AIRegulation/siemens_ragas
7
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update for ragas

Browse Source
This commit is contained in:
wangwei
2026-07-01 17:53:00 +08:00
parent 2bb804b059
commit 4e74e1b247
15 changed files with 507 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_metric_presenter.py
+20 -1
View File
@@ -40,7 +40,14 @@ const result = {{
desc: p.describeMetric("faithfulness"),
noiseDesc: p.describeMetric("noise_sensitivity"),
noiseBin: p.binColor("noise_sensitivity", 0.0),
faithBin: p.binColor("faithfulness", 0.8)
faithBin: p.binColor("faithfulness", 0.8),
lowerBetterNoise: p.isLowerBetter("noise_sensitivity"),
lowerBetterFaith: p.isLowerBetter("faithfulness"),
upHigher: p.deltaInfo("faithfulness", 0.80, 0.60),
downHigher: p.deltaInfo("faithfulness", 0.60, 0.80),
noiseImproved: p.deltaInfo("noise_sensitivity", 0.10, 0.30),
noiseWorse: p.deltaInfo("noise_sensitivity", 0.30, 0.10),
noBaseline: p.deltaInfo("faithfulness", 0.80, null)
}};
console.log(JSON.stringify(result));
"""
@@ -55,6 +62,15 @@ console.log(JSON.stringify(result));
assert '"noiseDesc":"' in output
assert '"noiseBin":"#16a34a"' in output
assert '"faithBin":"#16a34a"' in output
assert '"lowerBetterNoise":true' in output
assert '"lowerBetterFaith":false' in output
# higher-better: rising value is an improvement (green ▲); falling is a regression (red ▼)
assert '"upHigher":{"hasData":true,"delta":0.2,"improved":true,"arrow":"▲","magnitude":"0.20","cls":"delta-good"}' in output
assert '"downHigher":{"hasData":true,"delta":-0.2,"improved":false,"arrow":"▼","magnitude":"0.20","cls":"delta-bad"}' in output
# noise_sensitivity (lower-better): falling value is an improvement (green ▼)
assert '"noiseImproved":{"hasData":true,"delta":-0.2,"improved":true,"arrow":"▼","magnitude":"0.20","cls":"delta-good"}' in output
assert '"noiseWorse":{"hasData":true,"delta":0.2,"improved":false,"arrow":"▲","magnitude":"0.20","cls":"delta-bad"}' in output
assert '"noBaseline":{"hasData":false' in output
def test_report_and_index_load_metric_presenter_helper() -> None:
@@ -66,3 +82,6 @@ def test_report_and_index_load_metric_presenter_helper() -> None:
assert "js/metric_presenter.js" in index_html
assert "MetricPresenter.describeMetric" in report_js
assert "MetricPresenter.scoreClass" in app_js
# history comparison table uses the direction-aware delta helper
assert "MetricPresenter.deltaInfo" in report_js
assert "history-table" in report_js