elasticsearch之Pipeline 聚合分析

Pipeline 聚合分析

DELETE employees

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}

在员工数最多的工种中，找出平均工资最低的工种

先通过aggregation找出所有工作的平均工资，然后通过pipeline管道的sibling 分析出工资最低的工种， 在buckts_path中指定再次聚合分析的路径

POST employees/_search
{
  "size": 0,
  "aggs": {
    "job_salary_avg": {
      "terms": {
        "field": "job.keyword"
      },
      "aggs": {
        "salary_avg": {
          "avg": {
            "field": "salary"
          }
        }
      }
    },
    "min_salary_avg":{
      "min_bucket": {
        "buckets_path": "job_salary_avg>salary_avg"
      }
    }
  }
}

找出平均工资最高的工作类型

POST employees/_search
{
  "size": 0,
  "aggs": {
    "job": {
      "terms": {
        "field": "job.keyword"
      },
      "aggs": {
        "job_avg": {
          "avg": {
            "field": "salary"
          }
        }
      }
    },
    "max_salary_avg":{
      "max_bucket": {
        "buckets_path": "job>job_avg"
      }
    }
  }
}

计算出平均工资的平均工资

POST employees/_search
{
  "size": 0,
  "aggs": {
    "job": {
      "terms": {
        "field": "job.keyword"
      },
      "aggs": {
        "job_avg": {
          "avg": {
            "field": "salary"
          }
        }
      }
    },
    "avg_salary_avg":{
      "avg_bucket": {
        "buckets_path": "job>job_avg"
      }
    }
  }
}

平均工资的统计分析

POST employees/_search
{
  "size": 0,
  "aggs": {
    "job": {
      "terms": {
        "field": "job.keyword"
      },
      "aggs": {
        "job_avg": {
          "avg": {
            "field": "salary"
          }
        }
      }
    },
    "stats_salary_avg":{
      "stats_bucket": {
        "buckets_path": "job>job_avg"
      }
    }
  }
}

parent pipeline derivative

按照年龄，对工资进行求导

POST employees/_search
{
  "size": 0,
  "aggs": {
    "age": {
      "histogram": {
        "field": "age",
        "interval": 1,
        "min_doc_count": 1
      },
      "aggs": {
        "avg_salary": {
          "avg": {
            "field": "salary"
          }
        },
        "derivative_avg_salary": {
          "derivative": {
            "buckets_path": "avg_salary"
          }
        }
      }
    }
  }
}