我有以下r配置:
操作系统:linux r版本3.0.1(2013-05-16)rmr2版本2.2.1 rhdfs版本1.0.6 hadoop版本1.2.0
如何使用hadoop和rmr2包转换svm模型的结果?所以我可以像平常一样使用构建的模型,比如:
predict(svm1, "new data")
我有以下代码:
# set eviremonet variables
Sys.setenv(HADOOP_CMD="~/Downloads/hadoop-1.2.0/bin/hadoop")
Sys.setenv(HADOOP_HOME="~/Downloads/hadoop-1.2.0/")
# start hadoop
# load librarys
library(rmr2)
library(rhdfs)
library(e1071)
# load sample data
data(iris)
# init hdfs
hdfs.init()
# push data to hdfs
iris.dfs <- to.dfs(iris)
# define map function
iris.map <- function(k, v)
{
svm(v$Species ~ ., data=v)
}
# rum mar job
iris.svm <- mapreduce(input=iris.dfs, map=iris.map)
# get result back
iris.res <- from.dfs(iris.svm)
svm1 <- svm(iris$Species ~ ., data=iris)
class(iris.res)
class(svm1)
两个课程的结果如下:
> class(iris.res)
[1] "list"
> class(svm1)
[1] "svm.formula" "svm"
> str(svm1)
List of 30
$ call : language svm(formula = iris$Species ~ ., data = iris)
$ type : num 0
$ kernel : num 2
$ cost : num 1
$ degree : num 3
$ gamma : num 0,25
$ coef0 : num 0
$ nu : num 0,5
$ epsilon : num 0,1
$ sparse : logi FALSE
$ scaled : logi [1:4] TRUE TRUE TRUE TRUE
$ x.scale :List of 2
..$ scaled:center: Named num [1:4] 5,84 3,06 3,76 1,20
.. ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
..$ scaled:scale : Named num [1:4] 0,828 0,436 1,765 0,762
.. ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
$ y.scale : NULL
$ nclasses : int 3
$ levels : chr [1:3] "setosa" "versicolor" "virginica"
$ tot.nSV : int 51
$ nSV : int [1:3] 8 22 21
$ labels : int [1:3] 1 2 3
$ SV : num [1:51, 1:4] -1,743 -1,864 -0,173 -0,535 -1,501 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:51] "9" "14" "16" "21" ...
.. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
$ index : int [1:51] 9 14 16 21 23 24 26 42 51 53 ...
$ rho : num [1:3] -0,0203 0,1312 -0,0629
$ compprob : logi FALSE
$ probA : NULL
$ probB : NULL
$ sigma : NULL
$ coefs : num [1:51, 1:2] 0,0891 0,0000 0,8652 0,0000 0,0000 ...
$ na.action : NULL
$ fitted : 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" ...
$ decision.values: num [1:150, 1:3] 1,20 1,06 1,18 1,11 1,19 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:150] "1" "2" "3" "4" ...
.. ..$ : chr [1:3] "setosa/versicolor" "setosa/virginica" "versicolor/virginica"
$ terms :Classes 'terms', 'formula' length 3 iris$Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width
.. ..- attr(*, "variables")= language list(iris$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] "iris$Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
.. .. .. ..$ : 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: R_GlobalEnv>
.. ..- attr(*, "predvars")= language list(iris$Species, Sepal.Length, Sepal.Width, Petal.Length, Petal.Width)
.. ..- attr(*, "dataClasses")= Named chr [1:5] "factor" "numeric" "numeric" "numeric" ...
