Update app.py

app.py

@@ -1,49 +1,71 @@
 import streamlit as st
+import pandas as pd
 import numpy as np
 from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
 
-# Streamlit page config
+# Streamlit UI
 st.set_page_config(page_title="BigMart Sales Predictor", page_icon="🛒", layout="centered")
+st.title("🛒 BigMart Sales Prediction using Real Dataset")
+st.markdown("Fill in the product details to get a sales prediction.")
 
-st.title("🛒 BigMart Sales Prediction")
-st.markdown("Enter item details below to predict sales:")
+# Load and preprocess dataset
+@st.cache_data
+def load_data():
+    data = pd.read_csv("Train.csv")  # 👈 Make sure Train.csv is in the same directory
+    # Handle missing values
+    data.fillna(data.mean(numeric_only=True), inplace=True)
+    data.fillna("Unknown", inplace=True)
+    
+    # Encode categorical columns
+    label_enc = LabelEncoder()
+    for col in ['Item_Fat_Content', 'Item_Type', 'Outlet_Identifier', 'Outlet_Size', 'Outlet_Location_Type', 'Outlet_Type']:
+        data[col] = label_enc.fit_transform(data[col])
+    return data
+
+df = load_data()
+
+# Select features and target
+features = ['Item_Weight', 'Item_Visibility', 'Item_MRP']
+target = 'Item_Outlet_Sales'
+
+X = df[features]
+y = df[target]
 
-# Input fields
+# Train model
+model = LinearRegression()
+model.fit(X, y)
+
+# Input UI
 product_name = st.text_input("📦 Product Name")
-item_weight = st.number_input("⚖️ Item Weight (in kg)", min_value=0.0, step=0.1)
+item_weight = st.number_input("⚖️ Item Weight (kg)", min_value=0.0, step=0.1)
 item_visibility = st.slider("👀 Item Visibility", 0.0, 1.0, 0.05)
 item_mrp = st.number_input("💰 Item MRP", min_value=0.0, step=1.0)
 
-# Predict button
+# Prediction
 if st.button("Predict Sales"):
     if not product_name:
         st.warning("Please enter a product name.")
     else:
-        # Dummy training data for demo
-        X_train = np.array([
-            [9.3, 0.016, 249.8],
-            [5.92, 0.019, 48.27],
-            [17.5, 0.016, 141.62],
-            [19.2, 0.0075, 182.095],
-        ])
-        y_train = np.array([3735.14, 443.42, 2233.6, 3612.47])  # Target: Item_Outlet_Sales
-
-        # Train model
-        model = LinearRegression()
-        model.fit(X_train, y_train)
-
-        # Prepare user input
         user_input = np.array([[item_weight, item_visibility, item_mrp]])
         predicted_sales = model.predict(user_input)[0]
-
         st.success(f"📈 Predicted Sales for '{product_name}': ₹{predicted_sales:,.2f}")
+        
+        # Optional: Download Prediction
+        result_df = pd.DataFrame({
+            "Product Name": [product_name],
+            "Item Weight": [item_weight],
+            "Item Visibility": [item_visibility],
+            "Item MRP": [item_mrp],
+            "Predicted Sales": [predicted_sales]
+        })
 
-# Sidebar
+        st.download_button("📥 Download Result as CSV", result_df.to_csv(index=False), file_name="prediction.csv", mime="text/csv")
+
+# Sidebar Info
 st.sidebar.title("📌 About")
-st.sidebar.markdown(
-    """
-    This app predicts sales based on item weight, visibility, and MRP using a demo ML model.
-    
-    🔧 Replace with a trained model on BigMart dataset for real-world use!
-    """
-)
+st.sidebar.markdown("""
+This app uses a **real BigMart dataset** from Kaggle and a **Linear Regression model** to predict sales.
+You can customize features or switch to advanced ML models later!
+""")