org.apache.spark.ml.regression.LinearRegressionModel Java Examples

public static void main(String[] args) {
  SparkSession spark = SparkSession
    .builder()
    .appName("JavaLinearRegressionWithElasticNetExample")
    .getOrCreate();

  // $example on$
  // Load training data.
  Dataset<Row> training = spark.read().format("libsvm")
    .load("data/mllib/sample_linear_regression_data.txt");

  LinearRegression lr = new LinearRegression()
    .setMaxIter(10)
    .setRegParam(0.3)
    .setElasticNetParam(0.8);

  // Fit the model.
  LinearRegressionModel lrModel = lr.fit(training);

  // Print the coefficients and intercept for linear regression.
  System.out.println("Coefficients: "
    + lrModel.coefficients() + " Intercept: " + lrModel.intercept());

  // Summarize the model over the training set and print out some metrics.
  LinearRegressionTrainingSummary trainingSummary = lrModel.summary();
  System.out.println("numIterations: " + trainingSummary.totalIterations());
  System.out.println("objectiveHistory: " + Vectors.dense(trainingSummary.objectiveHistory()));
  trainingSummary.residuals().show();
  System.out.println("RMSE: " + trainingSummary.rootMeanSquaredError());
  System.out.println("r2: " + trainingSummary.r2());
  // $example off$

  spark.stop();
}
 

private void start() {
  SparkSession spark = SparkSession.builder().appName(
      "Simple prediction from Text File").master("local").getOrCreate();

  spark.udf().register("vectorBuilder", new VectorBuilder(), new VectorUDT());

  String filename = "data/tuple-data-file.csv";
  StructType schema = new StructType(
      new StructField[] { new StructField("_c0", DataTypes.DoubleType, false,
          Metadata.empty()),
          new StructField("_c1", DataTypes.DoubleType, false, Metadata
              .empty()),
          new StructField("features", new VectorUDT(), true, Metadata
              .empty()), });

  Dataset<Row> df = spark.read().format("csv").schema(schema).option("header",
      "false")
      .load(filename);
  df = df.withColumn("valuefeatures", df.col("_c0")).drop("_c0");
  df = df.withColumn("label", df.col("_c1")).drop("_c1");
  df.printSchema();

  df = df.withColumn("features", callUDF("vectorBuilder", df.col(
      "valuefeatures")));
  df.printSchema();
  df.show();

  LinearRegression lr = new LinearRegression().setMaxIter(20);// .setRegParam(1).setElasticNetParam(1);

  // Fit the model to the data.
  LinearRegressionModel model = lr.fit(df);

  // Given a dataset, predict each point's label, and show the results.
  model.transform(df).show();

  LinearRegressionTrainingSummary trainingSummary = model.summary();
  System.out.println("numIterations: " + trainingSummary.totalIterations());
  System.out.println("objectiveHistory: " + Vectors.dense(trainingSummary
      .objectiveHistory()));
  trainingSummary.residuals().show();
  System.out.println("RMSE: " + trainingSummary.rootMeanSquaredError());
  System.out.println("r2: " + trainingSummary.r2());

  double intercept = model.intercept();
  System.out.println("Interesection: " + intercept);
  double regParam = model.getRegParam();
  System.out.println("Regression parameter: " + regParam);
  double tol = model.getTol();
  System.out.println("Tol: " + tol);
  Double feature = 7.0;
  Vector features = Vectors.dense(feature);
  double p = model.predict(features);

  System.out.println("Prediction for feature " + feature + " is " + p);
  System.out.println(8 * regParam + intercept);
}
 

public LinearRegressionModelConverter(LinearRegressionModel model){
	super(model);
}
 

@Override
public Model encodeModel(Schema schema){
	LinearRegressionModel model = getTransformer();

	return LinearModelUtil.createRegression(this, model.coefficients(), model.intercept(), schema);
}