hadoop DataStatistics 源码
haddop DataStatistics 代码
文件路径：/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/speculate/DataStatistics.java
/**
* 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
* 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.
*/
package org.apache.hadoop.mapreduce.v2.app.speculate;
public class DataStatistics {
/**
* factor used to calculate confidence interval within 95%.
*/
private static final double DEFAULT_CI_FACTOR = 1.96;
private int count = 0;
private double sum = 0;
private double sumSquares = 0;
public DataStatistics() {
}
public DataStatistics(final double initNum) {
this.count = 1;
this.sum = initNum;
this.sumSquares = initNum * initNum;
}
public synchronized void add(final double newNum) {
this.count++;
this.sum += newNum;
this.sumSquares += newNum * newNum;
}
public synchronized void updateStatistics(final double old,
final double update) {
this.sum += update - old;
this.sumSquares += (update * update) - (old * old);
}
public synchronized double mean() {
return count == 0 ? 0.0 : sum / count;
}
public synchronized double var() {
// E(X^2) - E(X)^2
if (count <= 1) {
return 0.0;
}
double mean = mean();
return Math.max((sumSquares / count) - mean * mean, 0.0d);
}
public synchronized double std() {
return Math.sqrt(this.var());
}
public synchronized double outlier(final float sigma) {
if (count != 0.0) {
return mean() + std() * sigma;
}
return 0.0;
}
public synchronized double count() {
return count;
}
/**
* calculates the mean value within 95% ConfidenceInterval.
* 1.96 is standard for 95 %
*
* @return the mean value adding 95% confidence interval
*/
public synchronized double meanCI() {
if (count <= 1) {
return 0.0;
}
double currMean = mean();
double currStd = std();
return currMean + (DEFAULT_CI_FACTOR * currStd / Math.sqrt(count));
}
public String toString() {
return "DataStatistics: count is " + count + ", sum is " + sum
+ ", sumSquares is " + sumSquares + " mean is " + mean()
+ " std() is " + std() + ", meanCI() is " + meanCI();
}
}
相关信息
相关文章
hadoop ExponentiallySmoothedTaskRuntimeEstimator 源码
hadoop LegacyTaskRuntimeEstimator 源码
hadoop NullTaskRuntimesEngine 源码
hadoop SimpleExponentialTaskRuntimeEstimator 源码
0
赞
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