Upload Flask backend files

Dockerfile

@@ -1,10 +1,3 @@
-# Dockerfile for SuperKart Streamlit Frontend
-FROM python:3.10-slim
-
-WORKDIR /app
-
-COPY . .
-
-RUN pip install --no-cache-dir -r requirements.txt
-
-CMD ["streamlit", "run", "app.py", "--server.port=7861", "--server.address=0.0.0.0"]
+# Backend
+#docker build -t superkart-backend .
+#docker run -p 7860:7860 superkart-backend

app.py

@@ -1,52 +1,62 @@
-import streamlit as st
+import joblib
 import pandas as pd
-import requests
-
-st.title("🛒 SuperKart Quarterly Sales Predictor")
-
-# Input form
-st.subheader("🔍 Predict Store's Quarterly Sales")
-
-store_id = st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"])
-product_type = st.selectbox("Product Type", ["Dairy", "Soft Drinks", "Meat", "Canned", "Frozen Foods"])
-sugar_content = st.selectbox("Product Sugar Content", ["Low", "Medium", "High", "No Added Sugar"])
-store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Grocery Store", "Food Mart"])
-city_type = st.selectbox("City Type", ["Urban", "Semi-Urban", "Rural"])
-store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
-
-est_year = st.number_input("Store Establishment Year", min_value=1980, max_value=2025, value=2005)
-weight = st.number_input("Product Weight", min_value=0.0, value=12.0)
-area = st.number_input("Product Allocated Area", min_value=0.0, value=125.0)
-mrp = st.number_input("Product MRP", min_value=0.0, value=120.0)
-
-input_data = pd.DataFrame([{
-    'Store_Id': store_id,
-    'Product_Type': product_type,
-    'Product_Sugar_Content': sugar_content,
-    'Store_Type': store_type,
-    'Store_Location_City_Type': city_type,
-    'Store_Size': store_size,
-    'Store_Establishment_Year': est_year,
-    'Product_Weight': weight,
-    'Product_Allocated_Area': area,
-    'Product_MRP': mrp
-}])
-
-if st.button("Predict Sales"):
-    api_url = "https://<your-backend-space>.hf.space/v1/storesales"
-    response = requests.post(api_url, json=input_data.to_dict(orient='records'))
-    if response.status_code == 200:
-        result = response.json()
-        st.success(f"📦 Predicted Total Sales: ₹{result['Total_Store_Sales']:,.2f}")
-    else:
-        st.error(f"❌ API Error: {response.text}")
-
-st.subheader("📁 Batch Prediction via CSV")
-file = st.file_uploader("Upload CSV", type=["csv"])
-
-if file and st.button("Predict Batch"):
-    response = requests.post("https://<your-backend-space>.hf.space/v1/storesalesbatch", files={"file": file})
-    if response.status_code == 200:
-        st.write(pd.DataFrame(response.json()))
-    else:
-        st.error(f"❌ Batch API Error: {response.text}")
+from flask import Flask, request, jsonify
+from waitress import serve
+
+app = Flask("SuperKart_Quarterly_Sales_Predictor")
+
+# Load model
+model = joblib.load("deployment_files/quarterly_sales_prediction_model_v1_0.joblib")
+
+@app.get('/')
+def home():
+    return "✅ SuperKart API is live"
+
+@app.post('/v1/storesales')
+def predict_sales():
+    try:
+        data = request.get_json()
+        df = pd.DataFrame(data)
+
+        feature_cols = [
+            'Product_Weight', 'Product_Allocated_Area',
+            'Product_MRP', 'Product_Sugar_Content', 'Product_Type',
+            'Store_Establishment_Year', 'Store_Id',  'Store_Type',
+            'Store_Size', 'Store_Location_City_Type'
+        ]
+# 'Product_Sugar_Content', 'Product_Type',
+        predictions = model.predict(df[feature_cols])
+        total_sales = round(predictions.sum(), 2)
+
+        return jsonify({'Total_Store_Sales': total_sales})
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.post('/v1/storesalesbatch')
+def predict_batch():
+    try:
+        file = request.files['file']
+        df = pd.read_csv(file)
+
+         feature_cols = [
+            'Product_Weight', 'Product_Allocated_Area',
+            'Product_MRP', 'Product_Sugar_Content', 'Product_Type',
+            'Store_Establishment_Year', 'Store_Id',  'Store_Type',
+            'Store_Size', 'Store_Location_City_Type'
+        ]
+
+        df['Predicted_Sales'] = model.predict(df[feature_cols])
+        summary = (
+            df.groupby('Store_Id')['Predicted_Sales']
+            .sum()
+            .round(2)
+            .reset_index()
+            .rename(columns={'Predicted_Sales': 'Total_Sales'})
+        )
+
+        return summary.to_dict(orient="records")
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == '__main__':
+    serve(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -1,3 +1,8 @@
-streamlit==1.34.0
+Flask==2.2.2
+waitress==2.1.2
 pandas==2.2.2
-requests==2.31.0
+numpy==1.26.4
+joblib==1.4.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+