From 2e9b8db645dbea19019e861a10dc4b8dcc8ba4dc Mon Sep 17 00:00:00 2001
From: Arzaan <25bee110@nith.ac.in>
Date: Wed, 3 Jun 2026 03:08:29 +0530
Subject: [PATCH] Fix region dummy variables - only 3 columns were created

Changed drop_first=True to False and dropped region_northeast as reference category.
---
 insurance.ipynb | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/insurance.ipynb b/insurance.ipynb
index bc89d6a..791426c 100644
--- a/insurance.ipynb
+++ b/insurance.ipynb
@@ -1517,7 +1517,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_cleaned = pd.get_dummies(df_cleaned,columns = ['region'],drop_first=True)"
+    "df_cleaned = pd.get_dummies(df_cleaned, columns=['region'], drop_first=False)",
+    "df_cleaned = df_cleaned.drop(columns=['region_northeast'])  # northeast as reference"
    ]
   },
   {