ElasticSearch7.3学习(二十九)----聚合实战之使用Java api实现电视案例
一、数据准备
创建索引及映射
建立价格、颜色、品牌、售卖日期字段
PUT /tvsPUT /tvs/_mapping
{
"properties": {
"price": {
"type": "long"
},
"color": {
"type": "keyword"
},
"brand": {
"type": "keyword"
},
"sold_date": {
"type": "date"
}
}
}插入数据
POST /tvs/_bulk
{"index":{}}
{"price":1000,"color":"红色","brand":"长虹","sold_date":"2019-10-28"}
{"index":{}}
{"price":2000,"color":"红色","brand":"长虹","sold_date":"2019-11-05"}
{"index":{}}
{"price":3000,"color":"绿色","brand":"小米","sold_date":"2019-05-18"}
{"index":{}}
{"price":1500,"color":"蓝色","brand":"TCL","sold_date":"2019-07-02"}
{"index":{}}
{"price":1200,"color":"绿色","brand":"TCL","sold_date":"2019-08-19"}
{"index":{}}
{"price":2000,"color":"红色","brand":"长虹","sold_date":"2019-11-05"}
{"index":{}}
{"price":8000,"color":"红色","brand":"三星","sold_date":"2020-01-01"}
{"index":{}}
{"price":2500,"color":"蓝色","brand":"小米","sold_date":"2020-02-12"}二、 按照颜色分组，计算每个颜色卖出的个数
ES语句
GET /tvs/_search
{
"size": 0,
"query": {
"match_all": {}
},
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
}
}
}
}返回
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"group_by_color" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "红色",
"doc_count" : 4
},
{
"key" : "绿色",
"doc_count" : 2
},
{
"key" : "蓝色",
"doc_count" : 2
}
]
}
}
}Java代码
//按照颜色分组，计算每个颜色卖出的个数
@Test
public void testAggs() throws IOException {
//1 构建请求
SearchRequest searchRequest=new SearchRequest("tvs");
//请求体
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.query(QueryBuilders.matchAllQuery());
TermsAggregationBuilder termsAggregationBuilder = AggregationBuilders.terms("group_by_color").field("color");
searchSourceBuilder.aggregation(termsAggregationBuilder);
//请求体放入请求头
searchRequest.source(searchSourceBuilder);
//2 执行
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
Aggregations aggregations = searchResponse.getAggregations();
Terms group_by_color = aggregations.get("group_by_color");
List<? extends Terms.Bucket> buckets = group_by_color.getBuckets();
for (Terms.Bucket bucket : buckets) {
String key = bucket.getKeyAsString();
System.out.println("key:"+key);
long docCount = bucket.getDocCount();
System.out.println("docCount:"+docCount);
System.out.println("=================================");
}
}结果
三、按照颜色分组，计算每个颜色卖出的个数，每个颜色卖出的平均价格
ES语句
GET /tvs/_search
{
"size": 0,
"query": {
"match_all": {}
},
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
},
"aggs": {
"avg_price": {
"avg": {
"field": "price"
}
}
}
}
}
}返回结果
{
"took" : 2,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"group_by_color" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "红色",
"doc_count" : 4,
"avg_price" : {
"value" : 3250.0
}
},
{
"key" : "绿色",
"doc_count" : 2,
"avg_price" : {
"value" : 2100.0
}
},
{
"key" : "蓝色",
"doc_count" : 2,
"avg_price" : {
"value" : 2000.0
}
}
]
}
}
}Java代码
// 按照颜色分组，计算每个颜色卖出的个数，每个颜色卖出的平均价格
@Test
public void testAggsAndAvg() throws IOException {
//1 构建请求
SearchRequest searchRequest=new SearchRequest("tvs");
//请求体
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.query(QueryBuilders.matchAllQuery());
TermsAggregationBuilder termsAggregationBuilder = AggregationBuilders.terms("group_by_color").field("color");
//terms聚合下填充一个子聚合
AvgAggregationBuilder avgAggregationBuilder = AggregationBuilders.avg("avg_price").field("price");
termsAggregationBuilder.subAggregation(avgAggregationBuilder);
searchSourceBuilder.aggregation(termsAggregationBuilder);
//请求体放入请求头
searchRequest.source(searchSourceBuilder);
//2 执行
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
Aggregations aggregations = searchResponse.getAggregations();
Terms group_by_color = aggregations.get("group_by_color");
List<? extends Terms.Bucket> buckets = group_by_color.getBuckets();
for (Terms.Bucket bucket : buckets) {
String key = bucket.getKeyAsString();
System.out.println("key:"+key);
long docCount = bucket.getDocCount();
System.out.println("docCount:"+docCount);
Aggregations aggregations1 = bucket.getAggregations();
Avg avg_price = aggregations1.get("avg_price");
double value = avg_price.getValue();
System.out.println("value:"+value);
System.out.println("=================================");
}
}返回结果
四、按照颜色分组，计算每个颜色卖出的个数，以及每个颜色卖出的平均值、最大值、最小值、总和
ES语句
GET /tvs/_search
{
"size": 0,
"aggs": {
