Interface ISignificantTextAggregation
An aggregation that returns interesting or unusual occurrences of free-text terms in a set.
Namespace: OpenSearch.Client
Assembly: OpenSearch.Client.dll
Syntax
public interface ISignificantTextAggregation : IBucketAggregation, IAggregation
Properties
| Edit this page View SourceBackgroundFilter
The default source of statistical information for background term frequencies is the entire index. This scope can be narrowed through the use of a background filter to focus in on significant terms within a narrower context
Declaration
[DataMember(Name = "background_filter")]
QueryContainer BackgroundFilter { get; set; }
Property Value
| Type | Description |
|---|---|
| QueryContainer |
ChiSquare
Use chi square to calculate significance score
Declaration
[DataMember(Name = "chi_square")]
IChiSquareHeuristic ChiSquare { get; set; }
Property Value
| Type | Description |
|---|---|
| IChiSquareHeuristic |
Exclude
Exclude term values for which buckets will be created.
Declaration
[DataMember(Name = "exclude")]
IncludeExclude Exclude { get; set; }
Property Value
| Type | Description |
|---|---|
| IncludeExclude |
ExecutionHint
Determines the mechanism by which aggregations are executed
Declaration
[DataMember(Name = "execution_hint")]
TermsAggregationExecutionHint? ExecutionHint { get; set; }
Property Value
| Type | Description |
|---|---|
| TermsAggregationExecutionHint? |
Field
The field on which to run the aggregation
Declaration
[DataMember(Name = "field")]
Field Field { get; set; }
Property Value
| Type | Description |
|---|---|
| Field |
FilterDuplicateText
Whether to filter out near-duplicate text
Declaration
[DataMember(Name = "filter_duplicate_text")]
bool? FilterDuplicateText { get; set; }
Property Value
| Type | Description |
|---|---|
| bool? |
GoogleNormalizedDistance
Use Google normalized distance to calculate significance score
Declaration
[DataMember(Name = "gnd")]
IGoogleNormalizedDistanceHeuristic GoogleNormalizedDistance { get; set; }
Property Value
| Type | Description |
|---|---|
| IGoogleNormalizedDistanceHeuristic |
Include
Include term values for which buckets will be created.
Declaration
[DataMember(Name = "include")]
IncludeExclude Include { get; set; }
Property Value
| Type | Description |
|---|---|
| IncludeExclude |
MinimumDocumentCount
Return only terms that match equal to or more than a configurable number of hits
Declaration
[DataMember(Name = "min_doc_count")]
long? MinimumDocumentCount { get; set; }
Property Value
| Type | Description |
|---|---|
| long? |
MutualInformation
Use mutual information to calculate significance score
Declaration
[DataMember(Name = "mutual_information")]
IMutualInformationHeuristic MutualInformation { get; set; }
Property Value
| Type | Description |
|---|---|
| IMutualInformationHeuristic |
PercentageScore
Use percentage to calculate significance score.
A simple calculation of the number of documents in the foreground sample with a term divided by the number of documents in the background with the term. By default this produces a score greater than zero and less than one.
Declaration
[DataMember(Name = "percentage")]
IPercentageScoreHeuristic PercentageScore { get; set; }
Property Value
| Type | Description |
|---|---|
| IPercentageScoreHeuristic |
Script
Use a script to calculate a custom significance score.
Declaration
[DataMember(Name = "script_heuristic")]
IScriptedHeuristic Script { get; set; }
Property Value
| Type | Description |
|---|---|
| IScriptedHeuristic |
ShardMinimumDocumentCount
Regulates the certainty a shard has if the term should actually be added to the candidate list or not with respect to the MinimumDocumentCount. Terms will only be considered if their local shard frequency within the set is higher than the ShardMinimumDocumentCount.
Declaration
[DataMember(Name = "shard_min_doc_count")]
long? ShardMinimumDocumentCount { get; set; }
Property Value
| Type | Description |
|---|---|
| long? |
ShardSize
Controls the number of candidate terms produced by each shard from which the Size of terms is selected.
Declaration
[DataMember(Name = "shard_size")]
int? ShardSize { get; set; }
Property Value
| Type | Description |
|---|---|
| int? |
Size
Defines how many term buckets should be returned out of the overall terms list
Declaration
[DataMember(Name = "size")]
int? Size { get; set; }
Property Value
| Type | Description |
|---|---|
| int? |
SourceFields
Ordinarily the indexed field name and the original JSON field being retrieved share the same name. However with more complex field mappings using features like copy_to the source JSON field(s) and the indexed field being aggregated can differ. In these cases it is possible to list the JSON _source fields from which text will be analyzed using SourceFields
Declaration
[DataMember(Name = "source_fields")]
Fields SourceFields { get; set; }
Property Value
| Type | Description |
|---|---|
| Fields |