Update app.py

app.py

@@ -4,15 +4,18 @@ from sklearn.preprocessing import LabelEncoder
 import gradio as gr
 import numpy as np
 
-
 # Load the data
 df = pd.read_csv('insurance_data.csv')
 
 # Convert categorical columns to numeric using Label Encoding
-le = LabelEncoder()
-df['sex'] = le.fit_transform(df['sex'])
-df['smoker'] = le.fit_transform(df['smoker'])
-df['region'] = le.fit_transform(df['region'])
+le_sex = LabelEncoder()
+df['sex'] = le_sex.fit_transform(df['sex'])
+
+le_smoker = LabelEncoder()
+df['smoker'] = le_smoker.fit_transform(df['smoker'])
+
+le_region = LabelEncoder()
+df['region'] = le_region.fit_transform(df['region'])
 
 # Split the data into features (X) and target (y)
 X = df.drop('expenses', axis=1)
@@ -33,9 +36,9 @@ def categorize_expense(expense):
 
 # Define prediction function
 def predict_risk(age, sex, bmi, children, smoker, region):
-    sex = le.transform([sex])[0]  # encode 'sex'
-    smoker = le.transform([smoker])[0]  # encode 'smoker'
-    region = le.transform([region])[0]  # encode 'region'
+    sex = le_sex.transform([sex])[0]  # encode 'sex'
+    smoker = le_smoker.transform([smoker])[0]  # encode 'smoker'
+    region = le_region.transform([region])[0]  # encode 'region'
     expense = model.predict(np.array([age, sex, bmi, children, smoker, region]).reshape(1, -1))[0]
     return categorize_expense(expense)