Multiclass classification model evaluation using Spark 2.0

In this recipe, we explore MulticlassMetrics, which allows you to evaluate a model that classifies the output to more than two labels (for example, red, blue, green, purple, do-not-know). It highlights the use of a confusion matrix (confusionMatrix) and model accuracy.

How to do it...

1. Start a new project in IntelliJ or in an IDE of your choice. Make sure that the necessary JAR files are included.

2. Set up the package location where the program will reside:

package spark.ml.cookbook.chapter4

3. Import the necessary packages for SparkContext to get access to the cluster:

import org.apache.spark.sql.SparkSession
import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS
import org.apache.spark.mllib.evaluation.MulticlassMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils

4. Create Spark's configuration and SparkContext:

val spark = SparkSession
.builder
.master("local[*]")
.appName...