{"id":27158,"date":"2026-01-02T09:00:39","date_gmt":"2026-01-02T00:00:39","guid":{"rendered":"https:\/\/blog.agentsoft.co.kr\/index.php\/2026\/01\/02\/27158\/"},"modified":"2026-01-02T09:00:39","modified_gmt":"2026-01-02T00:00:39","slug":"data-preparation","status":"publish","type":"post","link":"https:\/\/blog.agentsoft.co.kr\/index.php\/2026\/01\/02\/27158\/","title":{"rendered":"Data Preparation"},"content":{"rendered":"

<\/p>\n

\ubaa9\ucc28<\/strong><\/p>\n

1. feature extraction and portability
\n2. data cleaning
\n3. data reduction and transformation<\/p>\n

\ubcf8\ubb38\ub0b4\uc6a9<\/strong><\/p>\n

1. feature extraction and portability
\nfeature extraction\uc740 \ub2e4\uc591\ud55c \ucd9c\ucc98(\uc13c\uc11c, \uc774\ubbf8\uc9c0, \uc6f9 \uae30\ub85d, \uce68\uc785\uac10\uc9c0, \ubb38\uc11c \ub4f1)\uc5d0\uc11c \ub370\uc774\ud130\ub97c \uc5bb\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4. portability\ub294 \ub2e4\ub978 \uc720\ud615\uc73c\ub85c \ub370\uc774\ud130\ub97c \ubcc0\ud658\ud558\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4.
\nPortability Example Discretization: \uac00\uc7a5 \ud754\ud558\uac8c \uc0ac\uc6a9\ub418\ub294 \ubcc0\ud658\uc774\uba70, \uc815\ubcf4\ub97c \uc77c\ubd80\ubd84 \uc18c\uc2e4\ud558\ub294 \uac83\uc774 \ud2b9\uc9d5\uc774\ub2e4. \ubb38\uc81c\uc810\uc740 \uc77c\uc815\ud558\uc9c0 \uc54a\uc740 \uac04\uaca9\uc73c\ub85c \ub370\uc774\ud130\ub4e4\uc774 \ubd88\uc77c\uce58\ud558\uac8c \ubd84\ubc30\ub418\uc5b4 \uc788\ub2e4\ub294 \uac83\uc774\ub2e4. \u2460 Equi-width ranges: \uac01 \ubc94\uc704 [a,b]\ub294 b-a\uc640 \uac19\uc740 \ubc29\uc2dd\uc73c\ub85c \uc120\ud0dd \ub418\uace0, \ubd88\uc77c\uce58\ud558\uac8c \ubd84\ubc30\ub418\uc5b4 \uc788\ub294 \ub370\uc774\ud130\uc5d0\ub294 \uc801\uc6a9\ub418\uc9c0 \uc54a\ub294\ub2e4. [\ucd5c\uc19f\uac12, \ucd5c\ub313\uac12]\uc740 \u03c6\uc815\ub3c4\uc758 \uc77c\uc815\ud55c \uae38\uc774\ub85c \ub098\ub204\uc5b4 \uc9c4\ub2e4. \u2461 Equi-log ranges: \uac01 \ubc94\uc704 [a,b]\ub294 log(b)-log(a)\uc640 \uac19\uc740 \ubc29\uc2dd\uc73c\ub85c \uc120\ud0dd\ub41c\ub2e4. \uc774\ub7ec\ud55c \ubc29\ubc95\uc758 \ubc94\uc704 \uc120\ud0dd\uc740 \uae30\ud558\ud559\uc801\uc73c\ub85c \ud06c\uae30\uac00 \uc99d\uac00\ud558\ub294 \ud6a8\uacfc\uac00 \uc788\ub2e4. \u2462 Equi-depth ranges: \uac01 \ubc94\uc704\ub294 \ub3d9\uc77c\ud55c \uc218\uc758 \uae30\ub85d\uc744 \uac16\uace0, \uac01 \ubc94\uc704\uc5d0 \uc138\ubd84\ud654\ub97c \uc81c\uacf5\ud558\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4. Binarization: categorical\ud55c \uc131\uc9c8\uc744 binary\ud55c \ud615\ud0dc\ub85c \ubc14\uafb8\uace0 binary\ub41c \ub370\uc774\ud130\uc5d0 \ub300\ud574\uc11c numeric algorithms\ub97c \uc0ac\uc6a9\ud55c\ub2e4. \u03c6\uc18d\uc131 \uc911 \ud558\ub098\ub294 1\uac12\uc744 \uac00\uc9c0\uace0, \ub098\uba38\uc9c0\ub294 0\uac12\uc744 \uac00\uc9c4\ub2e4. LSA: \ucc28\uc6d0\uc774 \ub192\uc544\uc9c0\uba74 \uacf5\uac04\uc758 \ud06c\uae30\ub294 \uae30\ud558\uae09\uc218\uc801\uc73c\ub85c \ucee4\uc838\uc11c \ub370\uc774\ud130 \ubd84\ud3ec\uac00 sparse\ud558\uac8c \ub418\uace0 \uc131\ub2a5\uc740 \uae30\ud558\uae09\uc218\uc801\uc73c\ub85c \ub5a8\uc5b4\uc9c0\ub294 \uac83\uc744 \ucc28\uc6d0\uc758 \uc800\uc8fc\ub77c\uace0 \ubd80\ub978\ub2e4. \ub530\ub77c\uc11c LSA\ub294 \ub0ae\uc740 \ucc28\uc6d0\uc5d0\uc11c \ub370\uc774\ud130\ub97c sparse\ud558\uc9c0 \uc54a\uc740 \ud45c\ud604\uc73c\ub85c \ubcc0\ud658\ud558\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4. \ubcc0\ud658 \ud6c4 \uc2a4\ucf00\uc77c\ub9c1\uc744 \uc801\uc6a9\ud558\uae30\ub3c4 \ud558\ub294\ub370, \uc2a4\ucf00\uc77c\ub9c1\uc740 \ub2e4\uc591\ud55c \uae38\uc774\uc758 \ubb38\uc790\ub4e4\uc744 \uade0\uc77c\ud558\uac8c \ubcc0\ud658\ud558\ub294\ub370 \ud544\uc694\ud558\ub2e4.<\/p>\n

