[clangd] Update CC Ranking model with better sampling.

[usaxena95]

Summary

A better sampling strategy was used to generate the dataset for this
model.
New signals introduced in this model:

• NumNameInContext: Number of words in the context that matches the name of the candidate.
• FractionNameInContext: Fraction of the words in context matching the name of the candidate.

We remove the signal IsForbidden from the model and down rank
forbidden signals aggresively.

[adamcz]

clang-tools-extra/clangd/Quality.cpp

515

Please add a guard for division by zero

[usaxena95]

Addressed comments.

clang-tools-extra/clangd/Quality.cpp

evaluateDecisionForest(const SymbolQualitySignals &Quality,
   E.setIsDeprecated(Quality.Deprecated);
   E.setIsReservedName(Quality.ReservedName);
   E.setIsImplementationDetail(Quality.ImplementationDetail);
   E.setNumReferences(Quality.References);
   E.setSymbolCategory(Quality.Category);
 
   SymbolRelevanceSignals::DerivedSignals Derived =
       Relevance.calculateDerivedSignals();
-  E.setIsNameInContext(Derived.NameMatchesContext);
-  E.setIsForbidden(Relevance.Forbidden);
+  int NumMatch = 0;
+  if (Relevance.ContextWords) {
+    for (const auto &Word : Relevance.ContextWords->keys()) {
+      if (Relevance.Name.contains_lower(Word)) {
+        ++NumMatch;
+      }
+    }
+  }
+  E.setIsNameInContext(NumMatch > 0);
+  E.setNumNameInContext(NumMatch);
+  E.setFractionNameInContext(
+      Relevance.ContextWords ? NumMatch * 1.0 / Relevance.ContextWords->size()
+                             : 0);
   E.setIsInBaseClass(Relevance.InBaseClass);
-  E.setFileProximityDistance(Derived.FileProximityDistance);
+  E.setFileProximityDistanceCost(Derived.FileProximityDistance);
   E.setSemaFileProximityScore(Relevance.SemaFileProximityScore);
-  E.setSymbolScopeDistance(Derived.ScopeProximityDistance);
+  E.setSymbolScopeDistanceCost(Derived.ScopeProximityDistance);
   E.setSemaSaysInScope(Relevance.SemaSaysInScope);
   E.setScope(Relevance.Scope);
   E.setContextKind(Relevance.Context);
   E.setIsInstanceMember(Relevance.IsInstanceMember);
   E.setHadContextType(Relevance.HadContextType);
   E.setHadSymbolType(Relevance.HadSymbolType);
   E.setTypeMatchesPreferred(Relevance.TypeMatchesPreferred);
-  E.setFilterLength(Relevance.FilterLength);
 
   DecisionForestScores Scores;
   // Exponentiating DecisionForest prediction makes the score of each tree a
   // multiplciative boost (like NameMatch). This allows us to weigh the
   // prediciton score and NameMatch appropriately.
   Scores.ExcludingName = pow(Base, Evaluate(E));
   // NeedsFixIts is not part of the DecisionForest as generating training
   // data that needs fixits is not-feasible.
   if (Relevance.NeedsFixIts)
     Scores.ExcludingName *= 0.5;
+  if (Relevance.Forbidden)
+    Scores.ExcludingName *= 0;
+
   // NameMatch should be a multiplier on total score to support rescoring.
   Scores.Total = Relevance.NameMatch * Scores.ExcludingName;
   return Scores;
 }
 
 // Produces an integer that sorts in the same order as F.
 // That is: a < b <==> encodeFloat(a) < encodeFloat(b).
 static uint32_t encodeFloat(float F) {

clang-tools-extra/clangd/quality/model/features.json

 [
     {
-        "name": "FilterLength",
-        "kind": "NUMBER"
-    },
-    {
         "name": "IsDeprecated",
         "kind": "NUMBER"
     },
     {
         "name": "IsReservedName",
         "kind": "NUMBER"
     },
     {
         "name": "IsImplementationDetail",
         "kind": "NUMBER"
     },
     {
         "name": "NumReferences",
         "kind": "NUMBER"
     },
     {
-        "name": "IsNameInContext",
+        "name": "NumNameInContext",
         "kind": "NUMBER"
     },
     {
-        "name": "IsForbidden",
+        "name": "FractionNameInContext",
+        "kind": "NUMBER"
+    },
+    {
+        "name": "IsNameInContext",
         "kind": "NUMBER"
     },
     {
         "name": "IsInBaseClass",
         "kind": "NUMBER"
     },
     {
-        "name": "FileProximityDistance",
+        "name": "FileProximityDistanceCost",
         "kind": "NUMBER"
     },
     {
         "name": "SemaFileProximityScore",
         "kind": "NUMBER"
     },
     {
-        "name": "SymbolScopeDistance",
+        "name": "SymbolScopeDistanceCost",
         "kind": "NUMBER"
     },
     {
         "name": "SemaSaysInScope",
         "kind": "NUMBER"
     },
     {
         "name": "IsInstanceMember",
[
         "header": "clang/Sema/CodeCompleteConsumer.h"
     },
     {
         "name": "Scope",
         "kind": "ENUM",
         "type": "clang::clangd::SymbolRelevanceSignals::AccessibleScope",
         "header": "Quality.h"
     }
-]
+]