{"id":468,"date":"2018-09-10T21:42:53","date_gmt":"2018-09-10T12:42:53","guid":{"rendered":"https:\/\/best-biostatistics.com\/toukei-er\/entry\/how-to-do-bagging-in-r\/"},"modified":"2024-10-12T23:04:21","modified_gmt":"2024-10-12T14:04:21","slug":"how-to-do-bagging-in-r","status":"publish","type":"post","link":"https:\/\/best-biostatistics.com\/toukei-er\/entry\/how-to-do-bagging-in-r\/","title":{"rendered":"R \u3067\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u306e\u30d0\u30ae\u30f3\u30b0\u3092\u884c\u3046\u65b9\u6cd5"},"content":{"rendered":"\n

\u30d0\u30ae\u30f3\u30b0\u3068\u3044\u3046\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u3092 R \u3067\u3084\u3063\u3066\u307f\u308b\u3002<\/p>\n\n\n\n\n\n\n\n

\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3068\u30d0\u30ae\u30f3\u30b0\u306e\u9055\u3044<\/h2>\n\n\n\n

\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3068\u30d0\u30ae\u30f3\u30b0\u306e\u9055\u3044\u306f\u3001\u4ee5\u4e0b\u306e\u8a18\u4e8b\u3092\u53c2\u7167\u3002<\/p>\n\n\n

\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\u3042\u308f\u305b\u3066\u8aad\u307f\u305f\u3044<\/span>\n\t\t\t\t\t
\"\"<\/figure><\/div>\t\t\t\t\t
\n\t\t\t\t\t\t\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3068\u30d0\u30ae\u30f3\u30b0\u306e\u9055\u3044<\/a>\n\t\t\t\t\t\t\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3068\u30d0\u30ae\u30f3\u30b0\u306f\u3001\u6c7a\u5b9a\u6728\u3092\u3088\u308a\u6c4e\u7528\u5316\u3059\u308b\u305f\u3081\u306b\u8003\u3048\u3089\u308c\u305f\u624b\u6cd5\u3002 \u9055\u3044\u306f\u4f55\u304b\uff1f \u6982\u5ff5\u7684\u306a\u7c21\u5358\u306a\u8aac\u660e\u3002 \u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u3068\u30d0\u30ae\u30f3\u30b0\u306e\u7dcf\u79f0 \u30a2\u30f3\u30b5\u30f3\u30d6…<\/span>\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\n\n\n\n\n\n

\u30d0\u30ae\u30f3\u30b0\u306e\u305f\u3081\u306e R \u30d1\u30c3\u30b1\u30fc\u30b8\u306e\u6e96\u5099<\/h2>\n\n\n\n

adabag\u30d1\u30c3\u30b1\u30fc\u30b8\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u3002<\/p>\n\n\n\n

