如何使用mlr自定义分类模型
How to use mlr to customize classification model
正在研究mlr，尝试定制自己的分类模型。我正在使用 https://mlr-org.github.io/mlr-tutorial/release/html/create_learner/index.html#classification 中的示例。这是我的代码：
library(mlr)
library(MASS)
makeRLearner.classif.lda = function() {
makeRLearnerClassif(
cl = "classif.lda",
package = "MASS",
par.set = makeParamSet(
makeDiscreteLearnerParam(id = "method", default = "moment", values = c("moment", "mle", "mve", "t")),
makeNumericLearnerParam(id = "nu", lower = 2, requires = quote(method == "t")),
makeNumericLearnerParam(id = "tol", default = 1e-4, lower = 0),
makeDiscreteLearnerParam(id = "predict.method", values = c("plug-in", "predictive", "debiased"),
default = "plug-in", when = "predict"),
makeLogicalLearnerParam(id = "CV", default = FALSE, tunable = FALSE)
),
properties = c("twoclass", "multiclass", "numerics", "factors", "prob"),
name = "Linear Discriminant Analysis",
short.name = "lda",
note = "Learner param 'predict.method' maps to 'method' in predict.lda."
)
}
trainLearner.classif.lda = function(.learner, .task, .subset, .weights = NULL, ...) {
f = getTaskFormula(.task)
MASS::lda(f, data = getTaskData(.task, .subset), ...)
}
predictLearner.classif.lda = function(.learner, .model, .newdata, predict.method = "plug-in", ...) {
p = predict(.model$learner.model, newdata = .newdata, method = predict.method, ...)
if (.learner$predict.type == "response")
return(p$class) else return(p$posterior)
}
data(iris)
train = sample(1:nrow(iris), nrow(iris) / 1.5)
test = sample(1:nrow(iris), nrow(iris) / 6)
task <- makeClassifTask(data=iris,target='Species')
lrn <- makeRLearner.classif.lda()
tr <- trainLearner.classif.lda(.learner=lrn,.task=task,.subset=train)
pred <- predictLearner.classif.lda(.learner=lrn,.model=tr,.newdata=test)
我刚刚从网站上复制并粘贴了三个函数。但是我遇到了以下错误：
Error in UseMethod("predict") :
no applicable method for 'predict' applied to an object of class "NULL"
我发现我的tr里没有$learner.model，本来应该有的，转入预测函数。我的 tr 有：
> str(tr)
List of 10
$ prior : Named num [1:3] 0.38 0.3 0.32
..- attr(*, "names")= chr [1:3] "setosa" "versicolor" "virginica"
$ counts : Named int [1:3] 38 30 32
..- attr(*, "names")= chr [1:3] "setosa" "versicolor" "virginica"
$ means : num [1:3, 1:4] 5.02 5.94 6.65 3.47 2.83 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:3] "setosa" "versicolor" "virginica"
.. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
$ scaling: num [1:4, 1:2] 0.869 1.384 -2.214 -2.954 0.157 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
.. ..$ : chr [1:2] "LD1" "LD2"
$ lev : chr [1:3] "setosa" "versicolor" "virginica"
$ svd : num [1:2] 41.78 2.91
$ N : int 100
$ call : language lda(formula = f, data = getTaskData(.task, .subset))
$ 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")= int 1
.. ..- attr(*, "response")= int 1
.. ..- attr(*, ".Environment")=<environment: 0x00000000213a8150>
.. ..- 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" ...
