运行结果

统计每个学员的总成绩

这个是索引库使用通配符

优先在本地查询

只在本地节点中查询

只在指定id的节点里面进行查询

查询指定分片的数据

参考代码ESTestAggregation.java

package com.dajiangtai.djt_spider.elasticsearch;

import java.net.InetAddress;
import java.net.UnknownHostException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit; import org.codehaus.jackson.map.ObjectMapper;
import org.elasticsearch.action.bulk.BackoffPolicy;
import org.elasticsearch.action.bulk.BulkProcessor;
import org.elasticsearch.action.bulk.BulkRequest;
import org.elasticsearch.action.bulk.BulkResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.index.IndexResponse;
import org.elasticsearch.action.search.SearchRequestBuilder;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.transport.TransportClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.InetSocketTransportAddress;
import org.elasticsearch.common.unit.ByteSizeUnit;
import org.elasticsearch.common.unit.ByteSizeValue;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.bucket.terms.Terms;
import org.elasticsearch.search.aggregations.bucket.terms.Terms.Bucket;
import org.elasticsearch.search.aggregations.metrics.sum.Sum;
import org.junit.Before;
import org.junit.Test;
/**
* Aggregation 操作
*
* @author 大讲台
*
*/
public class ESTestAggregation {
private TransportClient client; @Before
public void test0() throws UnknownHostException { // 开启client.transport.sniff功能,探测集群所有节点
Settings settings = Settings.settingsBuilder()
.put("cluster.name", "escluster")
.put("client.transport.sniff", true).build();
// on startup
// 获取TransportClient
client = TransportClient
.builder()
.settings(settings)
.build()
.addTransportAddress(
new InetSocketTransportAddress(InetAddress
.getByName("master"), 9300))
.addTransportAddress(
new InetSocketTransportAddress(InetAddress
.getByName("slave1"), 9300))
.addTransportAddress(
new InetSocketTransportAddress(InetAddress
.getByName("slave2"), 9300));
}
/**
* Aggregation 分组统计相同年龄学员个数
* @throws Exception
*/
@Test
public void test1() throws Exception {
SearchRequestBuilder builder = client.prepareSearch("djt1");
builder.setTypes("user")
.setQuery(QueryBuilders.matchAllQuery())
//按年龄分组聚合统计
.addAggregation(AggregationBuilders.terms("by_age").field("age").size(0))
; SearchResponse searchResponse = builder.get();
//获取分组信息
Terms terms = searchResponse.getAggregations().get("by_age");
List<Bucket> buckets = terms.getBuckets();
for (Bucket bucket : buckets) {
System.out.println(bucket.getKey()+":"+bucket.getDocCount());
}
} /**
* Aggregation 分组统计每个学员的总成绩
* @throws Exception
*/
@Test
public void test2() throws Exception {
SearchRequestBuilder builder = client.prepareSearch("djt2");
builder.setTypes("user")
.setQuery(QueryBuilders.matchAllQuery())
//按姓名分组聚合统计
.addAggregation(AggregationBuilders.terms("by_name")
.field("name")
.subAggregation(AggregationBuilders.sum("sum_score")
.field("score"))
.size(0))
;
SearchResponse searchResponse = builder.get();
//获取分组信息
Terms terms = searchResponse.getAggregations().get("by_name");
List<Bucket> buckets = terms.getBuckets();
for (Bucket bucket : buckets) {
Sum sum = bucket.getAggregations().get("sum_score");
System.out.println(bucket.getKey()+":"+sum.getValue());
}
} /**
* 支持多索引和多类型查询
* @throws Exception
*/
@Test
public void test3() throws Exception {
SearchRequestBuilder builder
= client//.prepareSearch("djt1","djt2")//可以指定多个索引库
.prepareSearch("djt*")//索引库可以使用通配符
