spark-mllib-RegressionEvaluator.adoc

RegressionEvaluator — Evaluator of Regression Models

RegressionEvaluator is an Evaluator of regression models (e.g. ALS, DecisionTreeRegressor, DecisionTreeClassifier, GBTRegressor, GBTClassifier, RandomForestRegressor, RandomForestClassifier, LinearRegression, RFormula, NaiveBayes, LogisticRegression, MultilayerPerceptronClassifier, LinearSVC, GeneralizedLinearRegression).

Table 1. RegressionEvaluator’s Metrics and isLargerBetter Flag

Metric	Description	isLargerBetter
rmse	Root mean squared error	false
mse	Mean squared error	false
r2	(default) Unadjusted coefficient of determination Regression through the origin	true
mae	Mean absolute error	false

import org.apache.spark.ml.evaluation.RegressionEvaluator
val regEval = new RegressionEvaluator().
  setMetricName("r2").
  setPredictionCol("prediction").
  setLabelCol("label")

scala> regEval.isLargerBetter
res0: Boolean = true

scala> println(regEval.explainParams)
labelCol: label column name (default: label, current: label)
metricName: metric name in evaluation (mse|rmse|r2|mae) (default: rmse, current: r2)
predictionCol: prediction column name (default: prediction, current: prediction)

Table 2. RegressionEvaluator' Parameters

Parameter	Default Value	Description
metricName	areaUnderROC	Name of the classification metric for evaluation Can be one of the following: mae, mse, rmse (default), r2
predictionCol	prediction	Name of the column with predictions
labelCol	label	Name of the column with indexed labels

// prepare a fake input dataset using transformers
import org.apache.spark.ml.feature.Tokenizer
val tok = new Tokenizer().setInputCol("text")

import org.apache.spark.ml.feature.HashingTF
val hashTF = new HashingTF()
  .setInputCol(tok.getOutputCol)  // it reads the output of tok
  .setOutputCol("features")

// Scala trick to chain transform methods
// It's of little to no use since we've got Pipelines
// Just to have it as an alternative
val transform = (tok.transform _).andThen(hashTF.transform _)

val dataset = Seq((0, "hello world", 0.0)).toDF("id", "text", "label")

// we're using Linear Regression algorithm
import org.apache.spark.ml.regression.LinearRegression
val lr = new LinearRegression

import org.apache.spark.ml.Pipeline
val pipeline = new Pipeline().setStages(Array(tok, hashTF, lr))

val model = pipeline.fit(dataset)

// Let's do prediction
// Note that we're using the same dataset as for fitting the model
// Something you'd definitely not be doing in prod
val predictions = model.transform(dataset)

// Now we're ready to evaluate the model
// Evaluator works on datasets with predictions

import org.apache.spark.ml.evaluation.RegressionEvaluator
val regEval = new RegressionEvaluator

scala> regEval.evaluate(predictions)
res0: Double = 0.0

Evaluating Model Output — evaluate Method

evaluate(dataset: Dataset[_]): Double

Note	evaluate is part of Evaluator Contract.

evaluate…​FIXME