"group_by_color": {
"terms": {
"field": "color"
},
"aggs": {
"avg_price": {
"avg": {
"field": "price"
}
},
"min_price": {
"min": {
"field": "price"
}
},
"max_price": {
"max": {
"field": "price"
}
},
"sum_price": {
"sum": {
"field": "price"
}
}
}
}
}
}返回结果
{
"took" : 1,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"group_by_color" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "红色",
"doc_count" : 4,
"max_price" : {
"value" : 8000.0
},
"min_price" : {
"value" : 1000.0
},
"avg_price" : {
"value" : 3250.0
},
"sum_price" : {
"value" : 13000.0
}
},
{
"key" : "绿色",
"doc_count" : 2,
"max_price" : {
"value" : 3000.0
},
"min_price" : {
"value" : 1200.0
},
"avg_price" : {
"value" : 2100.0
},
"sum_price" : {
"value" : 4200.0
}
},
{
"key" : "蓝色",
"doc_count" : 2,
"max_price" : {
"value" : 2500.0
},
"min_price" : {
"value" : 1500.0
},
"avg_price" : {
"value" : 2000.0
},
"sum_price" : {
"value" : 4000.0
}
}
]
}
}
}Java代码
// 按照颜色分组，计算每个颜色卖出的个数，以及每个颜色卖出的平均值、最大值、最小值、总和。
@Test
public void testAggsAndMore() throws IOException {
//1 构建请求
SearchRequest searchRequest=new SearchRequest("tvs");
//请求体
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.query(QueryBuilders.matchAllQuery());
TermsAggregationBuilder termsAggregationBuilder = AggregationBuilders.terms("group_by_color").field("color");
//termsAggregationBuilder里放入多个子聚合
AvgAggregationBuilder avgAggregationBuilder = AggregationBuilders.avg("avg_price").field("price");
MinAggregationBuilder minAggregationBuilder = AggregationBuilders.min("min_price").field("price");
MaxAggregationBuilder maxAggregationBuilder = AggregationBuilders.max("max_price").field("price");
SumAggregationBuilder sumAggregationBuilder = AggregationBuilders.sum("sum_price").field("price");
termsAggregationBuilder.subAggregation(avgAggregationBuilder);
termsAggregationBuilder.subAggregation(minAggregationBuilder);
termsAggregationBuilder.subAggregation(maxAggregationBuilder);
termsAggregationBuilder.subAggregation(sumAggregationBuilder);
searchSourceBuilder.aggregation(termsAggregationBuilder);
//请求体放入请求头
searchRequest.source(searchSourceBuilder);
//2 执行
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
Aggregations aggregations = searchResponse.getAggregations();
Terms group_by_color = aggregations.get("group_by_color");
List<? extends Terms.Bucket> buckets = group_by_color.getBuckets();
for (Terms.Bucket bucket : buckets) {
String key = bucket.getKeyAsString();
System.out.println("key:"+key);
long docCount = bucket.getDocCount();
System.out.println("docCount:"+docCount);
Aggregations aggregations1 = bucket.getAggregations();
Max max_price = aggregations1.get("max_price");
double maxPriceValue = max_price.getValue();
System.out.println("maxPriceValue:"+maxPriceValue);
Min min_price = aggregations1.get("min_price");
double minPriceValue = min_price.getValue();
System.out.println("minPriceValue:"+minPriceValue);
Avg avg_price = aggregations1.get("avg_price");
double avgPriceValue = avg_price.getValue();
System.out.println("avgPriceValue:"+avgPriceValue);
Sum sum_price = aggregations1.get("sum_price");
double sumPriceValue = sum_price.getValue();
System.out.println("sumPriceValue:"+sumPriceValue);
System.out.println("=================================");
}
}返回结果
五、按照售价每2000价格划分范围，算出每个区间的销售总额
ES语句
GET /tvs/_search
{
"size": 0,
"aggs": {
"by_histogram": {
"histogram": {
"field": "price",
"interval": 2000
},
"aggs": {
"income": {
"sum": {
"field": "price"
}
}
}
}
}
}返回结果
查看代码
{
"took" : 0,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"by_histogram" : {
"buckets" : [
{
"key" : 0.0,
"doc_count" : 3,
"income" : {
"value" : 3700.0
}
},
{
"key" : 2000.0,
"doc_count" : 4,
"income" : {
"value" : 9500.0
}
},
{
"key" : 4000.0,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
},
{
"key" : 6000.0,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
},
{
"key" : 8000.0,
"doc_count" : 1,
"income" : {
"value" : 8000.0
}
}
]
}
}
}Java代码
// 按照售价每2000价格划分范围，算出每个区间的销售总额 histogram
@Test
public void testAggsAndHistogram() throws IOException {
//1 构建请求
SearchRequest searchRequest=new SearchRequest("tvs");
//请求体
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.query(QueryBuilders.matchAllQuery());
HistogramAggregationBuilder histogramAggregationBuilder =
