{"id":3045,"date":"2023-07-19T11:54:34","date_gmt":"2023-07-19T11:54:34","guid":{"rendered":"https:\/\/statorials.org\/cn\/split-r-%e6%b5%8b%e8%af%95%e5%88%97%e8%bd%a6\/"},"modified":"2023-07-19T11:54:34","modified_gmt":"2023-07-19T11:54:34","slug":"split-r-%e6%b5%8b%e8%af%95%e5%88%97%e8%bd%a6","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/split-r-%e6%b5%8b%e8%af%95%e5%88%97%e8%bd%a6\/","title":{"rendered":"\u5982\u4f55\u5728\u8bad\u7ec3\u4e2d\u5206\u5272\u6570\u636e& r \u4e2d\u7684\u6d4b\u8bd5\u96c6\uff083 \u79cd\u65b9\u6cd5\uff09"},"content":{"rendered":"

<\/p>\n

\n

\u901a\u5e38\uff0c\u5f53\u6211\u4eec\u5c06\u673a\u5668\u5b66\u4e60\u7b97\u6cd5<\/a>\u5e94\u7528\u4e8e\u6570\u636e\u96c6\u65f6\uff0c\u6211\u4eec\u9996\u5148\u5c06\u6570\u636e\u96c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\u3002<\/span><\/p>\n

\u5728 R \u4e2d\uff0c\u5c06\u6570\u636e\u62c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\u7684\u5e38\u7528\u65b9\u6cd5\u6709\u4ee5\u4e0b\u4e09\u79cd\uff1a<\/span><\/p>\n

\u65b9\u6cd5\u4e00\uff1a\u4f7f\u7528Base R<\/strong><\/span><\/p>\n

 #make this example reproducible\n<\/span>set. seeds<\/span> (1)\n\n#use 70% of dataset as training set and 30% as test set\n<\/span>sample <- sample(c( TRUE<\/span> , FALSE<\/span> ), nrow(df), replace= TRUE<\/span> , prob=c( 0.7<\/span> , 0.3<\/span> ))\ntrain <- df[sample, ]\ntest <- df[!sample, ]<\/strong><\/pre>\n
\u65b9\u6cd52\uff1a\u4f7f\u7528caTools\u5305<\/strong><\/span><\/p>\n
 library<\/span> (caTools)<\/span>\n\n#make this example reproducible\n<\/span>set. seeds<\/span> (1)\n\n#use 70% of dataset as training set and 30% as test set\n<\/span>sample <- sample. split<\/span> (df$any_column_name, SplitRatio = 0.7<\/span> )\ntrain <- subset(df, sample == TRUE<\/span> )\ntest <- subset(df, sample == FALSE<\/span> )<\/strong><\/pre>\n
\u65b9\u6cd53\uff1a\u4f7f\u7528dplyr\u5305<\/strong><\/span><\/p>\n
 library<\/span> (dplyr)<\/span>\n\n#make this example reproducible\n<\/span>set. seeds<\/span> (1)\n\n#create ID column\n<\/span>df$id <- 1:nrow(df)\n\n#use 70% of dataset as training set and 30% as test set<\/span>\ntrain <- df %>% dplyr::sample_frac( 0.70<\/span> )\ntest <- dplyr::anti_join(df, train, by = ' id<\/span> ')<\/strong><\/pre>\n
\u793a\u4f8b 1\uff1a\u4f7f\u7528 Base R \u5c06\u6570\u636e\u62c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6<\/strong><\/span><\/h3>\n
\u4ee5\u4e0b\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528 R \u5e93\u5c06 iris \u6570\u636e\u96c6\u62c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\uff0c\u4f7f\u7528 70% \u7684\u884c\u4f5c\u4e3a\u8bad\u7ec3\u96c6\uff0c\u5269\u4f59\u7684 30% \u4f5c\u4e3a\u6d4b\u8bd5\u96c6\uff1a<\/span><\/span><\/p>\n
 #load iris dataset\n<\/span>data(iris)\n\n#make this example reproducible\n<\/span>set. seeds<\/span> (1)\n\n#Use 70% of dataset as training set and remaining 30% as testing set\n<\/span>sample <- sample(c( TRUE<\/span> , FALSE<\/span> ), nrow(iris), replace= TRUE<\/span> , prob=c( 0.7<\/span> , 0.3<\/span> ))\ntrain <- iris[sample, ]\ntest <- iris[!sample, ]\n\n#view dimensions of training set\n<\/span>sun(train)\n\n[1] 106 5\n\n#view dimensions of test set\n<\/span>dim(test)\n\n[1] 44 5<\/strong><\/pre>\n
\u4ece\u7ed3\u679c\u6211\u4eec\u53ef\u4ee5\u770b\u51fa\uff1a<\/span><\/p>\n
\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5728\u5b9e\u8df5\u4e2d\u4f7f\u7528 R \u4e2d\u5185\u7f6e\u7684iris \u6570\u636e\u96c6<\/a>\u6765\u4f7f\u7528\u6bcf\u79cd\u65b9\u6cd5\u3002<\/span><\/p>\n