elasticsearch 按热门点击聚合结果分组
我想根据用户上次访问的时间筛选出文档,并获取单个用户最近访问的文档,然后根据报价代码对所有筛选出的文档进行分组 我通过执行tophits聚合来获取用户最近访问的文档。但是,我无法使用offercode对tophits聚合的结果进行分组 ES查询以获取用户的最新文档elasticsearch 按热门点击聚合结果分组,elasticsearch,lucene,elasticsearch,Lucene,我想根据用户上次访问的时间筛选出文档,并获取单个用户最近访问的文档,然后根据报价代码对所有筛选出的文档进行分组 我通过执行tophits聚合来获取用户最近访问的文档。但是,我无法使用offercode对tophits聚合的结果进行分组 ES查询以获取用户的最新文档 { "took": 53, "timed_out": false, "_shards": { "total": 2, "successful": 2, "fail
{
"took": 53,
"timed_out": false,
"_shards": {
"total": 2,
"successful": 2,
"failed": 0
},
"hits": {
"total": 6,
"max_score": 1.0,
"hits": [{
"_index": "db",
"_type": "users",
"_id": "AVOiyjHmzUObmc5euUGS",
"_score": 1.0,
"_source": {
"user": "james",
"lastvisited": "2016/01/20 02:03:11",
"browser": "chrome",
"offercode": "JB20"
}
}, {
"_index": "db",
"_type": "users",
"_id": "AVOiyjIQzUObmc5euUGT",
"_score": 1.0,
"_source": {
"user": "james",
"lastvisited": "2016/01/20 03:04:15",
"browser": "firefox",
"offercode": "JB20,JB50"
}
}, {
"_index": "db",
"_type": "users",
"_id": "AVOiyjIlzUObmc5euUGU",
"_score": 1.0,
"_source": {
"user": "james",
"lastvisited": "2016/01/21 00:15:21",
"browser": "chrome",
"offercode": "JB20,JB50,JB100"
}
}, {
"_index": "db",
"_type": "users",
"_id": "AVOiyjJKzUObmc5euUGW",
"_score": 1.0,
"_source": {
"user": "peter",
"lastvisited": "2016/01/20 02:32:22",
"browser": "chrome",
"offercode": "JB20,JB50,JB100"
}
}, {
"_index": "db",
"_type": "users",
"_id": "AVOiy4jhzUObmc5euUGX",
"_score": 1.0,
"_source": {
"user": "james",
"lastvisited": "2016/01/19 02:03:11",
"browser": "chrome",
"offercode": ""
}
}, {
"_index": "db",
"_type": "users",
"_id": "AVOiyjI2zUObmc5euUGV",
"_score": 1.0,
"_source": {
"user": "adams",
"lastvisited": "2016/01/20 00:12:11",
"browser": "chrome",
"offercode": "JB10"
}
}]
}
}
ES输出
curl -XGET localhost:9200/account/users/_search?pretty -d'{
"size": "0",
"query": {
"bool": {
"must": {
"range": {
"lastvisited": {
"gte": "2016/01/19",
"lte": "2016/01/21"
}
}
}
}
},
"aggs": {
"lastvisited_users": {
"terms": {
"field": "user"
}
,
"aggs": {
"top_user_hits": {
"top_hits": {
"sort": [
{
"lastvisited": {
"order": "desc"
}
}
],
"_source": {
"include": [
"user","offercode","lastvisited"
]
},
"size": 1
}
}
}
}
}}'
{
"took" : 4,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"failed" : 0
},
"hits" : {
"total" : 6,
"max_score" : 0.0,
"hits" : [ ]
},
"aggregations" : {
"lastvisited_users" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [ {
"key" : "james",
"doc_count" : 3,
"top_user_hits" : {
"hits" : {
"total" : 3,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexIEz1WBU8vnnZ2d",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 03:04:15",
"offercode" : "JB20,JB50",
"user" : "james"
},
"sort" : [ 1453259055000 ]
} ]
}
}
}, {
"key" : "adams",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexJMz1WBU8vnnZ2h",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 00:12:11",
"offercode" : "JB10",
"user" : "adams"
