解释SVM图R

时间:2019-02-08 09:25:26

标签: r machine-learning plot svm

我正在使用SVM模型拟合

  m <- svm(training_S$Class~., data = training_S)

training_S如下所示:

> str(training_S)
'data.frame':   21173 obs. of  31 variables:
 $ L2A_T30STG_20170601T110651_B02_10m: num  1546 1579 1506 1555 1580 ...
 $ L2A_T30STG_20170601T110651_B03_10m: num  1882 1895 1841 1871 1851 ...
 $ L2A_T30STG_20170601T110651_B04_10m: num  2187 2191 2161 2175 2166 ...
 $ L2A_T30STG_20170601T110651_B08_10m: num  2269 2323 2225 2229 2270 ...
 $ L2A_T30STG_20170601T110651_B11_20m: num  2555 2595 2555 2555 2595 ...
 $ L2A_T30STG_20170601T110651_B12_20m: num  2026 2049 2026 2026 2049 ...
 $ L2A_T30STG_20170611T110621_B02_10m: num  1442 1459 1399 1401 1425 ...
 $ L2A_T30STG_20170611T110621_B03_10m: num  1772 1813 1751 1759 1777 ...
 $ L2A_T30STG_20170611T110621_B04_10m: num  2091 2086 2038 2068 2082 ...
 $ L2A_T30STG_20170611T110621_B08_10m: num  2524 2530 2408 2460 2502 ...
 $ L2A_T30STG_20170611T110621_B11_20m: num  2581 2603 2581 2581 2603 ...
 $ L2A_T30STG_20170611T110621_B12_20m: num  2025 2035 2025 2025 2035 ...
 $ L2A_T30STG_20170621T110651_B02_10m: num  1176 1174 1168 1179 1136 ...
 $ L2A_T30STG_20170621T110651_B03_10m: num  1454 1444 1471 1471 1450 ...
 $ L2A_T30STG_20170621T110651_B04_10m: num  1590 1609 1616 1605 1581 ...
 $ L2A_T30STG_20170621T110651_B08_10m: num  2627 2650 2553 2613 2612 ...
 $ L2A_T30STG_20170621T110651_B11_20m: num  2365 2365 2365 2365 2365 ...
 $ L2A_T30STG_20170621T110651_B12_20m: num  1730 1708 1730 1730 1708 ...
 $ L2A_T30STG_20170701T111051_B02_10m: num  890 875 895 888 927 ...
 $ L2A_T30STG_20170701T111051_B03_10m: num  1270 1246 1259 1285 1270 ...
 $ L2A_T30STG_20170701T111051_B04_10m: num  1280 1295 1251 1260 1293 ...
 $ L2A_T30STG_20170701T111051_B08_10m: num  3467 3444 3445 3459 3422 ...
 $ L2A_T30STG_20170701T111051_B11_20m: num  2381 2368 2381 2381 2368 ...
 $ L2A_T30STG_20170701T111051_B12_20m: num  1591 1583 1591 1591 1583 ...
 $ L2A_T30STG_20170711T110651_B02_10m: num  564 643 588 629 660 578 705 627 603 564 ...
 $ L2A_T30STG_20170711T110651_B03_10m: num  1038 1034 1024 1056 1065 ...
 $ L2A_T30STG_20170711T110651_B04_10m: num  810 804 807 816 836 785 918 851 826 734 ...
 $ L2A_T30STG_20170711T110651_B08_10m: num  4053 4061 4097 4021 4058 ...
 $ L2A_T30STG_20170711T110651_B11_20m: num  2196 2173 2196 2196 2173 ...
 $ L2A_T30STG_20170711T110651_B12_20m: num  1258 1243 1258 1258 1243 ...
 $ Class                             : Factor w/ 6 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...

拟合模型后,我在解释SVM模型的plot时遇到问题。使用以下代码查看这两个变量之间的平面:

plot(m,training_S, L2A_T30STG_20170601T110651_B02_10m ~ L2A_T30STG_20170711T110651_B04_10m)

我明白了,这对我来说很难解释。我的解释技巧做错了吗?

仅提供更多信息,我已将本指南用作参考 http://uc-r.github.io/svm enter image description here

0 个答案:

没有答案