org.apache.spark.ml.classification.LogisticRegressionModel Java Examples

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

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

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

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

    // Print the coefficients and intercept for multinomial logistic regression
    System.out.println("Coefficients: \n"
            + lrModel.coefficientMatrix() + " \nIntercept: " + lrModel.interceptVector());
    // $example off$

    spark.stop();
}
 

@Override
public LogisticRegressionModelInfo getModelInfo(final LogisticRegressionModel sparkLRModel) {
    final LogisticRegressionModelInfo logisticRegressionModelInfo = new LogisticRegressionModelInfo();
    logisticRegressionModelInfo.setWeights(sparkLRModel.coefficients().toArray());
    logisticRegressionModelInfo.setIntercept(sparkLRModel.intercept());
    logisticRegressionModelInfo.setNumClasses(sparkLRModel.numClasses());
    logisticRegressionModelInfo.setNumFeatures(sparkLRModel.numFeatures());
    logisticRegressionModelInfo.setThreshold(sparkLRModel.getThreshold());

    Set<String> inputKeys = new LinkedHashSet<String>();
    inputKeys.add(sparkLRModel.getFeaturesCol());
    logisticRegressionModelInfo.setInputKeys(inputKeys);

    Set<String> outputKeys = new LinkedHashSet<String>();
    outputKeys.add(sparkLRModel.getPredictionCol());
    outputKeys.add(sparkLRModel.getProbabilityCol());
    logisticRegressionModelInfo.setOutputKeys(outputKeys);

    return logisticRegressionModelInfo;
}
 

@Override
public LogisticRegressionModelInfo getModelInfo(final LogisticRegressionModel sparkLRModel, DataFrame df) {
    final LogisticRegressionModelInfo logisticRegressionModelInfo = new LogisticRegressionModelInfo();
    logisticRegressionModelInfo.setWeights(sparkLRModel.coefficients().toArray());
    logisticRegressionModelInfo.setIntercept(sparkLRModel.intercept());
    logisticRegressionModelInfo.setNumClasses(sparkLRModel.numClasses());
    logisticRegressionModelInfo.setNumFeatures(sparkLRModel.numFeatures());
    logisticRegressionModelInfo.setThreshold(sparkLRModel.getThreshold());
    logisticRegressionModelInfo.setProbabilityKey(sparkLRModel.getProbabilityCol());

    Set<String> inputKeys = new LinkedHashSet<String>();
    inputKeys.add(sparkLRModel.getFeaturesCol());
    logisticRegressionModelInfo.setInputKeys(inputKeys);

    Set<String> outputKeys = new LinkedHashSet<String>();
    outputKeys.add(sparkLRModel.getPredictionCol());
    outputKeys.add(sparkLRModel.getProbabilityCol());
    logisticRegressionModelInfo.setOutputKeys(outputKeys);

    return logisticRegressionModelInfo;
}
 

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

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

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

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

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

  // We can also use the multinomial family for binary classification
  LogisticRegression mlr = new LogisticRegression()
          .setMaxIter(10)
          .setRegParam(0.3)
          .setElasticNetParam(0.8)
          .setFamily("multinomial");

  // Fit the model
  LogisticRegressionModel mlrModel = mlr.fit(training);

  // Print the coefficients and intercepts for logistic regression with multinomial family
  System.out.println("Multinomial coefficients: " + lrModel.coefficientMatrix()
    + "\nMultinomial intercepts: " + mlrModel.interceptVector());
  // $example off$

  spark.stop();
}
 

public void printModel() {
	LogisticRegressionModel lrModel = (LogisticRegressionModel) model.stages()[2];
	System.out.println("intercept = " + lrModel.intercept());
	System.out.println("number of features = " + lrModel.numFeatures());
	System.out.println("regularization parameter = " + lrModel.getRegParam());
	System.out.println(lrModel.explainParams());
}
 

@Test
public void testLogisticRegression() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";

    Dataset<Row> trainingData = spark.read().format("libsvm").load(datapath);

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegression().fit(trainingData);

    //Export this model
    byte[] exportedModel = ModelExporter.export(lrmodel);

    //Import and get Transformer
    Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);

    //validate predictions
    List<LabeledPoint> testPoints = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD().collect();
    for (LabeledPoint i : testPoints) {
        Vector v = i.features().asML();
        double actual = lrmodel.predict(v);

        Map<String, Object> data = new HashMap<String, Object>();
        data.put("features", v.toArray());
        transformer.transform(data);
        double predicted = (double) data.get("prediction");

        assertEquals(actual, predicted, 0.01);
    }
}
 

@Test
public void shouldExportAndImportCorrectly() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";

