Metric - 单值输出 & 多值输出
Aggregation 属于 Search 的 一部分。一般情况下，建议将其 Size 指定为 0。以工资统计信息为例：
先插入工资数据：
DELETE /employees
PUT /employees/
{
"mappings" : {
"properties" : {
"age" : {
"type" : "integer"
},
"gender" : {
"type" : "keyword"
},
"job" : {
"type" : "text",
"fields" : {
"keyword" : {
"type" : "keyword",
"ignore_above" : 50
}
}
},
"name" : {
"type" : "keyword"
},
"salary" : {
"type" : "integer"
}
}
}
}
PUT /employees/_bulk
{ "index" : { "_id" : "1" } }
{ "name" : "Emma","age":32,"job":"Product Manager","gender":"female","salary":35000 }
{ "index" : { "_id" : "2" } }
{ "name" : "Underwood","age":41,"job":"Dev Manager","gender":"male","salary": 50000}
{ "index" : { "_id" : "3" } }
{ "name" : "Tran","age":25,"job":"Web Designer","gender":"male","salary":18000 }
{ "index" : { "_id" : "4" } }
{ "name" : "Rivera","age":26,"job":"Web Designer","gender":"female","salary": 22000}
{ "index" : { "_id" : "5" } }
{ "name" : "Rose","age":25,"job":"QA","gender":"female","salary":18000 }
{ "index" : { "_id" : "6" } }
{ "name" : "Lucy","age":31,"job":"QA","gender":"female","salary": 25000}
{ "index" : { "_id" : "7" } }
{ "name" : "Byrd","age":27,"job":"QA","gender":"male","salary":20000 }
{ "index" : { "_id" : "8" } }
{ "name" : "Foster","age":27,"job":"Java Programmer","gender":"male","salary": 20000}
{ "index" : { "_id" : "9" } }
{ "name" : "Gregory","age":32,"job":"Java Programmer","gender":"male","salary":22000 }
{ "index" : { "_id" : "10" } }
{ "name" : "Bryant","age":20,"job":"Java Programmer","gender":"male","salary": 9000}
{ "index" : { "_id" : "11" } }
{ "name" : "Jenny","age":36,"job":"Java Programmer","gender":"female","salary":38000 }
{ "index" : { "_id" : "12" } }
{ "name" : "Mcdonald","age":31,"job":"Java Programmer","gender":"male","salary": 32000}
{ "index" : { "_id" : "13" } }
{ "name" : "Jonthna","age":30,"job":"Java Programmer","gender":"female","salary":30000 }
{ "index" : { "_id" : "14" } }
{ "name" : "Marshall","age":32,"job":"Javascript Programmer","gender":"male","salary": 25000}
{ "index" : { "_id" : "15" } }
{ "name" : "King","age":33,"job":"Java Programmer","gender":"male","salary":28000 }
{ "index" : { "_id" : "16" } }
{ "name" : "Mccarthy","age":21,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : { "_id" : "17" } }
{ "name" : "Goodwin","age":25,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : { "_id" : "18" } }
{ "name" : "Catherine","age":29,"job":"Javascript Programmer","gender":"female","salary": 20000}
{ "index" : { "_id" : "19" } }
{ "name" : "Boone","age":30,"job":"DBA","gender":"male","salary": 30000}
{ "index" : { "_id" : "20" } }
{ "name" : "Kathy","age":29,"job":"DBA","gender":"female","salary": 20000}
# 多个 Metric 聚合，找到最低最高和平均工资
POST employees/_search
{
"size": 0,
"aggs": {
"max_salary": {
"max": {
"field": "salary"
}
},
"min_salary": {
"min": {
"field": "salary"
}
},
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
}
# Metric 聚合，找到最低的工资
POST employees/_search
{
"size": 0,
"aggs": {
"min_salary": {
"min": {
"field":"salary"
}
}
}
}
# Metric 聚合，找到最高的工资
POST employees/_search
{
"size": 0,
"aggs": {
"max_salary": {
"max": {
"field":"salary"
}
}
}
}
# 一个聚合，输出多值
POST employees/_search
{
"size": 0,
"aggs": {
"stats_salary": {
"stats": {
"field":"salary"
}
}
}
}
Bucket - Terms & 数字范围
按照⼀定的规则，将⽂档分配到不同的 桶中，从⽽达到分类的⽬的。ES 提供的 ⼀些常⻅见的 Bucket Aggregation:
- terms
- 数组类型：Range / Data Range，Histogram / Date Histogram
- ⽀持嵌套：也就在桶⾥再做分桶
Terms aggregation
Terms aggretion 字段需要打开 fielddata，才能进行 Terms aggregation，keyword 默认支持 doc_values，Text 需要在 Mapping 中 enable。
# 对keword 进行聚合
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field":"job.keyword"
}
}
}
}
# 对 Text 字段进行 terms 聚合查询，失败
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field":"job"
}
}
}
}
# 对 Text 字段打开 fielddata，支持terms aggregation
PUT employees/_mapping
{
"properties" : {
"job":{
"type": "text",
"fielddata": true
}
}
}
