Java SparkSession.stop方法代码示例

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {
	SparkSession spark = SparkSession.builder()
			.master("local[8]")
			.appName("PCAExpt")
			.getOrCreate();

	// Load and parse data
	String filePath = "/home/kchoppella/book/Chapter09/data/covtypeNorm.csv";

	// Loads data.
	Dataset<Row> inDataset = spark.read()
			.format("com.databricks.spark.csv")
			.option("header", "true")
			.option("inferSchema", true)
			.load(filePath);
	ArrayList<String> inputColsList = new ArrayList<String>(Arrays.asList(inDataset.columns()));
	
	//Make single features column for feature vectors 
	inputColsList.remove("class");
	String[] inputCols = inputColsList.parallelStream().toArray(String[]::new);
	
	//Prepare dataset for training with all features in "features" column
	VectorAssembler assembler = new VectorAssembler().setInputCols(inputCols).setOutputCol("features");
	Dataset<Row> dataset = assembler.transform(inDataset);

	PCAModel pca = new PCA()
			.setK(16)
			.setInputCol("features")
			.setOutputCol("pcaFeatures")
			.fit(dataset);

	Dataset<Row> result = pca.transform(dataset).select("pcaFeatures");
	System.out.println("Explained variance:");
	System.out.println(pca.explainedVariance());
	result.show(false);
	// $example off$
	spark.stop();
}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {

		SparkSession spark = SparkSession.builder()
				.master("local[8]")
				.appName("KMeansExpt")
				.getOrCreate();
 
		// Load and parse data
		String filePath = "/home/kchoppella/book/Chapter09/data/covtypeNorm.csv";

		// Loads data.
		Dataset<Row> inDataset = spark.read()
				.format("com.databricks.spark.csv")
				.option("header", "true")
				.option("inferSchema", true)
				.load(filePath);
		ArrayList<String> inputColsList = new ArrayList<String>(Arrays.asList(inDataset.columns()));
		
		//Make single features column for feature vectors 
		inputColsList.remove("class");
		String[] inputCols = inputColsList.parallelStream().toArray(String[]::new);
		
		//Prepare dataset for training with all features in "features" column
		VectorAssembler assembler = new VectorAssembler().setInputCols(inputCols).setOutputCol("features");
		Dataset<Row> dataset = assembler.transform(inDataset);

		KMeans kmeans = new KMeans().setK(27).setSeed(1L);
		KMeansModel model = kmeans.fit(dataset);

		// Evaluate clustering by computing Within Set Sum of Squared Errors.
		double WSSSE = model.computeCost(dataset);
		System.out.println("Within Set Sum of Squared Errors = " + WSSSE);

		// Shows the result.
		Vector[] centers = model.clusterCenters();
		System.out.println("Cluster Centers: ");
		for (Vector center: centers) {
		  System.out.println(center);
		}
		
		spark.stop();
	}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {

		SparkSession spark = SparkSession.builder()
				.master("local[8]")
				.appName("BisectingKMeansExpt")
				.getOrCreate();
 
		// Load and parse data
		String filePath = "/home/kchoppella/book/Chapter09/data/covtypeNorm.csv";

		// Loads data.
		Dataset<Row> inDataset = spark.read()
				.format("com.databricks.spark.csv")
				.option("header", "true")
				.option("inferSchema", true)
				.load(filePath);
		
		//Make single features column for feature vectors 
		ArrayList<String> inputColsList = new ArrayList<String>(Arrays.asList(inDataset.columns()));
		inputColsList.remove("class");
		String[] inputCols = inputColsList.parallelStream().toArray(String[]::new);
		
		//Prepare dataset for training with all features in "features" column
		VectorAssembler assembler = new VectorAssembler().setInputCols(inputCols).setOutputCol("features");
		Dataset<Row> dataset = assembler.transform(inDataset);

		// Trains a bisecting k-means model.
		BisectingKMeans bkm = new BisectingKMeans().setK(27).setSeed(1);
		BisectingKMeansModel model = bkm.fit(dataset);

