評価指標 - RDDベースAPI

from pyspark.mllib.classification import LogisticRegressionWithLBFGS
from pyspark.mllib.evaluation import BinaryClassificationMetrics
from pyspark.mllib.util import MLUtils

# Several of the methods available in scala are currently missing from pyspark
# Load training data in LIBSVM format
data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")

# Split data into training (60%) and test (40%)
training, test = data.randomSplit([0.6, 0.4], seed=11)
training.cache()

# Run training algorithm to build the model
model = LogisticRegressionWithLBFGS.train(training)

# Compute raw scores on the test set
predictionAndLabels = test.map(lambda lp: (float(model.predict(lp.features)), lp.label))

# Instantiate metrics object
metrics = BinaryClassificationMetrics(predictionAndLabels)

# Area under precision-recall curve
print("Area under PR = %s" % metrics.areaUnderPR)

# Area under ROC curve
print("Area under ROC = %s" % metrics.areaUnderROC)

import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils

// Load training data in LIBSVM format
val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")

// Split data into training (60%) and test (40%)
val Array(training, test) = data.randomSplit(Array(0.6, 0.4), seed = 11L)
training.cache()

// Run training algorithm to build the model
val model = new LogisticRegressionWithLBFGS()
  .setNumClasses(2)
  .run(training)

// Clear the prediction threshold so the model will return probabilities
model.clearThreshold()

// Compute raw scores on the test set
val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
  val prediction = model.predict(features)
  (prediction, label)
}

// Instantiate metrics object
val metrics = new BinaryClassificationMetrics(predictionAndLabels)

// Precision by threshold
val precision = metrics.precisionByThreshold()
precision.collect().foreach { case (t, p) =>
  println(s"Threshold: $t, Precision: $p")
}

// Recall by threshold
val recall = metrics.recallByThreshold()
recall.collect().foreach { case (t, r) =>
  println(s"Threshold: $t, Recall: $r")
}

// Precision-Recall Curve
val PRC = metrics.pr()

// F-measure
val f1Score = metrics.fMeasureByThreshold()
f1Score.collect().foreach { case (t, f) =>
  println(s"Threshold: $t, F-score: $f, Beta = 1")
}

val beta = 0.5
val fScore = metrics.fMeasureByThreshold(beta)
fScore.collect().foreach { case (t, f) =>
  println(s"Threshold: $t, F-score: $f, Beta = 0.5")
}

// AUPRC
val auPRC = metrics.areaUnderPR()
println(s"Area under precision-recall curve = $auPRC")

// Compute thresholds used in ROC and PR curves
val thresholds = precision.map(_._1)

// ROC Curve
val roc = metrics.roc()

// AUROC
val auROC = metrics.areaUnderROC()
println(s"Area under ROC = $auROC")

import scala.Tuple2;

import org.apache.spark.api.java.*;
import org.apache.spark.mllib.classification.LogisticRegressionModel;
import org.apache.spark.mllib.classification.LogisticRegressionWithLBFGS;
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;

String path = "data/mllib/sample_binary_classification_data.txt";
JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc, path).toJavaRDD();

// Split initial RDD into two... [60% training data, 40% testing data].
JavaRDD<LabeledPoint>[] splits =
  data.randomSplit(new double[]{0.6, 0.4}, 11L);
JavaRDD<LabeledPoint> training = splits[0].cache();
JavaRDD<LabeledPoint> test = splits[1];

// Run training algorithm to build the model.
LogisticRegressionModel model = new LogisticRegressionWithLBFGS()
  .setNumClasses(2)
  .run(training.rdd());

// Clear the prediction threshold so the model will return probabilities
model.clearThreshold();

// Compute raw scores on the test set.
JavaPairRDD<Object, Object> predictionAndLabels = test.mapToPair(p ->
  new Tuple2<>(model.predict(p.features()), p.label()));

// Get evaluation metrics.
BinaryClassificationMetrics metrics =
  new BinaryClassificationMetrics(predictionAndLabels.rdd());

// Precision by threshold
JavaRDD<Tuple2<Object, Object>> precision = metrics.precisionByThreshold().toJavaRDD();
System.out.println("Precision by threshold: " + precision.collect());

// Recall by threshold
JavaRDD<?> recall = metrics.recallByThreshold().toJavaRDD();
System.out.println("Recall by threshold: " + recall.collect());

