search（14）- elastic4s-统计范围：global, filter,post-filter bucket

  聚合通常做用在query范围内。不带query的aggregation请求其实是在match_all{}查询范围内进行统计的：

GET /cartxns/_search { "aggs": { "all_colors": { "terms": {"field" : "color.keyword"} } } } } GET /cartxns/_search { "query": { "match_all": {} }, "aggs": { "all_colors": { "terms": {"field" : "color.keyword"} } } } }

上面这两个请求结果相同：

  "aggregations" : { "all_colors" : { "doc_count_error_upper_bound" : 0, "sum_other_doc_count" : 0, "buckets" : [ { "key" : "red", "doc_count" : 4 }, { "key" : "blue", "doc_count" : 2 }, { "key" : "green", "doc_count" : 2 } ] } }

虽然不少时候咱们都但愿在query做用域下进行统计，但也会碰到须要统计不含任何query条件的汇总数。好比在统计某个车款平价售价的同时又须要知道所有车款的平均售价。这里所有车款平价售价就是一种global bucket统计：

GET /cartxns/_search { "query" : { "match" : {"make.keyword": "ford"} } , "aggs": { "avg_ford": { "avg": { "field": "price" } }, "avg_all" : { "global": {}, "aggs": { "avg_price": { "avg": {"field": "price"} } } } } }

搜索结果和聚合结果以下：

 "hits" : { "total" : { "value" : 2, "relation" : "eq" }, "max_score" : 1.2809337, "hits" : [ { "_index" : "cartxns", "_type" : "_doc", "_id" : "NGVXAnIBSDa1Wo5UqLc3", "_score" : 1.2809337, "_source" : { "price" : 30000, "color" : "green", "make" : "ford", "sold" : "2014-05-18" } }, { "_index" : "cartxns", "_type" : "_doc", "_id" : "OWVYAnIBSDa1Wo5UTrf8", "_score" : 1.2809337, "_source" : { "price" : 25000, "color" : "blue", "make" : "ford", "sold" : "2014-02-12" } } ] }, "aggregations" : { "avg_all" : { "doc_count" : 8, "avg_price" : { "value" : 26500.0 } }, "avg_ford" : { "value" : 27500.0 } }

用elastic4s来表达：

 val aggGlob = search("cartxns").query( matchQuery("make.keyword","ford") ).aggregations( avgAggregation("single_avg").field("price"), globalAggregation("all_avg").subaggs( avgAggregation("avg_price").field("price") ) ) println(aggGlob.show) val globResult = client.execute(aggGlob).await

  if (globResult.isSuccess) { val gavg = globResult.result.aggregations.global("all_avg").avg("avg_price") val savg = globResult.result.aggregations.avg("single_avg") println(s"${savg.value},${gavg.value}") globResult.result.hits.hits.foreach(h => println(s"${h.sourceAsMap}")) } else println(s"error: ${globResult.error.causedBy.getOrElse("unknown")}") ... POST:/cartxns/_search? StringEntity({"query":{"match":{"make.keyword":{"query":"ford"}}},"aggs":{"single_avg":{"avg":{"field":"price"}},"all_avg":{"global":{},"aggs":{"avg_price":{"avg":{"field":"price"}}}}}},Some(application/json)) 27500.0,26500.0 Map(price -> 30000, color -> green, make -> ford, sold -> 2014-05-18) Map(price -> 25000, color -> blue, make -> ford, sold -> 2014-02-12)

filter-bucket的做用是：在query结果内再进行筛选后统计。好比：查询全部honda车款交易，但只统计honda某个月销售： 

GET /cartxns/_search { "query": { "match": { "make.keyword": "honda" } }, "aggs": { "sales_this_month": { "filter": { "range" : {"sold" : { "from" : "2014-10-01", "to" : "2014-11-01" }} }, "aggs": { "month_total": { "sum": {"field": "price"} } } } } }