    Dataset<Row> trainingData = spark.read().format("libsvm").load(datapath);

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegression().fit(trainingData);

    //Export this model
    byte[] exportedModel = ModelExporter.export(lrmodel);

    //Import it back
    LogisticRegressionModelInfo importedModel = (LogisticRegressionModelInfo) ModelImporter.importModelInfo(exportedModel);

    //check if they are exactly equal with respect to their fields
    //it maybe edge cases eg. order of elements in the list is changed
    assertEquals(lrmodel.intercept(), importedModel.getIntercept(), 0.01);
    assertEquals(lrmodel.numClasses(), importedModel.getNumClasses(), 0.01);
    assertEquals(lrmodel.numFeatures(), importedModel.getNumFeatures(), 0.01);
    assertEquals(lrmodel.getThreshold(), importedModel.getThreshold(), 0.01);
    for (int i = 0; i < importedModel.getNumFeatures(); i++)
        assertEquals(lrmodel.coefficients().toArray()[i], importedModel.getWeights()[i], 0.01);

    assertEquals(lrmodel.getFeaturesCol(), importedModel.getInputKeys().iterator().next());
    assertEquals(lrmodel.getPredictionCol(), importedModel.getOutputKeys().iterator().next());
}
 

@Test
public void testLogisticRegression() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";

    DataFrame trainingData = sqlContext.read().format("libsvm").load(datapath);

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegression().fit(trainingData);

    //Export this model
    byte[] exportedModel = ModelExporter.export(lrmodel, trainingData);

    //Import and get Transformer
    Transformer transformer = ModelImporter.importAndGetTransformer(exportedModel);

    //validate predictions
    List<LabeledPoint> testPoints = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD().collect();
    for (LabeledPoint i : testPoints) {
        Vector v = i.features();
        double actual = lrmodel.predict(v);

        Map<String, Object> data = new HashMap<String, Object>();
        data.put("features", v.toArray());
        transformer.transform(data);
        double predicted = (double) data.get("prediction");

        assertEquals(actual, predicted, EPSILON);
    }
}
 

@Test
public void shouldExportAndImportCorrectly() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";

    DataFrame trainingData = sqlContext.read().format("libsvm").load(datapath);

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegression().fit(trainingData);

    //Export this model
    byte[] exportedModel = ModelExporter.export(lrmodel, trainingData);

    //Import it back
    LogisticRegressionModelInfo importedModel = (LogisticRegressionModelInfo) ModelImporter.importModelInfo(exportedModel);

    //check if they are exactly equal with respect to their fields
    //it maybe edge cases eg. order of elements in the list is changed
    assertEquals(lrmodel.intercept(), importedModel.getIntercept(), EPSILON);
    assertEquals(lrmodel.numClasses(), importedModel.getNumClasses(), EPSILON);
    assertEquals(lrmodel.numFeatures(), importedModel.getNumFeatures(), EPSILON);
    assertEquals(lrmodel.getThreshold(), importedModel.getThreshold(), EPSILON);
    for (int i = 0; i < importedModel.getNumFeatures(); i++)
        assertEquals(lrmodel.weights().toArray()[i], importedModel.getWeights()[i], EPSILON);

    assertEquals(lrmodel.getFeaturesCol(), importedModel.getInputKeys().iterator().next());
    assertEquals(lrmodel.getPredictionCol(), importedModel.getOutputKeys().iterator().next());
}
 

public static void main(String[] args) {
   SparkSession spark = SparkSession
     .builder().master("local").config("spark.sql.warehouse.dir", "file:///C:/Users/sumit.kumar/Downloads/bin/warehouse")
     .appName("JavaEstimatorTransformerParamExample")
     .getOrCreate();
   Logger rootLogger = LogManager.getRootLogger();
rootLogger.setLevel(Level.WARN);
   // $example on$
   // Prepare training data.
   List<Row> dataTraining = Arrays.asList(
       RowFactory.create(1.0, Vectors.dense(0.0, 1.1, 0.1)),
       RowFactory.create(0.0, Vectors.dense(2.0, 1.0, -1.0)),
       RowFactory.create(0.0, Vectors.dense(2.0, 1.3, 1.0)),
       RowFactory.create(1.0, Vectors.dense(0.0, 1.2, -0.5))
   );
   StructType schema = new StructType(new StructField[]{
       new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
       new StructField("features", new VectorUDT(), false, Metadata.empty())
   });
   Dataset<Row> training = spark.createDataFrame(dataTraining, schema);

   // Create a LogisticRegression instance. This instance is an Estimator.
   LogisticRegression lr = new LogisticRegression();
   // Print out the parameters, documentation, and any default values.
   System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");

   // We may set parameters using setter methods.
   lr.setMaxIter(10).setRegParam(0.01);