// F Score by threshold
JavaRDD<?> f1Score = metrics.fMeasureByThreshold().toJavaRDD();
System.out.println("F1 Score by threshold: " + f1Score.collect());

JavaRDD<?> f2Score = metrics.fMeasureByThreshold(2.0).toJavaRDD();
System.out.println("F2 Score by threshold: " + f2Score.collect());

// Precision-recall curve
JavaRDD<?> prc = metrics.pr().toJavaRDD();
System.out.println("Precision-recall curve: " + prc.collect());

// Thresholds
JavaRDD<Double> thresholds = precision.map(t -> Double.parseDouble(t._1().toString()));

// ROC Curve
JavaRDD<?> roc = metrics.roc().toJavaRDD();
System.out.println("ROC curve: " + roc.collect());

// AUPRC
System.out.println("Area under precision-recall curve = " + metrics.areaUnderPR());

// AUROC
System.out.println("Area under ROC = " + metrics.areaUnderROC());

// Save and load model
model.save(sc, "target/tmp/LogisticRegressionModel");
LogisticRegressionModel.load(sc, "target/tmp/LogisticRegressionModel");

from pyspark.mllib.classification import LogisticRegressionWithLBFGS
from pyspark.mllib.util import MLUtils
from pyspark.mllib.evaluation import MulticlassMetrics

# Load training data in LIBSVM format
data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_multiclass_classification_data.txt")

# Split data into training (60%) and test (40%)
training, test = data.randomSplit([0.6, 0.4], seed=11)
training.cache()

# Run training algorithm to build the model
model = LogisticRegressionWithLBFGS.train(training, numClasses=3)

# Compute raw scores on the test set
predictionAndLabels = test.map(lambda lp: (float(model.predict(lp.features)), lp.label))

# Instantiate metrics object
metrics = MulticlassMetrics(predictionAndLabels)

# Overall statistics
precision = metrics.precision(1.0)
recall = metrics.recall(1.0)
f1Score = metrics.fMeasure(1.0)
print("Summary Stats")
print("Precision = %s" % precision)
print("Recall = %s" % recall)
print("F1 Score = %s" % f1Score)

# Statistics by class
labels = data.map(lambda lp: lp.label).distinct().collect()
for label in sorted(labels):
    print("Class %s precision = %s" % (label, metrics.precision(label)))
    print("Class %s recall = %s" % (label, metrics.recall(label)))
    print("Class %s F1 Measure = %s" % (label, metrics.fMeasure(label, beta=1.0)))

# Weighted stats
print("Weighted recall = %s" % metrics.weightedRecall)
print("Weighted precision = %s" % metrics.weightedPrecision)
print("Weighted F(1) Score = %s" % metrics.weightedFMeasure())
print("Weighted F(0.5) Score = %s" % metrics.weightedFMeasure(beta=0.5))
print("Weighted false positive rate = %s" % metrics.weightedFalsePositiveRate)

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

// Load training data in LIBSVM format
val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_multiclass_classification_data.txt")

// Split data into training (60%) and test (40%)
val Array(training, test) = data.randomSplit(Array(0.6, 0.4), seed = 11L)
training.cache()

// Run training algorithm to build the model
val model = new LogisticRegressionWithLBFGS()
  .setNumClasses(3)
  .run(training)

// Compute raw scores on the test set
val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
  val prediction = model.predict(features)
  (prediction, label)
}

// Instantiate metrics object
val metrics = new MulticlassMetrics(predictionAndLabels)

// Confusion matrix
println("Confusion matrix:")
println(metrics.confusionMatrix)

// Overall Statistics
val accuracy = metrics.accuracy
println("Summary Statistics")
println(s"Accuracy = $accuracy")

// Precision by label
val labels = metrics.labels
labels.foreach { l =>
  println(s"Precision($l) = " + metrics.precision(l))
}

// Recall by label
labels.foreach { l =>
  println(s"Recall($l) = " + metrics.recall(l))
}

// False positive rate by label
labels.foreach { l =>
  println(s"FPR($l) = " + metrics.falsePositiveRate(l))
}

// F-measure by label
labels.foreach { l =>
  println(s"F1-Score($l) = " + metrics.fMeasure(l))
}

