import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@SuppressWarnings("unchecked")
public T trainWithSGD(int numIterations){    
    //Train the model
    if(modelName.equals("SVMModel")){
      SVMModel svmmodel = SVMWithSGD.train(trainingData.rdd(), numIterations);
      this.model = (T)(Object) svmmodel;
    } 
    else if(modelName.equals("LogisticRegressionModel")){
      LogisticRegressionModel lrmodel = LogisticRegressionWithSGD.train(trainingData.rdd(), numIterations);
      this.model = (T)(Object) lrmodel;
    } 

    //Evalute the trained model      
    EvaluateProcess<T> evalProcess = new EvaluateProcess<T>(model, modelName, validData, numClasses);
    evalProcess.evalute(numClasses);
  return model;
}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@Test
public void shouldExportAndImportCorrectly() {
    String datapath = "src/test/resources/binary_classification_test.libsvm";
    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD();

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegressionWithSGD().run(data.rdd());

    //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((double) lrmodel.getThreshold().get(), importedModel.getThreshold(), 0.01);
    for (int i = 0; i < importedModel.getNumFeatures(); i++)
        assertEquals(lrmodel.weights().toArray()[i], importedModel.getWeights()[i], 0.01);

}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@Test
public void shouldExportAndImportCorrectly() {
    String datapath = "src/test/resources/binary_classification_test.libsvm";
    JavaRDD<LabeledPoint> data = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD();

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegressionWithSGD().run(data.rdd());

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

    //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((double) lrmodel.getThreshold().get(), importedModel.getThreshold(), EPSILON);
    for (int i = 0; i < importedModel.getNumFeatures(); i++)
        assertEquals(lrmodel.weights().toArray()[i], importedModel.getWeights()[i], EPSILON);

}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@Test
public void testLogisticRegression() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";
    JavaRDD<LabeledPoint> trainingData = MLUtils.loadLibSVMFile(jsc.sc(), datapath).toJavaRDD();

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegressionWithSGD().run(trainingData.rdd());

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

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

    //validate predictions
    List<LabeledPoint> testPoints = trainingData.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, 0.01);
    }
}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@Test
public void testLogisticRegression() {
    //prepare data
    String datapath = "src/test/resources/binary_classification_test.libsvm";
    JavaRDD<LabeledPoint> trainingData = MLUtils.loadLibSVMFile(sc.sc(), datapath).toJavaRDD();

    //Train model in spark
    LogisticRegressionModel lrmodel = new LogisticRegressionWithSGD().run(trainingData.rdd());

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

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

    //validate predictions
    List<LabeledPoint> testPoints = trainingData.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);
    }
}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
/**
 * TODO add another overloaded method to avoid Regularization.
 * This method uses stochastic gradient descent (SGD) algorithm to train a logistic regression model
 *
 * @param trainingDataset               Training dataset as a JavaRDD of labeled points
 * @param noOfIterations                No of iterations
 * @param initialLearningRate           Initial learning rate
 * @param regularizationType            Regularization type : L1 or L2
 * @param regularizationParameter       Regularization parameter
 * @param dataFractionPerSGDIteration   Data fraction per SGD iteration
 * @return                              Logistic regression model
 */
public LogisticRegressionModel trainWithSGD(JavaRDD<LabeledPoint> trainingDataset, double initialLearningRate,
        int noOfIterations, String regularizationType, double regularizationParameter,
        double dataFractionPerSGDIteration) {
    LogisticRegressionWithSGD lrSGD = new LogisticRegressionWithSGD(initialLearningRate, noOfIterations, 
            regularizationParameter, dataFractionPerSGDIteration);
    if (MLConstants.L1.equals(regularizationType)) {
        lrSGD.optimizer().setUpdater(new L1Updater());
    } else if (MLConstants.L2.equals(regularizationType)) {
        lrSGD.optimizer().setUpdater(new SquaredL2Updater());
    }
    lrSGD.setIntercept(true);
    return lrSGD.run(trainingDataset.rdd());
}
 

import org.apache.spark.mllib.classification.LogisticRegressionWithSGD; //导入依赖的package包/类
@Override
protected BaseSparkClassificationModel trainInternal(String modelId, RDD<LabeledPoint> trainingRDD)
  throws LensException {
  LogisticRegressionModel lrModel = LogisticRegressionWithSGD.train(trainingRDD, iterations, stepSize,
    minBatchFraction);
  return new LogitRegressionClassificationModel(modelId, lrModel);
}