.setTypes("user");//支持多个类型,但不支持通配符 SearchResponse searchResponse = builder.get(); SearchHits hits = searchResponse.getHits();
SearchHit[] hits2 = hits.getHits();
for (SearchHit searchHit : hits2) {
System.out.println(searchHit.getSourceAsString());
}
}
/**
* 分片查询方式
* @throws Exception
*/
@Test
public void test4() throws Exception {
SearchRequestBuilder
builder = client.prepareSearch("djt3")
.setTypes("user")
//.setPreference("_local")
//.setPreference("_only_local")
//.setPreference("_primary")
//.setPreference("_replica")
//.setPreference("_primary_first")
//.setPreference("_replica_first")
//.setPreference("_only_node:crKxtA2fRTG1UZdPN8QtaA")
//.setPreference("_prefer_node:nJL_MqcsSle6gY7iujoAlw")
.setPreference("_shards:3")
;
SearchResponse searchResponse = builder.get();
SearchHits hits = searchResponse.getHits();
SearchHit[] hits2 = hits.getHits();
for (SearchHit searchHit : hits2) {
System.out.println(searchHit.getSourceAsString());
}
}
/**
* 极速查询:通过路由插入数据(同一类别数据在一个分片)
* @throws Exception
*/
@Test
public void test5() throws Exception {
Acount acount = new Acount("13602546655","tom1","male",16);
Acount acount2 = new Acount("13602546655","tom2","male",17);
Acount acount3 = new Acount("13602546655","tom3","male",18);
Acount acount4 = new Acount("18903762536","john1","male",28);
Acount acount5 = new Acount("18903762536","john2","male",29);
Acount acount6 = new Acount("18903762536","john3","male",30);
List<Acount> list = new ArrayList<Acount>();
list.add(acount);
list.add(acount2);
list.add(acount3);
list.add(acount4);
list.add(acount5);
list.add(acount6); BulkProcessor bulkProcessor = BulkProcessor.builder(
client,
new BulkProcessor.Listener() { public void beforeBulk(long executionId, BulkRequest request) {
// TODO Auto-generated method stub
System.out.println(request.numberOfActions());
} public void afterBulk(long executionId, BulkRequest request,
Throwable failure) {
// TODO Auto-generated method stub
System.out.println(failure.getMessage());
} public void afterBulk(long executionId, BulkRequest request,
BulkResponse response) {
// TODO Auto-generated method stub
System.out.println(response.hasFailures());
}
})
.setBulkActions(1000) // 每个批次的最大数量
.setBulkSize(new ByteSizeValue(1, ByteSizeUnit.GB))// 每个批次的最大字节数
.setFlushInterval(TimeValue.timeValueSeconds(5))// 每批提交时间间隔
.setConcurrentRequests(1) //设置多少个并发处理线程
//可以允许用户自定义当一个或者多个bulk请求失败后,该执行如何操作
.setBackoffPolicy(
BackoffPolicy.exponentialBackoff(TimeValue.timeValueMillis(100), 3))
.build();
for (Acount a : list) {
ObjectMapper mapper = new ObjectMapper(); byte[] json = mapper.writeValueAsBytes(a);
bulkProcessor.add(new IndexRequest("djt3", "user")
.routing(a.getPhone().substring(0, 3))
.source(json));
} //阻塞至所有的请求线程处理完毕后,断开连接资源
bulkProcessor.awaitClose(3, TimeUnit.MINUTES);
client.close();
}
/**
* 极速查询:通过路由极速查询,也可以通过分片shards查询演示
*
* @throws Exception
*/
@Test
public void test6() throws Exception {
SearchRequestBuilder builder = client.prepareSearch("djt3")//可以指定多个索引库
.setTypes("user");//支持多个类型,但不支持通配符
builder.setQuery(QueryBuilders.matchAllQuery())
.setRouting("13602546655".substring(0, 3))
//.setRouting("18903762536".substring(0, 3))
;
SearchResponse searchResponse = builder.get(); SearchHits hits = searchResponse.getHits();
SearchHit[] hits2 = hits.getHits();
for (SearchHit searchHit : hits2) {
System.out.println(searchHit.getSourceAsString());
}
}
}