// Weighted stats
println(s"Weighted precision: ${metrics.weightedPrecision}")
println(s"Weighted recall: ${metrics.weightedRecall}")
println(s"Weighted F1 score: ${metrics.weightedFMeasure}")
println(s"Weighted false positive rate: ${metrics.weightedFalsePositiveRate}")

import scala.Tuple2;

import org.apache.spark.api.java.*;
import org.apache.spark.mllib.classification.LogisticRegressionModel;
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;
import org.apache.spark.mllib.linalg.Matrix;

String path = "data/mllib/sample_multiclass_classification_data.txt";
JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc, path).toJavaRDD();

// Split initial RDD into two... [60% training data, 40% testing data].
JavaRDD<LabeledPoint>[] splits = data.randomSplit(new double[]{0.6, 0.4}, 11L);
JavaRDD<LabeledPoint> training = splits[0].cache();
JavaRDD<LabeledPoint> test = splits[1];

// Run training algorithm to build the model.
LogisticRegressionModel model = new LogisticRegressionWithLBFGS()
  .setNumClasses(3)
  .run(training.rdd());

// Compute raw scores on the test set.
JavaPairRDD<Object, Object> predictionAndLabels = test.mapToPair(p ->
  new Tuple2<>(model.predict(p.features()), p.label()));

// Get evaluation metrics.
MulticlassMetrics metrics = new MulticlassMetrics(predictionAndLabels.rdd());

// Confusion matrix
Matrix confusion = metrics.confusionMatrix();
System.out.println("Confusion matrix: \n" + confusion);

// Overall statistics
System.out.println("Accuracy = " + metrics.accuracy());

// Stats by labels
for (int i = 0; i < metrics.labels().length; i++) {
  System.out.format("Class %f precision = %f\n", metrics.labels()[i],metrics.precision(
    metrics.labels()[i]));
  System.out.format("Class %f recall = %f\n", metrics.labels()[i], metrics.recall(
    metrics.labels()[i]));
  System.out.format("Class %f F1 score = %f\n", metrics.labels()[i], metrics.fMeasure(
    metrics.labels()[i]));
}

//Weighted stats
System.out.format("Weighted precision = %f\n", metrics.weightedPrecision());
System.out.format("Weighted recall = %f\n", metrics.weightedRecall());
System.out.format("Weighted F1 score = %f\n", metrics.weightedFMeasure());
System.out.format("Weighted false positive rate = %f\n", metrics.weightedFalsePositiveRate());

// Save and load model
model.save(sc, "target/tmp/LogisticRegressionModel");
LogisticRegressionModel sameModel = LogisticRegressionModel.load(sc,
  "target/tmp/LogisticRegressionModel");

from pyspark.mllib.evaluation import MultilabelMetrics

scoreAndLabels = sc.parallelize([
    ([0.0, 1.0], [0.0, 2.0]),
    ([0.0, 2.0], [0.0, 1.0]),
    ([], [0.0]),
    ([2.0], [2.0]),
    ([2.0, 0.0], [2.0, 0.0]),
    ([0.0, 1.0, 2.0], [0.0, 1.0]),
    ([1.0], [1.0, 2.0])])

# Instantiate metrics object
metrics = MultilabelMetrics(scoreAndLabels)

# Summary stats
print("Recall = %s" % metrics.recall())
print("Precision = %s" % metrics.precision())
print("F1 measure = %s" % metrics.f1Measure())
print("Accuracy = %s" % metrics.accuracy)

# Individual label stats
labels = scoreAndLabels.flatMap(lambda x: x[1]).distinct().collect()
for label in labels:
    print("Class %s precision = %s" % (label, metrics.precision(label)))
    print("Class %s recall = %s" % (label, metrics.recall(label)))
    print("Class %s F1 Measure = %s" % (label, metrics.f1Measure(label)))

# Micro stats
print("Micro precision = %s" % metrics.microPrecision)
print("Micro recall = %s" % metrics.microRecall)
print("Micro F1 measure = %s" % metrics.microF1Measure)

# Hamming loss
print("Hamming loss = %s" % metrics.hammingLoss)

# Subset accuracy
print("Subset accuracy = %s" % metrics.subsetAccuracy)

import org.apache.spark.mllib.evaluation.MultilabelMetrics
import org.apache.spark.rdd.RDD

val scoreAndLabels: RDD[(Array[Double], Array[Double])] = sc.parallelize(
  Seq((Array(0.0, 1.0), Array(0.0, 2.0)),
    (Array(0.0, 2.0), Array(0.0, 1.0)),
    (Array.empty[Double], Array(0.0)),
    (Array(2.0), Array(2.0)),
    (Array(2.0, 0.0), Array(2.0, 0.0)),
    (Array(0.0, 1.0, 2.0), Array(0.0, 1.0)),
    (Array(1.0), Array(1.0, 2.0))), 2)

