elasticsearch disable term frequency scoring

Question

I want to change the scoring system in elasticsearch to get rid of counting multiple appearances of a term. For example, I want:

"texas texas texas"

and

"texas"

to come out as the same score. I had found this mapping that elasticsearch said would disable term frequency counting but my searches do not come out as the same score:

"mappings":{
"business": {   
   "properties" : {
       "name" : {
          "type" : "string",
          "index_options" : "docs",
          "norms" : { "enabled": false}}
        }
    }
}

}

Any help will be appreciated, I have not been able to find a lot of information on this.

I am adding my search code and what gets returned when I use explain.

My search code:

Settings settings = ImmutableSettings.settingsBuilder().put("cluster.name", "escluster").build();
    Client client = new TransportClient(settings)
    .addTransportAddress(new InetSocketTransportAddress("127.0.0.1", 9300));

    SearchRequest request =  Requests.searchRequest("businesses")
            .source(SearchSourceBuilder.searchSource().query(QueryBuilders.boolQuery()
            .should(QueryBuilders.matchQuery("name", "Texas")
            .minimumShouldMatch("1")))).searchType(SearchType.DFS_QUERY_THEN_FETCH);
    
    ExplainRequest request2 = client.prepareIndex("businesses", "business")

and when I search with explain I get:

  "took" : 14,
  "timed_out" : false,
  "_shards" : {
    "total" : 3,
    "successful" : 3,
    "failed" : 0
  },
  "hits" : {
    "total" : 2,
    "max_score" : 1.0,
    "hits" : [ {
      "_shard" : 1,
      "_node" : "BTqBPVDET5Kr83r-CYPqfA",
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9U5KBks4zEorv9YI4n",
      "_score" : 1.0,
      "_source":{
"name" : "texas"
}
,
      "_explanation" : {
        "value" : 1.0,
        "description" : "weight(_all:texas in 0) [PerFieldSimilarity], result of:",
        "details" : [ {
          "value" : 1.0,
          "description" : "fieldWeight in 0, product of:",
          "details" : [ {
            "value" : 1.0,
            "description" : "tf(freq=1.0), with freq of:",
            "details" : [ {
              "value" : 1.0,
              "description" : "termFreq=1.0"
            } ]
          }, {
            "value" : 1.0,
            "description" : "idf(docFreq=2, maxDocs=3)"
          }, {
            "value" : 1.0,
            "description" : "fieldNorm(doc=0)"
          } ]
        } ]
      }
    }, {
      "_shard" : 1,
      "_node" : "BTqBPVDET5Kr83r-CYPqfA",
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9U5K6Ks4zEorv9YI4o",
      "_score" : 0.8660254,
      "_source":{
"name" : "texas texas texas"
}
,
      "_explanation" : {
        "value" : 0.8660254,
        "description" : "weight(_all:texas in 0) [PerFieldSimilarity], result of:",
        "details" : [ {
          "value" : 0.8660254,
          "description" : "fieldWeight in 0, product of:",
          "details" : [ {
            "value" : 1.7320508,
            "description" : "tf(freq=3.0), with freq of:",
            "details" : [ {
              "value" : 3.0,
              "description" : "termFreq=3.0"
            } ]
          }, {
            "value" : 1.0,
            "description" : "idf(docFreq=2, maxDocs=3)"
          }, {
            "value" : 0.5,
            "description" : "fieldNorm(doc=0)"
          } ]
        } ]
      }
    } ]
  }
    

It looks like it is still considering frequency and doc frequency. Any ideas? Sorry for the bad formatting I don't know why it is appearing so grotesque.

My code from the browser search http://localhost:9200/businesses/business/_search?pretty=true&qname=texas is:

    {
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 3,
    "successful" : 3,
    "failed" : 0
  },
  "hits" : {
    "total" : 4,
    "max_score" : 1.0,
    "hits" : [ {
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9YcCKjKvtg8NgyozGK",
      "_score" : 1.0,
      "_source":{"business" : {
"name" : "texas texas texas texas" }
}
    }, {
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9YateBKvtg8Ngyoy-p",
      "_score" : 1.0,
      "_source":{
"name" : "texas" }

    }, {
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9YavVnKvtg8Ngyoy-4",
      "_score" : 1.0,
      "_source":{
"name" : "texas texas texas" }

    }, {
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9Yb7NgKvtg8NgyozFf",
      "_score" : 1.0,
      "_source":{"business" : {
"name" : "texas texas texas" }
}
    } ]
  }
}

It finds all 4 objects I have in there and has them all the same score. When I run my java API search with explain I get:

    {
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 3,
    "successful" : 3,
    "failed" : 0
  },
  "hits" : {
    "total" : 2,
    "max_score" : 1.287682,
    "hits" : [ {
      "_shard" : 1,
      "_node" : "BTqBPVDET5Kr83r-CYPqfA",
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9YateBKvtg8Ngyoy-p",
      "_score" : 1.287682,
      "_source":{
"name" : "texas" }
,
      "_explanation" : {
        "value" : 1.287682,
        "description" : "weight(name:texas in 0) [PerFieldSimilarity], result of:",
        "details" : [ {
          "value" : 1.287682,
          "description" : "fieldWeight in 0, product of:",
          "details" : [ {
            "value" : 1.0,
            "description" : "tf(freq=1.0), with freq of:",
            "details" : [ {
              "value" : 1.0,
              "description" : "termFreq=1.0"
            } ]
          }, {
            "value" : 1.287682,
            "description" : "idf(docFreq=2, maxDocs=4)"
          }, {
            "value" : 1.0,
            "description" : "fieldNorm(doc=0)"
          } ]
        } ]
      }
    }, {
      "_shard" : 1,
      "_node" : "BTqBPVDET5Kr83r-CYPqfA",
      "_index" : "businesses",
      "_type" : "business",
      "_id" : "AU9YavVnKvtg8Ngyoy-4",
      "_score" : 1.1151654,
      "_source":{
"name" : "texas texas texas" }
,
      "_explanation" : {
        "value" : 1.1151654,
        "description" : "weight(name:texas in 0) [PerFieldSimilarity], result of:",
        "details" : [ {
          "value" : 1.1151654,
          "description" : "fieldWeight in 0, product of:",
          "details" : [ {
            "value" : 1.7320508,
            "description" : "tf(freq=3.0), with freq of:",
            "details" : [ {
              "value" : 3.0,
              "description" : "termFreq=3.0"
            } ]
          }, {
            "value" : 1.287682,
            "description" : "idf(docFreq=2, maxDocs=4)"
          }, {
            "value" : 0.5,
            "description" : "fieldNorm(doc=0)"
          } ]
        } ]
      }
    } ]
  }
}

Answer 1

Looks like one cannot override the index options for a field after the field has been initial set in mapping

Example:

put test
put test/business/_mapping
{

      "properties": {
         "name": {
            "type": "string",
           "index_options": "freqs",
            "norms": {
               "enabled": false
            }
         }
      }

}
put test/business/_mapping
{

      "properties": {
         "name": {
            "type": "string",
            "index_options": "docs",
            "norms": {
               "enabled": false
            }
         }
      }

}
get  test/business/_mapping

   {
   "test": {
      "mappings": {
         "business": {
            "properties": {
               "name": {
                  "type": "string",
                  "norms": {
                     "enabled": false
                  },
                  "index_options": "freqs"
               }
            }
         }
      }
   }
}

You would have to recreate the index to pick up the new mapping