从JavaRDD生成直方图

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.SparkConf;

import java.util.Arrays;
import java.util.List;

public class HistogramExample {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("HistogramExample").setMaster("local[*]");
        JavaSparkContext sc = new JavaSparkContext(conf);

        // 示例数据
        List<Integer> data = Arrays.asList(1, 2, 3, 4, 5, 6, 7, 8, 9, 10);
        JavaRDD<Integer> rdd = sc.parallelize(data);

        // 定义桶的数量和范围
        int numBins = 5;
        double minValue = 1.0;
        double maxValue = 10.0;

        // 计算每个桶的范围
        double binWidth = (maxValue - minValue) / numBins;
        List<Double> binEdges = Arrays.asList(
                minValue, minValue + binWidth, minValue + 2 * binWidth,
                minValue + 3 * binWidth, minValue + 4 * binWidth, maxValue
        );

        // 生成直方图
        List<Integer> histogram = rdd.histogram(binEdges);

        // 打印直方图
        for (int i = 0; i < histogram.size() - 1; i++) {
            System.out.println("Bin " + i + ": [" + binEdges.get(i) + ", " + binEdges.get(i + 1) + ") - Count: " + histogram.get(i));
        }

        sc.stop();
    }
}