spark CorrelationsExample 源码
spark CorrelationsExample 代码
文件路径：/examples/src/main/scala/org/apache/spark/examples/mllib/CorrelationsExample.scala
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
// scalastyle:off println
package org.apache.spark.examples.mllib
import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.linalg._
import org.apache.spark.mllib.stat.Statistics
import org.apache.spark.rdd.RDD
// $example off$
object CorrelationsExample {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("CorrelationsExample")
val sc = new SparkContext(conf)
// $example on$
val seriesX: RDD[Double] = sc.parallelize(Array(1, 2, 3, 3, 5)) // a series
// must have the same number of partitions and cardinality as seriesX
val seriesY: RDD[Double] = sc.parallelize(Array(11, 22, 33, 33, 555))
// compute the correlation using Pearson's method. Enter "spearman" for Spearman's method. If a
// method is not specified, Pearson's method will be used by default.
val correlation: Double = Statistics.corr(seriesX, seriesY, "pearson")
println(s"Correlation is: $correlation")
val data: RDD[Vector] = sc.parallelize(
Seq(
Vectors.dense(1.0, 10.0, 100.0),
Vectors.dense(2.0, 20.0, 200.0),
Vectors.dense(5.0, 33.0, 366.0))
) // note that each Vector is a row and not a column
// calculate the correlation matrix using Pearson's method. Use "spearman" for Spearman's method
// If a method is not specified, Pearson's method will be used by default.
val correlMatrix: Matrix = Statistics.corr(data, "pearson")
println(correlMatrix.toString)
// $example off$
sc.stop()
}
}
// scalastyle:on println
相关信息
相关文章
spark AssociationRulesExample 源码
spark BinaryClassificationMetricsExample 源码
spark BisectingKMeansExample 源码
0
赞
- 所属分类： 前端技术
- 本文标签：
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
7、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