Update app.py

app.py

@@ -54,8 +54,33 @@ def model_fit(X_train,y_train):
   hgb.fit(X_train,y_train)
   return hgb
 
-df,X_train,X_test,y_train,y_test = final_df(df)
-model = model_fit(X_train,y_train)
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+
+# define the preprocessing steps
+categorical_features = ['Company Name', 'Model Name', 'Location', 'Engine Type', 'Color', 'Assembly', 'Body Type', 'Transmission Type', 'Registration Status']
+numeric_features = ['Model Year', 'Mileage', 'Engine Capacity']
+
+categorical_transformer = Pipeline(steps=[
+    ('onehot', OneHotEncoder(drop='if_binary', handle_unknown='ignore'))
+])
+
+numeric_transformer = StandardScaler()
+
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', numeric_transformer, numeric_features),
+        ('cat', categorical_transformer, categorical_features)
+    ]
+)
+
+# create the pipeline
+model = Pipeline(steps=[('preprocessor', preprocessor),
+                        ('hgb', HistGradientBoostingRegressor())])
+
+# fit the pipeline
+model.fit(X_train, y_train)
 
 import streamlit as st
 
@@ -74,8 +99,7 @@ def price(companyName,modelName,modelYear,locaiton,mileage,engineType,engineCapa
       'Transmission Type':[transmissionType],
       'Registration Status':[registrationStatus]
   })
-  input_data = pd.get_dummies(input_data, drop_first=True)
-  prediction=model.predict(input_data)[0]
+  prediction = model.predict(input_data)[0]
   return prediction
 st.title('Car Price Prediction:car @yusufenes')
 st.write('Please Chose Car Specifications')