张宗平
40ec960cf8
Critical eval-pipeline bugs found while running the stage-2 model:
1. parse_anomaly_segments only recognized {"segments\:[[s,e]]}; the training
data (data/instruct.py) emits {"anomaly_regions":[{"start","end"}]}.
The model learned the correct format but scored 0 → VUS-PR=0. Now accepts
both schemas + a balanced-brace JSON scanner (the flat regex could not
match nested objects the model emits).
2. qa_judge._extract_json had the same nesting bug — reuse the scanner.
3. Generation truncated at 64-96 tokens (too short for stats JSON) → bumped
to 192 in report + instruct_check.
Report enhancements:
- wire the pure-LLM baseline (series-as-text, no TS modality) so design §5.4
'model vs pure LLM' is actually computed. Heavy predictors built/evaluated
one at a time with GPU cleanup (single 12GB card).
- add QA-judge table across all 6 categories (design §6.5 问答均分).
- add --pure_llm / --max_per_cat flags.
Results (reports/eval-2026-06-30.md): model QA-judge mean 2.45 vs pure_llm
0.88 (2.8x); anomaly localization (VUS-PR) is the weak point — neither
model nor pure_llm localize well; TS-modality ablation change_rate 0.98.
124 lines
4.6 KiB
Python
124 lines
4.6 KiB
Python
"""Tests for eval/parse_answer.py (T5.1)."""
|
|
import json
|
|
|
|
import numpy as np
|
|
|
|
from tsmm.eval.parse_answer import parse_anomaly_segments, answer_to_point_scores
|
|
|
|
|
|
class TestParseSegments:
|
|
def test_clean_json(self):
|
|
text = '{"segments": [[10, 20], [30, 40]], "type": "spike"}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(10, 20), (30, 40)]
|
|
|
|
def test_json_in_prose(self):
|
|
text = 'The anomalies are: {"segments": [[5, 8]], "type":"level_shift"} per your request.'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(5, 8)]
|
|
|
|
def test_nested_brackets(self):
|
|
text = '{"segments": [[320, 360]], "type":"spike", "score":0.9}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(320, 360)]
|
|
|
|
def test_multiple_json_objects(self):
|
|
# when multiple JSON-ish blobs exist, take the one with a segments key
|
|
text = 'some text {"foo": 1} then {"segments":[[1,2]]}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(1, 2)]
|
|
|
|
def test_no_json_returns_empty_fail(self):
|
|
text = "I cannot find any anomaly."
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is False
|
|
assert segs == []
|
|
|
|
def test_malformed_json_fallback_to_regex(self):
|
|
# if JSON parse fails but [s,e] patterns exist, regex-extract them
|
|
text = 'anomalies at [100, 150] and [200, 250]'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
# ok=False because no valid JSON, but segments extracted via fallback
|
|
assert segs == [(100, 150), (200, 250)]
|
|
|
|
def test_anomaly_regions_schema(self):
|
|
# the schema data/instruct.py actually emits (nested, start/end objects)
|
|
text = '{"anomaly_regions": [{"start": 10, "end": 93}, {"start": 245, "end": 286}], "n_regions": 2}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(10, 93), (245, 286)]
|
|
|
|
def test_anomaly_regions_in_prose(self):
|
|
text = 'Based on the series: {"anomaly_regions": [{"start": 5, "end": 8}]} done.'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(5, 8)]
|
|
|
|
def test_segments_with_start_end_objects(self):
|
|
# also accept the {start,end} object form under the 'segments' key
|
|
text = '{"segments": [{"start": 1, "end": 4}]}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == [(1, 4)]
|
|
|
|
def test_balanced_json_handles_nested(self):
|
|
from tsmm.eval.parse_answer import _extract_balanced_json
|
|
text = 'x {"a": {"b": 1}, "c": [2,3]} y {"d": 4}'
|
|
blobs = _extract_balanced_json(text)
|
|
# outer nested object + the flat one, but NOT the inner {"b":1} alone
|
|
assert any('"a"' in b and '"b"' in b for b in blobs)
|
|
assert '{"d": 4}' in blobs
|
|
|
|
def test_empty_segments_list(self):
|
|
text = '{"segments": [], "type": "none"}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
assert segs == []
|
|
|
|
def test_single_int_segment(self):
|
|
# segments might be [start] only or [[s]] — be lenient
|
|
text = '{"segments": [[42]]}'
|
|
segs, ok = parse_anomaly_segments(text)
|
|
assert ok is True
|
|
# single-element segment treated as point
|
|
assert segs == [(42, 42)]
|
|
|
|
|
|
class TestAnswerToPointScores:
|
|
def test_basic(self):
|
|
text = '{"segments": [[2, 5]]}'
|
|
scores, ok = answer_to_point_scores(text, T=10)
|
|
assert ok is True
|
|
assert scores.shape == (10,)
|
|
assert list(scores) == [0, 0, 1, 1, 1, 1, 0, 0, 0, 0]
|
|
|
|
def test_multiple_segments(self):
|
|
text = '{"segments": [[0, 2], [7, 9]]}'
|
|
scores, ok = answer_to_point_scores(text, T=10)
|
|
assert ok is True
|
|
assert list(scores) == [1, 1, 1, 0, 0, 0, 0, 1, 1, 1]
|
|
|
|
def test_no_anomaly_all_zero(self):
|
|
text = '{"segments": []}'
|
|
scores, ok = answer_to_point_scores(text, T=8)
|
|
assert ok is True
|
|
assert float(scores.sum()) == 0.0
|
|
|
|
def test_parse_fail_all_zero(self):
|
|
text = "no idea"
|
|
scores, ok = answer_to_point_scores(text, T=8)
|
|
assert ok is False
|
|
assert scores.shape == (8,)
|
|
assert float(scores.sum()) == 0.0
|
|
|
|
def test_clips_to_T(self):
|
|
# segment beyond T is clipped
|
|
text = '{"segments": [[5, 100]]}'
|
|
scores, ok = answer_to_point_scores(text, T=10)
|
|
assert ok is True
|
|
assert float(scores.sum()) == 5.0 # indices 5..9
|