\ucd9c\ucc98 : \ud574\ud53c\ucea0\ud37c\uc2a4<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

\ubaa9\ucc28 1. feature extraction and portability 2. data cleaning 3. data reduction and transformation \ubcf8\ubb38\ub0b4\uc6a9 1. feature extraction and portability feature extraction\uc740 \ub2e4\uc591\ud55c \ucd9c\ucc98(\uc13c\uc11c, \uc774\ubbf8\uc9c0, \uc6f9 \uae30\ub85d, \uce68\uc785\uac10\uc9c0, \ubb38\uc11c \ub4f1)\uc5d0\uc11c \ub370\uc774\ud130\ub97c \uc5bb\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4. portability\ub294 \ub2e4\ub978 \uc720\ud615\uc73c\ub85c \ub370\uc774\ud130\ub97c \ubcc0\ud658\ud558\ub294 \uac83\uc744 \ub9d0\ud55c\ub2e4. Portability Example Discretization: \uac00\uc7a5 \ud754\ud558\uac8c \uc0ac\uc6a9\ub418\ub294 \ubcc0\ud658\uc774\uba70, \uc815\ubcf4\ub97c \uc77c\ubd80\ubd84 \uc18c\uc2e4\ud558\ub294 \uac83\uc774 \ud2b9\uc9d5\uc774\ub2e4. \ubb38\uc81c\uc810\uc740 \uc77c\uc815\ud558\uc9c0 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[1780,33907,9992,12593],"class_list":["post-27158","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-21-","tag-data-preparation","tag-9992","tag-12593"],"_links":{"self":[{"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/posts\/27158","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/comments?post=27158"}],"version-history":[{"count":0,"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/posts\/27158\/revisions"}],"wp:attachment":[{"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/media?parent=27158"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/categories?post=27158"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.agentsoft.co.kr\/index.php\/wp-json\/wp\/v2\/tags?post=27158"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}