   // Learn a LogisticRegression model. This uses the parameters stored in lr.
   LogisticRegressionModel model1 = lr.fit(training);
   // Since model1 is a Model (i.e., a Transformer produced by an Estimator),
   // we can view the parameters it used during fit().
   // This prints the parameter (name: value) pairs, where names are unique IDs for this
   // LogisticRegression instance.
   System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());

   // We may alternatively specify parameters using a ParamMap.
   ParamMap paramMap = new ParamMap()
     .put(lr.maxIter().w(20))  // Specify 1 Param.
     .put(lr.maxIter(), 30)  // This overwrites the original maxIter.
     .put(lr.regParam().w(0.1), lr.threshold().w(0.55));  // Specify multiple Params.

   // One can also combine ParamMaps.
   ParamMap paramMap2 = new ParamMap()
     .put(lr.probabilityCol().w("myProbability"));  // Change output column name
   ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);

   // Now learn a new model using the paramMapCombined parameters.
   // paramMapCombined overrides all parameters set earlier via lr.set* methods.
   LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
   System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());

   // Prepare test documents.
   List<Row> dataTest = Arrays.asList(
       RowFactory.create(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
       RowFactory.create(0.0, Vectors.dense(3.0, 2.0, -0.1)),
       RowFactory.create(1.0, Vectors.dense(0.0, 2.2, -1.5))
   );
   Dataset<Row> test = spark.createDataFrame(dataTest, schema);

   // Make predictions on test documents using the Transformer.transform() method.
   // LogisticRegression.transform will only use the 'features' column.
   // Note that model2.transform() outputs a 'myProbability' column instead of the usual
   // 'probability' column since we renamed the lr.probabilityCol parameter previously.
   Dataset<Row> results = model2.transform(test);
   Dataset<Row> rows = results.select("features", "label", "myProbability", "prediction");
   for (Row r: rows.collectAsList()) {
     System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2)
       + ", prediction=" + r.get(3));
   }
   // $example off$

   spark.stop();
 }
 

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

  // $example on$
  // Prepare training data.
  List<Row> dataTraining = Arrays.asList(
      RowFactory.create(1.0, Vectors.dense(0.0, 1.1, 0.1)),
      RowFactory.create(0.0, Vectors.dense(2.0, 1.0, -1.0)),
      RowFactory.create(0.0, Vectors.dense(2.0, 1.3, 1.0)),
      RowFactory.create(1.0, Vectors.dense(0.0, 1.2, -0.5))
  );
  StructType schema = new StructType(new StructField[]{
      new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
      new StructField("features", new VectorUDT(), false, Metadata.empty())
  });
  Dataset<Row> training = spark.createDataFrame(dataTraining, schema);

  // Create a LogisticRegression instance. This instance is an Estimator.
  LogisticRegression lr = new LogisticRegression();
  // Print out the parameters, documentation, and any default values.
  System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");

  // We may set parameters using setter methods.
  lr.setMaxIter(10).setRegParam(0.01);

  // Learn a LogisticRegression model. This uses the parameters stored in lr.
  LogisticRegressionModel model1 = lr.fit(training);
  // Since model1 is a Model (i.e., a Transformer produced by an Estimator),
  // we can view the parameters it used during fit().
  // This prints the parameter (name: value) pairs, where names are unique IDs for this
  // LogisticRegression instance.
  System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());

  // We may alternatively specify parameters using a ParamMap.
  ParamMap paramMap = new ParamMap()
    .put(lr.maxIter().w(20))  // Specify 1 Param.
    .put(lr.maxIter(), 30)  // This overwrites the original maxIter.
    .put(lr.regParam().w(0.1), lr.threshold().w(0.55));  // Specify multiple Params.

  // One can also combine ParamMaps.
  ParamMap paramMap2 = new ParamMap()
    .put(lr.probabilityCol().w("myProbability"));  // Change output column name
  ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);

  // Now learn a new model using the paramMapCombined parameters.
  // paramMapCombined overrides all parameters set earlier via lr.set* methods.
  LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
  System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());

  // Prepare test documents.
  List<Row> dataTest = Arrays.asList(
      RowFactory.create(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
      RowFactory.create(0.0, Vectors.dense(3.0, 2.0, -0.1)),
      RowFactory.create(1.0, Vectors.dense(0.0, 2.2, -1.5))
  );
  Dataset<Row> test = spark.createDataFrame(dataTest, schema);

