[SPARK-17499][SparkR][ML][MLLib] make the default params in sparkR spark.mlp consistent with MultilayerPerceptronClassifier

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)
           })
 

R/pkg/inst/tests/testthat/test_mllib.R

@@ -383,6 +383,25 @@ 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", {

mllib/src/main/scala/org/apache/spark/ml/r/MultilayerPerceptronClassifierWrapper.scala

@@ -53,26 +53,26 @@ private[r] object MultilayerPerceptronClassifierWrapper
   def fit(
       data: DataFrame,
       blockSize: Int,
-      layers: Array[Double],
+      layers: Array[Int],
       solver: String,
       maxIter: Int,
       tol: Double,
       stepSize: Double,
-      seed: Int
+      seed: String
      ): MultilayerPerceptronClassifierWrapper = {
     // get labels and feature names from output schema
     val schema = data.schema
 
     // assemble and fit the pipeline
     val mlp = new MultilayerPerceptronClassifier()
-      .setLayers(layers.map(_.toInt))
+      .setLayers(layers)
       .setBlockSize(blockSize)
       .setSolver(solver)
       .setMaxIter(maxIter)
       .setTol(tol)
       .setStepSize(stepSize)
-      .setSeed(seed)
       .setPredictionCol(PREDICTED_LABEL_COL)
+    if (seed != null && seed.length > 0) mlp.setSeed(seed.toInt)
     val pipeline = new Pipeline()
       .setStages(Array(mlp))
       .fit(data)