R 中的错误：没有适用于“预测”的适用方法应用于“regsubsets”类的对象

Question

我试图运行教科书 ISLR 中的代码。这是关于最佳子集选择：

library(ISLR) #contain data Hitters
library(leaps) #use regsubsets
regfit.full=regsubsets(Salary~.,Hitters)
predict(regfit.full)

然后R显示错误：

Error in UseMethod("predict") :no applicable method for 'predict' applied to an object of class "regsubsets" 

我使用的是 Windows RStudio 版本 0.99.893，R-3.2.4revised-win。 我真的不知道为什么“预测”不能应用于“regsubsets”。

其他信息：

> sessionInfo()
R version 3.2.4 Revised (2016-03-16 r70336)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows >= 8 x64 (build 9200)

locale:
[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252    LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                           LC_TIME=English_United States.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] ISLR_1.0  leaps_2.9

loaded via a namespace (and not attached):
[1] tools_3.2.4

> methods(predict)
     [1] predict.ar*                predict.Arima*             predict.arima0*            predict.glm               
     [5] predict.HoltWinters*       predict.lm                 predict.loess*             predict.mlm*              
     [9] predict.nls*               predict.poly*              predict.ppr*               predict.prcomp*           
    [13] predict.princomp*          predict.smooth.spline*     predict.smooth.spline.fit* predict.StructTS*         
    see '?methods' for accessing help and source code

> regfit.full
Subset selection object
Call: regsubsets.formula(Salary ~ ., Hitters)
19 Variables  (and intercept)
           Forced in Forced out
AtBat          FALSE      FALSE
Hits           FALSE      FALSE
HmRun          FALSE      FALSE
Runs           FALSE      FALSE
RBI            FALSE      FALSE
Walks          FALSE      FALSE
Years          FALSE      FALSE
CAtBat         FALSE      FALSE
CHits          FALSE      FALSE
CHmRun         FALSE      FALSE
CRuns          FALSE      FALSE
CRBI           FALSE      FALSE
CWalks         FALSE      FALSE
LeagueN        FALSE      FALSE
DivisionW      FALSE      FALSE
PutOuts        FALSE      FALSE
Assists        FALSE      FALSE
Errors         FALSE      FALSE
NewLeagueN     FALSE      FALSE
1 subsets of each size up to 8
Selection Algorithm: exhaustive

Answer 1

regsubsets 没有预测方法。我们需要自己写一个。这是取自 http://www.science.smith.edu/~jcrouser/SDS293/labs/lab9-r.html:

的示例

predict.regsubsets = function(object, newdata, id, ...) {
    form = as.formula(object$call[[2]])
    mat = model.matrix(form, newdata)
    coefi = coef(object, id = id)
    mat[, names(coefi)] %*% coefi
}