},
"sort" : [ 1453248731000 ]
} ]
}
}
}, {
"key" : "adamsnew",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexJhz1WBU8vnnZ2i",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 00:12:11",
"offercode" : "JB1010,aka10",
"user" : "adamsnew"
},
"sort" : [ 1453248731000 ]
} ]
}
}
}, {
"key" : "peter",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexIoz1WBU8vnnZ2f",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 02:32:22",
"offercode" : "JB20,JB50,JB100",
"user" : "peter"
},
"sort" : [ 1453257142000 ]
} ]
}
}
} ]
}
}
}
现在,我想聚合tophits聚合的结果
预期产出
curl -XGET localhost:9200/account/users/_search?pretty -d'{
"size": "0",
"query": {
"bool": {
"must": {
"range": {
"lastvisited": {
"gte": "2016/01/19",
"lte": "2016/01/21"
}
}
}
}
},
"aggs": {
"lastvisited_users": {
"terms": {
"field": "user"
}
,
"aggs": {
"top_user_hits": {
"top_hits": {
"sort": [
{
"lastvisited": {
"order": "desc"
}
}
],
"_source": {
"include": [
"user","offercode","lastvisited"
]
},
"size": 1
}
}
}
}
}}'
{
"took" : 4,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"failed" : 0
},
"hits" : {
"total" : 6,
"max_score" : 0.0,
"hits" : [ ]
},
"aggregations" : {
"lastvisited_users" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [ {
"key" : "james",
"doc_count" : 3,
"top_user_hits" : {
"hits" : {
"total" : 3,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexIEz1WBU8vnnZ2d",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 03:04:15",
"offercode" : "JB20,JB50",
"user" : "james"
},
"sort" : [ 1453259055000 ]
} ]
}
}
}, {
"key" : "adams",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexJMz1WBU8vnnZ2h",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 00:12:11",
"offercode" : "JB10",
"user" : "adams"
},
"sort" : [ 1453248731000 ]
} ]
}
}
}, {
"key" : "adamsnew",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexJhz1WBU8vnnZ2i",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 00:12:11",
"offercode" : "JB1010,aka10",
"user" : "adamsnew"
},
"sort" : [ 1453248731000 ]
} ]
}
}
}, {
"key" : "peter",
"doc_count" : 1,
"top_user_hits" : {
"hits" : {
"total" : 1,
"max_score" : null,
"hits" : [ {
"_index" : "accounts",
"_type" : "users",
"_id" : "AVOtexIoz1WBU8vnnZ2f",
"_score" : null,
"_source" : {
"lastvisited" : "2016/01/20 02:32:22",
"offercode" : "JB20,JB50,JB100",
"user" : "peter"
},
"sort" : [ 1453257142000 ]
} ]
}
}
} ]
}
}
}
我尝试使用管道聚合,但我不知道如何根据tophits聚合的结果进行分组 这可能会解决您的问题:
{
"offercode_grouped": {
"JB20": 1,
"JB10": 1,
"JB20,JB50": 1,
"JB20,JB50,JB100": 2,
"":1
}
}
我希望我能正确理解你的问题。我想我找到了一个有点老套的“解决方案” 它是、和的组合 创建新索引 索引文件 获取聚合 回应 除非每个索引只有一个碎片,否则需要指定索引数据的时间。这是因为
sampler
聚合是按每个碎片计算的。因此,我们需要确保特定用户的所有数据都在同一个分片中,以获得每个用户得分最高的文档
Sampler
聚合按分数返回文档。这就是为什么我们需要修改文档的分数。在这里,功能\分数查询
可以提供帮助。使用字段\u值\u因子
,分数只是上次就诊的时间戳-因此就诊越近,分数越高
更新:使用字段值\u系数
可能存在\u分数
准确性问题。有关更多信息,请参阅问题。这就是为什么在本期中使用了clintongormley建议的衰减
函数的原因。因为从原点
两侧都适用。这意味着比源文件早1天和比源文件早1天的文件获得相同的\u分数。这就是为什么我们需要过滤掉较新的文档(请参阅查询中的范围过滤器)
