Examples with SignificantTerms org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms used on opensource projects

Example 6 with SignificantTerms

use of org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms in project elasticsearch by elastic.

the class SignificantTermsIT method testStructuredAnalysisWithIncludeExclude.

public void testStructuredAnalysisWithIncludeExclude() throws Exception {
    long[] excludeTerms = { MUSIC_CATEGORY };
    SearchResponse response = client().prepareSearch("test").setSearchType(SearchType.QUERY_THEN_FETCH).setQuery(new TermQueryBuilder("description", "paul")).setFrom(0).setSize(60).setExplain(true).addAggregation(significantTerms("mySignificantTerms").field("fact_category").executionHint(randomExecutionHint()).minDocCount(1).includeExclude(new IncludeExclude(null, excludeTerms))).execute().actionGet();
    assertSearchResponse(response);
    SignificantTerms topTerms = response.getAggregations().get("mySignificantTerms");
    Number topCategory = (Number) topTerms.getBuckets().iterator().next().getKey();
    assertTrue(topCategory.equals(Long.valueOf(OTHER_CATEGORY)));
}

Example 7 with SignificantTerms

use of org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms in project elasticsearch by elastic.

the class SignificantTermsIT method testTextAnalysisGND.

public void testTextAnalysisGND() throws Exception {
    SearchResponse response = client().prepareSearch("test").setSearchType(SearchType.QUERY_THEN_FETCH).setQuery(new TermQueryBuilder("description", "terje")).setFrom(0).setSize(60).setExplain(true).addAggregation(significantTerms("mySignificantTerms").field("description").executionHint(randomExecutionHint()).significanceHeuristic(new GND(true)).minDocCount(2)).execute().actionGet();
    assertSearchResponse(response);
    SignificantTerms topTerms = response.getAggregations().get("mySignificantTerms");
    checkExpectedStringTermsFound(topTerms);
}

Example 8 with SignificantTerms

use of org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms in project elasticsearch by elastic.

the class SignificantTermsIT method testTextAnalysisPercentageScore.

public void testTextAnalysisPercentageScore() throws Exception {
    SearchResponse response = client().prepareSearch("test").setSearchType(SearchType.QUERY_THEN_FETCH).setQuery(new TermQueryBuilder("description", "terje")).setFrom(0).setSize(60).setExplain(true).addAggregation(significantTerms("mySignificantTerms").field("description").executionHint(randomExecutionHint()).significanceHeuristic(new PercentageScore()).minDocCount(2)).execute().actionGet();
    assertSearchResponse(response);
    SignificantTerms topTerms = response.getAggregations().get("mySignificantTerms");
    checkExpectedStringTermsFound(topTerms);
}

Example 9 with SignificantTerms

use of org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms in project elasticsearch by elastic.

the class SignificantTermsIT method testMutualInformation.

public void testMutualInformation() throws Exception {
    SearchResponse response = client().prepareSearch("test").setSearchType(SearchType.QUERY_THEN_FETCH).setQuery(new TermQueryBuilder("description", "terje")).setFrom(0).setSize(60).setExplain(true).addAggregation(significantTerms("mySignificantTerms").field("description").executionHint(randomExecutionHint()).significanceHeuristic(new MutualInformation(false, true)).minDocCount(1)).execute().actionGet();
    assertSearchResponse(response);
    SignificantTerms topTerms = response.getAggregations().get("mySignificantTerms");
    checkExpectedStringTermsFound(topTerms);
}

Example 10 with SignificantTerms

use of org.elasticsearch.search.aggregations.bucket.significant.SignificantTerms in project elasticsearch by elastic.

the class SignificantTermsIT method testBadFilteredAnalysis.

public void testBadFilteredAnalysis() throws Exception {
    // Deliberately using a bad choice of filter here for the background context in order
    // to test robustness.
    // We search for the name of a snowboarder but use music-related content (fact_category:1)
    // as the background source of term statistics.
    SearchResponse response = client().prepareSearch("test").setSearchType(SearchType.QUERY_THEN_FETCH).setQuery(new TermQueryBuilder("description", "terje")).setFrom(0).setSize(60).setExplain(true).addAggregation(significantTerms("mySignificantTerms").field("description").minDocCount(2).backgroundFilter(QueryBuilders.termQuery("fact_category", 1))).execute().actionGet();
    assertSearchResponse(response);
    SignificantTerms topTerms = response.getAggregations().get("mySignificantTerms");
    // We expect at least one of the significant terms to have been selected on the basis
    // that it is present in the foreground selection but entirely missing from the filtered
    // background used as context.
    boolean hasMissingBackgroundTerms = false;
    for (Bucket topTerm : topTerms) {
        if (topTerm.getSupersetDf() == 0) {
            hasMissingBackgroundTerms = true;
            break;
        }
    }
    assertTrue(hasMissingBackgroundTerms);
}