个人中心
文章发布
退出
作者热门文章
- html - 出于某种原因，IE8 对我的 Sass 文件中继承的 html5 CSS 不友好？
- JMeter 在响应断言中使用 span 标签的问题
- html - 在 :hover and :active? 上具有不同效果的 CSS 动画
- html - 相对于居中的 html 内容固定的 CSS 重复背景？
25
4
我目前正在处理我需要从ES获得的一个非常烦人的查询。
我的文档是嵌套文档，它们的索引看起来像这样:
"mydocs" : {
"properties" : {
"doc" : {
"type" : "nested",
"properties" : {
"name" : {"type" : "string", "store" : "yes", "index" : "analyzed"},
"tagln" : {"type" : "string", "store" : "yes", "index" : "analyzed"},
"tags" : {"type" : "string", "store" : "yes", "index" : "analyzed"},
"featured" : {"type" : "integer", "store" : "yes", "index" : "not_analyzed"}
"blkd" : {"type" : "integer", "store" : "yes", "index" : "not_analyzed"},
... etc ...
}
{
"from" : 0,
"size" : 10,
"query" : {
"nested" : {
"query" : {
"filtered" : {
"query" : {
"bool" : {
"must" : [ {
"term" : {
"doc.blkd" : 0
}
} ],
"should" : [ {
"function_score" : {
"functions" : [ {
"field_value_factor" : {
"field" : "doc.featured",
"factor" : 10000.0
}
} ],
"score_mode" : "sum",
"boost_mode" : "sum"
}
}, {
"constant_score" : {
"filter" : {
"query_string" : {
"query" : "featured*",
"fields" : [ "doc.name^1000.0" ]
}
},
"boost" : 1000.0
}
}, {
"constant_score" : {
"filter" : {
"query_string" : {
"query" : "featured*",
"fields" : [ "doc.tags^10.0" ],
"boost" : 10.0
}
}
}
}, {
"constant_score" : {
"filter" : {
"query_string" : {
"query" : "featured*",
"fields" : [ "doc.tagln^10.0" ],
"boost" : 10.0
}
}
}
} ],
"minimum_should_match" : "0"
}
}
}
},
"path" : "doc",
"score_mode" : "sum"
}
},
"explain" : false,
"sort" : [ {
"_score" : { }
} ]
}
"_explanation": {
"value": 4000.0024,
"description": "sum of:",
"details": [
{
"value": 4000.0024,
"description": "Score based on child doc range from 387 to 387",
"details": []
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 0.0009999962,
"description": "-ConstantScore(_type:.percolator) #(+*:* -_type:__*), product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 0.0009999962,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
}
{
"from" : 0,
"size" : 10,
"query" : {
"nested" : {
"query" : {
"filtered" : {
"query" : {
"bool" : {
"must" : [ {
"term" : {
"doc.blkd" : 0
}
} ],
"should" : [ {
"function_score" : {
"functions" : [ {
"field_value_factor" : {
"field" : "doc.featured",
"factor" : 10000.0
}
} ],
"score_mode" : "sum",
"boost_mode" : "sum"
}
}, {
"constant_score" : {
"filter" : {
"query_string" : {
"query" : "*featured*",
"fields" : [ "doc.name^1000.0" ]
}
},
"boost" : 1000.0
}
}, {
"query_string" : {
"query" : "*featured*",
"fields" : [ "doc.tags^100.0" ],
"boost" : 100.0
}
}, {
"constant_score" : {
"filter" : {
"query_string" : {
"query" : "*featured*",
"fields" : [ "doc.tagln^10.0" ],
"boost" : 10.0
}
}
}
} ],
"disable_coord" : true,
"minimum_should_match" : "0"
}
},
"filter" : {
"bool" : {
"should" : [ {
"query_string" : {
"query" : "*featured*",
"fields" : [ "doc.name^1000000.0", "doc.tags^10.0", "doc.tagln^10.0" ],
"boost" : 1000.0
}
} ],
"minimum_should_match" : "0"
}
}
}
},
"path" : "doc",
"score_mode" : "sum",
"inner_hits" : {
"explain" : "true"
}
}
},
"explain" : false,
"sort" : [ {
"_score" : { }
} ]
}
"max_score": 10001,
"hits": [
{
"_index": "myindex",
"_type": "mydocs",
"_id": "1111",
"_score": 10001,
"_ttl": 86158563,
"_source": {
"meta": {
"id": "1111",
"rev": "35-14602ccf5c3d429e0000000002000000",
"expiration": 0,
"flags": 33554432
},
"doc": {
"featured": 1,
"tagln": "hello location 1",
"blkd": 0,
"tags": [
"UsLocTaglinefeat"
],
"name": "hello US location featured"
}
},
"inner_hits": {
"doc": {
"hits": {
"total": 1,
"max_score": 10001,
"hits": [
{
"_shard": 1,
"_node": "YIXx2rrKR2O5q9519FIr_Q",
"_index": "myindex",
"_type": "mydocs",
"_id": "1111",
"_nested": {
"field": "doc",
"offset": 0
},
"_score": 10001,
"_source": {
"featured": 1,
"tagln": "hello location 1",
"blkd": 0,
"tags": [
"UsLocTaglinefeat"
],
"name": "hello US location featured"
},
"_explanation": {
"value": 10001,
"description": "sum of:",
"details": [
{
"value": 10001,
"description": "sum of:",
"details": [
{
"value": 0.0041682906,
"description": "weight(doc.blkd:`\b\u0000\u0000\u0000\u0000 in 0) [PerFieldSimilarity], result of:",
"details": [
{
"value": 0.0041682906,
"description": "score(doc=0,freq=1.0), product of:",
"details": [
{
"value": 0.0020365636,
"description": "queryWeight, product of:",
"details": [
{
"value": 2.0467274,
"description": "idf(docFreq=177, maxDocs=507)",
"details": []
},
{
"value": 0.0009950341,
"description": "queryNorm",
"details": []
}
]
},
{
"value": 2.0467274,
"description": "fieldWeight in 0, product of:",
"details": [
{
"value": 1,
"description": "tf(freq=1.0), with freq of:",
"details": [
{
"value": 1,
"description": "termFreq=1.0",
"details": []
}
]
},
{
"value": 2.0467274,
"description": "idf(docFreq=177, maxDocs=507)",
"details": []
},
{
"value": 1,
"description": "fieldNorm(doc=0)",
"details": []
}
]
}
]
}
]
},
{
"value": 10000.001,
"description": "sum of",
"details": [
{
"value": 0.0009950341,
"description": "*:*, product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 0.0009950341,
"description": "queryNorm",
"details": []
}
]
},
{
"value": 10000,
"description": "min of:",
"details": [
{
"value": 10000,
"description": "field value function: none(doc['doc.featured'].value * factor=10000.0)",
"details": []
},
{
"value": 3.4028235e+38,
"description": "maxBoost",
"details": []
}
]
}
]
},
{
"value": 0.9950341,
"description": "ConstantScore(doc.name:*featured*), product of:",
"details": [
{
"value": 1000,
"description": "boost",
"details": []
},
{
"value": 0.0009950341,
"description": "queryNorm",
"details": []
}
]
}
]
},
{
"value": 0,
"description": "match on required clause, product of:",
"details": [
{
"value": 0,
"description": "# clause",
"details": []
},
{
"value": 0.0009950341,
"description": "((doc.name:*featured*)^1000000.0 | (doc.tags:*featured*)^10.0 | (doc.tagln:*featured*)^10.0), product of:",
"details": [
{
"value": 1,
"description": "boost",
"details": []
},
{
"value": 0.0009950341,
"description": "queryNorm",
"details": []
}
]
}
]
}
]
}
}
]
}
}
}
},
最佳答案
对于OP中的查询，您需要在 bool(boolean) 查询中启用disable_coord以获得所需的行为。
同时启用inner_hits并在其中设置explain:true将提供嵌套文档的评分详细信息。此功能在Elasticsearch 1.5及更高版本中可用。
例:
{
"query": {
"nested": {
"query": {
"filtered": {
"query": {
"bool": {
"disable_coord": "true",
"must": [
{
"term": {
"doc.blkd": 0
}
}
],
"should": [
{
"function_score": {
"functions": [
{
"field_value_factor": {
"field": "doc.featured",
"factor": 10000
}
}
],
"score_mode": "sum",
"boost_mode": "sum"
}
},
{