$ xlevels: Named list()
- attr(*, "class")= chr "lda"
我试过注册学习者，但我想我的方法不对。这是我的代码：
registerS3method("makeRLearner.classif.lda", "<awesome_new_learner_class>", makeRLearner.classif.lda.<awesome_new_learner_class>)
registerS3method("trainLearner.classif.lda", "<awesome_new_learner_class>", trainLearner.classif.lda.<awesome_new_learner_class>)
registerS3method("predictLearner.classif.lda", "<awesome_new_learner_class>", predictLearner.classif.lda.<awesome_new_learner_class>)
可能我不应该只是从网站上复制代码。但我不知道该怎么做。我真的是 mlr 包的新手。
这里有一个完整的例子，使用的是mlr自带的iris任务。除了仔细查看 mlr 文档之外，您可能会发现 R 中编程的一般介绍很有用，特别是关于参数名称——您看到的错误的原因是您没有传递模型到 predict()（.model 不是该参数的名称，它是您在定义中对变量的称呼）。
library(mlr)
library(MASS)
makeRLearner.classif.lda1 = function() {
makeRLearnerClassif(
cl = "classif.lda1",
package = "MASS",
par.set = makeParamSet(
makeDiscreteLearnerParam(id = "method", default = "moment", values = c("moment", "mle", "mve", "t")),
makeNumericLearnerParam(id = "nu", lower = 2, requires = quote(method == "t")),
makeNumericLearnerParam(id = "tol", default = 1e-4, lower = 0),
makeDiscreteLearnerParam(id = "predict.method", values = c("plug-in", "predictive", "debiased"),
default = "plug-in", when = "predict"),
makeLogicalLearnerParam(id = "CV", default = FALSE, tunable = FALSE)
),
properties = c("twoclass", "multiclass", "numerics", "factors", "prob"),
name = "Linear Discriminant Analysis",
short.name = "lda",
note = "Learner param 'predict.method' maps to 'method' in predict.lda."
)
}
trainLearner.classif.lda1 = function(.learner, .task, .subset, .weights = NULL, ...) {
f = getTaskFormula(.task)
MASS::lda(f, data = getTaskData(.task, .subset), ...)
}
predictLearner.classif.lda1 = function(.learner, .model, .newdata, predict.method = "plug-in", ...) {
p = predict(.model$learner.model, newdata = .newdata, method = predict.method, ...)
if (.learner$predict.type == "response")
return(p$class) else return(p$posterior)
}
registerS3method("makeRLearner", "classif.lda1", makeRLearner.classif.lda1)
registerS3method("trainLearner", "classif.lda1", trainLearner.classif.lda1)
registerS3method("predictLearner", "classif.lda1", predictLearner.classif.lda1)
lrn = makeLearner("classif.lda1")
mod = train(lrn, iris.task)
pred = predict(mod, iris.task)
正在研究mlr，尝试定制自己的分类模型。我正在使用 https://mlr-org.github.io/mlr-tutorial/release/html/create_learner/index.html#classification 中的示例。这是我的代码：
library(mlr)
library(MASS)
makeRLearner.classif.lda = function() {
makeRLearnerClassif(
cl = "classif.lda",
package = "MASS",
par.set = makeParamSet(
makeDiscreteLearnerParam(id = "method", default = "moment", values = c("moment", "mle", "mve", "t")),
makeNumericLearnerParam(id = "nu", lower = 2, requires = quote(method == "t")),
makeNumericLearnerParam(id = "tol", default = 1e-4, lower = 0),
makeDiscreteLearnerParam(id = "predict.method", values = c("plug-in", "predictive", "debiased"),
default = "plug-in", when = "predict"),
makeLogicalLearnerParam(id = "CV", default = FALSE, tunable = FALSE)
),
properties = c("twoclass", "multiclass", "numerics", "factors", "prob"),
name = "Linear Discriminant Analysis",
short.name = "lda",
note = "Learner param 'predict.method' maps to 'method' in predict.lda."
)
}
trainLearner.classif.lda = function(.learner, .task, .subset, .weights = NULL, ...) {
f = getTaskFormula(.task)
MASS::lda(f, data = getTaskData(.task, .subset), ...)
}
predictLearner.classif.lda = function(.learner, .model, .newdata, predict.method = "plug-in", ...) {
p = predict(.model$learner.model, newdata = .newdata, method = predict.method, ...)