// Instantiate metrics object
val metrics = new MultilabelMetrics(scoreAndLabels)

// Summary stats
println(s"Recall = ${metrics.recall}")
println(s"Precision = ${metrics.precision}")
println(s"F1 measure = ${metrics.f1Measure}")
println(s"Accuracy = ${metrics.accuracy}")

// Individual label stats
metrics.labels.foreach(label =>
  println(s"Class $label precision = ${metrics.precision(label)}"))
metrics.labels.foreach(label => println(s"Class $label recall = ${metrics.recall(label)}"))
metrics.labels.foreach(label => println(s"Class $label F1-score = ${metrics.f1Measure(label)}"))

// Micro stats
println(s"Micro recall = ${metrics.microRecall}")
println(s"Micro precision = ${metrics.microPrecision}")
println(s"Micro F1 measure = ${metrics.microF1Measure}")

// Hamming loss
println(s"Hamming loss = ${metrics.hammingLoss}")

// Subset accuracy
println(s"Subset accuracy = ${metrics.subsetAccuracy}")

import java.util.Arrays;
import java.util.List;

import scala.Tuple2;

import org.apache.spark.api.java.*;
import org.apache.spark.mllib.evaluation.MultilabelMetrics;
import org.apache.spark.SparkConf;

List<Tuple2<double[], double[]>> data = Arrays.asList(
  new Tuple2<>(new double[]{0.0, 1.0}, new double[]{0.0, 2.0}),
  new Tuple2<>(new double[]{0.0, 2.0}, new double[]{0.0, 1.0}),
  new Tuple2<>(new double[]{}, new double[]{0.0}),
  new Tuple2<>(new double[]{2.0}, new double[]{2.0}),
  new Tuple2<>(new double[]{2.0, 0.0}, new double[]{2.0, 0.0}),
  new Tuple2<>(new double[]{0.0, 1.0, 2.0}, new double[]{0.0, 1.0}),
  new Tuple2<>(new double[]{1.0}, new double[]{1.0, 2.0})
);
JavaRDD<Tuple2<double[], double[]>> scoreAndLabels = sc.parallelize(data);

// Instantiate metrics object
MultilabelMetrics metrics = new MultilabelMetrics(scoreAndLabels.rdd());

// Summary stats
System.out.format("Recall = %f\n", metrics.recall());
System.out.format("Precision = %f\n", metrics.precision());
System.out.format("F1 measure = %f\n", metrics.f1Measure());
System.out.format("Accuracy = %f\n", metrics.accuracy());

// Stats by labels
for (int i = 0; i < metrics.labels().length - 1; i++) {
  System.out.format("Class %1.1f precision = %f\n", metrics.labels()[i], metrics.precision(
    metrics.labels()[i]));
  System.out.format("Class %1.1f recall = %f\n", metrics.labels()[i], metrics.recall(
    metrics.labels()[i]));
  System.out.format("Class %1.1f F1 score = %f\n", metrics.labels()[i], metrics.f1Measure(
    metrics.labels()[i]));
}

// Micro stats
System.out.format("Micro recall = %f\n", metrics.microRecall());
System.out.format("Micro precision = %f\n", metrics.microPrecision());
System.out.format("Micro F1 measure = %f\n", metrics.microF1Measure());

// Hamming loss
System.out.format("Hamming loss = %f\n", metrics.hammingLoss());

// Subset accuracy
System.out.format("Subset accuracy = %f\n", metrics.subsetAccuracy());

from pyspark.mllib.recommendation import ALS, Rating
from pyspark.mllib.evaluation import RegressionMetrics

# Read in the ratings data
lines = sc.textFile("data/mllib/sample_movielens_data.txt")

def parseLine(line):
    fields = line.split("::")
    return Rating(int(fields[0]), int(fields[1]), float(fields[2]) - 2.5)
ratings = lines.map(lambda r: parseLine(r))

