本文整理汇总了Java中org.apache.spark.api.java.JavaPairRDD.keys方法的典型用法代码示例。如果您正苦于以下问题：Java JavaPairRDD.keys方法的具体用法？Java JavaPairRDD.keys怎么用？Java JavaPairRDD.keys使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.spark.api.java.JavaPairRDD的用法示例。
在下文中一共展示了JavaPairRDD.keys方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: parallizeUsers
import org.apache.spark.api.java.JavaPairRDD; //导入方法依赖的package包/类
public JavaRDD<String> parallizeUsers(Map<String, Double> userDocs) {
// prepare list for parallize
List<Tuple2<String, Double>> list = new ArrayList<>();
for (String user : userDocs.keySet()) {
list.add(new Tuple2<String, Double>(user, userDocs.get(user)));
}
// group users
ThePartitionProblemSolver solution = new KGreedyPartitionSolver();
Map<String, Integer> userGroups = solution.solve(userDocs, this.partition);
JavaPairRDD<String, Double> pairRdd = spark.sc.parallelizePairs(list);
JavaPairRDD<String, Double> userPairRDD = pairRdd.partitionBy(new logPartitioner(userGroups, this.partition));
// repartitioned user RDD
return userPairRDD.keys();
}
示例2: buildSVDMatrix
import org.apache.spark.api.java.JavaPairRDD; //导入方法依赖的package包/类
/**
* Build svd matrix from CSV file.
*
* @param tfidfCSVfile tf-idf matrix csv file
* @param svdDimension: Dimension of matrix after singular value decomposition
* @return row matrix
*/
public RowMatrix buildSVDMatrix(String tfidfCSVfile, int svdDimension) {
RowMatrix svdMatrix = null;
JavaPairRDD<String, Vector> tfidfRDD = MatrixUtil.loadVectorFromCSV(spark, tfidfCSVfile, 2);
JavaRDD<Vector> vectorRDD = tfidfRDD.values();
svdMatrix = MatrixUtil.buildSVDMatrix(vectorRDD, svdDimension);
this.svdMatrix = svdMatrix;
this.wordRDD = tfidfRDD.keys();
return svdMatrix;
}
示例3: calTermSimfromMatrix
import org.apache.spark.api.java.JavaPairRDD; //导入方法依赖的package包/类
/**
* Calculate term similarity from CSV matrix.
*
* @param csvFileName csv file of matrix, each row is a term, and each column is a
* dimension in feature space
* @param skipRow number of rows to skip in input CSV file e.g. header
* @return Linkage triple list
*/
public List<LinkageTriple> calTermSimfromMatrix(String csvFileName, int skipRow) {
JavaPairRDD<String, Vector> importRDD = MatrixUtil.loadVectorFromCSV(spark, csvFileName, skipRow);
if (importRDD == null || importRDD.values().first().size() == 0) {
return null;
}
CoordinateMatrix simMatrix = SimilarityUtil.calculateSimilarityFromVector(importRDD.values());
JavaRDD<String> rowKeyRDD = importRDD.keys();
return SimilarityUtil.matrixToTriples(rowKeyRDD, simMatrix);
}