		// Evaluate clustering by computing Within Set Sum of Squared Errors.
		double WSSSE = model.computeCost(dataset);
		System.out.println("Within Set Sum of Squared Errors = " + WSSSE);

		// Shows the result.
		Vector[] centers = model.clusterCenters();
		System.out.println("Cluster Centers: ");
		for (Vector center: centers) {
		  System.out.println(center);
		}
		
		spark.stop();
	}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {
	SparkSession spark = SparkSession.builder()
			.master("local[8]")
			.appName("KMeansWithPCAExpt")
			.getOrCreate();

	// Load and parse data
	String filePath = "/home/kchoppella/book/Chapter09/data/covtypeNorm.csv";

	// Loads data.
	Dataset<Row> inDataset = spark.read()
			.format("com.databricks.spark.csv")
			.option("header", "true")
			.option("inferSchema", true)
			.load(filePath);
	ArrayList<String> inputColsList = new ArrayList<String>(Arrays.asList(inDataset.columns()));
	
	//Make single features column for feature vectors 
	inputColsList.remove("class");
	String[] inputCols = inputColsList.parallelStream().toArray(String[]::new);
	
	//Prepare dataset for training with all features in "features" column
	VectorAssembler assembler = new VectorAssembler().setInputCols(inputCols).setOutputCol("features");
	Dataset<Row> dataset = assembler.transform(inDataset);

	PCAModel pca = new PCA()
			.setK(16)
			.setInputCol("features")
			.setOutputCol("pcaFeatures")
			.fit(dataset);

	Dataset<Row> result = pca.transform(dataset).select("pcaFeatures");
	System.out.println("Explained variance:");
	System.out.println(pca.explainedVariance());
	result.show(false);
	
	KMeans kmeans = new KMeans().setK(27).setSeed(1L);
	KMeansModel model = kmeans.fit(dataset);

	// Evaluate clustering by computing Within Set Sum of Squared Errors.
	double WSSSE = model.computeCost(dataset);
	System.out.println("Within Set Sum of Squared Errors = " + WSSSE);

	// $example off$
	spark.stop();
}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {

		SparkSession spark = SparkSession.builder()
				.master("local[8]")
				.appName("GaussianMixtureModelExpt")
				.getOrCreate();

		// Load and parse data
		String filePath = "/home/kchoppella/book/Chapter09/data/covtypeNorm.csv";

		// Loads data.
		Dataset<Row> inDataset = spark.read()
				.format("com.databricks.spark.csv")
				.option("header", "true")
				.option("inferSchema", true)
				.load(filePath);
		ArrayList<String> inputColsList = new ArrayList<String>(Arrays.asList(inDataset.columns()));
		
		//Make single features column for feature vectors 
		inputColsList.remove("class");
		String[] inputCols = inputColsList.parallelStream().toArray(String[]::new);
		
		//Prepare dataset for training with all features in "features" column
		VectorAssembler assembler = new VectorAssembler().setInputCols(inputCols).setOutputCol("features");
		Dataset<Row> dataset = assembler.transform(inDataset);

		PCAModel pca = new PCA()
				.setK(16)
				.setInputCol("features")
				.setOutputCol("pcaFeatures")
				.fit(dataset);

		Dataset<Row> result = pca.transform(dataset).select("pcaFeatures").withColumnRenamed("pcaFeatures", "features");
		
		String outPath = "/home/kchoppella/book/Chapter09/data/gmm_params.csv";

		try {
			BufferedWriter writer = Files.newBufferedWriter(Paths.get(outPath));

			// Cluster the data into multiple classes using KMeans
			int numClusters = 27;
			GaussianMixtureModel gmm = new GaussianMixture()
					.setK(numClusters).
					fit(result);
			int numIterations = gmm.getK();
			// Output the parameters of the mixture model
			for (int i = 0; i < numIterations; i++) {
				String msg = String.format("Gaussian %d:\nweight=%f\nmu=%s\nsigma=\n%s\n\n",
					          i, 
					          gmm.weights()[i], 
					          gmm.gaussians()[i].mean(), 
					          gmm.gaussians()[i].cov());