# Train a model on to predict user-product ratings
model = ALS.train(ratings, 10, 10, 0.01)

# Get predicted ratings on all existing user-product pairs
testData = ratings.map(lambda p: (p.user, p.product))
predictions = model.predictAll(testData).map(lambda r: ((r.user, r.product), r.rating))

ratingsTuple = ratings.map(lambda r: ((r.user, r.product), r.rating))
scoreAndLabels = predictions.join(ratingsTuple).map(lambda tup: tup[1])

# Instantiate regression metrics to compare predicted and actual ratings
metrics = RegressionMetrics(scoreAndLabels)

# Root mean squared error
print("RMSE = %s" % metrics.rootMeanSquaredError)

# R-squared
print("R-squared = %s" % metrics.r2)

import org.apache.spark.mllib.evaluation.{RankingMetrics, RegressionMetrics}
import org.apache.spark.mllib.recommendation.{ALS, Rating}

// Read in the ratings data
val ratings = spark.read.textFile("data/mllib/sample_movielens_data.txt").rdd.map { line =>
  val fields = line.split("::")
  Rating(fields(0).toInt, fields(1).toInt, fields(2).toDouble - 2.5)
}.cache()

// Map ratings to 1 or 0, 1 indicating a movie that should be recommended
val binarizedRatings = ratings.map(r => Rating(r.user, r.product,
  if (r.rating > 0) 1.0 else 0.0)).cache()

// Summarize ratings
val numRatings = ratings.count()
val numUsers = ratings.map(_.user).distinct().count()
val numMovies = ratings.map(_.product).distinct().count()
println(s"Got $numRatings ratings from $numUsers users on $numMovies movies.")

// Build the model
val numIterations = 10
val rank = 10
val lambda = 0.01
val model = ALS.train(ratings, rank, numIterations, lambda)

// Define a function to scale ratings from 0 to 1
def scaledRating(r: Rating): Rating = {
  val scaledRating = math.max(math.min(r.rating, 1.0), 0.0)
  Rating(r.user, r.product, scaledRating)
}

// Get sorted top ten predictions for each user and then scale from [0, 1]
val userRecommended = model.recommendProductsForUsers(10).map { case (user, recs) =>
  (user, recs.map(scaledRating))
}

// Assume that any movie a user rated 3 or higher (which maps to a 1) is a relevant document
// Compare with top ten most relevant documents
val userMovies = binarizedRatings.groupBy(_.user)
val relevantDocuments = userMovies.join(userRecommended).map { case (user, (actual,
predictions)) =>
  (predictions.map(_.product), actual.filter(_.rating > 0.0).map(_.product).toArray)
}

// Instantiate metrics object
val metrics = new RankingMetrics(relevantDocuments)

// Precision at K
Array(1, 3, 5).foreach { k =>
  println(s"Precision at $k = ${metrics.precisionAt(k)}")
}

// Mean average precision
println(s"Mean average precision = ${metrics.meanAveragePrecision}")

// Mean average precision at k
println(s"Mean average precision at 2 = ${metrics.meanAveragePrecisionAt(2)}")

// Normalized discounted cumulative gain
Array(1, 3, 5).foreach { k =>
  println(s"NDCG at $k = ${metrics.ndcgAt(k)}")
}

// Recall at K
Array(1, 3, 5).foreach { k =>
  println(s"Recall at $k = ${metrics.recallAt(k)}")
}

// Get predictions for each data point
val allPredictions = model.predict(ratings.map(r => (r.user, r.product))).map(r => ((r.user,
  r.product), r.rating))
val allRatings = ratings.map(r => ((r.user, r.product), r.rating))
val predictionsAndLabels = allPredictions.join(allRatings).map { case ((user, product),
(predicted, actual)) =>
  (predicted, actual)
}

// Get the RMSE using regression metrics
val regressionMetrics = new RegressionMetrics(predictionsAndLabels)
println(s"RMSE = ${regressionMetrics.rootMeanSquaredError}")

// R-squared
println(s"R-squared = ${regressionMetrics.r2}")

import java.util.*;

import scala.Tuple2;

import org.apache.spark.api.java.*;
import org.apache.spark.mllib.evaluation.RegressionMetrics;
import org.apache.spark.mllib.evaluation.RankingMetrics;
import org.apache.spark.mllib.recommendation.ALS;
import org.apache.spark.mllib.recommendation.MatrixFactorizationModel;
import org.apache.spark.mllib.recommendation.Rating;

