POST /testcopy/_bulk
{"index":{"_id": 1}}
{"empId" : "111","name" : "员工1","age" : 20,"sex" : "男","mobile" : "19000001111","salary":1333,"deptName" : "技术部","provice" : "湖北省","city":"武汉","area":"光谷大道","address":"湖北省武汉市洪山区光谷大厦","content" : "i like to write best elasticsearch article"}
{"index":{"_id": 2}}
{"empId" : "222","name" : "员工2","age" : 25,"sex" : "男","mobile" : "19000002222","salary":15963,"deptName" : "销售部","provice" : "湖北省","city":"武汉","area":"江汉区","address" : "湖北省武汉市江汉路","content" : "i think java is the best programming language"}
{"index":{"_id": 3}}
{ "empId" : "333","name" : "员工3","age" : 30,"sex" : "男","mobile" : "19000003333","salary":20000,"deptName" : "技术部","provice" : "湖北省","city":"武汉","area":"经济技术开发区","address" : "湖北省武汉市经济开发区","content" : "i am only an elasticsearch beginner"}
{"index":{"_id": 4}}
{"empId" : "444","name" : "员工4","age" : 20,"sex" : "女","mobile" : "19000004444","salary":5600,"deptName" : "销售部","provice" : "湖北省","city":"武汉","area":"沌口开发区","address" : "湖北省武汉市沌口开发区","content" : "elasticsearch and hadoop are all very good solution, i am a beginner"}
{"index":{"_id": 5}}
{ "empId" : "555","name" : "员工5","age" : 20,"sex" : "男","mobile" : "19000005555","salary":9665,"deptName" : "测试部","provice" : "湖北省","city":"高新开发区","area":"武汉","address" : "湖北省武汉市东湖隧道","content" : "spark is best big data solution based on scala ,an programming language similar to java"}
{"index":{"_id": 6}}
{"empId" : "666","name" : "员工6","age" : 30,"sex" : "女","mobile" : "19000006666","salary":30000,"deptName" : "技术部","provice" : "武汉市","city":"湖北省","area":"江汉区","address" : "湖北省武汉市江汉路","content" : "i like java developer"}
{"index":{"_id": 7}}
{"empId" : "777","name" : "员工7","age" : 60,"sex" : "女","mobile" : "19000007777","salary":52130,"deptName" : "测试部","provice" : "湖北省","city":"黄冈市","area":"边城区","address" : "湖北省黄冈市边城区","content" : "i like elasticsearch developer"}
{"index":{"_id": 8}}
{"empId" : "888","name" : "员工8","age" : 19,"sex" : "女","mobile" : "19000008888","salary":60000,"deptName" : "技术部","provice" : "湖北省","city":"武汉","area":"汉阳区","address" : "湖北省武汉市江汉大学","content" : "i like spark language"}
{"index":{"_id": 9}}
{"empId" : "999","name" : "员工9","age" : 40,"sex" : "男","mobile" : "19000009999","salary":23000,"deptName" : "销售部","provice" : "河南省","city":"郑州市","area":"二七区","address" : "河南省郑州市郑州大学","content" : "i like java developer"}
{"index":{"_id": 10}}
{"empId" : "101010","name" : "张湖北","age" : 35,"sex" : "男","mobile" : "19000001010","salary":18000,"deptName" : "测试部","provice" : "湖北省","city":"武汉","area":"高新开发区","address" : "湖北省武汉市东湖高新","content" : "i like java developer i also like elasticsearch"}
{"index":{"_id": 11}}
{"empId" : "111111","name" : "王河南","age" : 61,"sex" : "男","mobile" : "19000001011","salary":10000,"deptName" : "销售部",,"provice" : "河南省","city":"开封市","area":"金明区","address" : "河南省开封市河南大学","content" : "i am not like java "}
{"index":{"_id": 12}}