首先，查询结果应该不受影响。同时还获得查询结果车款某个月的销售额：

 "hits" : { "total" : { "value" : 3, "relation" : "eq" }, "max_score" : 0.9444616, "hits" : [ { "_index" : "cartxns", "_type" : "_doc", "_id" : "MmVXAnIBSDa1Wo5UqLc3", "_score" : 0.9444616, "_source" : { "price" : 10000, "color" : "red", "make" : "honda", "sold" : "2014-10-28" } }, { "_index" : "cartxns", "_type" : "_doc", "_id" : "M2VXAnIBSDa1Wo5UqLc3", "_score" : 0.9444616, "_source" : { "price" : 20000, "color" : "red", "make" : "honda", "sold" : "2014-11-05" } }, { "_index" : "cartxns", "_type" : "_doc", "_id" : "N2VXAnIBSDa1Wo5UqLc3", "_score" : 0.9444616, "_source" : { "price" : 20000, "color" : "red", "make" : "honda", "sold" : "2014-11-05" } } ] }, "aggregations" : { "sales_this_month" : { "doc_count" : 1, "month_total" : { "value" : 10000.0 } } }

elastic4s示范以下： 

  val aggfilter = search("cartxns").query( matchQuery("make.keyword","honda") ).aggregations( filterAgg("sales_the_month",rangeQuery("sold").gte("2014-10-01").lte("2014-11-01")) .subaggs(sumAggregation("monthly_sales").field("price")) ) println(aggfilter.show) val filterResult = client.execute(aggfilter).await

  if (filterResult.isSuccess) { val ms = filterResult.result.aggregations.filter("sales_the_month") .sum("monthly_sales").value println(s"${ms}") filterResult.result.hits.hits.foreach(h => println(s"${h.sourceAsMap}")) } else println(s"error: ${filterResult.error.causedBy.getOrElse("unknown")}") ... POST:/cartxns/_search? StringEntity({"query":{"match":{"make.keyword":{"query":"honda"}}},"aggs":{"sales_the_month":{"filter":{"range":{"sold":{"gte":"2014-10-01","lte":"2014-11-01"}}},"aggs":{"monthly_sales":{"sum":{"field":"price"}}}}}},Some(application/json)) 10000.0 Map(price -> 10000, color -> red, make -> honda, sold -> 2014-10-28) Map(price -> 20000, color -> red, make -> honda, sold -> 2014-11-05) Map(price -> 20000, color -> red, make -> honda, sold -> 2014-11-05)

最后一个是post-filter。post-filter一样是对query结果的筛选，可是在完成了整个query后对结果的筛选。也就是说若是query还涉及到聚合，那么聚合不受筛选影响：

GET /cartxns/_search { "query": { "match": { "make.keyword": "ford" } }, "post_filter": { "match" : { "color.keyword" : "blue" } } ,"aggs": { "colors": { "terms": { "field": "color.keyword", "size": 10 } } } }

查询和聚合结果以下：

  "hits" : { "total" : { "value" : 1, "relation" : "eq" }, "max_score" : 1.2809337, "hits" : [ { "_index" : "cartxns", "_type" : "_doc", "_id" : "OWVYAnIBSDa1Wo5UTrf8", "_score" : 1.2809337, "_source" : { "price" : 25000, "color" : "blue", "make" : "ford", "sold" : "2014-02-12" } } ] }, "aggregations" : { "colors" : { "doc_count_error_upper_bound" : 0, "sum_other_doc_count" : 0, "buckets" : [ { "key" : "blue", "doc_count" : 1 }, { "key" : "green", "doc_count" : 1 } ] } } }

能够看到：查询结果显示了通过post-filter筛选的结果，但聚合并无受到filter影响。

elastic4s示范代码：

 val aggPost = search("cartxns").query( matchQuery("make.keyword","ford") ).postFilter(matchQuery("color.keyword","blue")) .aggregations( termsAgg("colors","color.keyword") ) println(aggPost.show) val postResult = client.execute(aggPost).await

  if (postResult.isSuccess) { postResult.result.hits.hits.foreach(h => println(s"${h.sourceAsMap}")) postResult.result.aggregations.terms("colors").buckets .foreach(b => println(s"${b.key},${b.docCount}")) } else println(s"error: ${postResult.error.causedBy.getOrElse("unknown")}") ... POST:/cartxns/_search? StringEntity({"query":{"match":{"make.keyword":{"query":"ford"}}},"post_filter":{"match":{"color.keyword":{"query":"blue"}}},"aggs":{"colors":{"terms":{"field":"color.keyword"}}}},Some(application/json)) Map(price -> 25000, color -> blue, make -> ford, sold -> 2014-02-12) blue,1 green,1