1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
|
// Copyright 2012-present Oliver Eilhard. All rights reserved.
// Use of this source code is governed by a MIT-license.
// See http://olivere.mit-license.org/license.txt for details.
package elastic
// SignificantSignificantTermsAggregation is an aggregation that returns interesting
// or unusual occurrences of terms in a set.
// See: https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html
type SignificantTermsAggregation struct {
field string
subAggregations map[string]Aggregation
meta map[string]interface{}
minDocCount *int
shardMinDocCount *int
requiredSize *int
shardSize *int
filter Query
executionHint string
significanceHeuristic SignificanceHeuristic
}
func NewSignificantTermsAggregation() *SignificantTermsAggregation {
return &SignificantTermsAggregation{
subAggregations: make(map[string]Aggregation, 0),
}
}
func (a *SignificantTermsAggregation) Field(field string) *SignificantTermsAggregation {
a.field = field
return a
}
func (a *SignificantTermsAggregation) SubAggregation(name string, subAggregation Aggregation) *SignificantTermsAggregation {
a.subAggregations[name] = subAggregation
return a
}
// Meta sets the meta data to be included in the aggregation response.
func (a *SignificantTermsAggregation) Meta(metaData map[string]interface{}) *SignificantTermsAggregation {
a.meta = metaData
return a
}
func (a *SignificantTermsAggregation) MinDocCount(minDocCount int) *SignificantTermsAggregation {
a.minDocCount = &minDocCount
return a
}
func (a *SignificantTermsAggregation) ShardMinDocCount(shardMinDocCount int) *SignificantTermsAggregation {
a.shardMinDocCount = &shardMinDocCount
return a
}
func (a *SignificantTermsAggregation) RequiredSize(requiredSize int) *SignificantTermsAggregation {
a.requiredSize = &requiredSize
return a
}
func (a *SignificantTermsAggregation) ShardSize(shardSize int) *SignificantTermsAggregation {
a.shardSize = &shardSize
return a
}
func (a *SignificantTermsAggregation) BackgroundFilter(filter Query) *SignificantTermsAggregation {
a.filter = filter
return a
}
func (a *SignificantTermsAggregation) ExecutionHint(hint string) *SignificantTermsAggregation {
a.executionHint = hint
return a
}
func (a *SignificantTermsAggregation) SignificanceHeuristic(heuristic SignificanceHeuristic) *SignificantTermsAggregation {
a.significanceHeuristic = heuristic
return a
}
func (a *SignificantTermsAggregation) Source() (interface{}, error) {
// Example:
// {
// "query" : {
// "terms" : {"force" : [ "British Transport Police" ]}
// },
// "aggregations" : {
// "significantCrimeTypes" : {
// "significant_terms" : { "field" : "crime_type" }
// }
// }
// }
//
// This method returns only the
// { "significant_terms" : { "field" : "crime_type" }
// part.
source := make(map[string]interface{})
opts := make(map[string]interface{})
source["significant_terms"] = opts
if a.field != "" {
opts["field"] = a.field
}
if a.requiredSize != nil {
opts["size"] = *a.requiredSize // not a typo!
}
if a.shardSize != nil {
opts["shard_size"] = *a.shardSize
}
if a.minDocCount != nil {
opts["min_doc_count"] = *a.minDocCount
}
if a.shardMinDocCount != nil {
opts["shard_min_doc_count"] = *a.shardMinDocCount
}
if a.executionHint != "" {
opts["execution_hint"] = a.executionHint
}
if a.filter != nil {
src, err := a.filter.Source()
if err != nil {
return nil, err
}
opts["background_filter"] = src
}
if a.significanceHeuristic != nil {
name := a.significanceHeuristic.Name()
src, err := a.significanceHeuristic.Source()
if err != nil {
return nil, err
}
opts[name] = src
}
// AggregationBuilder (SubAggregations)
if len(a.subAggregations) > 0 {
aggsMap := make(map[string]interface{})
source["aggregations"] = aggsMap
for name, aggregate := range a.subAggregations {
src, err := aggregate.Source()
if err != nil {
return nil, err
}
aggsMap[name] = src
}
}
// Add Meta data if available
if len(a.meta) > 0 {
source["meta"] = a.meta
}
return source, nil
}
// -- Significance heuristics --
type SignificanceHeuristic interface {
Name() string
Source() (interface{}, error)
}
// -- Chi Square --
// ChiSquareSignificanceHeuristic implements Chi square as described
// in "Information Retrieval", Manning et al., Chapter 13.5.2.
//
// See https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_chi_square
// for details.
type ChiSquareSignificanceHeuristic struct {
backgroundIsSuperset *bool
includeNegatives *bool
}
// NewChiSquareSignificanceHeuristic initializes a new ChiSquareSignificanceHeuristic.
func NewChiSquareSignificanceHeuristic() *ChiSquareSignificanceHeuristic {
return &ChiSquareSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *ChiSquareSignificanceHeuristic) Name() string {
return "chi_square"
}
// BackgroundIsSuperset indicates whether you defined a custom background
// filter that represents a difference set of documents that you want to
// compare to.
func (sh *ChiSquareSignificanceHeuristic) BackgroundIsSuperset(backgroundIsSuperset bool) *ChiSquareSignificanceHeuristic {
sh.backgroundIsSuperset = &backgroundIsSuperset
return sh
}
// IncludeNegatives indicates whether to filter out the terms that appear
// much less in the subset than in the background without the subset.
func (sh *ChiSquareSignificanceHeuristic) IncludeNegatives(includeNegatives bool) *ChiSquareSignificanceHeuristic {
sh.includeNegatives = &includeNegatives
return sh
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *ChiSquareSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
if sh.backgroundIsSuperset != nil {
source["background_is_superset"] = *sh.backgroundIsSuperset
}
if sh.includeNegatives != nil {
source["include_negatives"] = *sh.includeNegatives
}
return source, nil
}
// -- GND --
// GNDSignificanceHeuristic implements the "Google Normalized Distance"
// as described in "The Google Similarity Distance", Cilibrasi and Vitanyi,
// 2007.
