Blame view

scripts/evaluation/eval_framework/reports.py 1.95 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
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
  
  
  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",
          "",
      ]
      for key, value in sorted((payload.get("aggregate_metrics") or {}).items()):
          lines.append(f"- {key}: {value}")
      distribution = payload.get("aggregate_distribution") or {}
      if distribution:
          lines.extend(
              [
                  "",
                  "## Label Distribution",
                  "",
a345b01f   tangwang   eval framework
32
33
34
                  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...
35
36
37
38
39
40
41
42
43
44
                  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("")
          for key, value in sorted((item.get("metrics") or {}).items()):
              lines.append(f"- {key}: {value}")
          distribution = item.get("distribution") or {}
a345b01f   tangwang   eval framework
45
46
47
          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...
48
49
50
          lines.append(f"- Irrelevant: {distribution.get(RELEVANCE_IRRELEVANT, 0)}")
          lines.append("")
      return "\n".join(lines)