install.packages(\"adabag\")<\/code><\/pre>\n\n\n\n
\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u5f8c\u3001\u547c\u3073\u51fa\u3057\u3066\u304a\u304f\u3002<\/p>\n\n\n\n
library(adabag)<\/code><\/pre>\n\n\n\n
\uff1e\uff1e\u3082\u3046\u7d71\u8a08\u3067\u60a9\u3080\u306e\u306f\u7d42\u308f\u308a\u306b\u3057\u307e\u305b\u3093\u304b\uff1f\u00a0<\/a><\/strong><\/span><\/p>\r\n\"\"<\/a>\r\n
\u21911\u4e07\u4eba\u4ee5\u4e0a\u306e\u533b\u7642\u5f93\u4e8b\u8005\u304c\u8cfc\u8aad\u4e2d<\/span><\/strong><\/span><\/p><\/div>
\u30d0\u30ae\u30f3\u30b0\u305f\u3081\u306e\u30c7\u30fc\u30bf\u306e\u6e96\u5099<\/h2>\n\n\n\n
\u4f8b\u984c\u306e\u30c7\u30fc\u30bf\u3092\u6e96\u5099\u3059\u308b\u3002<\/p>\n\n\n\n
\u30c7\u30fc\u30bf\u306firis\u3092\u4f7f\u3046\u3002<\/p>\n\n\n\n
iris\u306f150\u884c\u306e\u30c7\u30fc\u30bf\u3002\u4e00\u90e8\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u306b\u3059\u308b\u3002<\/p>\n\n\n\n
150\u309250\u305a\u30643\u3064\u306b\u5206\u3051\u3066\u3001\u305d\u308c\u305e\u308c50\u500b\u304b\u308935\u500b\u3092\u30e9\u30f3\u30c0\u30e0\u306b\u53d6\u308a\u3060\u3057\u3066\u3001105\u500b\u306esub\u3068\u3044\u3046\u6570\u5217\u3092\u4f5c\u308b\u3002sub\u306b\u4e00\u81f4\u3059\u308b\u884c\u756a\u53f7\u306e\u30c7\u30fc\u30bf\u3092\u5b66\u7fd2\u30c7\u30fc\u30bf\u306b\u3059\u308b\u3002<\/p>\n\n\n\n
\u3044\u3064\u3082\u540c\u3058\u7d50\u679c\u304c\u3067\u304d\u308b\u3088\u3046\u306bseed\u3092\u6c7a\u3081\u3066\u304a\u304f\u3002<\/p>\n\n\n\n
set.seed(17)\nsub <- c(sample(1:50, 35), sample(51:100, 35), sample(101:150, 35))<\/code><\/pre>\n\n\n\n
\u30d0\u30ae\u30f3\u30b0\u306e\u89e3\u6790\u4f8b<\/h2>\n\n\n\n
iris\u306eSpecies\u3092\u5206\u985e\u3059\u308b\u8b58\u5225\u5668\u3092bagging\u3067\u6c42\u3081\u308b\u3002mfinal\u306f\u5206\u985e\u6728\u306e\u6570\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u306f100\u3002<\/p>\n\n\n\n
set.seed(17)\niris.bagging<-bagging(Species ~ ., data=iris[sub,], mfinal=10)\niris.bagging<\/code><\/pre>\n\n\n\n
\u5206\u985e\u6728\u306f\u4ee5\u4e0b\u306e10\u500b\u304c\u4f5c\u3089\u308c\u305f\u3002<\/p>\n\n\n\n
> iris.bagging$trees\n1<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 66 versicolor (0.3238095 0.3714286 0.3047619)\n2) Petal.Length< 2.5 34  0 setosa (1.0000000 0.0000000 0.0000000) *\n3) Petal.Length>=2.5 71 32 versicolor (0.0000000 0.5492958 0.4507042)\n6) Petal.Width< 1.7 40  1 versicolor (0.0000000 0.9750000 0.0250000) *\n7) Petal.Width>=1.7 31  0 virginica (0.0000000 0.0000000 1.0000000) *\n2<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 67 setosa (0.36190476 0.29523810 0.34285714)\n2) Petal.Length< 2.5 38  0 setosa (1.00000000 0.00000000 0.00000000) *\n3) Petal.Length>=2.5 67 31 virginica (0.00000000 0.46268657 0.53731343)\n6) Petal.Width< 1.75 34  3 versicolor (0.00000000 0.91176471 0.08823529) *\n7) Petal.Width>=1.75 33  0 virginica (0.00000000 0.00000000 1.00000000) *\n3<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 59 versicolor (0.20000000 0.43809524 0.36190476)\n2) Petal.Width< 1.7 71 25 versicolor (0.29577465 0.64788732 0.05633803)\n4) Petal.Length< 2.5 21  0 setosa (1.00000000 0.00000000 