注意:我只是使用示例中可以看到的数据进行了此查询,因此需要更大的数据集来测试查询。但是我认为它应该可以工作…检查这个解决方案:它比较有限,但适合生产:请共享索引的映射。@Richa在帖子中添加了es映射您将无法基于提供的分组,因为它是一个分析的字符串和值'JB20,JB50,JB100`将被分为JB20
,JB50
,JB100
@Richa。没问题,我会将字段更改为“未分析”。但是我想知道,如果我更改分析,是否有可能得到结果。您可以通过在用户
字段上应用聚合
来获取用户最近访问的文档,但是您将无法在提供
字段上聚合。我会试着给你回复。我想他是在要求弹性DSL查询。如果您试图建议一种使用SQL的方法,您应该解释您的答案。这绝对是我所期望的。对于较小的数据,它工作得很好,我尝试了10000条记录。聚合仅返回13个文档的输出。文档中有多少用户?如果有13个用户,那么它将按预期工作(我仍然可能不完全理解您的用例:)。它应该为每个用户获得一个文档(最新的一个-最后一次访问),并计算这13个文档的聚合…您的理解是正确的。我有10000个索引类型的唯一用户。但是,聚合返回的数据只有13个,我试图生成具有10000个唯一用户的数据集。使用1个碎片时,聚合返回100个文档。这是因为用于采样器聚合的shard_size
选项默认为100。增加价值有帮助。我也尝试了100个碎片(使用回答中提到的routing
)。速度慢了很多。特别是使用高碎片大小选项。所以我认为它不适合生产,但应该可以工作…()我面临一个函数分数查询的问题。它为所有匹配的文档返回相同的分数。你知道吗?
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/1?routing=james" -d'
{
"user": "james",
"lastvisited": "2016/01/20 02:03:11",
"browser": "chrome",
"offercode": "JB20"
}'
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/2?routing=james" -d'
{
"user": "james",
"lastvisited": "2016/01/20 03:04:15",
"browser": "firefox",
"offercode": "JB20,JB50"
}'
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/3?routing=james" -d'
{
"user": "james",
"lastvisited": "2016/01/21 00:15:21",
"browser": "chrome",
"offercode": "JB20,JB50,JB100"
}'
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/4?routing=peter" -d'
{
"user": "peter",
"lastvisited": "2016/01/20 02:32:22",
"browser": "chrome",
"offercode": "JB20,JB50,JB100"
}'
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/5?routing=james" -d'
{
"user": "james",
"lastvisited": "2016/01/19 02:03:11",
"browser": "chrome",
"offercode": ""
}'
curl -s -XPUT "http://127.0.0.1:9200/stackoverflow/document/6?routing=adams" -d'
{
"user": "adams",
"lastvisited": "2016/01/20 00:12:11",
"browser": "chrome",
"offercode": "JB10"
}'
curl -XPOST "http://127.0.0.1:9200/stackoverflow/_search" -d'
{
"query": {
"function_score": {
"boost_mode": "replace", // we need to replace document score with the result of the functions
"query": {
"bool": {
"filter": [
{
"range": { // get documents within the date range
"lastvisited": {
"gte": "2016/01/19 00:00:00",
"lte": "2016/01/21 23:59:59"
}
}
}
]
}
},
"functions": [
{
"linear": {
"lastvisited": {
"origin": "2016/01/21 23:59:59", // same as lastvisited lte filter
"scale": "2d" // set the scale - please, see elasticsearch docs for more info https://www.elastic.co/guide/en/elasticsearch/reference/2.3/query-dsl-function-score-query.html#function-decay
}
}
}
]
}
},
"aggs": {
"user": {
"sampler": { // get top scored document per user
"field": "user",
"max_docs_per_value": 1
},
"aggs": {
"offers": { // aggregate user documents per `offercode`
"terms": {
"field": "offercode"
}
}
}
}
},
"size": 0
}'
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 6,
"max_score": 0,
"hits": []
},
"aggregations": {
"user": {
"doc_count": 3,
"offers": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "JB20,JB50,JB100",
"doc_count": 2
},
{
"key": "JB10",
"doc_count": 1
}
]
}
}
}
}