update threshhold to 97% after measuring 2x 100 runs and getting 3 failures. (#50)

austinworks · web-flow · commit 007358187468 · 2025-03-14T13:43:37.000-07:00
diff --git a/.tool-versions b/.tool-versions
@@ -0,0 +1,2 @@
+python 3.13.2
+uv 0.6.6
diff --git a/examples/team_recommender/tests/example_9_threshold/test_measurement_is_within_threshold.py b/examples/team_recommender/tests/example_9_threshold/test_measurement_is_within_threshold.py
@@ -163,8 +163,8 @@ def test_metrics_within_range():
         )
         results.append(test_runner.run_once(run))
 
-    failure_threshold = 0.9
-    assert generations <= 1 or is_within_expected(
+    failure_threshold = 0.97
+    assert is_within_expected(
         failure_threshold, sum(not result for result in results), generations
     ), f"Expected {failure_threshold} to be within the confidence interval of the success rate"
 

Original file line number	Diff line number	Diff line change
`@@ -163,8 +163,8 @@ def test_metrics_within_range():`
`163`	`163`	`)`
`164`	`164`	`results.append(test_runner.run_once(run))`
`165`	`165`
`166`		`- failure_threshold = 0.9`
`167`		`- assert generations <= 1 or is_within_expected(`
	`166`	`+ failure_threshold = 0.97`
	`167`	`+ assert is_within_expected(`
`168`	`168`	`failure_threshold, sum(not result for result in results), generations`
`169`	`169`	`), f"Expected {failure_threshold} to be within the confidence interval of the success rate"`
`170`	`170`