[cr-mixer/home-mixer] Remove getLinearRankingParams in EarlybirdTen…

…sorflowBasedSimilarityEngine Remove unused ranking params which are specified by services when making an Earlybird relevance search. For cr-mixer: since we always set useTensorflowRanking = true in EarlybirdSimilarityEngineRouter, we will only ever use the TensorFlowBasedScoringFunction for ranking search results. That function doesn't rely on any of the linear params specified in getLinearRankingParams, nor the boosts because we set applyBoosts = false in the request. These parameters are therefore strictly redundant. The parameters in home-mixer can be removed for essentially the same reason—the parameters are redundant given that we use the Tensorflow scoring function and don't apply boosts.
kowsar89 · Apr 5, 2023 · 138bb51 · 138bb51
1 parent 3496189
commit 138bb51
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 60 deletions.
diff --git a/...ala/com/twitter/cr_mixer/similarity_engine/EarlybirdTensorflowBasedSimilarityEngine.scala b/...ala/com/twitter/cr_mixer/similarity_engine/EarlybirdTensorflowBasedSimilarityEngine.scala
@@ -6,8 +6,6 @@ import com.twitter.search.earlybird.thriftscala.EarlybirdService
 import com.twitter.search.earlybird.thriftscala.ThriftSearchQuery
 import com.twitter.util.Time
 import com.twitter.search.common.query.thriftjava.thriftscala.CollectorParams
-import com.twitter.search.common.ranking.thriftscala.ThriftAgeDecayRankingParams
-import com.twitter.search.common.ranking.thriftscala.ThriftLinearFeatureRankingParams
 import com.twitter.search.common.ranking.thriftscala.ThriftRankingParams
 import com.twitter.search.common.ranking.thriftscala.ThriftScoringFunctionType
 import com.twitter.search.earlybird.thriftscala.ThriftSearchRelevanceOptions
@@ -97,7 +95,7 @@ object EarlybirdTensorflowBasedSimilarityEngine {
       // Whether to collect conversation IDs. Remove it for now.
       // collectConversationId = Gate.True(), // true for Home
       rankingMode = ThriftSearchRankingMode.Relevance,
-      relevanceOptions = Some(getRelevanceOptions(query.useTensorflowRanking)),
+      relevanceOptions = Some(getRelevanceOptions),
       collectorParams = Some(
         CollectorParams(
           // numResultsToReturn defines how many results each EB shard will return to search root
@@ -116,13 +114,11 @@ object EarlybirdTensorflowBasedSimilarityEngine {
   // The specific values of recap relevance/reranking options correspond to
   // experiment: enable_recap_reranking_2988,timeline_internal_disable_recap_filter
   // bucket    : enable_rerank,disable_filter
-  private def getRelevanceOptions(useTensorflowRanking: Boolean): ThriftSearchRelevanceOptions = {
+  private def getRelevanceOptions: ThriftSearchRelevanceOptions = {
     ThriftSearchRelevanceOptions(
       proximityScoring = true,
       maxConsecutiveSameUser = Some(2),
-      rankingParams =
-        if (useTensorflowRanking) Some(getTensorflowBasedRankingParams)
-        else Some(getLinearRankingParams),
+      rankingParams = Some(getTensorflowBasedRankingParams),
       maxHitsToProcess = Some(500),
       maxUserBlendCount = Some(3),
       proximityPhraseWeight = 9.0,
@@ -131,41 +127,12 @@ object EarlybirdTensorflowBasedSimilarityEngine {
   }
 
   private def getTensorflowBasedRankingParams: ThriftRankingParams = {
-    getLinearRankingParams.copy(
+    ThriftRankingParams(
       `type` = Some(ThriftScoringFunctionType.TensorflowBased),
       selectedTensorflowModel = Some("timelines_rectweet_replica"),
+      minScore = -1.0e100,
       applyBoosts = false,
       authorSpecificScoreAdjustments = None
     )
   }
-
-  private def getLinearRankingParams: ThriftRankingParams = {
-    ThriftRankingParams(
-      `type` = Some(ThriftScoringFunctionType.Linear),
-      minScore = -1.0e100,
-      retweetCountParams = Some(ThriftLinearFeatureRankingParams(weight = 20.0)),
-      replyCountParams = Some(ThriftLinearFeatureRankingParams(weight = 1.0)),
-      reputationParams = Some(ThriftLinearFeatureRankingParams(weight = 0.2)),
-      luceneScoreParams = Some(ThriftLinearFeatureRankingParams(weight = 2.0)),
-      textScoreParams = Some(ThriftLinearFeatureRankingParams(weight = 0.18)),
-      urlParams = Some(ThriftLinearFeatureRankingParams(weight = 2.0)),
-      isReplyParams = Some(ThriftLinearFeatureRankingParams(weight = 1.0)),
-      favCountParams = Some(ThriftLinearFeatureRankingParams(weight = 30.0)),
-      langEnglishUIBoost = 0.5,
-      langEnglishTweetBoost = 0.2,
-      langDefaultBoost = 0.02,
-      unknownLanguageBoost = 0.05,
-      offensiveBoost = 0.1,
-      inTrustedCircleBoost = 3.0,
-      multipleHashtagsOrTrendsBoost = 0.6,
-      inDirectFollowBoost = 4.0,
-      tweetHasTrendBoost = 1.1,
-      selfTweetBoost = 2.0,
-      tweetHasImageUrlBoost = 2.0,
-      tweetHasVideoUrlBoost = 2.0,
-      useUserLanguageInfo = true,
-      ageDecayParams = Some(ThriftAgeDecayRankingParams(slope = 0.005, base = 1.0))
-    )
-  }
-
 }
diff --git a/...xer/server/src/main/scala/com/twitter/home_mixer/util/earlybird/RelevanceSearchUtil.scala b/...xer/server/src/main/scala/com/twitter/home_mixer/util/earlybird/RelevanceSearchUtil.scala
@@ -15,28 +15,6 @@ object RelevanceSearchUtil {
       `type` = Some(scr.ThriftScoringFunctionType.TensorflowBased),
       selectedTensorflowModel = Some("timelines_rectweet_replica"),
       minScore = -1.0e100,
-      retweetCountParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 20.0)),
-      replyCountParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 1.0)),
-      reputationParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 0.2)),
-      luceneScoreParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 2.0)),
-      textScoreParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 0.18)),
-      urlParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 2.0)),
-      isReplyParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 1.0)),
-      favCountParams = Some(scr.ThriftLinearFeatureRankingParams(weight = 30.0)),
-      langEnglishUIBoost = 0.5,
-      langEnglishTweetBoost = 0.2,
-      langDefaultBoost = 0.02,
-      unknownLanguageBoost = 0.05,
-      offensiveBoost = 0.1,
-      inTrustedCircleBoost = 3.0,
-      multipleHashtagsOrTrendsBoost = 0.6,
-      inDirectFollowBoost = 4.0,
-      tweetHasTrendBoost = 1.1,
-      selfTweetBoost = 2.0,
-      tweetHasImageUrlBoost = 2.0,
-      tweetHasVideoUrlBoost = 2.0,
-      useUserLanguageInfo = true,
-      ageDecayParams = Some(scr.ThriftAgeDecayRankingParams(slope = 0.005, base = 1.0)),
       selectedModels = Some(Map("home_mixer_unified_engagement_prod" -> 1.0)),
       applyBoosts = false,
     )