Blame view

scripts/evaluation/eval_framework/reports.py 2.64 KB
c81b0fc1   tangwang   scripts/evaluatio...
1
2
3
4
5
6
  """Markdown and text reports for batch evaluation."""
  
  from __future__ import annotations
  
  from typing import Any, Dict
  
a345b01f   tangwang   eval framework
7
  from .constants import RELEVANCE_EXACT, RELEVANCE_HIGH, RELEVANCE_IRRELEVANT, RELEVANCE_LOW
c81b0fc1   tangwang   scripts/evaluatio...
8
9
  
  
7ddd4cb3   tangwang   评估体系从三等级->四等级 Exa...
10
11
12
13
14
15
16
17
18
19
20
21
22
  def _append_metric_block(lines: list[str], metrics: Dict[str, Any]) -> None:
      primary_keys = ("NDCG@5", "NDCG@10", "NDCG@20", "Exact_Precision@10", "Strong_Precision@10", "Gain_Recall@50")
      included = set()
      for key in primary_keys:
          if key in metrics:
              lines.append(f"- {key}: {metrics[key]}")
              included.add(key)
      for key, value in sorted(metrics.items()):
          if key in included:
              continue
          lines.append(f"- {key}: {value}")
  
  
c81b0fc1   tangwang   scripts/evaluatio...
23
24
25
26
27
28
29
30
31
32
33
34
35
  def render_batch_report_markdown(payload: Dict[str, Any]) -> str:
      lines = [
          "# Search Batch Evaluation",
          "",
          f"- Batch ID: {payload['batch_id']}",
          f"- Created at: {payload['created_at']}",
          f"- Tenant ID: {payload['tenant_id']}",
          f"- Query count: {len(payload['queries'])}",
          f"- Top K: {payload['top_k']}",
          "",
          "## Aggregate Metrics",
          "",
      ]
7ddd4cb3   tangwang   评估体系从三等级->四等级 Exa...
36
37
38
39
40
41
42
43
44
45
      metric_context = payload.get("metric_context") or {}
      if metric_context:
          lines.extend(
              [
                  f"- Primary metric: {metric_context.get('primary_metric', 'N/A')}",
                  f"- Gain scheme: {metric_context.get('gain_scheme', {})}",
                  "",
              ]
          )
      _append_metric_block(lines, payload.get("aggregate_metrics") or {})
c81b0fc1   tangwang   scripts/evaluatio...
46
47
48
49
50
51
52
      distribution = payload.get("aggregate_distribution") or {}
      if distribution:
          lines.extend(
              [
                  "",
                  "## Label Distribution",
                  "",
a345b01f   tangwang   eval framework
53
54
55
                  f"- Exact Match: {distribution.get(RELEVANCE_EXACT, 0)}",
                  f"- High Relevant: {distribution.get(RELEVANCE_HIGH, 0)}",
                  f"- Low Relevant: {distribution.get(RELEVANCE_LOW, 0)}",
c81b0fc1   tangwang   scripts/evaluatio...
56
57
58
59
60
61
62
                  f"- Irrelevant: {distribution.get(RELEVANCE_IRRELEVANT, 0)}",
              ]
          )
      lines.extend(["", "## Per Query", ""])
      for item in payload.get("per_query") or []:
          lines.append(f"### {item['query']}")
          lines.append("")
7ddd4cb3   tangwang   评估体系从三等级->四等级 Exa...
63
          _append_metric_block(lines, item.get("metrics") or {})
c81b0fc1   tangwang   scripts/evaluatio...
64
          distribution = item.get("distribution") or {}
a345b01f   tangwang   eval framework
65
66
67
          lines.append(f"- Exact Match: {distribution.get(RELEVANCE_EXACT, 0)}")
          lines.append(f"- High Relevant: {distribution.get(RELEVANCE_HIGH, 0)}")
          lines.append(f"- Low Relevant: {distribution.get(RELEVANCE_LOW, 0)}")
c81b0fc1   tangwang   scripts/evaluatio...
68
69
70
          lines.append(f"- Irrelevant: {distribution.get(RELEVANCE_IRRELEVANT, 0)}")
          lines.append("")
      return "\n".join(lines)