Anydoc / anydoc parser engine (push) Canceled after 0s
App / Format, vet, test, and build (push) Canceled after 0s
CLI / test (macos-latest / go 1.26) (push) Canceled after 0s
CLI / test (ubuntu-latest / go 1.26) (push) Canceled after 0s
CLI / test (windows-latest / go 1.26) (push) Canceled after 0s
Build and Push Docker Image / build-ui (push) Canceled after 0s
Build and Push Docker Image / build-docreader (push) Canceled after 0s
Build and Push Docker Image / build-sandbox (push) Canceled after 0s
Build and Push Docker Image / build-app (amd64, linux/amd64, ubuntu-latest) (push) Canceled after 0s
Build and Push Docker Image / build-app (arm64, linux/arm64, ubuntu-24.04-arm) (push) Canceled after 0s
DocReader / Python tests and Go client tests (push) Canceled after 0s
Build & Publish (dsh-weknora) / Typecheck, test, pack (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (pinned) (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (latest, advisory) (push) Canceled after 0s
Frontend / Test, type-check, and build (push) Canceled after 0s
Go Lint Cache / warm lint cache (.) (push) Canceled after 0s
Go Lint Cache / warm lint cache (cli) (push) Canceled after 0s
Go Lint Cache / warm lint cache (client) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.10) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.11) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.12) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.13) (push) Canceled after 0s
Build and Push Docker Image / merge (push) Canceled after 0s
Build & Publish (dsh-weknora) / Publish to npm (push) Canceled after 0s
Build & Publish (mcp-server) / Build sdist + wheel (push) Canceled after 0s
Build & Publish (mcp-server) / Publish to PyPI (push) Canceled after 0s
86 lines
1.7 KiB
Go
86 lines
1.7 KiB
Go
package metric
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/Tencent/WeKnora/internal/types"
|
|
)
|
|
|
|
func TestMAPMetric_Compute(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
input *types.MetricInput
|
|
expected float64
|
|
}{
|
|
{
|
|
name: "total match",
|
|
input: &types.MetricInput{
|
|
RetrievalGT: [][]int{{2, 4, 6}},
|
|
RetrievalIDs: []int{2, 4, 6},
|
|
},
|
|
expected: 1.0,
|
|
},
|
|
{
|
|
name: "no match",
|
|
input: &types.MetricInput{
|
|
RetrievalGT: [][]int{{1, 2}},
|
|
RetrievalIDs: []int{3, 4},
|
|
},
|
|
expected: 0.0,
|
|
},
|
|
{
|
|
name: "partial match",
|
|
input: &types.MetricInput{
|
|
RetrievalGT: [][]int{{1, 2, 3}},
|
|
RetrievalIDs: []int{2, 5, 1, 3},
|
|
},
|
|
// AP = (1/1 + 2/3 + 3/4)/3 ≈ 0.80555555
|
|
expected: 0.8055555555555555,
|
|
},
|
|
{
|
|
name: "empty ground truth",
|
|
input: &types.MetricInput{
|
|
RetrievalGT: [][]int{},
|
|
RetrievalIDs: []int{1, 2},
|
|
},
|
|
expected: 0.0,
|
|
},
|
|
{
|
|
name: "multiple queries",
|
|
input: &types.MetricInput{
|
|
RetrievalGT: [][]int{
|
|
{1, 2},
|
|
{3, 4},
|
|
},
|
|
RetrievalIDs: []int{1, 3, 2, 4},
|
|
},
|
|
// Query1 AP: (1/1 + 2/3)/2 ≈ 0.8333
|
|
// Query2 AP: (1/2 + 2/4)/2 = 0.5
|
|
// MAP: (0.8333 + 0.5)/2 ≈ 0.6667
|
|
expected: 0.6666666666666666,
|
|
},
|
|
}
|
|
|
|
metric := NewMAPMetric()
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := metric.Compute(tt.input)
|
|
if !almostEqual(got, tt.expected, 1e-6) {
|
|
t.Errorf("Compute() = %v, want %v", got, tt.expected)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// Helper function to compare floating point numbers with tolerance
|
|
func almostEqual(a, b, tolerance float64) bool {
|
|
if a == b {
|
|
return true
|
|
}
|
|
diff := a - b
|
|
if diff < 0 {
|
|
diff = -diff
|
|
}
|
|
return diff < tolerance
|
|
}
|