Question

我一直试图使用facet来获得字段的术语频率。我的查询只返回一个匹配，所以我希望facet返回特定字段中频率最高的条件。

我的映射：

{
"mappings":{
    "document":{
        "properties":{
            "tags":{
                "type":"object",
                "properties":{
                    "title":{
                        "fields":{
                            "partial":{
                                "search_analyzer":"main",
                                "index_analyzer":"partial",
                                "type":"string",
                                "index" : "analyzed"
                            }
                            "title":{
                                "type":"string",
                                "analyzer":"main",
                                "index" : "analyzed"
                            }
                        },
                        "type":"multi_field"
                    }
                }
            }
        }
    }
},

"settings":{
    "analysis":{
        "filter":{
            "name_ngrams":{
                "side":"front",
                "max_gram":50,
                "min_gram":2,
                "type":"edgeNGram"
            }
        },

        "analyzer":{
            "main":{
                "filter": ["standard", "lowercase", "asciifolding"],
                "type": "custom",
                "tokenizer": "standard"
            },
            "partial":{
                "filter":["standard","lowercase","asciifolding","name_ngrams"],
                "type": "custom",
                "tokenizer": "standard"
            }
        }
    }
}

}

测试数据：

 curl -XPUT localhost:9200/testindex/document -d '{"tags": {"title": "people also kill people"}}'

查询：

 curl -XGET 'localhost:9200/testindex/document/_search?pretty=1' -d '
{
    "query":
    {
       "term": { "tags.title": "people" }
    },
    "facets": {
       "popular_tags": { "terms": {"field": "tags.title"}}
    }
}'

此结果

"hits" : {
   "total" : 1,
    "max_score" : 0.99381393,
    "hits" : [ {
    "_index" : "testindex",
    "_type" : "document",
    "_id" : "uI5k0wggR9KAvG9o7S7L2g",
    "_score" : 0.99381393, "_source" : {"tags": {"title": "people also kill people"}}
 } ]
},
"facets" : {
  "popular_tags" : {
  "_type" : "terms",
  "missing" : 0,
  "total" : 3,
  "other" : 0,
  "terms" : [ {
    "term" : "people",
    "count" : 1            // I expect this to be 2
   }, {
    "term" : "kill",
    "count" : 1
  }, {
    "term" : "also",
    "count" : 1
  } ]
}

}

以上结果不是我想要的。我希望频率计数为2

"hits" : {
   "total" : 1,
   "max_score" : 0.99381393,
   "hits" : [ {
   "_index" : "testindex",
   "_type" : "document",
   "_id" : "uI5k0wggR9KAvG9o7S7L2g",
   "_score" : 0.99381393, "_source" : {"tags": {"title": "people also kill people"}}
} ]
},
"facets" : {
"popular_tags" : {
  "_type" : "terms",
  "missing" : 0,
  "total" : 3,
  "other" : 0,
  "terms" : [ {
    "term" : "people",
    "count" : 2            
  }, {
    "term" : "kill",
    "count" : 1
  }, {
    "term" : "also",
    "count" : 1
  } ]
 }
}

我如何实现这一目标？面对错误的方式？

Answer 1

方面计算文档，而不是属于它们的条款。你得到1，因为只有一个文档包含该术语，发生的次数并不重要。我不知道返回术语频率的开箱即用的方式，方面不是一个好的选择如果启用术语向量，该信息可以存储在索引中，但是现在无法从elasticsearch中读取术语向量。

Answer 2

不幸的是，Elastic中没有字段的术语频率。 GitHub项目Index TermList正在使用Lucene的条款并计算所有文档的总出现次数，您可以根据需要进行检查和替换。

elasticsearch - 单个字段的返回项频率

2 个答案: