From 4e6e9c156c62f2932c2b502558f45c53f182cc0c Mon Sep 17 00:00:00 2001 From: cfiutak1 Date: Tue, 2 Apr 2019 01:02:41 -0400 Subject: [PATCH] Update Part 1 - Introduction to Machine Learning with scikit-learn.md --- Part 1 - Introduction to Machine Learning with scikit-learn.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Part 1 - Introduction to Machine Learning with scikit-learn.md b/Part 1 - Introduction to Machine Learning with scikit-learn.md index d1487b2..df3944f 100644 --- a/Part 1 - Introduction to Machine Learning with scikit-learn.md +++ b/Part 1 - Introduction to Machine Learning with scikit-learn.md @@ -77,7 +77,7 @@ Continuing our analogy of studying for a math exam, ### 🤔 Food for Thought -It can be tough to find a good ratio between the training and testing set size. In this case, we split it evenly (`test_size=0.5`), but many algorithms use much smaller testing set sizes (closer to 0.2). Although it may be tempting to improve your algorithm's accuracy by increasing the size of the training set, also consider that this will increase the margin of error of your testing accuracy. +It can be tough to find a good ratio between the training and testing set size. In this case, we split it evenly (`test_size=0.5`), but many algorithms use much smaller testing set sizes (closer to 0.2). Although it may be tempting to improve your algorithm's accuracy by increasing the size of the training set, also consider that this will increase testing accuracy's margin of error. ---