\u305f\u3088\u3046\u306b\u3001\u30c7\u30fc\u30bf\u306e\u54c1\u8cea\u3092\u5927\u5e45\u306b\u4e0a\u3052\u308b\u305f\u3081\u306b\u3067\u304d\u308b\u3053\u3068\u306f\u591a\u3044\u306e\u3067\u3059\u3002\u307e\u305a\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u542b\u307e\u308c\u3066\u3044\u308b\u7a7a\u767d\u5024\u304c\u3044\u304f\u3064\u3042\u308a\u3001\u3042\u308b\u7279\u5b9a\u306e\u5024\uff08\u30ad\u30fc\u30ef\u30fc\u30c9\u306a\u3069\uff09\u304c\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u5168\u4f53\u3067\u3069\u306e\u304f\u3089\u3044\u306e\u983b\u5ea6\u3067\u4f7f\u7528\u3055\u308c\u3066\u3044\u308b\u304b\u3092\u7c21\u5358\u306b\u628a\u63e1\u3059\u308b\u65b9\u6cd5\u3092\u5b66\u3073\u307e\u3057\u305f\u3002\u3053\u306e\u30ec\u30c3\u30b9\u30f3\u3067\u306f\u3001OpenRefine\u3092\u5229\u7528\u3057\u3066\u91cd\u8907\u3084\u30b9\u30da\u30eb\u306e\u4e0d\u4e00\u81f4\u306a\u3069\u306e\u7e70\u308a\u8fd4\u3057\u767a\u751f\u3059\u308b\u554f\u984c\u3092\u81ea\u52d5\u3067\u89e3\u6c7a\u3059\u308b\u65b9\u6cd5\u3082\u7d39\u4ecb\u3057\u307e\u3057\u305f\u3002OpenRefine\u3067\u306f\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u30b3\u30d4\u30fc\u3067\u4f5c\u696d\u3092\u5b9f\u65bd\u3057\u3066\u3044\u308b\u3060\u3051\u3067\u306a\u304f\u3001\u30a8\u30e9\u30fc\u304c\u767a\u751f\u3057\u305f\u969b\u306b\u306f\u30b9\u30c6\u30c3\u30d7\u3092\u3055\u304b\u306e\u307c\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u306e\u3067\u3001\u305f\u3081\u3089\u3046\u3053\u3068\u306a\u304f\u8272\u3005\u3068\u30af\u30ea\u30fc\u30cb\u30f3\u30b0\u6a5f\u80fd\u3092\u8a66\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<h5 class=\"wp-block-heading\"><strong>\u8457\u8005\u306b\u3064\u3044\u3066<\/strong><\/h5>\n\n\n\n<p>Seth van Hooland\u6c0f\u306f\u30d6\u30ea\u30e5\u30c3\u30bb\u30eb\u81ea\u7531\u5927\u5b66\u306e\u60c5\u5831\u901a\u4fe1\u79d1\u5b66\u90e8\u306e\u51c6\u6559\u6388\u3067\u3059\u3002<br>Ruben Verborgh\u6c0f\u306f\u30b2\u30f3\u30c8\u5927\u5b66\u30de\u30eb\u30c1\u30e1\u30c7\u30a3\u30a2\u30e9\u30dc\u306b\u6240\u5c5e\u3059\u308b\u30dd\u30b9\u30c9\u30af\u7814\u7a76\u54e1\u3067\u3059\u3002<br>Max De Wilde\u6c0f\u306f\u30d6\u30ea\u30e5\u30c3\u30bb\u30eb\u81ea\u7531\u5927\u5b66\u60c5\u5831\u901a\u4fe1\u79d1\u5b66\u90e8\u306e\u535a\u58eb\u8ab2\u7a0b\u306e\u5b66\u751f\u3067\u3059\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<h5 class=\"wp-block-heading\">\u5f15\u7528\u306e\u969b\u306f\u3053\u3061\u3089\u3092\u3054\u5229\u7528\u304f\u3060\u3055\u3044<\/h5>\n\n\n\n<p>\uff1c\u539f\u8457\uff1e<br>Seth van Hooland, Ruben Verborgh, and Max De Wilde, &#8220;Cleaning Data with OpenRefine,&#8221;&nbsp;<em>The Programming Historian<\/em>&nbsp;2 (2013), <a href=\"https:\/\/programminghistorian.org\/en\/lessons\/cleaning-data-with-openrefine\">https:\/\/programminghistorian.org\/en\/lessons\/cleaning-data-with-openrefine<\/a>.<\/p>\n\n\n\n<p>\uff1c\u7ffb\u8a33\u8a18\u4e8b\uff1e<br>Seth van Hooland, Ruben Verborgh, and Max De Wildet\u8457. \u83ca\u6c60\u4fe1\u5f66\u8a33. OpenRefine\u3067\u30c7\u30fc\u30bf\u3092\u304d\u308c\u3044\u306b\u3059\u308b\u65b9\u6cd5. \u6771\u30a2\u30b8\u30a2DH\u30dd\u30fc\u30bf\u30eb. 2019. <a href=\"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/?p=468\">https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/?p=468<\/a>.<\/p>\n\n\n\n<a rel=\"license\" href=\"http:\/\/creativecommons.org\/licenses\/by\/4.0\/\"><img decoding=\"async\" alt=\"\u30af\u30ea\u30a8\u30a4\u30c6\u30a3\u30d6\u30fb\u30b3\u30e2\u30f3\u30ba\u30fb\u30e9\u30a4\u30bb\u30f3\u30b9\" style=\"border-width:0\" src=\"https:\/\/i.creativecommons.org\/l\/by\/4.0\/88x31.png\"><\/a><br>\u3053\u306e \u4f5c\u54c1 \u306f <a rel=\"license\" href=\"http:\/\/creativecommons.org\/licenses\/by\/4.0\/\">\u30af\u30ea\u30a8\u30a4\u30c6\u30a3\u30d6\u30fb\u30b3\u30e2\u30f3\u30ba \u8868\u793a 4.0 \u56fd\u969b \u30e9\u30a4\u30bb\u30f3\u30b9<\/a>\u306e\u4e0b\u306b\u63d0\u4f9b\u3055\u308c\u3066\u3044\u307e\u3059\u3002\n\n\n\n<div class=\"fb-comments\" data-href=\"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/?p=468\" data-numposts=\"5\" data-width=\"100%\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Seth van Hooland, Ruben Verborgh, Max De<\/p>\n","protected":false},"author":1,"featured_media":471,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[2],"tags":[17,16,14,12],"_links":{"self":[{"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/posts\/468"}],"collection":[{"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=468"}],"version-history":[{"count":19,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/posts\/468\/revisions"}],"predecessor-version":[{"id":785,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/posts\/468\/revisions\/785"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=\/wp\/v2\/media\/471"}],"wp:attachment":[{"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=468"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=468"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dh.ku-orcas.kansai-u.ac.jp\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}