org.apache.spark.ml.param.ParamMap Java Examples

public static void main(String[] args) {
	System.setProperty("hadoop.home.dir", "E:\\sumitK\\Hadoop");
	SparkSession sparkSession = SparkSession
			.builder()
			.master("local")
			.config("spark.sql.warehouse.dir",
					"file:///E:/sumitK/Hadoop/warehouse")
			.appName("BikeRentalPrediction").getOrCreate();
	Logger rootLogger = LogManager.getRootLogger();
	rootLogger.setLevel(Level.WARN);
	//We use the sqlContext.read method to read the data and set a few options:
	//  'format': specifies the Spark CSV data source
	//  'header': set to true to indicate that the first line of the CSV data file is a header
    // The file is called 'hour.csv'.	
	Dataset<Row> ds=sparkSession.read()
			  .format("org.apache.spark.sql.execution.datasources.csv.CSVFileFormat")
			  .option("header", "true")
			  .load("E:\\sumitK\\Hadoop\\Bike-Sharing-Dataset\\hour.csv");
	
	ds.cache();
	
	ds.select("season").show();;
	
	ds.show();
	
	System.out.println("Our dataset has rows :: "+ ds.count());
	
	Dataset<Row> df = ds.drop("instant").drop("dteday").drop("casual").drop("registered");
	df.printSchema();
	//col("...") is preferable to df.col("...")
	Dataset<Row> dformatted = df.select(col("season").cast(DataTypes.IntegerType),
			                            col("yr").cast(DataTypes.IntegerType),
										col("mnth").cast(DataTypes.IntegerType),
										col("hr").cast(DataTypes.IntegerType),
										col("holiday").cast(DataTypes.IntegerType),
										col("weekday").cast(DataTypes.IntegerType),
										col("workingday").cast(DataTypes.IntegerType),
										col("weathersit").cast(DataTypes.IntegerType),
										col("temp").cast(DataTypes.IntegerType),
										col("atemp").cast(DataTypes.IntegerType),
										col("hum").cast(DataTypes.IntegerType),
										col("windspeed").cast(DataTypes.IntegerType),
										col("cnt").cast(DataTypes.IntegerType));
	
	
dformatted.printSchema();	
Dataset<Row>[] data=	dformatted.randomSplit(new double[]{0.7,0.3});
System.out.println("We have training examples count :: "+ data[0].count()+" and test examples count ::"+data[1].count());

///
//removing 'cnt' cloumn and then forming str array
String[] featuresCols = dformatted.drop("cnt").columns();

for(String str:featuresCols){
	System.out.println(str+" :: ");
}

//This concatenates all feature columns into a single feature vector in a new column "rawFeatures".
VectorAssembler vectorAssembler = new VectorAssembler().setInputCols(featuresCols).setOutputCol("rawFeatures");
//This identifies categorical features and indexes them.
VectorIndexer vectorIndexer= new VectorIndexer().setInputCol("rawFeatures").setOutputCol("features").setMaxCategories(4);

//Takes the "features" column and learns to predict "cnt"
GBTRegressor gbt = new GBTRegressor().setLabelCol("cnt");
		
// Define a grid of hyperparameters to test:
  //  - maxDepth: max depth of each decision tree in the GBT ensemble
//  - maxIter: iterations, i.e., number of trees in each GBT ensemble
// In this example notebook, we keep these values small.  In practice, to get the highest accuracy, you would likely want to try deeper trees (10 or higher) and more trees in the ensemble (>100).
ParamMap[]	paramGrid = new ParamGridBuilder().addGrid(gbt.maxDepth(),new int[]{2, 5}).addGrid(gbt.maxIter(),new int[] {10, 100}).build();
// We define an evaluation metric.  This tells CrossValidator how well we are doing by comparing the true labels with predictions.
RegressionEvaluator evaluator = new RegressionEvaluator().setMetricName("rmse").setLabelCol(gbt.getLabelCol()).setPredictionCol(gbt.getPredictionCol());

//	# Declare the CrossValidator, which runs model tuning for us.
	CrossValidator cv = new CrossValidator().setEstimator(gbt).setEvaluator(evaluator).setEstimatorParamMaps(paramGrid);
		
	Pipeline pipeline = new Pipeline().setStages(new PipelineStage[]{vectorAssembler,vectorIndexer,cv});
			
	PipelineModel pipelineModel=pipeline.fit(data[0]);
	
	Dataset<Row> predictions = pipelineModel.transform(data[1]);
	
	predictions.show();
	//predictions.select("cnt", "prediction", *featuresCols);
}
 

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("JavaModelSelectionViaTrainValidationSplitExample")
    .getOrCreate();

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

  // Prepare training and test data.
  Dataset<Row>[] splits = data.randomSplit(new double[] {0.9, 0.1}, 12345);
  Dataset<Row> training = splits[0];
  Dataset<Row> test = splits[1];