  // Make predictions on test documents using the Transformer.transform() method.
  // LogisticRegression.transform will only use the 'features' column.
  // Note that model2.transform() outputs a 'myProbability' column instead of the usual
  // 'probability' column since we renamed the lr.probabilityCol parameter previously.
  Dataset<Row> results = model2.transform(test);
  Dataset<Row> rows = results.select("features", "label", "myProbability", "prediction");
  for (Row r: rows.collectAsList()) {
    System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2)
      + ", prediction=" + r.get(3));
  }
  // $example off$

  spark.stop();
}
 

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

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

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

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

  // $example on$
  // Extract the summary from the returned LogisticRegressionModel instance trained in the earlier
  // example
  LogisticRegressionTrainingSummary trainingSummary = lrModel.summary();

  // Obtain the loss per iteration.
  double[] objectiveHistory = trainingSummary.objectiveHistory();
  for (double lossPerIteration : objectiveHistory) {
    System.out.println(lossPerIteration);
  }

  // Obtain the metrics useful to judge performance on test data.
  // We cast the summary to a BinaryLogisticRegressionSummary since the problem is a binary
  // classification problem.
  BinaryLogisticRegressionSummary binarySummary =
    (BinaryLogisticRegressionSummary) trainingSummary;

  // Obtain the receiver-operating characteristic as a dataframe and areaUnderROC.
  Dataset<Row> roc = binarySummary.roc();
  roc.show();
  roc.select("FPR").show();
  System.out.println(binarySummary.areaUnderROC());

  // Get the threshold corresponding to the maximum F-Measure and rerun LogisticRegression with
  // this selected threshold.
  Dataset<Row> fMeasure = binarySummary.fMeasureByThreshold();
  double maxFMeasure = fMeasure.select(functions.max("F-Measure")).head().getDouble(0);
  double bestThreshold = fMeasure.where(fMeasure.col("F-Measure").equalTo(maxFMeasure))
    .select("threshold").head().getDouble(0);
  lrModel.setThreshold(bestThreshold);
  // $example off$

  spark.stop();
}
 

public LogisticRegressionModelConverter(LogisticRegressionModel model){
	super(model);
}
 

/**
 * Trains a whitespace classifier model and save the resulting pipeline model
 * to an external file. 
 * @param sentences a list of tokenized sentences.
 * @param pipelineModelFileName
 * @param numFeatures
 */
public void train(List<String> sentences, String pipelineModelFileName, int numFeatures) {
	List<WhitespaceContext> contexts = new ArrayList<WhitespaceContext>(sentences.size());
	int id = 0;
	for (String sentence : sentences) {
		sentence = sentence.trim();
		for (int j = 0; j < sentence.length(); j++) {
			char c = sentence.charAt(j);
			if (c == ' ' || c == '_') {
				WhitespaceContext context = new WhitespaceContext();
				context.setId(id++);
				context.setContext(extractContext(sentence, j));
				context.setLabel(c == ' ' ? 0d : 1d);
				contexts.add(context);
			}
		}
	}
	JavaRDD<WhitespaceContext> jrdd = jsc.parallelize(contexts);
	DataFrame df = sqlContext.createDataFrame(jrdd, WhitespaceContext.class);
	df.show(false);
	System.out.println("N = " + df.count());
	df.groupBy("label").count().show();
	
	org.apache.spark.ml.feature.Tokenizer tokenizer = new Tokenizer()
			.setInputCol("context").setOutputCol("words");
	HashingTF hashingTF = new HashingTF().setNumFeatures(numFeatures)
			.setInputCol(tokenizer.getOutputCol()).setOutputCol("features");
	LogisticRegression lr = new LogisticRegression().setMaxIter(100)
			.setRegParam(0.01);
	Pipeline pipeline = new Pipeline().setStages(new PipelineStage[] {
			tokenizer, hashingTF, lr });
	model = pipeline.fit(df);
	
	try {
		model.write().overwrite().save(pipelineModelFileName);
	} catch (IOException e) {
		e.printStackTrace();
	}
	
	DataFrame predictions = model.transform(df);
	predictions.show();
	MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator().setMetricName("precision");
	double accuracy = evaluator.evaluate(predictions);
	System.out.println("training accuracy = " + accuracy);
	
	LogisticRegressionModel lrModel = (LogisticRegressionModel) model.stages()[2];
	LogisticRegressionTrainingSummary trainingSummary = lrModel.summary();
	double[] objectiveHistory = trainingSummary.objectiveHistory();
	System.out.println("#(iterations) = " + objectiveHistory.length);
	for (double lossPerIteration : objectiveHistory) {
	  System.out.println(lossPerIteration);
	}
	
}
 

@Override
public Class<LogisticRegressionModel> getSource() {
    return LogisticRegressionModel.class;
}
 

@Override
public Class<LogisticRegressionModel> getSource() {
    return LogisticRegressionModel.class;
}