Upload folder using huggingface_hub

app.py

@@ -1,97 +1,158 @@
 
 import streamlit as st
 import pandas as pd
-
-# Custom module imports
-from predictor.batch_handler import get_predictions, get_single_prediction
-from predictor.chart_plotter import plot_actual_vs_predicted
-from predictor.utils import reorder_columns, get_csv_download
+import requests
+import altair as alt
 
 st.set_page_config(page_title="SuperKart Sales Predictor", layout="wide")
 
-# App header
-st.markdown("## 🛒 SuperKart Sales Predictor")
-st.write("Use the tabs below to predict sales for a single product or upload a CSV file for batch prediction.")
+st.title("🛒 SuperKart Sales Predictor")
+st.markdown("Use the tabs below to predict sales for a single product or upload a CSV file for batch prediction.")
 
-# Define tabs
+# Create two tabs
 tab1, tab2 = st.tabs(["🔍 Single Prediction", "📄 Batch Prediction"])
 
-# 🔍 TAB 1: Single Prediction
+# ----------------- Tab 1: Single Prediction -----------------
 with tab1:
-    st.subheader("🔍 Enter Product Details for Prediction")
-
-    with st.form("single_form"):
-        col1, col2 = st.columns(2)
-
-        with col1:
-            product_weight = st.number_input("Product Weight (kg)", min_value=0.0)
-            sugar_content = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
-            allocated_area = st.number_input("Allocated Area (m²)", min_value=0.0)
-            product_type = st.selectbox("Product Type", ["Dairy", "Canned", "Frozen Foods", "Health and Hygiene", "Baking Goods"])
-
-        with col2:
-            mrp = st.number_input("Product MRP (₹)", min_value=0.0)
-            store_id = st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"])
-            store_year = st.number_input("Establishment Year", min_value=1980, max_value=2025)
+    col1, col2 = st.columns(2)
+
+    with col1:
+        with st.expander("📦 Product Details", expanded=True):
+            product_weight = st.slider("Product Weight (kg)", 4.0, 22.0, 12.65, 0.1)
+            product_allocated_area = st.slider("Allocated Shelf Area", 0.0, 0.3, 0.07, 0.01)
+            product_mrp = st.slider("Product MRP", 31.0, 266.0, 147.0)
+            product_sugar_content = st.radio("Sugar Content", ["Low Sugar", "Regular", "No Sugar", "reg"], horizontal=True)
+            product_type = st.selectbox("Product Type", [
+                "Fruits and Vegetables", "Snack Foods", "Frozen Foods", "Dairy", "Household", "Baking Goods",
+                "Canned", "Health and Hygiene", "Meat", "Soft Drinks", "Breads", "Hard Drinks", "Others",
+                "Starchy Foods", "Breakfast", "Seafood"
+            ])
+
+    with col2:
+        with st.expander("🏬 Store Details", expanded=True):
+            store_id = st.radio("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"], horizontal=True)
             store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
-            city_type = st.selectbox("Store City Tier", ["Tier 1", "Tier 2", "Tier 3"])
-            store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Departmental Store", "Food Mart"])
-
-        submitted = st.form_submit_button("🔮 Predict Sales")
-
-        if submitted:
-            input_record = {
+            store_location = st.radio("City Tier", ["Tier 1", "Tier 2", "Tier 3"], horizontal=True)
+            store_type = st.selectbox("Store Type", [
+                "Supermarket Type1", "Supermarket Type2", "Departmental Store", "Grocery Store"
+            ])
+            est_year = st.slider("Establishment Year", 1987, 2009, 2002)
+
+    # Submit action
+    if st.button("🎯 Predict Sales 🎯"):
+        try:
+            payload = {
                 "Product_Weight": product_weight,
-                "Product_Sugar_Content": sugar_content,
-                "Product_Allocated_Area": allocated_area,
+                "Product_Allocated_Area": product_allocated_area,
+                "Product_MRP": product_mrp,
+                "Product_Sugar_Content": product_sugar_content,
                 "Product_Type": product_type,
-                "Product_MRP": mrp,
                 "Store_Id": store_id,
-                "Store_Establishment_Year": store_year,
                 "Store_Size": store_size,
-                "Store_Location_City_Type": city_type,
-                "Store_Type": store_type
+                "Store_Location_City_Type": store_location,
+                "Store_Type": store_type,
+                "Store_Establishment_Year": est_year
             }
 
