Update app.py

app.py

@@ -1,166 +1,68 @@
-import re
 import streamlit as st
 import pandas as pd
 import joblib
 
-# ================================
 # Load trained model
-# ================================
-MODEL_PATH = "superkart_sales_prediction_model_v1_0.joblib"
-model = joblib.load(MODEL_PATH)
-
-# ================================
-# Training feature columns (must match training dataset)
-# ================================
-FEATURE_COLUMNS = [
-    "Product_Weight","Product_Allocated_Area","Product_MRP","Store_Age",
-    "Product_Sugar_Content_no sugar","Product_Sugar_Content_regular",
-    "Product_Type_breads","Product_Type_breakfast","Product_Type_canned",
-    "Product_Type_dairy","Product_Type_frozen foods",
-    "Product_Type_fruits and vegetables","Product_Type_hard drinks",
-    "Product_Type_health and hygiene","Product_Type_household",
-    "Product_Type_meat","Product_Type_others","Product_Type_seafood",
-    "Product_Type_snack foods","Product_Type_soft drinks",
-    "Product_Type_starchy foods",
-    "Store_Size_medium","Store_Size_small",
-    "Store_Location_City_Type_tier 2","Store_Location_City_Type_tier 3",
-    "Store_Id_out002","Store_Id_out003","Store_Id_out004",
-    "Store_Type_food mart","Store_Type_supermarket type1","Store_Type_supermarket type2",
-    "Product_Group_Code_fd","Product_Group_Code_nc"
-]
-
-# ================================
-# Store metadata
-# ================================
-valid_store_ids = ["OUT001", "OUT002", "OUT003", "OUT004"]
-store_meta = {
-    "OUT001": {"year": 1987, "size": "High",   "city_type": "Tier 2", "store_type": "Supermarket Type1"},
-    "OUT002": {"year": 1998, "size": "Small",  "city_type": "Tier 3", "store_type": "Food Mart"},
-    "OUT003": {"year": 1999, "size": "Medium", "city_type": "Tier 1", "store_type": "Departmental Store"},
-    "OUT004": {"year": 2009, "size": "Medium", "city_type": "Tier 2", "store_type": "Supermarket Type2"},
-}
-
-# ================================
-# Preprocessing function
-# ================================
-def preprocess_input(user_inputs):
-    """Convert raw form inputs into one-hot encoded feature vector."""
-    row = dict.fromkeys(FEATURE_COLUMNS, 0)
-
-    # Numeric
-    row["Product_Weight"] = user_inputs["Product_Weight"]
-    row["Product_Allocated_Area"] = user_inputs["Product_Allocated_Area"]
-    row["Product_MRP"] = user_inputs["Product_MRP"]
-    row["Store_Age"] = 2025 - user_inputs["Store_Establishment_Year"]
-
-    # Sugar content
-    if user_inputs["Product_Sugar_Content"].lower() == "no sugar":
-        row["Product_Sugar_Content_no sugar"] = 1
-    elif user_inputs["Product_Sugar_Content"].lower() == "regular":
-        row["Product_Sugar_Content_regular"] = 1
-    # (low sugar is baseline → all zeros)
-
-    # Product type
-    col_name = f"Product_Type_{user_inputs['Product_Type'].lower()}"
-    if col_name in row:
-        row[col_name] = 1
-
-    # Store size
-    if user_inputs["Store_Size"].lower() == "medium":
-        row["Store_Size_medium"] = 1
-    elif user_inputs["Store_Size"].lower() == "small":
-        row["Store_Size_small"] = 1
-    # (high = baseline)
-
-    # Store location
-    if user_inputs["Store_Location_City_Type"].lower() == "tier 2":
-        row["Store_Location_City_Type_tier 2"] = 1
-    elif user_inputs["Store_Location_City_Type"].lower() == "tier 3":
-        row["Store_Location_City_Type_tier 3"] = 1
-    # (tier 1 = baseline)
-
-    # Store ID
-    if user_inputs["Store_Id"].lower() == "out002":
-        row["Store_Id_out002"] = 1
-    elif user_inputs["Store_Id"].lower() == "out003":
-        row["Store_Id_out003"] = 1
-    elif user_inputs["Store_Id"].lower() == "out004":
-        row["Store_Id_out004"] = 1
-    # (out001 = baseline)
-
-    # Store Type
-    if user_inputs["Store_Type"].lower() == "food mart":
-        row["Store_Type_food mart"] = 1
-    elif user_inputs["Store_Type"].lower() == "supermarket type1":
-        row["Store_Type_supermarket type1"] = 1
-    elif user_inputs["Store_Type"].lower() == "supermarket type2":
-        row["Store_Type_supermarket type2"] = 1
-    # (departmental store = baseline)
-
-    # Product group code (dummy rule: FD → food, NC → non-consumable)
-    if user_inputs["Product_Id"].startswith("FD"):
-        row["Product_Group_Code_fd"] = 1
-    else:
-        row["Product_Group_Code_nc"] = 1
-
-    return pd.DataFrame([row], columns=FEATURE_COLUMNS)
-
-# ================================
-# Streamlit UI
-# ================================
-st.title("SmartKart: Product Sales Prediction")
-st.subheader("Online Prediction")
-
-# Product ID validation
