lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ver Jan5th

Browse Source 
debugged
This commit is contained in:
David Chang
2024-01-05 15:20:47 +08:00
parent 5fedf5b891
commit eeb8a120d6
17 changed files with 158 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
desktop_env/evaluators/metrics/general.py
View File

@@ -18,13 +18,13 @@ def check_csv(result: str, rules: Dict[str, List[Dict[str, str]]]) -> float:
float
"""
expect_metrics = [False] * len(rules["except"])
expect_metrics = [False] * len(rules.get("expect", []))
unexpect_metric = True
with open(result) as f:
reader = csv.DictReader(f)
for rcd in reader:
for i, r in enumerate(rules["expect"]):
for i, r in enumerate(rules.get("expect", [])):
expect_metrics[i] = expect_metrics[i] or _match_record(r, rcd)
unexpect_metric = unexpect_metric and all(_match_record(r, rcd) for r in rules["unexpect"])
unexpect_metric = unexpect_metric and all(_match_record(r, rcd) for r in rules.get("unexpect", []))
return float(all(expect_metrics) and unexpect_metric)