"constant_score": {
"filter": {
"query_string": {
"query": "featured*",
"fields": [
"doc.name^1000.0"
]
}
},
"boost": 1000
}
},
{
"constant_score": {
"filter": {
"query_string": {
"query": "featured*",
"fields": [
"doc.tags^10.0"
],
"boost": 10
}
}
}
},
{
"constant_score": {
"filter": {
"query_string": {
"query": "featured*",
"fields": [
"doc.tagln^10.0"
],
"boost": 10
}
}
}
}
],
"minimum_should_match": "0"
}
}
}
},
"path": "doc",
"score_mode": "sum",
"inner_hits" : {
"explain" : "true"
}
}
}
}
{
"query": {
"nested": {
"query": {
"function_score": {
"functions": [
{
"field_value_factor": {
"field": "doc.featured",
"factor": 10000
}
},
{
"filter": {
"query_string": {
"query": "*featured*",
"fields": [
"doc.name^1000.0"
]
}
},
"weight": 1000
},
{
"filter": {
"query_string": {
"query": "*featured*",
"fields": [
"doc.tags^1000.0"
]
}
},
"weight": 100
},
{
"weight": 10,
"filter": {
"query_string": {
"query": "*featured*",
"fields": [
"doc.tagln^10.0"
]
}
}
}
],
"query": {
"term": {
"doc.blkd": 0
}
},
"score_mode": "sum",
"boost_mode": "sum"
}
},
"path": "doc",
"score_mode": "sum",
"inner_hits": {
"explain": "true"
}
}
}
}
关于elasticsearch - 匹配query_string文档的分数，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/38292157/
25
4
0
直接从 Python 代码运行 pylint 时，我似乎无法获得任何返回值。从命令行运行它会生成一个漂亮的报告，在底部有一个总结分数。 我已经尝试将“Run”的返回值放入一个变量中，并获取它的“rep
我是 Python 新手，正在尝试学习单词检测。我有一个带有单词的数据框 sharina['transcript'] Out[25]: 0 thank you for calling my
http://jsfiddle.net/q8P7Y/ 我在最后显示最终分数时遇到问题，有很多方法可以做到这一点，但我不确定什么是最好的。 正如你所看到的，下一个按钮只是 div 的显示/隐藏，而不是页
我使用滑动 slider 并有计数器分数。它计数很好，但我需要计数 =(所有幻灯片 - 1)。例如，如果我有 20 张幻灯片，我想显示总数 19。有什么办法可以做到这一点吗？我使用他们网站上的常规 j
我使用滑动 slider 并有计数器分数。它计数很好，但我需要计数 =(所有幻灯片 - 1)。例如，如果我有 20 张幻灯片，我想显示总数 19。有什么办法可以做到这一点吗？我使用他们网站上的常规 j
我试图在按下按钮时添加分数，分数显示在 JTextField 中，但是当按下按钮时，分数会添加，它显示为 0。我有一个存储分数的整数字段 private int score=0; yesButton
我可以在选项(单选按钮)随机播放之前计算分数/分数，如下面的代码所示。在Collection.shuffle()之前，选项是固定的，因为 CorrectChoice将始终分配给c2单选按钮。那么我可以
我在这里的代码只能得到87％的代码，因为“带有非正参数的加法参数什么也没做。我该如何解决呢？我尝试了更多的方法，但是我什至无法解决此错误在同学的帮助下 说明是： 对于此分配，您将创建一个存储分数的类。
昨天，我尝试以一种方式执行此操作...今天我尝试另一种方式，但仍然卡住了。我必须找到一种使用整数除法和取模来做到这一点的方法。这是我的代码，后面是错误消息。 public int evaluateFr
我这里有一些特殊字符: http://209.141.56.244/test/char.php 但是当我在这里通过 ajax 抓取这个文件时，它们显示为 back ?标记: http://209.14
我得到了一张图表 G与 n顶点，标记自 1至 n (2 a_1 -> a_2 -> ... a_k -> n A然后将占据 1 的所有“子节点”节点, a_1 , ... a_x (其中 x = ce
我有一个看起来像这样的 mongodb 集合: db.scores.insert({"name": "Bob", value: 96.3, timeStamp:'2010-9-27 9:32:00'}
我试图更好地了解 lucene 如何对我的搜索进行评分，以便我可以对我的搜索配置或文档内容进行必要的调整。 以下是分数明细的一部分。 产品: 0.34472802 = queryWeight,
在我网站上用户生成的帖子下，我有一个类似亚马逊的评级系统: Was this review helpful to you: Yes | No 如果有投票，我会在该行上方显示结果，如下所示:
对于我的项目，我需要找出哪些搜索结果被视为“良好”匹配。目前，分数因查询而异，因此需要以某种方式对它们进行标准化。标准化分数将允许选择高于给定阈值的结果。 我为 Lucene 找到了几个解决方案: h
我有一个由 57 个变量组成的数据文件。由于测量水平不均匀，我想将其中的大约 12 个转换为 z 分数。我查找了互联网资源和帮助文件。一个互联网资源建议我需要 Rbasic 包(不存在)。我使用了 s
我对 SOLR 核心运行查询并使用过滤器限制结果例如 fq: {!frange l=0.7 }query($q)。我知道 SOLR 分数不有绝对意义，但是0.7(只是一个例子)是计算出来的基于用户输入
我想找到不同的方法来解决我遇到的现实生活问题:想象一下进行一场比赛或一场游戏，在此期间用户收集积分。您必须构建一个查询来显示具有最佳“n”分数的用户列表。 我举一个例子来澄清。假设这是用户表，其中包含
我有很多 wiki 页面，我想训练一个分类器，看看是否可以通过一些特征(包括段落的位置和段落的 lucene 分数)来确定重点搜索的位置。我尝试将每个段落视为一个文档，这使我能够获得每个段落的 luc
我是 R 编程新手，在使用一些基本代码时遇到问题。 我有一个包含以下列的数据框:条件(因子)、用户(因子)和灵敏度(int)。对于每个用户有 20 个敏感项。我需要为每个用户创建一个具有标准化敏感度分
我是一名优秀的程序员,十分优秀！