Question

我正在使用在RData文件中提供给我的训练数据，以及我自己构建的数据框，其中包含我认为在训练数据中的所有列。

args = commandArgs(trailingOnly=TRUE)

model = readRDS(args[1])
m = model[[1]]

infile = fread(newDataPath, header=T)
setDF(infile)
i = infile[,!colnames(infile) %in% c("chr", "pos", "end")]

predictions = predict(m, i)

然而，运行这个，我得到了 variables in the training data missing in newdata。

使用colnames(i)，我可以找到newdata中的变量列表，但是如何对训练数据执行相同的操作 - 我认为这是类{{1}的对象}}？

Answer 1

您可以使用str查看模型的结构，以查找列名称的位置。

我假设您使用的是randomForest软件包，但对于其他型号来说它也是一样的。

library('randomForest')

model <- randomForest(Species ~ ., data = iris, ntree=5)

str(model)
#> List of 19
#>  $ call           : language randomForest(formula = Species ~ ., data = iris, ntree = 5)
#>  $ type           : chr "classification"
#>  $ predicted      : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
#>   ..- attr(*, "names")= chr [1:150] "1" "2" "3" "4" ...
#>  $ err.rate       : num [1:5, 1:4] 0.0862 0.0753 0.114 0.0714 0.0833 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : NULL
#>   .. ..$ : chr [1:4] "OOB" "setosa" "versicolor" "virginica"
#>  $ confusion      : num [1:3, 1:4] 45 0 0 0 41 8 0 3 35 0 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : chr [1:3] "setosa" "versicolor" "virginica"
#>   .. ..$ : chr [1:4] "setosa" "versicolor" "virginica" "class.error"
#>  $ votes          : matrix [1:150, 1:3] 1 1 1 1 1 1 1 1 1 1 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : chr [1:150] "1" "2" "3" "4" ...
#>   .. ..$ : chr [1:3] "setosa" "versicolor" "virginica"
#>  $ oob.times      : num [1:150] 1 2 1 1 3 1 2 2 2 2 ...
#>  $ classes        : chr [1:3] "setosa" "versicolor" "virginica"
#>  $ importance     : num [1:4, 1] 20.53 4.33 19.17 55.25
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
#>   .. ..$ : chr "MeanDecreaseGini"
#>  $ importanceSD   : NULL
#>  $ localImportance: NULL
#>  $ proximity      : NULL
#>  $ ntree          : num 5
#>  $ mtry           : num 2
#>  $ forest         :List of 14
#>   ..$ ndbigtree : int [1:5] 9 17 35 11 19
#>   ..$ nodestatus: int [1:35, 1:5] 1 1 -1 -1 1 1 -1 -1 -1 0 ...
#>   ..$ bestvar   : int [1:35, 1:5] 4 4 0 0 2 3 0 0 0 0 ...
#>   ..$ treemap   : int [1:35, 1:2, 1:5] 2 4 0 0 6 8 0 0 0 0 ...
#>   ..$ nodepred  : int [1:35, 1:5] 0 0 3 1 0 0 2 2 3 0 ...
#>   ..$ xbestsplit: num [1:35, 1:5] 1.65 0.8 0 0 2.25 4.75 0 0 0 0 ...
#>   ..$ pid       : num [1:3] 1 1 1
#>   ..$ cutoff    : num [1:3] 0.333 0.333 0.333
#>   ..$ ncat      : Named int [1:4] 1 1 1 1
#>   .. ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
#>   ..$ maxcat    : int 1
#>   ..$ nrnodes   : int 35
#>   ..$ ntree     : num 5
#>   ..$ nclass    : int 3
#>   ..$ xlevels   :List of 4
#>   .. ..$ Sepal.Length: num 0
#>   .. ..$ Sepal.Width : num 0
#>   .. ..$ Petal.Length: num 0
#>   .. ..$ Petal.Width : num 0
#>  $ y              : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
#>   ..- attr(*, "names")= chr [1:150] "1" "2" "3" "4" ...
#>  $ test           : NULL
#>  $ inbag          : NULL
#>  $ terms          :Classes 'terms', 'formula'  language Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width
#>   .. ..- attr(*, "variables")= language list(Species, Sepal.Length, Sepal.Width, Petal.Length, Petal.Width)
#>   .. ..- attr(*, "factors")= int [1:5, 1:4] 0 1 0 0 0 0 0 1 0 0 ...
#>   .. .. ..- attr(*, "dimnames")=List of 2
#>   .. .. .. ..$ : chr [1:5] "Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
#>   .. .. .. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
#>   .. ..- attr(*, "term.labels")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
#>   .. ..- attr(*, "order")= int [1:4] 1 1 1 1
#>   .. ..- attr(*, "intercept")= num 0
#>   .. ..- attr(*, "response")= int 1
#>   .. ..- attr(*, ".Environment")=<environment: 0x7f9bed91f8d8> 
#>   .. ..- attr(*, "predvars")= language list(Species, Sepal.Length, Sepal.Width, Petal.Length, Petal.Width)
#>   .. ..- attr(*, "dataClasses")= Named chr [1:5] "factor" "numeric" "numeric" "numeric" ...
#>   .. .. ..- attr(*, "names")= chr [1:5] "Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
#>  - attr(*, "class")= chr [1:2] "randomForest.formula" "randomForest"

attr(model$terms, 'term.labels')
#> [1] "Sepal.Length" "Sepal.Width"  "Petal.Length" "Petal.Width"

attr(model$terms, 'dataClasses')
#>      Species Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
#>     "factor"    "numeric"    "numeric"    "numeric"    "numeric"

Answer 2

通常，您可以查看intersect(names(train), names(test))或setdiff(names(train), names(test))以查找缺失的变量。

R：检查训练数据中的变量

2 个答案: