feat(recommendation): add pure Similarity function with weighted Jaccard

2026-04-27 20:04:35 -04:00
parent 00483539ad
commit a7211aacff
2 changed files with 170 additions and 0 deletions
@@ -0,0 +1,94 @@
+package recommendation
+
+import (
+	"math"
+	"testing"
+)
+
+func approxEq(a, b float64) bool { return math.Abs(a-b) < 1e-9 }
+
+func TestSimilarity_IdenticalVectors_Returns1(t *testing.T) {
+	v := SessionVector{
+		Artists: []string{"a1", "a2"},
+		Tags:    map[string]int{"rock": 2, "indie": 1},
+	}
+	got := Similarity(v, v, DefaultSimilarityWeights)
+	if !approxEq(got, 1.0) {
+		t.Errorf("Similarity(v,v) = %v, want 1.0", got)
+	}
+}
+
+func TestSimilarity_FullyDisjoint_Returns0(t *testing.T) {
+	a := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 1}}
+	b := SessionVector{Artists: []string{"a2"}, Tags: map[string]int{"jazz": 1}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if !approxEq(got, 0.0) {
+		t.Errorf("disjoint = %v, want 0.0", got)
+	}
+}
+
+func TestSimilarity_TagsOnlyShared_AppliesTagsWeight(t *testing.T) {
+	a := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 1}}
+	b := SessionVector{Artists: []string{"a2"}, Tags: map[string]int{"rock": 5}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if !approxEq(got, 0.7) {
+		t.Errorf("tags-only = %v, want 0.7", got)
+	}
+}
+
+func TestSimilarity_ArtistsOnlyShared_AppliesArtistsWeight(t *testing.T) {
+	a := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 1}}
+	b := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"jazz": 1}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if !approxEq(got, 0.3) {
+		t.Errorf("artists-only = %v, want 0.3", got)
+	}
+}
+
+func TestSimilarity_EitherSeed_Returns0(t *testing.T) {
+	v := SessionVector{Artists: []string{"a"}, Tags: map[string]int{"rock": 1}}
+	seed := SessionVector{Seed: true, Artists: []string{"a"}, Tags: map[string]int{"rock": 1}}
+	if got := Similarity(v, seed, DefaultSimilarityWeights); !approxEq(got, 0.0) {
+		t.Errorf("v vs seed = %v, want 0.0", got)
+	}
+	if got := Similarity(seed, v, DefaultSimilarityWeights); !approxEq(got, 0.0) {
+		t.Errorf("seed vs v = %v, want 0.0", got)
+	}
+}
+
+func TestSimilarity_BothEmpty_Returns0NotNaN(t *testing.T) {
+	a := SessionVector{}
+	b := SessionVector{}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if math.IsNaN(got) || !approxEq(got, 0.0) {
+		t.Errorf("empty = %v, want 0.0 (not NaN)", got)
+	}
+}
+
+func TestSimilarity_OneAxisEmptyOneSide_AxisContributesZero(t *testing.T) {
+	a := SessionVector{Tags: map[string]int{"rock": 1}}
+	b := SessionVector{Artists: []string{"a1"}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if !approxEq(got, 0.0) {
+		t.Errorf("one-axis-each = %v, want 0.0", got)
+	}
+}
+
+func TestSimilarity_PartialTagsOverlap(t *testing.T) {
+	a := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 1, "indie": 1}}
+	b := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 1, "jazz": 1}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	want := 0.7*(1.0/3.0) + 0.3*1.0
+	if !approxEq(got, want) {
+		t.Errorf("partial = %v, want %v", got, want)
+	}
+}
+
+func TestSimilarity_BagOfCountsCollapsesToSet(t *testing.T) {
+	a := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 2, "indie": 1}}
+	b := SessionVector{Artists: []string{"a1"}, Tags: map[string]int{"rock": 5, "indie": 3}}
+	got := Similarity(a, b, DefaultSimilarityWeights)
+	if !approxEq(got, 1.0) {
+		t.Errorf("set-collapse = %v, want 1.0", got)
+	}
+}