Update src/streamlit_app.py

src/streamlit_app.py

@@ -2,10 +2,13 @@ import streamlit as st
 import pandas as pd
 from datetime import datetime
 import joblib
+from sklearn.base import BaseEstimator, TransformerMixin
+from datetime import datetime
+from transformers import SugarContentReplacer,StoreAgeCalculator  # Import the custom transformer
 
 # Load the trained model
 def load_model():
-    return joblib.load("SuperKart_sales_prediction_model_v1_0.joblib")
+    return joblib.load("src/SuperKart_sales_prediction_model_v1_0.joblib")
 
 model = load_model()
 
@@ -39,21 +42,19 @@ input_data = {
     'Store_Type': [store_type],
 }
 
-# Custom transformer to calculate store age
-class StoreAgeCalculator(BaseEstimator, TransformerMixin):
-    def __init__(self):
-        self.current_year = datetime.now().year
+# Convert the input data to a DataFrame
+input_df = pd.DataFrame(input_data)
 
-    def fit(self, X, y=None):
+# Custom transformer to replace 'reg' with 'Regular' in Product_Sugar_Content
+class SugarContentReplacer(BaseEstimator, TransformerMixin):
+    def fit(self, input_df, y=None):
         return self
 
-    def transform(self, X):
-        X = X.copy()
-        X['Store_Age'] = self.current_year - X['Store_Establishment_Year']
-        return X.drop(columns=['Store_Establishment_Year'])
+    def transform(self, input_df):
+        input_df = input_df.copy()
+        input_df['Product_Sugar_Content'] = input_df['Product_Sugar_Content'].replace('reg', 'Regular')
+        return input_df
 
-# Convert the input data to a DataFrame
-input_df = pd.DataFrame(input_data)
 
 # Convert categorical columns to category type
 input_df['Product_Sugar_Content'] = input_df['Product_Sugar_Content'].astype('category')
@@ -63,6 +64,7 @@ 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)