聚合查询(aggs)
#用于进行聚合的字段必须是exact value,分词字段不可进行聚合,对于text字段如果需要使用聚合,需要开启fielddata,但是通常不建议;
#聚合查询分类
#1.分桶聚合(Bucket agregations):类比SQL中的group by的作用,主要用于统计不同类型数据的数量
#2.指标聚合(Metrics agregations):主要用于最大值、最小值、平均值、字段之和等指标的统计
#3.管道聚合(Pipeline agregations):用于对聚合的结果进行二次聚合,如要统计绑定数量最多的标签bucket,就是要先按照标签进行分桶,再在分桶的结果上计算最大值。
#语法
GET product/_search
{
"aggs": {
#聚合函数的名称
"<aggs_name>": {
#agg_type:聚合种类,比如是桶聚合(terms)或者是指标聚合(avg、sum、min、max等)
"<agg_type>": {
#字段名称或者叫域名
"field": "<field_name>"
}
}
}
}
桶聚合测试数据
## 数据
PUT product
{
"mappings" : {
"properties" : {
"createtime" : {
"type" : "date"
},
"date" : {
"type" : "date"
},
"desc" : {
"type" : "text",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 256
}
},
"analyzer":"ik_max_word"
},
"lv" : {
"type" : "text",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 256
}
}
},
"name" : {
"type" : "text",
"analyzer":"ik_max_word",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 256
}
}
},
"price" : {
"type" : "long"
},
"tags" : {
"type" : "text",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 256
}
}
},
"type" : {
"type" : "text",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 256
}
}
}
}
}
}
PUT /product/_doc/1
{
"name" : "小米手机",
"desc" : "手机中的战斗机",
"price" : 3999,
"lv":"旗舰机",
"type":"手机",
"createtime":"2020-10-01T08:00:00Z",
"tags": [ "性价比", "发烧", "不卡顿" ]
}
PUT /product/_doc/2
{
"name" : "小米NFC手机",
"desc" : "支持全功能NFC,手机中的滑翔机",
"price" : 4999,
"lv":"旗舰机",
"type":"手机",
"createtime":"2020-05-21T08:00:00Z",
"tags": [ "性价比", "发烧", "公交卡" ]
}
PUT /product/_doc/3
{
"name" : "NFC手机",
"desc" : "手机中的轰炸机",
"price" : 2999,
"lv":"高端机",
"type":"手机",
"createtime":"2020-06-20",
"tags": [ "性价比", "快充", "门禁卡" ]
}
PUT /product/_doc/4
{
"name" : "小米耳机",
"desc" : "耳机中的黄焖鸡",
"price" : 999,
"lv":"百元机",
"type":"耳机",
"createtime":"2020-06-23",
"tags": [ "降噪", "防水", "蓝牙" ]
}
PUT /product/_doc/5
{
"name" : "红米耳机",
"desc" : "耳机中的肯德基",
"price" : 399,
"type":"耳机",
"lv":"百元机",
"createtime":"2020-07-20",
"tags": [ "防火", "低音炮", "听声辨位" ]
}
PUT /product/_doc/6
{
"name" : "小米手机10",
"desc" : "充电贼快掉电更快,超级无敌望远镜,高刷电竞屏",
"price" : "",
"lv":"旗舰机",
"type":"手机",
"createtime":"2020-07-27",
"tags": [ "120HZ刷新率", "120W快充", "120倍变焦" ]
}
PUT /product/_doc/7
{
"name" : "挨炮 SE2",
"desc" : "除了CPU,一无是处",
"price" : "3299",
"lv":"旗舰机",
"type":"手机",
"createtime":"2020-07-21",
"tags": [ "割韭菜", "割韭菜", "割新韭菜" ]
}
PUT /product/_doc/8
{
"name" : "XS Max",
"desc" : "听说要出新款12手机了,终于可以换掉手中的4S了",
"price" : 4399,
"lv":"旗舰机",
"type":"手机",
"createtime":"2020-08-19",
"tags": [ "5V1A", "4G全网通", "大" ]
}
PUT /product/_doc/9
{
"name" : "小米电视",
"desc" : "70寸性价比只选,不要一万八,要不要八千八,只要两千九百九十八",
"price" : 2998,
"lv":"高端机",
"type":"耳机",
"createtime":"2020-08-16",
"tags": [ "巨馍", "家庭影院", "游戏" ]
}
PUT /product/_doc/10
{
"name" : "红米电视",
"desc" : "我比上边那个更划算,我也2998,我也70寸,但是我更好看",
"price" : 2999,
"type":"电视",
"lv":"高端机",
"createtime":"2020-08-28",
"tags": [ "大片", "蓝光8K", "超薄" ]
}
PUT /product/_doc/11
{
"name": "红米电视",
"desc": "我比上边那个更划算,我也2998,我也70寸,但是我更好看",
"price": 2998,
"type": "电视",
"lv": "高端机",
"createtime": "2020-08-28",
"tags": [
"大片",
"蓝光8K",
"超薄"
]
}
桶聚合查询
## 桶聚合 例:统计不同标签的商品数量
GET product/_search
{ #聚合查询
"aggs": {
#桶聚合查询
"tag_bucket": {
"terms": {
"field": "tags.keyword"
}
}
}
}
## 不显示hits数据:size:0
GET product/_search
{
"size": 0,
"aggs": {
"tag_bucket": {
"terms": {
"field": "tags.keyword"
}
}
}
}
## 排序
GET product/_search
{
"size": 0,
"aggs": {
"tag_bucket": {
"terms": {
"field": "tags.keyword",
"size": 3,
"order": {
"_count": "desc"
}
}
}
}
}
## doc_values和field_data
GET product/_search
{
"size": 0,
"aggs": {
"tag_bucket": {
"terms": {
"field": "name"
}
}
}
}
GET product/_search
{
"size": 0,
"aggs": {
"tag_bucket": {
"terms": {
"field": "name.keyword"
}
}
}
}
POST product/_mapping
{
"properties": {
"name": {
"type": "text",
"analyzer": "ik_max_word",
#通过修改fielddata为true来支持文本字段桶聚合查询
"fielddata": true
}
}
}
GET product/_search
{
"size": 0,
"aggs": {
"tag_bucket": {
"terms": {
"size": 20,
"field": "name"
}
}
}
}