目录
1. Test
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions._
import org.junit.Test
import util.{MathUtil, UDFUtil}
/**
* @author
* @version
* @date 2020/5/5
* @Description
*/
class PyToScala {
val spark: SparkSession = SparkSession
.builder()
.appName("local-test")
.master("local[4]")
//.enableHiveSupport()
.config("spark.shuffle.service.enabled", true)
.config("spark.driver.maxResultSize", "4G")
.config("spark.sql.parquet.writeLegacyFormat", true)
.getOrCreate()
import spark.implicits._
spark.sparkContext.setLogLevel("WARN")
@Test
def testPyBinCount(): Unit = {
/**
* import numpy as np
*
* array = np.array([5, 4, 4])
* bincount = np.bincount(array)
* ps = bincount / np.sum(array)
* # bin