String path = "data/mllib/sample_movielens_data.txt";
JavaRDD<String> data = sc.textFile(path);
JavaRDD<Rating> ratings = data.map(line -> {
    String[] parts = line.split("::");
    return new Rating(Integer.parseInt(parts[0]), Integer.parseInt(parts[1]), Double
        .parseDouble(parts[2]) - 2.5);
  });
ratings.cache();

// Train an ALS model
MatrixFactorizationModel model = ALS.train(JavaRDD.toRDD(ratings), 10, 10, 0.01);

// Get top 10 recommendations for every user and scale ratings from 0 to 1
JavaRDD<Tuple2<Object, Rating[]>> userRecs = model.recommendProductsForUsers(10).toJavaRDD();
JavaRDD<Tuple2<Object, Rating[]>> userRecsScaled = userRecs.map(t -> {
    Rating[] scaledRatings = new Rating[t._2().length];
    for (int i = 0; i < scaledRatings.length; i++) {
      double newRating = Math.max(Math.min(t._2()[i].rating(), 1.0), 0.0);
      scaledRatings[i] = new Rating(t._2()[i].user(), t._2()[i].product(), newRating);
    }
    return new Tuple2<>(t._1(), scaledRatings);
  });
JavaPairRDD<Object, Rating[]> userRecommended = JavaPairRDD.fromJavaRDD(userRecsScaled);

// Map ratings to 1 or 0, 1 indicating a movie that should be recommended
JavaRDD<Rating> binarizedRatings = ratings.map(r -> {
    double binaryRating;
    if (r.rating() > 0.0) {
      binaryRating = 1.0;
    } else {
      binaryRating = 0.0;
    }
    return new Rating(r.user(), r.product(), binaryRating);
  });

// Group ratings by common user
JavaPairRDD<Object, Iterable<Rating>> userMovies = binarizedRatings.groupBy(Rating::user);

// Get true relevant documents from all user ratings
JavaPairRDD<Object, List<Integer>> userMoviesList = userMovies.mapValues(docs -> {
    List<Integer> products = new ArrayList<>();
    for (Rating r : docs) {
      if (r.rating() > 0.0) {
        products.add(r.product());
      }
    }
    return products;
  });

// Extract the product id from each recommendation
JavaPairRDD<Object, List<Integer>> userRecommendedList = userRecommended.mapValues(docs -> {
    List<Integer> products = new ArrayList<>();
    for (Rating r : docs) {
      products.add(r.product());
    }
    return products;
  });
JavaRDD<Tuple2<List<Integer>, List<Integer>>> relevantDocs = userMoviesList.join(
  userRecommendedList).values();

// Instantiate the metrics object
RankingMetrics<Integer> metrics = RankingMetrics.of(relevantDocs);

// Precision, NDCG and Recall at k
Integer[] kVector = {1, 3, 5};
for (Integer k : kVector) {
  System.out.format("Precision at %d = %f\n", k, metrics.precisionAt(k));
  System.out.format("NDCG at %d = %f\n", k, metrics.ndcgAt(k));
  System.out.format("Recall at %d = %f\n", k, metrics.recallAt(k));
}

// Mean average precision
System.out.format("Mean average precision = %f\n", metrics.meanAveragePrecision());

//Mean average precision at k
System.out.format("Mean average precision at 2 = %f\n", metrics.meanAveragePrecisionAt(2));

// Evaluate the model using numerical ratings and regression metrics
JavaRDD<Tuple2<Object, Object>> userProducts =
    ratings.map(r -> new Tuple2<>(r.user(), r.product()));

JavaPairRDD<Tuple2<Integer, Integer>, Object> predictions = JavaPairRDD.fromJavaRDD(
  model.predict(JavaRDD.toRDD(userProducts)).toJavaRDD().map(r ->
    new Tuple2<>(new Tuple2<>(r.user(), r.product()), r.rating())));
JavaRDD<Tuple2<Object, Object>> ratesAndPreds =
  JavaPairRDD.fromJavaRDD(ratings.map(r ->
    new Tuple2<Tuple2<Integer, Integer>, Object>(
      new Tuple2<>(r.user(), r.product()),
      r.rating())
  )).join(predictions).values();

// Create regression metrics object
RegressionMetrics regressionMetrics = new RegressionMetrics(ratesAndPreds.rdd());

// Root mean squared error
System.out.format("RMSE = %f\n", regressionMetrics.rootMeanSquaredError());

// R-squared
System.out.format("R-squared = %f\n", regressionMetrics.r2());