ElasticSearch-返回唯一值

小开

最佳答案

你可以使用术语汇总。

{
"size": 0,
"aggs" : {
"langs" : {
"terms" : { "field" : "language",  "size" : 500 }
}
}}

聚合中的 size参数指定要包含在聚合结果中的最大术语数。如果需要所有结果，请将该值设置为大于数据中唯一项的数目。

搜索将返回以下内容:

{
"took" : 16,
"timed_out" : false,
"_shards" : {
"total" : 2,
"successful" : 2,
"failed" : 0
},
"hits" : {
"total" : 1000000,
"max_score" : 0.0,
"hits" : [ ]
},
"aggregations" : {
"langs" : {
"buckets" : [ {
"key" : "10",
"doc_count" : 244812
}, {
"key" : "11",
"doc_count" : 136794
 

}, {
"key" : "12",
"doc_count" : 32312
} ]
}
}
}

小开

Elasticsearch 1.1 + 有 一个 href = “ http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/search----------------------------------------------------------------------------------------- -，它会给你一个唯一的计数

请注意，它实际上是一个近似值，并且精度可能会随着高基数数据集而降低，但是在我的测试中它通常是相当精确的。

您还可以使用 precision_threshold参数来调整精度。

这张来自文档的图表显示了更高的 precision_threshold是如何导致更精确的结果的。

Relative error vs threshold

小开

我也在为我自己寻找这种解决方案。我在术语汇总中找到了参考。

因此，根据以下是正确的解决方案。

{
"aggs" : {
"langs" : {
"terms" : { "field" : "language",
"size" : 500 }
}
}}

但如果你遇到以下错误:

"error": {
"root_cause": [
{
"type": "illegal_argument_exception",
"reason": "Fielddata is disabled on text fields by default. Set fielddata=true on [fastest_method] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory. Alternatively use a keyword field instead."
}
]}

在这种情况下，您必须在请求中添加“ 关键词”，如下所示:

   {
"aggs" : {
"langs" : {
"terms" : { "field" : "language.keyword",
"size" : 500 }
}
}}

小开

如果希望获得每个 language字段唯一值的第一个文档，可以这样做:

{
"query": {
"match_all": {
}
},
"collapse": {
"field": "language.keyword",
"inner_hits": {
"name": "latest",
"size": 1
}
}
}

小开

如果你想得到所有的唯一值没有任何近似值或设置魔术数字(size: 500) ，然后使用 < a href = “ https://www.elastic.co/guide/en/elasticsearch/reference/current/search- 桶-复合聚合”rel = “ noReferrer”> COMPOSITE AGGREGATION (ES 6.5 +)。

来自正式文件:

“如果你想在一个嵌套的术语聚合中检索所有术语或所有术语组合，你应该使用复合聚合允许对所有可能的术语进行分页，而不是在术语聚合中设置大于字段基数的大小。术语聚合的目的是返回顶部术语，不允许分页。”

JavaScript 的实现例子:

const ITEMS_PER_PAGE = 1000;


const body =  {
"size": 0, // Returning only aggregation results: https://www.elastic.co/guide/en/elasticsearch/reference/current/returning-only-agg-results.html
"aggs" : {
"langs": {
"composite" : {
"size": ITEMS_PER_PAGE,
"sources" : [
{ "language": { "terms" : { "field": "language" } } }
]
}
}
}
};


const uniqueLanguages = [];


while (true) {
const result = await es.search(body);


const currentUniqueLangs = result.aggregations.langs.buckets.map(bucket => bucket.key);


uniqueLanguages.push(...currentUniqueLangs);


const after = result.aggregations.langs.after_key;


if (after) {
// continue paginating unique items
body.aggs.langs.composite.after = after;
} else {
break;
}
}


console.log(uniqueLanguages);

小开

必须用两个字段(导数 ID 和车辆类型)来区分，必须用最便宜的汽车来排序。

GET /cars/_search
{
"size": 0,
"aggs": {
"distinct_by_derivative_id": {
"terms": {
"field": "derivative_id"
},
"aggs": {
"vehicle_type": {
"terms": {
"field": "vehicle_type"
},
"aggs": {
"cheapest_vehicle": {
"top_hits": {
"sort": [
{ "rental": { "order": "asc" } }
],
"_source": { "includes": [ "manufacturer_name",
"rental",
"vehicle_type"
]
},
"size": 1
}
}
}
}
}
}
}
}

结果:

{
"took" : 3,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"distinct_by_derivative_id" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "04",
"doc_count" : 3,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 2,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 2,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "8",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Renault",
"rental" : 89.99
},
"sort" : [
89.99
]
}
]
}
}
},
{
"key" : "LCV",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "7",
"_score" : null,
"_source" : {
"vehicle_type" : "LCV",
"manufacturer_name" : "Ford",
"rental" : 99.99
},
"sort" : [
99.99
]
}
]
}
}
}
]
}
},
{
"key" : "01",
"doc_count" : 2,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "1",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Ford",
"rental" : 599.99
},
"sort" : [
599.99
]
}
]
}
}
},
{
"key" : "LCV",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "2",
"_score" : null,
"_source" : {
"vehicle_type" : "LCV",
"manufacturer_name" : "Ford",
"rental" : 599.99
},
"sort" : [
599.99
]
}
]
}
}
}
]
}
},
{
"key" : "02",
"doc_count" : 2,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 2,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 2,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "4",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Audi",
"rental" : 499.99
},
"sort" : [
499.99
]
}
]
}
}
}
]
}
},
{
"key" : "03",
"doc_count" : 1,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "5",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Audi",
"rental" : 399.99
},
"sort" : [
399.99
]
}
]
}
}
}
]
}
}
]
}
}
}

小开

Aggs 默认情况下会处理数值，如果你想处理字符串文件，你应该启用它