0.00000000) *\n5) Petal.Length>=2.5 50  4 versicolor (0.00000000 0.92000000 0.08000000) *\n3) Petal.Width>=1.7 34  0 virginica (0.00000000 0.00000000 1.00000000) *\n4<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 63 setosa (0.4000000 0.2761905 0.3238095)\n2) Petal.Length< 2.6 42  0 setosa (1.0000000 0.0000000 0.0000000) *\n3) Petal.Length>=2.6 63 29 virginica (0.0000000 0.4603175 0.5396825)\n6) Petal.Width< 1.75 33  4 versicolor (0.0000000 0.8787879 0.1212121)\n12) Petal.Length< 4.95 26  0 versicolor (0.0000000 1.0000000 0.0000000) *\n13) Petal.Length>=4.95 7  3 virginica (0.0000000 0.4285714 0.5714286) *\n7) Petal.Width>=1.75 30  0 virginica (0.0000000 0.0000000 1.0000000) *\n5<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 68 setosa (0.35238095 0.31428571 0.33333333)\n2) Petal.Length< 2.5 37  0 setosa (1.00000000 0.00000000 0.00000000) *\n3) Petal.Length>=2.5 68 33 virginica (0.00000000 0.48529412 0.51470588)\n6) Petal.Length< 4.8 31  0 versicolor (0.00000000 1.00000000 0.00000000) *\n7) Petal.Length>=4.8 37  2 virginica (0.00000000 0.05405405 0.94594595) *\n6<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 70 setosa (0.33333333 0.33333333 0.33333333)\n2) Petal.Length< 2.6 35  0 setosa (1.00000000 0.00000000 0.00000000) *\n3) Petal.Length>=2.6 70 35 versicolor (0.00000000 0.50000000 0.50000000)\n6) Petal.Length< 4.75 34  0 versicolor (0.00000000 1.00000000 0.00000000) *\n7) Petal.Length>=4.75 36  1 virginica (0.00000000 0.02777778 0.97222222) *\n7<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 60 versicolor (0.25714286 0.42857143 0.31428571)\n2) Petal.Length< 2.6 27  0 setosa (1.00000000 0.00000000 0.00000000) *\n3) Petal.Length>=2.6 78 33 versicolor (0.00000000 0.57692308 0.42307692)\n6) Petal.Length< 4.75 42  0 versicolor (0.00000000 1.00000000 0.00000000) *\n7) Petal.Length>=4.75 36  3 virginica (0.00000000 0.08333333 0.91666667) *\n8<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 66 setosa (0.37142857 0.30476190 0.32380952)\n2) Petal.Length< 2.6 39  0 setosa (1.00000000 0.00000000 0.00000000) *\n3) Petal.Length>=2.6 66 32 virginica (0.00000000 0.48484848 0.51515152)\n6) Petal.Length< 4.75 31  0 versicolor (0.00000000 1.00000000 0.00000000) *\n7) Petal.Length>=4.75 35  1 virginica (0.00000000 0.02857143 0.97142857) *\n9<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 59 versicolor (0.22857143 0.43809524 0.33333333)\n2) Petal.Width< 1.7 71 25 versicolor (0.33802817 0.64788732 0.01408451)\n4) Petal.Length< 2.6 24  0 setosa (1.00000000 0.00000000 0.00000000) *\n5) Petal.Length>=2.6 47  1 versicolor (0.00000000 0.97872340 0.02127660) *\n3) Petal.Width>=1.7 34  0 virginica (0.00000000 0.00000000 1.00000000) *\n10<\/a>\nn= 105\nnode), split, n, loss, yval, (yprob)\n* denotes terminal node\n1) root 105 67 setosa (0.3619048 0.3333333 0.3047619)\n2) Petal.Length< 2.6 38  0 setosa (1.0000000 0.0000000 0.0000000) *\n3) Petal.Length>=2.6 67 32 versicolor (0.0000000 0.5223881 0.4776119)\n6) Petal.Width< 1.7 35  0 versicolor (0.0000000 1.0000000 0.0000000) *\n7) Petal.Width>=1.7 32  0 virginica (0.0000000 0.0000000 1.0000000) *\n<\/code><\/pre>\n\n\n\n