  LinearRegression lr = new LinearRegression();

  // We use a ParamGridBuilder to construct a grid of parameters to search over.
  // TrainValidationSplit will try all combinations of values and determine best model using
  // the evaluator.
  ParamMap[] paramGrid = new ParamGridBuilder()
    .addGrid(lr.regParam(), new double[] {0.1, 0.01})
    .addGrid(lr.fitIntercept())
    .addGrid(lr.elasticNetParam(), new double[] {0.0, 0.5, 1.0})
    .build();

  // In this case the estimator is simply the linear regression.
  // A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
  TrainValidationSplit trainValidationSplit = new TrainValidationSplit()
    .setEstimator(lr)
    .setEvaluator(new RegressionEvaluator())
    .setEstimatorParamMaps(paramGrid)
    .setTrainRatio(0.8);  // 80% for training and the remaining 20% for validation

  // Run train validation split, and choose the best set of parameters.
  TrainValidationSplitModel model = trainValidationSplit.fit(training);

  // Make predictions on test data. model is the model with combination of parameters
  // that performed best.
  model.transform(test)
    .select("features", "label", "prediction")
    .show();
  // $example off$

  spark.stop();
}
 

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

  // $example on$
  // Prepare training documents, which are labeled.
  Dataset<Row> training = spark.createDataFrame(Arrays.asList(
    new JavaLabeledDocument(0L, "a b c d e spark", 1.0),
    new JavaLabeledDocument(1L, "b d", 0.0),
    new JavaLabeledDocument(2L,"spark f g h", 1.0),
    new JavaLabeledDocument(3L, "hadoop mapreduce", 0.0),
    new JavaLabeledDocument(4L, "b spark who", 1.0),
    new JavaLabeledDocument(5L, "g d a y", 0.0),
    new JavaLabeledDocument(6L, "spark fly", 1.0),
    new JavaLabeledDocument(7L, "was mapreduce", 0.0),
    new JavaLabeledDocument(8L, "e spark program", 1.0),
    new JavaLabeledDocument(9L, "a e c l", 0.0),
    new JavaLabeledDocument(10L, "spark compile", 1.0),
    new JavaLabeledDocument(11L, "hadoop software", 0.0)
  ), JavaLabeledDocument.class);

  // Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
  Tokenizer tokenizer = new Tokenizer()
    .setInputCol("text")
    .setOutputCol("words");
  HashingTF hashingTF = new HashingTF()
    .setNumFeatures(1000)
    .setInputCol(tokenizer.getOutputCol())
    .setOutputCol("features");
  LogisticRegression lr = new LogisticRegression()
    .setMaxIter(10)
    .setRegParam(0.01);
  Pipeline pipeline = new Pipeline()
    .setStages(new PipelineStage[] {tokenizer, hashingTF, lr});

  // We use a ParamGridBuilder to construct a grid of parameters to search over.
  // With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
  // this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
  ParamMap[] paramGrid = new ParamGridBuilder()
    .addGrid(hashingTF.numFeatures(), new int[] {10, 100, 1000})
    .addGrid(lr.regParam(), new double[] {0.1, 0.01})
    .build();

  // We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
  // This will allow us to jointly choose parameters for all Pipeline stages.
  // A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
  // Note that the evaluator here is a BinaryClassificationEvaluator and its default metric
  // is areaUnderROC.
  CrossValidator cv = new CrossValidator()
    .setEstimator(pipeline)
    .setEvaluator(new BinaryClassificationEvaluator())
    .setEstimatorParamMaps(paramGrid).setNumFolds(2);  // Use 3+ in practice

  // Run cross-validation, and choose the best set of parameters.
  CrossValidatorModel cvModel = cv.fit(training);

  // Prepare test documents, which are unlabeled.
  Dataset<Row> test = spark.createDataFrame(Arrays.asList(
    new JavaDocument(4L, "spark i j k"),
    new JavaDocument(5L, "l m n"),
    new JavaDocument(6L, "mapreduce spark"),
    new JavaDocument(7L, "apache hadoop")
  ), JavaDocument.class);

  // Make predictions on test documents. cvModel uses the best model found (lrModel).
  Dataset<Row> predictions = cvModel.transform(test);
  for (Row r : predictions.select("id", "text", "probability", "prediction").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();
}
 

@Override
public Estimator<CMMModel> copy(ParamMap extra) {
	return defaultCopy(extra);
}
 

@Override
public CMMModel copy(ParamMap extra) {
	return defaultCopy(extra);
}
 

@Override
public Params copy(ParamMap extra) {
	return defaultCopy(extra);
}
 

@Override
public Params copy(ParamMap extra) {
	return defaultCopy(extra);
}
 

@Override
public ColumnExploder copy(ParamMap extra){
	throw new UnsupportedOperationException();
}