AggregationBuilders.histogram("by_histogram").field("price").interval(2000);
SumAggregationBuilder sumAggregationBuilder = AggregationBuilders.sum("income").field("price");
histogramAggregationBuilder.subAggregation(sumAggregationBuilder);
searchSourceBuilder.aggregation(histogramAggregationBuilder);
//请求体放入请求头
searchRequest.source(searchSourceBuilder);
//2 执行
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
Aggregations aggregations = searchResponse.getAggregations();
Histogram group_by_color = aggregations.get("by_histogram");
List<? extends Histogram.Bucket> buckets = group_by_color.getBuckets();
for (Histogram.Bucket bucket : buckets) {
String keyAsString = bucket.getKeyAsString();
System.out.println("keyAsString:"+keyAsString);
long docCount = bucket.getDocCount();
System.out.println("docCount:"+docCount);
Aggregations aggregations1 = bucket.getAggregations();
Sum income = aggregations1.get("income");
double value = income.getValue();
System.out.println("value:"+value);
System.out.println("=================================");
}
}返回结果
六、计算每个季度的销售总额
ES语句
GET /tvs/_search
{
"size": 0,
"aggs": {
"sales": {
"date_histogram": {
"field": "sold_date",
"interval": "quarter",
"format": "yyyy-MM-dd",
"min_doc_count": 0,
"extended_bounds": {
"min": "2019-01-01",
"max": "2020-12-31"
}
},
"aggs": {
"income": {
"sum": {
"field": "price"
}
}
}
}
}
}返回结果
查看代码
#! Deprecation: [interval] on [date_histogram] is deprecated, use [fixed_interval] or [calendar_interval] in the future.
{
"took" : 6,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"sales" : {
"buckets" : [
{
"key_as_string" : "2019-01-01",
"key" : 1546300800000,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
},
{
"key_as_string" : "2019-04-01",
"key" : 1554076800000,
"doc_count" : 1,
"income" : {
"value" : 3000.0
}
},
{
"key_as_string" : "2019-07-01",
"key" : 1561939200000,
"doc_count" : 2,
"income" : {
"value" : 2700.0
}
},
{
"key_as_string" : "2019-10-01",
"key" : 1569888000000,
"doc_count" : 3,
"income" : {
"value" : 5000.0
}
},
{
"key_as_string" : "2020-01-01",
"key" : 1577836800000,
"doc_count" : 2,
"income" : {
"value" : 10500.0
}
},
{
"key_as_string" : "2020-04-01",
"key" : 1585699200000,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
},
{
"key_as_string" : "2020-07-01",
"key" : 1593561600000,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
},
{
"key_as_string" : "2020-10-01",
"key" : 1601510400000,
"doc_count" : 0,
"income" : {
"value" : 0.0
}
}
]
}
}
}Java代码
// 计算每个季度的销售总额
@Test
public void testAggsAndDateHistogram() throws IOException {
//1 构建请求
SearchRequest searchRequest=new SearchRequest("tvs");
//请求体
SearchSourceBuilder searchSourceBuilder=new SearchSourceBuilder();
searchSourceBuilder.size(0);
searchSourceBuilder.query(QueryBuilders.matchAllQuery());
DateHistogramAggregationBuilder dateHistogramAggregationBuilder =
AggregationBuilders.dateHistogram("date_histogram")
.field("sold_date")
.calendarInterval(DateHistogramInterval.QUARTER)
.format("yyyy-MM-dd")
.minDocCount(0)
.extendedBounds(new ExtendedBounds("2019-01-01", "2020-12-31"));
SumAggregationBuilder sumAggregationBuilder =
AggregationBuilders.sum("income").field("price");
dateHistogramAggregationBuilder.subAggregation(sumAggregationBuilder);
searchSourceBuilder.aggregation(dateHistogramAggregationBuilder);
//请求体放入请求头
searchRequest.source(searchSourceBuilder);
//2 执行
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
Aggregations aggregations = searchResponse.getAggregations();
ParsedDateHistogram date_histogram = aggregations.get("date_histogram");
List<? extends Histogram.Bucket> buckets = date_histogram.getBuckets();
for (Histogram.Bucket bucket : buckets) {
String keyAsString = bucket.getKeyAsString();
System.out.println("keyAsString:"+keyAsString);
long docCount = bucket.getDocCount();
System.out.println("docCount:"+docCount);
Aggregations aggregations1 = bucket.getAggregations();
Sum income = aggregations1.get("income");
double value = income.getValue();
System.out.println("value:"+value);
System.out.println("====================");
}
}返回结果
ElasticSearch7.3学习(二十九)----聚合实战之使用Java api实现电视案例的更多相关文章
- ElasticSearch7.3学习(二十八)----聚合实战之电视案例
一.电视案例 1.1 数据准备 创建索引及映射 建立价格.颜色.品牌.售卖日期 字段 PUT /tvs PUT /tvs/_mapping { "properties": { &q ...
