Regression - RDD-based API

Isotonic regression

Isotonic regression belongs to the family of regression algorithms. Formally isotonic regression is a problem where given a finite set of real numbers $Y = {y_1, y_2, ..., y_n}$ representing observed responses and $X = {x_1, x_2, ..., x_n}$ the unknown response values to be fitted finding a function that minimises

\begin{equation} f(x) = \sum_{i=1}^n w_i (y_i - x_i)^2 \end{equation}

with respect to complete order subject to $x_1\le x_2\le ...\le x_n$ where $w_i$ are positive weights. The resulting function is called isotonic regression and it is unique. It can be viewed as least squares problem under order restriction. Essentially isotonic regression is a monotonic function best fitting the original data points.

spark.mllib supports a pool adjacent violators algorithm which uses an approach to parallelizing isotonic regression. The training input is a RDD of tuples of three double values that represent label, feature and weight in this order. Additionally IsotonicRegression algorithm has one optional parameter called $isotonic$ defaulting to true. This argument specifies if the isotonic regression is isotonic (monotonically increasing) or antitonic (monotonically decreasing).

Training returns an IsotonicRegressionModel that can be used to predict labels for both known and unknown features. The result of isotonic regression is treated as piecewise linear function. The rules for prediction therefore are:

Examples

Data are read from a file where each line has a format label,feature i.e. 4710.28,500.00. The data are split to training and testing set. Model is created using the training set and a mean squared error is calculated from the predicted labels and real labels in the test set.

Refer to the IsotonicRegression Scala docs and IsotonicRegressionModel Scala docs for details on the API.

import org.apache.spark.mllib.regression.{IsotonicRegression, IsotonicRegressionModel}
import org.apache.spark.mllib.util.MLUtils

val data = MLUtils.loadLibSVMFile(sc,
  "data/mllib/sample_isotonic_regression_libsvm_data.txt").cache()

// Create label, feature, weight tuples from input data with weight set to default value 1.0.
val parsedData = data.map { labeledPoint =>
  (labeledPoint.label, labeledPoint.features(0), 1.0)
}

// Split data into training (60%) and test (40%) sets.
val splits = parsedData.randomSplit(Array(0.6, 0.4), seed = 11L)
val training = splits(0)
val test = splits(1)

// Create isotonic regression model from training data.
// Isotonic parameter defaults to true so it is only shown for demonstration
val model = new IsotonicRegression().setIsotonic(true).run(training)

// Create tuples of predicted and real labels.
val predictionAndLabel = test.map { point =>
  val predictedLabel = model.predict(point._2)
  (predictedLabel, point._1)
}

// Calculate mean squared error between predicted and real labels.
val meanSquaredError = predictionAndLabel.map { case (p, l) => math.pow((p - l), 2) }.mean()
println("Mean Squared Error = " + meanSquaredError)

// Save and load model
model.save(sc, "target/tmp/myIsotonicRegressionModel")
val sameModel = IsotonicRegressionModel.load(sc, "target/tmp/myIsotonicRegressionModel")
Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/IsotonicRegressionExample.scala" in the Spark repo.

Data are read from a file where each line has a format label,feature i.e. 4710.28,500.00. The data are split to training and testing set. Model is created using the training set and a mean squared error is calculated from the predicted labels and real labels in the test set.

Refer to the IsotonicRegression Java docs and IsotonicRegressionModel Java docs for details on the API.

import scala.Tuple2;
import scala.Tuple3;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.JavaDoubleRDD;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.regression.IsotonicRegression;
import org.apache.spark.mllib.regression.IsotonicRegressionModel;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;

JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(
  jsc.sc(), "data/mllib/sample_isotonic_regression_libsvm_data.txt").toJavaRDD();

// Create label, feature, weight tuples from input data with weight set to default value 1.0.
JavaRDD<Tuple3<Double, Double, Double>> parsedData = data.map(
  new Function<LabeledPoint, Tuple3<Double, Double, Double>>() {
    public Tuple3<Double, Double, Double> call(LabeledPoint point) {
      return new Tuple3<>(new Double(point.label()),
        new Double(point.features().apply(0)), 1.0);
    }
  }
);

// Split data into training (60%) and test (40%) sets.
JavaRDD<Tuple3<Double, Double, Double>>[] splits =
  parsedData.randomSplit(new double[]{0.6, 0.4}, 11L);
JavaRDD<Tuple3<Double, Double, Double>> training = splits[0];
JavaRDD<Tuple3<Double, Double, Double>> test = splits[1];

// Create isotonic regression model from training data.
// Isotonic parameter defaults to true so it is only shown for demonstration
final IsotonicRegressionModel model =
  new IsotonicRegression().setIsotonic(true).run(training);

// Create tuples of predicted and real labels.
JavaPairRDD<Double, Double> predictionAndLabel = test.mapToPair(
  new PairFunction<Tuple3<Double, Double, Double>, Double, Double>() {
    @Override
    public Tuple2<Double, Double> call(Tuple3<Double, Double, Double> point) {
      Double predictedLabel = model.predict(point._2());
      return new Tuple2<>(predictedLabel, point._1());
    }
  }
);

// Calculate mean squared error between predicted and real labels.
Double meanSquaredError = new JavaDoubleRDD(predictionAndLabel.map(
  new Function<Tuple2<Double, Double>, Object>() {
    @Override
    public Object call(Tuple2<Double, Double> pl) {
      return Math.pow(pl._1() - pl._2(), 2);
    }
  }
).rdd()).mean();
System.out.println("Mean Squared Error = " + meanSquaredError);

// Save and load model
model.save(jsc.sc(), "target/tmp/myIsotonicRegressionModel");
IsotonicRegressionModel sameModel =
  IsotonicRegressionModel.load(jsc.sc(), "target/tmp/myIsotonicRegressionModel");
Find full example code at "examples/src/main/java/org/apache/spark/examples/mllib/JavaIsotonicRegressionExample.java" in the Spark repo.

Data are read from a file where each line has a format label,feature i.e. 4710.28,500.00. The data are split to training and testing set. Model is created using the training set and a mean squared error is calculated from the predicted labels and real labels in the test set.

Refer to the IsotonicRegression Python docs and IsotonicRegressionModel Python docs for more details on the API.

import math
from pyspark.mllib.regression import LabeledPoint, IsotonicRegression, IsotonicRegressionModel
from pyspark.mllib.util import MLUtils

# Load and parse the data
def parsePoint(labeledData):
    return (labeledData.label, labeledData.features[0], 1.0)

data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_isotonic_regression_libsvm_data.txt")

# Create label, feature, weight tuples from input data with weight set to default value 1.0.
parsedData = data.map(parsePoint)

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

# Create isotonic regression model from training data.
# Isotonic parameter defaults to true so it is only shown for demonstration
model = IsotonicRegression.train(training)

# Create tuples of predicted and real labels.
predictionAndLabel = test.map(lambda p: (model.predict(p[1]), p[0]))

# Calculate mean squared error between predicted and real labels.
meanSquaredError = predictionAndLabel.map(lambda pl: math.pow((pl[0] - pl[1]), 2)).mean()
print("Mean Squared Error = " + str(meanSquaredError))

# Save and load model
model.save(sc, "target/tmp/myIsotonicRegressionModel")
sameModel = IsotonicRegressionModel.load(sc, "target/tmp/myIsotonicRegressionModel")
Find full example code at "examples/src/main/python/mllib/isotonic_regression_example.py" in the Spark repo.