				System.out.printf(msg);
				writer.write(msg + "\n");
				writer.flush();
			}
		} 
		catch (IOException iox) {
			System.out.println("Write Exception: \n");
			iox.printStackTrace();
		}
		finally {
		}
		
		spark.stop();
	}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
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();
 }
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {
    String query = null;
    String queryOverwrite = null;

    // Read program arguments

    for (int i = 0; i < args.length; i++) {
        if (args[i].equalsIgnoreCase("-query")) {
            query = args[i + 1];
        } else if (args[i].equalsIgnoreCase("-queryOverwrite")) {
            queryOverwrite = args[i + 1];
        }
    }

    if (query == null) {
        query = "message = 'Hello World'; \n"
                + "result = select cast(unix_timestamp() as timestamp) as time, '${message}' as message; \n"
                + "printTable(result);";
    } else if (query.toLowerCase().startsWith("http://") || query.toLowerCase().startsWith("https://")) {
        System.out.println("Fetching query from http: " + query);
        query = HttpUtils.get(query, null).getBody();
    }

    System.out.println("Query: " + query);
    System.out.println("Query Overwrite: " + queryOverwrite);

    // Start Spark Session

    String master = "local[1]";
    String appName = "QueryExampleJob";

    SparkConf sparkConf = new SparkConf()
            .setMaster(master)
            .setAppName(appName);

    SparkSession sparkSession = SparkSession
            .builder()
            .config(sparkConf).getOrCreate();

    // Load query from hdfs if it is hdfs url
    if (query.toLowerCase().startsWith("hdfs://")) {
        System.out.println("Fetching query from hdfs: " + query);
        Tuple2<String, String>[] tuples = (Tuple2<String, String>[]) sparkSession.sparkContext().wholeTextFiles(query, 1).collect();
        query = tuples[0]._2();
        System.out.println("Query: " + query);
    }

    // Run query
    QueryEngine engine = new QueryEngine();
    engine.executeScript(query, queryOverwrite, sparkSession, false);

    sparkSession.stop();
}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {
    // Prepare data as the input for the script.
    // This is just for demonstration. In real scenario, you will have your own data in database, hadoop, or other places.
    String connectionString = prepareJdbcData();
    String jsonFile = prepareJsonFile();

    // Start Spark Session

    String master = "local[1]";
    String appName = "QueryExecutionExample";

    SparkConf sparkConf = new SparkConf()
            .setMaster(master)
            .setAppName(appName);

    SparkSession sparkSession = SparkSession
            .builder()
            .config(sparkConf).getOrCreate();

    // Set log level to avoid too many outputs
    sparkSession.sparkContext().setLogLevel("ERROR");

    // Script to run
    String script =
            String.format("clients = sql jdbc set connectionString='%s'; select clientId, clientName from dim_client; \n", connectionString)
                    + String.format("orders = file json file://%s; \n", jsonFile)
                    + "result = select clientName,productName,totalCount from orders join clients on clients.clientId = orders.clientId; \n"
                    + String.format("writeJdbc('%s', 'jdbcTable', 'clientName,productName', 'clientName,productName', '', 'Append', result);", connectionString);

    System.out.println("-----------------------------------------------");
    System.out.println("Running script");
    System.out.println("-----------------------------------------------");
    System.out.println(script);
    System.out.println("-----------------------------------------------");

    // Run Script
    QueryEngine engine = new QueryEngine();
    engine.executeScript(script, sparkSession);

    // The data should be written into the database by writeJdbc action.
    // Let's query it and print it out.
    DataSetResult dataResult = SqlUtils.executeJdbcQuery(connectionString, "select * from jdbcTable");
    System.out.println("-----------------------------------------------");
    System.out.println("Data in jdbc table after executing script");
    System.out.println("-----------------------------------------------");
    dataResult.print();
    System.out.println("-----------------------------------------------");

    sparkSession.stop();
}