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)
|