//
// See https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_google_normalized_distance
// for details.
type GNDSignificanceHeuristic struct {
backgroundIsSuperset *bool
}
// NewGNDSignificanceHeuristic implements a new GNDSignificanceHeuristic.
func NewGNDSignificanceHeuristic() *GNDSignificanceHeuristic {
return &GNDSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *GNDSignificanceHeuristic) Name() string {
return "gnd"
}
// BackgroundIsSuperset indicates whether you defined a custom background
// filter that represents a difference set of documents that you want to
// compare to.
func (sh *GNDSignificanceHeuristic) BackgroundIsSuperset(backgroundIsSuperset bool) *GNDSignificanceHeuristic {
sh.backgroundIsSuperset = &backgroundIsSuperset
return sh
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *GNDSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
if sh.backgroundIsSuperset != nil {
source["background_is_superset"] = *sh.backgroundIsSuperset
}
return source, nil
}
// -- JLH Score --
// JLHScoreSignificanceHeuristic implements the JLH score as described in
// https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_jlh_score.
type JLHScoreSignificanceHeuristic struct{}
// NewJLHScoreSignificanceHeuristic initializes a new JLHScoreSignificanceHeuristic.
func NewJLHScoreSignificanceHeuristic() *JLHScoreSignificanceHeuristic {
return &JLHScoreSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *JLHScoreSignificanceHeuristic) Name() string {
return "jlh"
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *JLHScoreSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
return source, nil
}
// -- Mutual Information --
// MutualInformationSignificanceHeuristic implements Mutual information
// as described in "Information Retrieval", Manning et al., Chapter 13.5.1.
//
// See https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_mutual_information
// for details.
type MutualInformationSignificanceHeuristic struct {
backgroundIsSuperset *bool
includeNegatives *bool
}
// NewMutualInformationSignificanceHeuristic initializes a new instance of
// MutualInformationSignificanceHeuristic.
func NewMutualInformationSignificanceHeuristic() *MutualInformationSignificanceHeuristic {
return &MutualInformationSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *MutualInformationSignificanceHeuristic) Name() string {
return "mutual_information"
}
// BackgroundIsSuperset indicates whether you defined a custom background
// filter that represents a difference set of documents that you want to
// compare to.
func (sh *MutualInformationSignificanceHeuristic) BackgroundIsSuperset(backgroundIsSuperset bool) *MutualInformationSignificanceHeuristic {
sh.backgroundIsSuperset = &backgroundIsSuperset
return sh
}
// IncludeNegatives indicates whether to filter out the terms that appear
// much less in the subset than in the background without the subset.
func (sh *MutualInformationSignificanceHeuristic) IncludeNegatives(includeNegatives bool) *MutualInformationSignificanceHeuristic {
sh.includeNegatives = &includeNegatives
return sh
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *MutualInformationSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
if sh.backgroundIsSuperset != nil {
source["background_is_superset"] = *sh.backgroundIsSuperset
}
if sh.includeNegatives != nil {
source["include_negatives"] = *sh.includeNegatives
}
return source, nil
}
// -- Percentage Score --
// PercentageScoreSignificanceHeuristic implements the algorithm described
// in https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_percentage.
type PercentageScoreSignificanceHeuristic struct{}
// NewPercentageScoreSignificanceHeuristic initializes a new instance of
// PercentageScoreSignificanceHeuristic.
func NewPercentageScoreSignificanceHeuristic() *PercentageScoreSignificanceHeuristic {
return &PercentageScoreSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *PercentageScoreSignificanceHeuristic) Name() string {
return "percentage"
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *PercentageScoreSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
return source, nil
}
// -- Script --
// ScriptSignificanceHeuristic implements a scripted significance heuristic.
// See https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_scripted
// for details.
type ScriptSignificanceHeuristic struct {
script *Script
}
// NewScriptSignificanceHeuristic initializes a new instance of
// ScriptSignificanceHeuristic.
func NewScriptSignificanceHeuristic() *ScriptSignificanceHeuristic {
return &ScriptSignificanceHeuristic{}
}
// Name returns the name of the heuristic in the REST interface.
func (sh *ScriptSignificanceHeuristic) Name() string {
return "script_heuristic"
}
// Script specifies the script to use to get custom scores. The following
// parameters are available in the script: `_subset_freq`, `_superset_freq`,
// `_subset_size`, and `_superset_size`.
//
// See https://www.elastic.co/guide/en/elasticsearch/reference/5.2/search-aggregations-bucket-significantterms-aggregation.html#_scripted
// for details.
func (sh *ScriptSignificanceHeuristic) Script(script *Script) *ScriptSignificanceHeuristic {
sh.script = script
return sh
}
// Source returns the parameters that need to be added to the REST parameters.
func (sh *ScriptSignificanceHeuristic) Source() (interface{}, error) {
source := make(map[string]interface{})
if sh.script != nil {
src, err := sh.script.Source()
if err != nil {
return nil, err
}
source["script"] = src
}
return source, nil
}
|