diff options
author | WeichenXu <WeichenXu123@outlook.com> | 2016-09-23 11:14:22 -0700 |
---|---|---|
committer | Felix Cheung <felixcheung@apache.org> | 2016-09-23 11:14:22 -0700 |
commit | f89808b0fdbc04e1bdff1489a6ec4c84ddb2adc4 (patch) | |
tree | d7f2cb9d4e595f02e675b71ff19038fe203e2b1a /R/pkg | |
parent | 90d5754212425d55f992c939a2bc7d9ac6ef92b8 (diff) | |
download | spark-f89808b0fdbc04e1bdff1489a6ec4c84ddb2adc4.tar.gz spark-f89808b0fdbc04e1bdff1489a6ec4c84ddb2adc4.tar.bz2 spark-f89808b0fdbc04e1bdff1489a6ec4c84ddb2adc4.zip |
[SPARK-17499][SPARKR][ML][MLLIB] make the default params in sparkR spark.mlp consistent with MultilayerPerceptronClassifier
## What changes were proposed in this pull request?
update `MultilayerPerceptronClassifierWrapper.fit` paramter type:
`layers: Array[Int]`
`seed: String`
update several default params in sparkR `spark.mlp`:
`tol` --> 1e-6
`stepSize` --> 0.03
`seed` --> NULL ( when seed == NULL, the scala-side wrapper regard it as a `null` value and the seed will use the default one )
r-side `seed` only support 32bit integer.
remove `layers` default value, and move it in front of those parameters with default value.
add `layers` parameter validation check.
## How was this patch tested?
tests added.
Author: WeichenXu <WeichenXu123@outlook.com>
Closes #15051 from WeichenXu123/update_py_mlp_default.
Diffstat (limited to 'R/pkg')
-rw-r--r-- | R/pkg/R/mllib.R | 13 | ||||
-rw-r--r-- | R/pkg/inst/tests/testthat/test_mllib.R | 19 |
2 files changed, 29 insertions, 3 deletions
diff --git a/R/pkg/R/mllib.R b/R/pkg/R/mllib.R index 98db367a85..971c16658f 100644 --- a/R/pkg/R/mllib.R +++ b/R/pkg/R/mllib.R @@ -694,12 +694,19 @@ setMethod("predict", signature(object = "KMeansModel"), #' } #' @note spark.mlp since 2.1.0 setMethod("spark.mlp", signature(data = "SparkDataFrame"), - function(data, blockSize = 128, layers = c(3, 5, 2), solver = "l-bfgs", maxIter = 100, - tol = 0.5, stepSize = 1, seed = 1) { + function(data, layers, blockSize = 128, solver = "l-bfgs", maxIter = 100, + tol = 1E-6, stepSize = 0.03, seed = NULL) { + layers <- as.integer(na.omit(layers)) + if (length(layers) <= 1) { + stop ("layers must be a integer vector with length > 1.") + } + if (!is.null(seed)) { + seed <- as.character(as.integer(seed)) + } jobj <- callJStatic("org.apache.spark.ml.r.MultilayerPerceptronClassifierWrapper", "fit", data@sdf, as.integer(blockSize), as.array(layers), as.character(solver), as.integer(maxIter), as.numeric(tol), - as.numeric(stepSize), as.integer(seed)) + as.numeric(stepSize), seed) new("MultilayerPerceptronClassificationModel", jobj = jobj) }) diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R index 24c40a8823..a1eaaf2091 100644 --- a/R/pkg/inst/tests/testthat/test_mllib.R +++ b/R/pkg/inst/tests/testthat/test_mllib.R @@ -391,6 +391,25 @@ test_that("spark.mlp", { unlink(modelPath) + # Test default parameter + model <- spark.mlp(df, layers = c(4, 5, 4, 3)) + mlpPredictions <- collect(select(predict(model, mlpTestDF), "prediction")) + expect_equal(head(mlpPredictions$prediction, 10), c(1, 1, 1, 1, 0, 1, 2, 2, 1, 0)) + + # Test illegal parameter + expect_error(spark.mlp(df, layers = NULL), "layers must be a integer vector with length > 1.") + expect_error(spark.mlp(df, layers = c()), "layers must be a integer vector with length > 1.") + expect_error(spark.mlp(df, layers = c(3)), "layers must be a integer vector with length > 1.") + + # Test random seed + # default seed + model <- spark.mlp(df, layers = c(4, 5, 4, 3), maxIter = 10) + mlpPredictions <- collect(select(predict(model, mlpTestDF), "prediction")) + expect_equal(head(mlpPredictions$prediction, 12), c(1, 1, 1, 1, 0, 1, 2, 2, 1, 2, 0, 1)) + # seed equals 10 + model <- spark.mlp(df, layers = c(4, 5, 4, 3), maxIter = 10, seed = 10) + mlpPredictions <- collect(select(predict(model, mlpTestDF), "prediction")) + expect_equal(head(mlpPredictions$prediction, 12), c(1, 1, 1, 1, 2, 1, 2, 2, 1, 0, 0, 1)) }) test_that("spark.naiveBayes", { |