Update src/streamlit_app.py

src/streamlit_app.py

@@ -42,6 +42,26 @@ input_data = {
 # Convert the input data to a DataFrame
 input_df = pd.DataFrame(input_data)
 
+# Custom transformer to replace 'reg' with 'Regular' in Product_Sugar_Content
+class SugarContentReplacer(BaseEstimator, TransformerMixin):
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        X = X.copy()
+        X['Product_Sugar_Content'] = X['Product_Sugar_Content'].replace('reg', 'Regular')
+        return X
+
+    # Add get_feature_names_out method
+    def get_feature_names_out(self, input_features=None):
+        if input_features is None:
+            # Assuming the transformer operates on a single column if input_features is not provided
+            return ['Product_Sugar_Content']
+        else:
+            # Return the input feature names as the output feature names
+            return input_features
+
+
 # Convert categorical columns to category type
 input_df['Product_Sugar_Content'] = input_df['Product_Sugar_Content'].astype('category')
 input_df['Product_Type'] = input_df['Product_Type'].astype('category')
@@ -50,6 +70,7 @@ input_df['Store_Size'] = input_df['Store_Size'].astype('category')
 input_df['Store_Location_City_Type'] = input_df['Store_Location_City_Type'].astype('category')
 input_df['Store_Type'] = input_df['Store_Type'].astype('category')
 
+
 # Make predictions
 if st.button("Predict"):
     predictions = model.predict(input_df)