if (.learner$predict.type == "response")
return(p$class) else return(p$posterior)
}
data(iris)
train = sample(1:nrow(iris), nrow(iris) / 1.5)
test = sample(1:nrow(iris), nrow(iris) / 6)
task <- makeClassifTask(data=iris,target='Species')
lrn <- makeRLearner.classif.lda()
tr <- trainLearner.classif.lda(.learner=lrn,.task=task,.subset=train)
pred <- predictLearner.classif.lda(.learner=lrn,.model=tr,.newdata=test)
我刚刚从网站上复制并粘贴了三个函数。但是我遇到了以下错误：
Error in UseMethod("predict") :
no applicable method for 'predict' applied to an object of class "NULL"
我发现我的tr里没有$learner.model，本来应该有的，转入预测函数。我的 tr 有：
> str(tr)
List of 10
$ prior : Named num [1:3] 0.38 0.3 0.32
..- attr(*, "names")= chr [1:3] "setosa" "versicolor" "virginica"
$ counts : Named int [1:3] 38 30 32
..- attr(*, "names")= chr [1:3] "setosa" "versicolor" "virginica"
$ means : num [1:3, 1:4] 5.02 5.94 6.65 3.47 2.83 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:3] "setosa" "versicolor" "virginica"
.. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
$ scaling: num [1:4, 1:2] 0.869 1.384 -2.214 -2.954 0.157 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
.. ..$ : chr [1:2] "LD1" "LD2"
$ lev : chr [1:3] "setosa" "versicolor" "virginica"
$ svd : num [1:2] 41.78 2.91
$ N : int 100
$ call : language lda(formula = f, data = getTaskData(.task, .subset))
$ 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")= int 1
.. ..- attr(*, "response")= int 1
.. ..- attr(*, ".Environment")=<environment: 0x00000000213a8150>
.. ..- 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" ...
$ xlevels: Named list()
- attr(*, "class")= chr "lda"
我试过注册学习者，但我想我的方法不对。这是我的代码：
registerS3method("makeRLearner.classif.lda", "<awesome_new_learner_class>", makeRLearner.classif.lda.<awesome_new_learner_class>)
registerS3method("trainLearner.classif.lda", "<awesome_new_learner_class>", trainLearner.classif.lda.<awesome_new_learner_class>)
registerS3method("predictLearner.classif.lda", "<awesome_new_learner_class>", predictLearner.classif.lda.<awesome_new_learner_class>)
可能我不应该只是从网站上复制代码。但我不知道该怎么做。我真的是 mlr 包的新手。
这里有一个完整的例子，使用的是mlr自带的iris任务。除了仔细查看 mlr 文档之外，您可能会发现 R 中编程的一般介绍很有用，特别是关于参数名称——您看到的错误的原因是您没有传递模型到 predict()（.model 不是该参数的名称，它是您在定义中对变量的称呼）。
library(mlr)
library(MASS)
makeRLearner.classif.lda1 = function() {
makeRLearnerClassif(
cl = "classif.lda1",
package = "MASS",
par.set = makeParamSet(
makeDiscreteLearnerParam(id = "method", default = "moment", values = c("moment", "mle", "mve", "t")),
makeNumericLearnerParam(id = "nu", lower = 2, requires = quote(method == "t")),
makeNumericLearnerParam(id = "tol", default = 1e-4, lower = 0),
makeDiscreteLearnerParam(id = "predict.method", values = c("plug-in", "predictive", "debiased"),
default = "plug-in", when = "predict"),
makeLogicalLearnerParam(id = "CV", default = FALSE, tunable = FALSE)
),
properties = c("twoclass", "multiclass", "numerics", "factors", "prob"),
name = "Linear Discriminant Analysis",
short.name = "lda",
note = "Learner param 'predict.method' maps to 'method' in predict.lda."
)
}
trainLearner.classif.lda1 = function(.learner, .task, .subset, .weights = NULL, ...) {
f = getTaskFormula(.task)
MASS::lda(f, data = getTaskData(.task, .subset), ...)
}
predictLearner.classif.lda1 = function(.learner, .model, .newdata, predict.method = "plug-in", ...) {
p = predict(.model$learner.model, newdata = .newdata, method = predict.method, ...)
if (.learner$predict.type == "response")
return(p$class) else return(p$posterior)
}
registerS3method("makeRLearner", "classif.lda1", makeRLearner.classif.lda1)
registerS3method("trainLearner", "classif.lda1", trainLearner.classif.lda1)
registerS3method("predictLearner", "classif.lda1", predictLearner.classif.lda1)
lrn = makeLearner("classif.lda1")
mod = train(lrn, iris.task)
pred = predict(mod, iris.task)