elastisSearch-aggregations的更多相关文章

  1. hive的Query和Insert,Group by,Aggregations(聚合)操作

    1.Query (1)分区查询 在查询的过程中,采用那个分区来查询是通过系统自动的决定,但是必须是在分区列上基于where子查询. SELECT page_views.* FROM page_view ...

  2. ElasticSearch 的 聚合(Aggregations)

    Elasticsearch有一个功能叫做 聚合(aggregations) ,它允许你在数据上生成复杂的分析统计.它很像SQL中的 GROUP BY 但是功能更强大. Aggregations种类分为 ...

  3. aggregation 详解2(metrics aggregations)

    概述 权值聚合类型从需要聚合的文档中取一个值(value)来计算文档的相应权值(比如该值在这些文档中的max.sum等). 用于计算的值(value)可以是文档的字段(field),也可以是脚本(sc ...

  4. aggregation 详解4(pipeline aggregations)

    概述 管道聚合处理的对象是其它聚合的输出(桶或者桶的某些权值),而不是直接针对文档. 管道聚合的作用是为输出增加一些有用信息. 管道聚合大致分为两类: parent 此类聚合的"输入&quo ...

  5. aggregations 详解1(概述)

    aggregation分类 aggregations —— 聚合,提供了一种基于查询条件来对数据进行分桶.计算的方法.有点类似于 SQL 中的 group by 再加一些函数方法的操作. 聚合可以嵌套 ...

  6. Elasticsearch aggregations API

    聚合能力 Aggregation API 类似 SQL 中的 GROUP BY 语句,可以以某个字段来进行分组. Aggregation API 支持分级分组,多级的分组过程是由外到里的. Aggre ...

  7. Spark学习之路(十一)—— Spark SQL 聚合函数 Aggregations

    一.简单聚合 1.1 数据准备 // 需要导入spark sql内置的函数包 import org.apache.spark.sql.functions._ val spark = SparkSess ...

  8. Spark 系列(十一)—— Spark SQL 聚合函数 Aggregations

    一.简单聚合 1.1 数据准备 // 需要导入 spark sql 内置的函数包 import org.apache.spark.sql.functions._ val spark = SparkSe ...

  9. 使用 ElasticSearch Aggregations 进行统计分析(转)

    https://blog.csdn.net/cs729298/article/details/68926969 ElasticSearch 的特点随处可见:基于 Lucene 的分布式搜索引擎,友好的 ...

  10. Elasticsearch系列(二)--query、filter、aggregations

    本文基于ES6.4版本,我也是出于学习阶段,对学习内容做个记录,如果文中有错误,请指出. 实验数据: index:book type:novel mappings: { "mappings& ...

随机推荐

  1. P1002 谁拿了最多奖学金

    P1002 谁拿了最多奖学金 时间: 1000ms / 空间: 131072KiB / Java类名: Main 背景 NOIP2005复赛提高组第一题 描述 某校的惯例是在每学期的期末考试之后发放奖 ...

  2. Stack Overflow 2016年度 20个最佳Python问题(一)

    Stack Overflow 2016年度 20个最佳Python问题(一) https://zhuanlan.zhihu.com/p/25020763

  3. BZOJ4767: 两双手【组合数学+容斥原理】

    Description 老W是个棋艺高超的棋手,他最喜欢的棋子是马,更具体地,他更加喜欢马所行走的方式.老W下棋时觉得无聊,便决定加强马所行走的方式,更具体地,他有两双手,其中一双手能让马从(u,v) ...

  4. centos下安装必要组件(相当于apt-get install install build-essential)

    在centos下执行 : sudo yum groupinstall 'Development Tools'

  5. 《DSP using MATLAB》Problem 4.1

    用到的z变换的计算公式: 代码: %% ------------------------------------------------------------------------ %% Outp ...

  6. python type metaclass

    在python中一切皆对象, 所有类的鼻祖都是type, 也就是所有类都是通过type来创建. 传统创建类 class Foo(object): def __init__(self,name): se ...

  7. frameset的用法

    碰到一个frameset的问题,因为我比较懒,就先从网上拿来一篇基础知识,呵呵,好记性不如烂笔头啊        所谓框架便是网页画面分成几个框窗,同时取得多个 URL.只需要 <FRAMESE ...

  8. HDU1423 Greatest Common Increasing Subsequence

    题意 如标题. \(|s1|,|s2| \leq 500\) 分析 既然是dp问题的组合,那么考虑dp. 定义状态f(i,j)表示对第一个序列s1的前i个和第二个序列s2的前j个元素求最长上升公共子序 ...

  9. Sencha Touch+PhoneGap打造超级奶爸之喂养记(一) 源码免费提供(转)

    起源 非常高兴我的宝宝健康平安的出生了.对于初次做奶爸的我,喜悦过后,面临着各中担心,担心宝宝各项指标是否正常.最初几天都是在医院待着,从出生那一天开始,护士妹妹隔一段时间就会来问宝宝的喂奶,大小便, ...

  10. solr学习四(关于性能的杂知识)

    将所有只用于搜索的,而不需要作为结果的field(特别是一些比较大的field)的stored设置为false 比如我们在solr中index了一篇word,对于这篇word,我们只需要这篇文章的下载 ...