\u5206\u985e\u6728\u306e\u6c7a\u5b9a\u306f Plurality Vote\uff08\u591a\u6570\u4ee3\u8868\u5236\uff09\u3067\u6c7a\u3081\u308b\u3002<\/p>\n\n\n\n
The majority vote (the most often predicted class) \u3067\u4f75\u5408\u3059\u308b\u3002<\/p>\n\n\n\n
adabag: An R Package for Classification with Boosting and Bagging (PDF)<\/a><\/p>\n\n\n\n
\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\uff08-sub\u3067\u884c\u756a\u53f7\u3092\u6307\u5b9a\uff09\u3067\u4e88\u6e2c\u6027\u80fd\u3092\u78ba\u8a8d\u3059\u308b\u3002<\/p>\n\n\n\n
predict.bagging()\u3067\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u3067\u306e\u4e88\u6e2c\u304c\u884c\u3048\u308b\u3002<\/p>\n\n\n\n
iris.predbagging<-predict.bagging(iris.bagging, newdata=iris[-sub,])\niris.predbagging<\/code><\/pre>\n\n\n\n
Confusion table\u3067\u8aa4\u5206\u985e\u3092\u78ba\u8a8d\u3059\u308b\u3002<\/p>\n\n\n\n
versicolor\u3092virginica\u306b1\u4ef6\u3001virginica\u3092versicolor\u306b2\u4ef6\u3001\u8aa4\u5206\u985e\u3057\u305f\u3002<\/p>\n\n\n\n
> iris.predbagging$confusion\nObserved Class\nPredicted Class setosa versicolor virginica\nsetosa         15          0         0\nversicolor      0         14         2\nvirginica       0          1        13\n<\/code><\/pre>\n\n\n\n
\u8aa4\u5206\u985e\u7387\u306f0.067\uff086.7%\uff09\u3068\u8a08\u7b97\u3055\u308c\u305f\u3002<\/p>\n\n\n\n
> iris.predbagging$error\n[1] 0.06666667\n<\/code><\/pre>\n\n\n\n
\u307e\u3068\u3081<\/h2>\n\n\n\n
\u30d0\u30ae\u30f3\u30b0\u306f\u3001\u5b66\u7fd2\u30bb\u30c3\u30c8\u304b\u3089\u30d6\u30fc\u30c8\u30b9\u30c8\u30e9\u30c3\u30d7\u6cd5\u3067\u4f55\u5ea6\u3082\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u3057\u3066\u3001\u5206\u985e\u5668\u3092\u3044\u304f\u3064\u3082\u4f5c\u308a\u3001\u305d\u308c\u3092\u4f75\u5408\u3057\u3066\u3088\u308a\u3088\u3044\u5206\u985e\u5668\u3092\u4f5c\u308b\u65b9\u6cd5\u3002<\/p>\n\n\n\n
R\u3067\u306f\u3001adabag\u30d1\u30c3\u30b1\u30fc\u30b8\u306ebagging()\u3067\u5b9f\u884c\u53ef\u80fd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u30d0\u30ae\u30f3\u30b0\u3068\u3044\u3046\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u3092 R \u3067\u3084\u3063\u3066\u307f\u308b\u3002<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"swell_btn_cv_data":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[5,103],"tags":[],"class_list":["post-468","post","type-post","status-publish","format-standard","hentry","category-r","category-103"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/468","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/comments?post=468"}],"version-history":[{"count":2,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/468\/revisions"}],"predecessor-version":[{"id":2751,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/posts\/468\/revisions\/2751"}],"wp:attachment":[{"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/media?parent=468"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/categories?post=468"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/best-biostatistics.com\/toukei-er\/wp-json\/wp\/v2\/tags?post=468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}