-product_id = st.text_input("Product ID (2 uppercase letters + 4 digits, e.g., FD6114)", max_chars=6)
-product_id_valid = bool(re.fullmatch(r"[A-Z]{2}\d{4}", product_id))
-if product_id and not product_id_valid:
-    st.error("Invalid Product ID format; it must be 2 uppercase letters followed by 4 digits.")
-elif product_id_valid:
-    st.success("Product ID format is valid.")
-
-# Store selection
-store_id = st.selectbox("Store ID", options=valid_store_ids)
-meta = store_meta[store_id]
-st.text(f"Store Establishment Year: {meta['year']}")
-st.text(f"Store Size: {meta['size']}")
-st.text(f"Store Location City Type: {meta['city_type']}")
-st.text(f"Store Type: {meta['store_type']}")
-
-# Product features
-product_weight = st.number_input("Product Weight", min_value=0.0, value=12.0, format="%.2f")
-product_sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
-product_allocated_area = st.slider("Product Allocated Area Ratio", min_value=0.0, max_value=1.0, step=0.001, value=0.05)
-product_type = st.selectbox("Product Type", [
-    "Meat", "Snack Foods", "Hard Drinks", "Dairy", "Canned", "Soft Drinks",
-    "Health and Hygiene", "Baking Goods", "Bread", "Breakfast", "Frozen Foods",
-    "Fruits and Vegetables", "Household", "Seafood", "Starchy Foods", "Others"
-])
-product_mrp = st.number_input("Product MRP", min_value=0.0, value=150.0, format="%.2f")
-
-# Collect inputs
-user_inputs = {
-    "Product_Id": product_id,
+@st.cache_resource
+def load_model():
+    return joblib.load("superkart_sales_prediction_model_v1_0.joblib")
+
+model = load_model()
+
+st.set_page_config(page_title="SuperKart Sales Predictor", layout="wide")
+st.title("🛒 SuperKart Sales Prediction App")
+
+st.write("Fill in the product and store details below to predict sales.")
+
+# Input fields
+col1, col2 = st.columns(2)
+
+with col1:
+    product_weight = st.number_input("Product Weight", min_value=0.0, step=0.01)
+    product_allocated_area = st.number_input("Product Allocated Area", min_value=0.0, step=0.001)
+    product_mrp = st.number_input("Product MRP", min_value=0.0, step=0.01)
+    product_store_sales_total = st.number_input("Product Store Sales Total", min_value=0.0, step=0.01)
+    store_age = st.number_input("Store Age (Years)", min_value=0, step=1)
+
+with col2:
+    product_sugar_content = st.selectbox("Sugar Content", ["no sugar", "regular"])
+    product_type = st.selectbox(
+        "Product Type",
+        ["breads", "breakfast", "canned", "dairy", "frozen foods",
+         "fruits and vegetables", "hard drinks", "health and hygiene",
+         "household", "meat", "others", "seafood", "snack foods",
+         "soft drinks", "starchy foods"]
+    )
+    store_size = st.selectbox("Store Size", ["small", "medium"])
+    store_location_city_type = st.selectbox("Store Location City Type", ["tier 2", "tier 3"])
+    store_type = st.selectbox("Store Type", ["food mart", "supermarket type1", "supermarket type2"])
+    product_group_code = st.selectbox("Product Group Code", ["fd", "nc"])
+
+# Convert inputs to DataFrame
+input_data = {
     "Product_Weight": product_weight,
-    "Product_Sugar_Content": product_sugar_content,
     "Product_Allocated_Area": product_allocated_area,
-    "Product_Type": product_type,
     "Product_MRP": product_mrp,
-    "Store_Id": store_id,
-    "Store_Establishment_Year": meta['year'],
-    "Store_Size": meta['size'],
-    "Store_Location_City_Type": meta['city_type'],
-    "Store_Type": meta['store_type'],
+    "Product_Store_Sales_Total": product_store_sales_total,
+    "Store_Age": store_age,
+    f"Product_Sugar_Content_{product_sugar_content}": True,
+    f"Product_Type_{product_type}": True,
+    f"Store_Size_{store_size}": True,
+    f"Store_Location_City_Type_{store_location_city_type}": True,
+    f"Store_Type_{store_type}": True,
+    f"Product_Group_Code_{product_group_code}": True
 }
 
-# Predict button
+input_df = pd.DataFrame([input_data]).astype(object)
+
+# Align with model features
+if hasattr(model, "feature_names_in_"):
+    input_df = input_df.reindex(columns=model.feature_names_in_, fill_value=0)
+
+# Prediction
 if st.button("Predict"):
-    if not product_id_valid:
-        st.error("Please fix the Product ID before proceeding.")
-    else:
-        try:
-            processed = preprocess_input(user_inputs)
-            prediction = model.predict(processed)[0]
-            st.success(f"Predicted Product Sales: {prediction:.2f}")
-        except Exception as e:
-            st.error(f"Prediction failed: {e}")
+    try:
+        prediction = model.predict(input_df)[0]
+        st.success(f"Predicted Product Sales: {prediction:.2f}")
+    except Exception as e:
+        st.error(f"Prediction failed: {e}")