.. .. ..- attr(*, "names")= chr [1:5] "iris$Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
- attr(*, "class")= chr [1:2] "svm.formula" "svm"
> str(iris.res)
List of 2
$ key: NULL
$ val:List of 30
..$ call : language svm(formula = v$Species ~ ., data = v)
..$ type : num 0
..$ kernel : num 2
..$ cost : num 1
..$ degree : num 3
..$ gamma : num 0,25
..$ coef0 : num 0
..$ nu : num 0,5
..$ epsilon : num 0,1
..$ sparse : logi FALSE
..$ scaled : logi [1:4] TRUE TRUE TRUE TRUE
..$ x.scale :List of 2
.. ..$ scaled:center: Named num [1:4] 5,84 3,06 3,76 1,20
.. .. ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
.. ..$ scaled:scale : Named num [1:4] 0,828 0,436 1,765 0,762
.. .. ..- attr(*, "names")= chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
..$ y.scale : NULL
..$ nclasses : int 3
..$ levels : chr [1:3] "setosa" "versicolor" "virginica"
..$ tot.nSV : int 51
..$ nSV : int [1:3] 8 22 21
..$ labels : int [1:3] 1 2 3
..$ SV : num [1:51, 1:4] -1,743 -1,864 -0,173 -0,535 -1,501 ...
.. ..- attr(*, "dimnames")=List of 2
.. .. ..$ : chr [1:51] "9" "14" "16" "21" ...
.. .. ..$ : chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
..$ index : int [1:51] 9 14 16 21 23 24 26 42 51 53 ...
..$ rho : num [1:3] -0,0203 0,1312 -0,0629
..$ compprob : logi FALSE
..$ probA : NULL
..$ probB : NULL
..$ sigma : NULL
..$ coefs : num [1:51, 1:2] 0,0891 0,0000 0,8652 0,0000 0,0000 ...
..$ na.action : NULL
..$ fitted : 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" ...
..$ decision.values: num [1:150, 1:3] 1,20 1,06 1,18 1,11 1,19 ...
.. ..- attr(*, "dimnames")=List of 2
.. .. ..$ : chr [1:150] "1" "2" "3" "4" ...
.. .. ..$ : chr [1:3] "setosa/versicolor" "setosa/virginica" "versicolor/virginica"
..$ terms :Classes 'terms', 'formula' length 3 v$Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width
.. .. ..- attr(*, "variables")= language list(v$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] "v$Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
.. .. .. .. ..$ : 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: 0xb639820>
.. .. ..- attr(*, "predvars")= language list(v$Species, Sepal.Length, Sepal.Width, Petal.Length, Petal.Width)
.. .. ..- attr(*, "dataClasses")= Named chr [1:5] "factor" "numeric" "numeric" "numeric" ...
.. .. .. ..- attr(*, "names")= chr [1:5] "v$Species" "Sepal.Length" "Sepal.Width" "Petal.Length" ...
但是如何将结果列表转换为与通常smv调用相同的类呢?
1条答案
按热度按时间fgw7neuy1#
包起来就行了
svm(v$Species ~ ., data=v)
在一个list
调用map函数,如中所示list(svm(v$Species ~ ., data=v))
. Map只能返回列表、矩阵、向量和Dataframe。如果您返回了一个模型(显然不是我故意实现的),它将被强制到一个列表中。也许我可以防御性地这样做,每当返回值不是四个支持的值之一时,只要一巴掌list
但我不想太聪明,做太多的猜测。您的方法的另一个问题是map函数将在数据集的任意子集上被调用(对于较大的数据集),因此您将在输出中得到一个模型列表(在您对输出调用值之后)。所以现在你有多个支持向量机,你做什么,你把它当作一个陷阱?但是map阶段的子集是任意的,它们没有任何统计特性,比如随机化。在我看来,你认为rmr有超能力使svm函数并行分布,但它没有,它只会在不同数据块的集群上并行调用它。在一个小例子中,只有一个块,但这是骗人的。尝试rmr.options(keyval.length = 3)
看看非常小的块会发生什么(不是为了生产)。另一种方法是在单机上加载的最大样本上构建模型,然后并行运行predict。当然,这在学习阶段没有那么大的可伸缩性,但我知道一些大的初创公司就是这样做的。看看乌里拉塞森(urilaserson)在cloudera博客上的重采样文章,我想它会给你一些好主意。最后,我们有一个专门的论坛,为rmr和谷歌集团的相关软件包,你非常欢迎加入我们的社区。