- ElasticSearch7.3学习(二十五)----Doc value、query phase、fetch phase解析
1.Doc value 搜索的时候,要依靠倒排索引: 排序的时候,需要依靠正排索引,看到每个document的每个field,然后进行排序. 所谓的正排索引,其实就是doc values. 在建立索引 ...
- ElasticSearch7.3学习(二十六)----搜索（Search）参数总结、结果跳跃（bouncing results）问题解析
1.preference 首先引入一个bouncing results问题,两个document排序,field值相同:不同的shard上,可能排序不同:每次请求轮询打到不同的replica shar ...
- Java开发学习(二十九)----Maven依赖传递、可选依赖、排除依赖解析
现在的项目一般是拆分成一个个独立的模块,当在其他项目中想要使用独立出来的这些模块,只需要在其pom.xml使用<dependency>标签来进行jar包的引入即可. <depende ...
- ballerina 学习二十九 数据库操作
ballerina 数据操作也是比较方便的,官方也我们提供了数据操作的抽象,但是我们还是依赖数据库驱动的. 数据库驱动还是jdbc模式的 项目准备 项目结构 ├── mysql_demo │ ├── ...
- python学习 (二十九) range函数
1:list函数可以将其他类型转成list. print(list(range(0, 10))) 2: list函数把元组转成list t = (1, 3, 3, 5) print(list(t)) ...
- 渗透测试学习 二十九、kali安装，信息搜集，服务器扫描
kali安装,信息搜集,服务器扫描 kali介绍 Kali Linux是基于Debian的Linux发行版, 设计用于数字取证操作系统.由Offensive Security Ltd维护和资助.最先由 ...
- 前端学习(二十九）nodejs（笔记）
后台语言 java php .Net python Node.js------------------------------------------------- ...
- Salesforce LWC学习(二十九) getRecordNotifyChange（LDS拓展增强篇）
本篇参考: https://developer.salesforce.com/docs/component-library/documentation/en/lwc/data_ui_api https ...
随机推荐
- 【Android开发】富文本
SpannableString spannableString = new SpannableString("设置文字的前景色为淡蓝色"); ForegroundColorSpan ...
- box-shadow 阴影的高级用法，多个阴影叠加
box-shadow的这些用法你知道吗? $shadowH: ''; @for $i from 1 through 12 { $shadowH: #{$shadowH}, 0 ($i * 30px) ...
- B03. BootstrapBlazor实战 10分钟编写数据库维护项目
demo演示的是Sqlite驱动,FreeSql支持多种数据库,MySql/SqlServer/PostgreSQL/Oracle/Sqlite/Firebird/达梦/神通/人大金仓/翰高/华为Ga ...
- SSM实现个人博客-day04
项目源码免费下载:SSM实现个人博客 有问题询问vx:kht808 3.项目搭建(SSM整合) (1)创建maven工程,导入相应的依赖 <properties> <project. ...
- 使用 Jenkins 进行持续集成与发布流程图
应用构建和发布流程说明: 用户向 Gitlab 提交代码,代码中必须包含 Dockerfile 将代码提交到远程仓库 用户在发布应用时需要填写 git 仓库地址和分支.服务类型.服务名称.资源数量.实 ...
- 序列化之Serializer类与ModelSerializer类的使用
序列化之Serializer类的使用(5星) 作用: 序列化,序列化器会把模型对象转换成字典,经过response以后变成json字符串 反序列化,把客户端发送过来的数据,经过request以后变成字 ...
- 伪元素 Before & Aster
1. html 结构 <label class="is-required" for="name">姓名</label> <inpu ...
- python基础练习题（题目 矩阵对角线之和）
day25 --------------------------------------------------------------- 实例038:矩阵对角线之和 题目 求一个3*3矩阵主对角线元 ...
- Spring的3级缓存和循环引用的理解
此处是我自己的一个理解,防止以后忘记,如若那个地方理解不对,欢迎指出. 一.背景 在我们写代码的过程中一般会使用 @Autowired 来注入另外的一个对象,但有些时候发生了 循环依赖,但是我们的代码 ...
- 用python爬虫，对12306网站进行模拟登陆
from selenium import webdriver from time import sleep from PIL import Image from selenium.webdriver ...