Upload folder using huggingface_hub

app.py

@@ -1,68 +1,38 @@
-import streamlit as st
+import numpy as np
+import joblib
 import pandas as pd
-import requests
+from flask import Flask, request, jsonify
 
-st.title("SuperKart Sales Prediction")
+# Initialize the Flask app
+superkart_api = Flask("SuperKart Sales Prediction API")
 
-st.markdown("### Enter product-store data for sales prediction")
+# Load the trained model
+model = joblib.load("best_random_forest_model.joblib")
 
-# Create input fields (add/change according to your model's input features)
-product_id = st.text_input("Product ID", "")
-store_id = st.text_input("Store ID", "")
-quarter = st.selectbox("Quarter", ["Q1", "Q2", "Q3", "Q4"])
-year = st.number_input("Year", min_value=2000, max_value=2100, value=2025)
+@superkart_api.route('/', methods=['GET'])
+def home():
+    return "Welcome to the SuperKart Sales Prediction API!"
 
-if st.button("Predict Sales"):
-    if not product_id or not store_id:
-        st.error("Please enter Product ID and Store ID.")
-    else:
-        # Prepare JSON payload according to backend expected format
-        payload = {
-            "Product_ID": product_id,
-            "Store_ID": store_id,
-            "Quarter": quarter,
-            "Year": year
-        }
-
-        # Your backend API endpoint URL - adjust if different
-        API_URL = "https://huggingface.co/spaces/Fitjv/superkart_v0/api/v1/sales"
-
-        try:
-            response = requests.post(API_URL, json=payload)
-            response.raise_for_status()
-            data = response.json()
-            if 'Predicted Quarterly Sales (in INR)' in data:
-                st.success(f"Predicted Quarterly Sales: ₹{data['Predicted Quarterly Sales (in INR)']}")
-            else:
-                st.error("Unexpected response format from API.")
-        except Exception as e:
-            st.error(f"API request failed: {e}")
-
-st.markdown("---")
-st.markdown("### Batch Prediction (Upload CSV)")
-
-uploaded_file = st.file_uploader("Upload CSV file with input data", type=["csv"])
-
-if uploaded_file is not None:
+@superkart_api.route('/v1/sales', methods=['POST'])
+def predict_sales():
     try:
-        df = pd.read_csv(uploaded_file)
-        st.write("Input data preview:")
-        st.dataframe(df.head())
-
-        if st.button("Predict Batch Sales"):
-            API_BATCH_URL = "https://huggingface.co/spaces/Fitjv/superkart_v0/api/v1/salesbatch"
-            files = {"file": uploaded_file.getvalue()}
-            # Note: For requests with file upload, send as 'files' parameter
-            files = {"file": (uploaded_file.name, uploaded_file, "text/csv")}
-            response = requests.post(API_BATCH_URL, files=files)
-            response.raise_for_status()
-            result = response.json()
-            if isinstance(result, list):
-                result_df = pd.DataFrame(result)
-                st.success("Batch predictions received:")
-                st.dataframe(result_df.head())
-            else:
-                st.error("Unexpected response format from batch API.")
+        input_data = request.get_json()
+        df = pd.DataFrame([input_data])
+        prediction = model.predict(df)[0]
+        return jsonify({'Predicted Quarterly Sales (in INR)': round(float(prediction), 2)})
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
 
+@superkart_api.route('/v1/salesbatch', methods=['POST'])
+def predict_sales_batch():
+    try:
+        file = request.files['file']
+        input_df = pd.read_csv(file)
+        predictions = model.predict(input_df)
+        input_df['Predicted_Quarterly_Sales'] = [round(float(val), 2) for val in predictions]
+        return input_df.to_dict(orient='records')
     except Exception as e:
-        st.error(f"Failed to process uploaded file or API request: {e}")
+        return jsonify({'error': str(e)}), 400
+
+if __name__ == '__main__':
+    superkart_api.run(debug=True)

best_random_forest_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0d1b8dcea939914fdf7a7f127821acab001f3313e08444e6bd61c116b9d3ed6
+oid sha256:cd81c274fa9e445e81160011b41edf0b732fe4f8b7147c12f3447610fdbd3ff3
 size 45516023

requirements.txt

@@ -1,3 +1,9 @@
 pandas==2.2.2
-streamlit==1.43.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
 requests==2.28.1