{"empId" : "121212","name" : "张大学","age" : 26,"sex" : "女","mobile" : "19000001012","salary":1321,"deptName" : "测试部",,"provice" : "河南省","city":"开封市","area":"金明区","address" : "河南省开封市河南大学","content" : "i am java developer thing java is good"}
{"index":{"_id": 13}}
{"empId" : "131313","name" : "李江汉","age" : 36,"sex" : "男","mobile" : "19000001013","salary":1125,"deptName" : "销售部","provice" : "河南省","city":"郑州市","area":"二七区","address" : "河南省郑州市二七区","content" : "i like java and java is very best i like it do you like java "}
{"index":{"_id": 14}}
{"empId" : "141414","name" : "王技术","age" : 45,"sex" : "女","mobile" : "19000001014","salary":6222,"deptName" : "测试部",,"provice" : "河南省","city":"郑州市","area":"金水区","address" : "河南省郑州市金水区","content" : "i like c++"}
{"index":{"_id": 15}}
{"empId" : "151515","name" : "张测试","age" : 18,"sex" : "男","mobile" : "19000001015","salary":20000,"deptName" : "技术部",,"provice" : "河南省","city":"郑州市","area":"高新开发区","address" : "河南省郑州高新开发区","content" : "i think spark is good"}
这次的 嵌套分组 和上一篇文章的 Elasticsearch实战（十三）—聚合搜索Aggs聚合及Count，Avg操作 中的 3.3 嵌套分组内avg有什么区别？
之前文章是 先以部门 分组， 然后以 省份 分组， 统计 每个部门内，每个省份的人的 平均年龄，只求了一次平局年龄
aggs 是在terms 平级 开始操作 ， 只有一个平均年龄就是 部门内省份内的1个平均年龄
之前文章是 先以部门 分组， 然后以 省份 分组， 统计 每个部门内，每个省份的人的 平均年龄，只求了一次平局年龄， 没有求 部门的平均年龄
1.先分组 部门 deptName
2.在分组 省份 provice
3.然后在省份内 aggs 统计avg年龄
{
"size":0,
"aggs":{
"group_dept":{
"terms": {
"field": "deptName.keyword",
"size": 10
},
//dept分组内 term结束 就开始组内嵌套分组
"aggs": {
"group_provice": {
"terms": {
"field": "provice.keyword",
"size": 10
},
//provice分组内 term结束 就开始统计avg
"aggs": {
"provice_avg_age": {
"avg": {
"field": "age"
}
}
}
}
}
}
}
}
之前的查询结果
这次呢？ 不仅要统计 内层的avg 年龄，我还要统计外层的 部门内的 avg年龄，做了两次avg
部门分组， 求avg， 组内再分组 省份， 再求avg
#本次查询不是 基于组内 再进行 aggs ，而是 直接再 dept_avg_age 部门求平均年龄 平级 直接进行group_provice 省份分组
#然后在省份分组的 term平级 进行 aggs 进行 provice_avg_age 省内平均年龄
get /testcopy/_search
{
"size":0,
"aggs":{
"group_dept":{
"terms": {
"field": "deptName.keyword",
"size": 10,
"order": {
"dept_avg_age": "desc"
}
},
//dept分组 terms结束 直接aggs先求dept avg年龄
"aggs": {
"dept_avg_age": {
"avg": {
"field": "age"
}
},
//求完 dept avg age，dept_avg_age 同级别 直接并列分组名字,以provice分组
"group_provice":{
"terms": {
"field": "provice.keyword",
"size": 10,
"order": {
"provice_avg_age": "desc"
}
},
//group provice内部 ，terms结束 直接aggs 求provice avg年龄
"aggs": {
"provice_avg_age": {
"avg": {
"field": "age"
}
}
}
}
}
}
}
}
本次查询结果
求每个部门的 人数 的最大年龄，最小年龄， 年龄综合，平均年龄， aggs平级可以多个聚合种类 比如 max，min，sum，avg等
#aggs平级 四个名字，一次性做四次分组
get /testcopy/_search
{
"size":0,//不展示原始数据
"aggs":{
"group_dept":{
"terms": {
"field": "deptName.keyword",
"size": 10
},
//group分组内 term平级 进行 统计 max，min，sum，avg
"aggs": {
"max_age": {
"max": {
"field": "age"
}
},
//aggs内 max分组名称 平级 开始 min分组名称
"min_age":{
"min": {
"field": "age"
}
},
//aggs内 max,min 分组名称 平级 开始 sum分组名称
"sum_age":{
"sum": {
"field": "age"
}
},
//aggs内 max,min,sum 分组名称 平级 开始 avg分组名称
"avg_age":{
"avg": {
"field": "age"
}
}
}
}
}
}
查看结果
技术部 4人 max：30， avg：24.75， sum：99，min：19
销售部 4人 max：40， avg：30.25， sum：121，min：20
至此 我们已经学习了 聚合搜索 aggs 的基本用法，嵌套分组查询的多种用法及之前 分组查询的对比， 下一篇，我们介绍下 如何把 查询query，filter过滤，结合aggs 进行局部/全局聚合统计。