From 138ec4925c495ecc55900351bd66f3a74a4501e2 Mon Sep 17 00:00:00 2001 From: J Kim Date: Mon, 8 Jun 2026 10:40:19 -0400 Subject: [PATCH] Fixing typo 44% -> 42% --- notebooks/ML_EPMT_2026.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebooks/ML_EPMT_2026.md b/notebooks/ML_EPMT_2026.md index c7f58190..8e174b15 100644 --- a/notebooks/ML_EPMT_2026.md +++ b/notebooks/ML_EPMT_2026.md @@ -15,7 +15,7 @@ This document also exists for the purpose of making it easier for me to one day Unfortunately, this work failed to produce a model that predicts cpu_time well. The best $R^2$ results were 0.42 using the HistGradientBoostingRegressor. -While this exploratory phase did not yield a model ready for production, it successfully established a strong baseline. This successfully explains 44% of the variance in CPU utilization. However, this may suggest that a significant portion of `cpu_time` variance is likely driven by features not yet explored from or not yet captured by the EPMT database. +While this exploratory phase did not yield a model ready for production, it successfully established a strong baseline. This successfully explains 42% of the variance in CPU utilization. However, this may suggest that a significant portion of `cpu_time` variance is likely driven by features not yet explored from or not yet captured by the EPMT database. ## Dataset Curation & Features