# 对 Text 字段进行 terms 分词。分词后的terms
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field":"job"
}
}
}
}
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field":"job.keyword"
}
}
}
}
Cardinality，类似 SQL 中的 Distinct
# 对job.keyword 和 job 进行 terms 聚合，分桶的总数并不一样
POST employees/_search
{
"size": 0,
"aggs": {
"cardinate": {
"cardinality": {
"field": "job"
}
}
}
}
Bucket Size & Top Hits Demo
- 应⽤场景：当获取分桶后，桶内最匹配的顶部⽂档列表
- Size：按年龄分桶，找出指定数据量的分桶信息
- Top Hits：查看各个⼯种中，年纪最⼤的 3 名员⼯
# 对性别的 keyword 进行聚合
POST employees/_search
{
"size": 0,
"aggs": {
"gender": {
"terms": {
"field":"gender"
}
}
}
}
#指定 bucket 的 size
POST employees/_search
{
"size": 0,
"aggs": {
"ages_5": {
"terms": {
"field":"age",
"size":3
}
}
}
}
# 指定size，不同工种中，年纪最大的3个员工的具体信息
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field":"job.keyword"
},
"aggs":{
"old_employee":{
"top_hits":{
"size":3,
"sort":[
{
"age":{
"order":"desc"
}
}
]
}
}
}
}
}
}
Range & Histogram 聚合
#Salary Ranges 分桶，可以自己定义 key
POST employees/_search
{
"size": 0,
"aggs": {
"salary_range": {
"range": {
"field":"salary",
"ranges":[
{
"to":10000
},
{
"from":10000,
"to":20000
},
{
"key":">20000",
"from":20000
}
]
}
}
}
}
#Salary Histogram,工资0到10万，以 5000一个区间进行分桶
POST employees/_search
{
"size": 0,
"aggs": {
"salary_histrogram": {
"histogram": {
"field":"salary",
"interval":5000,
"extended_bounds":{
"min":0,
"max":100000
}
}
}
}
}
多次嵌套
# 嵌套聚合1，按照工作类型分桶，并统计工资信息
POST employees/_search
{
"size": 0,
"aggs": {
"Job_salary_stats": {
"terms": {
"field": "job.keyword"
},
"aggs": {
"salary": {
"stats": {
"field": "salary"
}
}
}
}
}
}
# 多次嵌套。根据工作类型分桶，然后按照性别分桶，计算工资的统计信息
POST employees/_search
{
"size": 0,
"aggs": {
"Job_gender_stats": {
"terms": {
"field": "job.keyword"
},
"aggs": {
"gender_stats": {
"terms": {
"field": "gender"
},
"aggs": {
"salary_stats": {
"stats": {
"field": "salary"
}
}
}
}
}
}
}
}
Pipeline 聚合分析
# 平均工资最低的工作类型
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field": "job.keyword",
"size": 10
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
},
"min_salary_by_job":{
"min_bucket": {
"buckets_path": "jobs>avg_salary"
}
}
}
}
# 平均工资最高的工作类型
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field": "job.keyword",
"size": 10
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
},
"max_salary_by_job":{
"max_bucket": {
"buckets_path": "jobs>avg_salary"
}
}
}
}
# 平均工资的平均工资
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field": "job.keyword",
"size": 10
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
},
"avg_salary_by_job":{
"avg_bucket": {
"buckets_path": "jobs>avg_salary"
}
}
}
}
# 平均工资的统计分析
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field": "job.keyword",
"size": 10
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
},
"stats_salary_by_job":{
"stats_bucket": {
"buckets_path": "jobs>avg_salary"
}
}
}
}
# 平均工资的百分位数
POST employees/_search
{
"size": 0,
"aggs": {
"jobs": {
"terms": {
"field": "job.keyword",
"size": 10
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
}
}
},
"percentiles_salary_by_job":{
"percentiles_bucket": {
"buckets_path": "jobs>avg_salary"
}
}
}
}
#按照年龄对平均工资求导
POST employees/_search
{
"size": 0,
"aggs": {
"age": {
"histogram": {
"field": "age",
"min_doc_count": 1,
"interval": 1
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
},
"derivative_avg_salary":{
"derivative": {
"buckets_path": "avg_salary"
}
}
}
}
}
}
#Cumulative_sum
POST employees/_search
{
"size": 0,
"aggs": {
"age": {
"histogram": {
"field": "age",
"min_doc_count": 1,
"interval": 1
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
},
"cumulative_salary":{
"cumulative_sum": {
"buckets_path": "avg_salary"
}
}
}
}
}
}
#Moving Function
POST employees/_search
{
"size": 0,
"aggs": {
"age": {
"histogram": {
"field": "age",
"min_doc_count": 1,
"interval": 1
},
"aggs": {
"avg_salary": {
"avg": {
"field": "salary"
}
},
"moving_avg_salary":{
"moving_fn": {
"buckets_path": "avg_salary",
"window":10,
"script": "MovingFunctions.min(values)"
}
}
}
}
}
}
相关文章
