Binomial classification example in Scala and GBM with H2O

Here is a sample for binomial classification problem using H2O GBM algorithm using Credit Card data set in Scala language.

The following sample is for multinomial classification problem. This sample is created using Spark 2.1.0 with Sparkling Water 2.1.4.

import org.apache.spark.h2o._
import water.support.SparkContextSupport.addFiles
import org.apache.spark.SparkFiles
import java.io.File
import water.support.{H2OFrameSupport, SparkContextSupport, ModelMetricsSupport}
import water.Key
import _root_.hex.glm.GLMModel
import _root_.hex.ModelMetricsBinomial


val hc = H2OContext.getOrCreate(sc)
import hc._
import hc.implicits._

addFiles(sc, "/Users/avkashchauhan/learn/deepwater/credit_card_clients.csv")
val creditCardData = new H2OFrame(new File(SparkFiles.get("credit_card_clients.csv")))

val ratios = Array[Double](0.8)
val keys = Array[String]("train.hex", "valid.hex")
val frs = H2OFrameSupport.split(creditCardData, keys, ratios)
val (train, valid) = (frs(0), frs(1))

def buildGLMModel(train: Frame, valid: Frame, response: String)
 (implicit h2oContext: H2OContext): GLMModel = {
 import _root_.hex.glm.GLMModel.GLMParameters.Family
 import _root_.hex.glm.GLM
 import _root_.hex.glm.GLMModel.GLMParameters
 val glmParams = new GLMParameters(Family.binomial)
 glmParams._train = train
 glmParams._valid = valid
 glmParams._response_column = response
 glmParams._alpha = Array[Double](0.5)
 val glm = new GLM(glmParams, Key.make("glmModel.hex"))
 glm.trainModel().get()
 //val glmModel = glm.trainModel().get()
}

val glmModel = buildGLMModel(train, valid, 'default_payment_next_month)(hc)

// Collect model metrics and evaluate model quality
val trainMetrics = ModelMetricsSupport.modelMetrics[ModelMetricsBinomial](glmModel, train)
val validMetrics = ModelMetricsSupport.modelMetrics[ModelMetricsBinomial](glmModel, valid)
println(trainMetrics.rmse)
println(validMetrics.rmse)
println(trainMetrics.mse)
println(validMetrics.mse)
println(trainMetrics.r2)
println(validMetrics.r2)
println(trainMetrics.auc)
println(validMetrics.auc)

// Preduction
addFiles(sc, "/Users/avkashchauhan/learn/deepwater/credit_card_predict.csv")
val creditPredictData = new H2OFrame(new File(SparkFiles.get("credit_card_predict.csv")))

val predictionFrame = glmModel.score(creditPredictData)
var predictonResults = asRDD[DoubleHolder](predictionFrame).collect.map(_.result.getOrElse(Double.NaN))

Thats it, enjoy!!

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s