Internal Server Error

Description

While trying to run the following R code on nunes release get the following error
java.lang.ClassCastException: hex.deeplearning.DeepLearningModel cannot be cast to hex.GridSearch
at hex.GridSearch$GridSearchProgress.serve(GridSearch.java:74)
at water.api.Request.serveGrid(Request.java:165)
at water.Request2.superServeGrid(Request2.java:490)
at water.Request2.serveGrid(Request2.java:411)
at water.api.Request.serve(Request.java:142)
at water.api.RequestServer.serve(RequestServer.java:518)
at water.NanoHTTPD$HTTPSession.run(NanoHTTPD.java:425)
at java.lang.Thread.run(Thread.java:745)

R script :

  1. The following two commands remove any previously installed H2O packages for R.
    if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
    if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }

  1. Next, we download, install and initialize the H2O package for R.
    install.packages("h2o", repos=(c("http://h2o-release.s3.amazonaws.com/h2o/rel-nunes/2/R", getOption("repos"))))
    library(h2o)
    h = h2o.init()

pathToFile = "/Users/paragsanghavi/Documents/h2o/smalldata/airlines/AirlinesTrain.csv.zip"
data.hex = h2o.importFile(h, pathToFile)

  1.  

    1. Summary stats, columns to ignore, quantiles and histograms
      summary(data.hex)

  1. Constructing test and train sets by sampling
    data.split = h2o.splitFrame(data = data.hex,ratios = 0.85)
    data.train = data.split[[1]]
    data.test = data.split[[2]]

  1. Set predictor and response variables

  2. Print the header of the dataset
    myY = "IsDepDelayed"
    myX = c("Origin", "Dest", "fDayofMonth", "fYear", "UniqueCarrier", "fDayOfWeek", "fMonth", "DepTime", "ArrTime", "Distance")

    1. Deep Learning epoch = 10
      data.dl = h2o.deeplearning(y = "IsDepDelayed", x = myX, data = data.train, classification=TRUE, hidden=c(1000), hidden_dropout_ratios= c(0.5), epochs = 1)

Apparently , specifying c(0.5) in the hidden dropout ratio causes this problem

Activity

Show:
Arno Candel
May 15, 2015, 6:34 PM

Fixed.

Fixed
Your pinned fields
Click on the next to a field label to start pinning.

Assignee

Arno Candel

Reporter

Parag Sanghavi

CustomerVisible

No