From 2a461752451fc449c8a6a2298b86e9b1513f5237 Mon Sep 17 00:00:00 2001
From: ben-jaynes <1btjaynes@gmail.com>
Date: Thu, 21 May 2026 18:33:15 -0700
Subject: [PATCH] vault backup: 2026-05-21 18:33:15

---
 .obsidian/graph.json                                   |  2 +-
 .../Class 5-21 (Ensemble Models).md                    | 10 +++++++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/.obsidian/graph.json b/.obsidian/graph.json
index 67663a8..fe44a4b 100644
--- a/.obsidian/graph.json
+++ b/.obsidian/graph.json
@@ -17,6 +17,6 @@
   "repelStrength": 10,
   "linkStrength": 1,
   "linkDistance": 250,
-  "scale": 0.2022585800147419,
+  "scale": 0.1719770322750558,
   "close": true
 }
\ No newline at end of file
diff --git a/Running Start/CSB320 - Machine Learning Concepts/Class 5-21 (Ensemble Models).md b/Running Start/CSB320 - Machine Learning Concepts/Class 5-21 (Ensemble Models).md
index 19ca47a..a9daa0a 100644
--- a/Running Start/CSB320 - Machine Learning Concepts/Class 5-21 (Ensemble Models).md	
+++ b/Running Start/CSB320 - Machine Learning Concepts/Class 5-21 (Ensemble Models).md	
@@ -5,4 +5,12 @@
 	- sampling is random
 	- Out of bag sample
 		- data that was never picked in bootstrapping
-		- 
\ No newline at end of file
+		- is often used for testing data (OOB samples were not in the training samples so the model has never seen them)
+		- with common techniques often ~30% of data is not picked (and forms OOB set)
+	- distribution of classes with bootstrapping will form a Gaussian distribution
+	- when enough samples are used bootstrap distributions will approximate population statistics
+		- Assumption is made with bootstrapping that the sample approximates the original population
+	- bootstrap samples are used as training sets, OOB samples serve as testing sets
+```python
+bootstrap_samples = [resample(df, replace=True, random_state=i) for i in range(5)]
+```