-            try:
-                prediction = get_single_prediction(input_record)
-                st.success(f"✅ Predicted Sales: ₹{prediction:,.2f}")
-                st.json({**input_record, "Predicted_Sales": prediction})
-            except Exception as e:
-                st.error(f"⚠️ Error during prediction: {e}")
+            url = "https://Pushpak21-SuperKart-Sales-Forecast-Backend.hf.space/predict"
+            response = requests.post(url, json=payload)
+            result = response.json()
+
+            if response.status_code == 200:
+                st.success(f"📈 Predicted Sales: ₹{result['prediction'][0]:,.2f}")
+            else:
+                st.error(f"❌ Error: {result.get('error', 'Unknown error')}")
+        
+        except Exception as e:
+            st.error(f"⚠️ Request failed: {e}")
 
-# 📄 TAB 2: Batch Prediction
+# ----------------- Tab 2: Batch Prediction -----------------
 with tab2:
     st.subheader("📄 Upload CSV for Batch Prediction")
     uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
 
-    if uploaded_file:
+    if uploaded_file is not None:
         try:
             df = pd.read_csv(uploaded_file)
 
             if df.empty:
-                st.warning("Uploaded file is empty.")
+                st.warning("Uploaded file is empty!")
             else:
                 st.write("📋 Uploaded Data Preview:")
                 st.dataframe(df.head())
 
-                df = get_predictions(df)
-                df = reorder_columns(df, ["Product_Store_Sales_Total", "Predicted_Sales"])
-
-                col1, col2 = st.columns([6, 1])
-                with col1:
-                    st.subheader("📈 Prediction Results:")
-                with col2:
-                    st.download_button(
-                        label="📥 Download CSV",
-                        data=get_csv_download(df),
-                        file_name="batch_predictions.csv",
-                        mime="text/csv",
-                        use_container_width=True
-                    )
-
-                st.dataframe(df)
-                plot_actual_vs_predicted(df)
+                # Convert DataFrame to list of records
+                records = df.to_dict(orient="records")
+
+                # Make prediction API call
+                response = requests.post(
+                    "https://Pushpak21-SuperKart-Sales-Forecast-Backend.hf.space/predict_batch",
+                    json=records
+                )
+
+                if response.status_code == 200:
+                    predictions = response.json().get("predictions", [])
+                    df["Predicted_Sales"] = predictions
+
+                    # Reorder columns: move actual & predicted sales to front
+                    priority_cols = ["Product_Store_Sales_Total", "Predicted_Sales"]
+                    other_cols = [col for col in df.columns if col not in priority_cols]
+                    df = df[priority_cols + other_cols]
+
+                    st.success("✅ Batch prediction complete!")
+
+                    # Header + Download button aligned
+                    col1, col2 = st.columns([6, 1])
+                    with col1:
+                        st.subheader("📈 Prediction Results:")
+                    with col2:
+                        csv = df.to_csv(index=False).encode('utf-8')
+                        st.download_button(
+                            label="📥 Download CSV",
+                            data=csv,
+                            file_name="batch_predictions.csv",
+                            mime="text/csv",
+                            use_container_width=True
+                        )
+
+                    # Display result table
+                    st.dataframe(df)
+
+                    # 📉 Altair Line Chart: Actual vs Predicted
+                    if "Product_Store_Sales_Total" in df.columns:
+                        plot_df = df[["Product_Store_Sales_Total", "Predicted_Sales"]].dropna()
+
+                        if not plot_df.empty:
+                            st.subheader("📉 Actual vs Predicted Sales")
+
+                            # Prepare long-format dataframe for Altair
+                            plot_df = plot_df.reset_index().rename(columns={
+                                "Product_Store_Sales_Total": "Actual Sales",
+                                "Predicted_Sales": "Predicted Sales",
+                                "index": "Index"
+                            })
+
+                            plot_df_melted = plot_df.melt(
+                                id_vars="Index",
+                                var_name="Type",
+                                value_name="Sales"
+                            )
+
+                            line_chart = alt.Chart(plot_df_melted).mark_line(point=True).encode(
+                                x=alt.X("Index:O", title="Record Index"),
+                                y=alt.Y("Sales:Q", title="Sales Value"),
+                                color=alt.Color("Type:N", title="Sales Type"),
+                                tooltip=["Index", "Type", "Sales"]
+                            ).properties(
+                                width=700,
+                                height=400
+                            )
+
+                            st.altair_chart(line_chart, use_container_width=True)
+                        else:
+                            st.info("ℹ️ Not enough valid rows for plotting.")
+                else:
+                    st.error(f"❌ API Error {response.status_code}: {response.text}")
 
         except Exception as e:
             st.error(f"⚠️ Error while processing the file: {e}")