app.py

# Import necessary libraries
import numpy as np
import joblib
import pandas as pd
from flask import Flask, request, jsonify
from huggingface_hub import hf_hub_download
import joblib
import tempfile
import streamlit as st
import io # Import io module

REPO_ID = "omoral02/RevenuePrediction"
FILENAME = "store-sales-prediction-model-v1-0.joblib"

# Write model to temp directory (writable in Hugging Face Spaces)
temp_dir = tempfile.gettempdir()
model_path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME, cache_dir=temp_dir)
model = joblib.load(model_path)

# Initialize the Flask app
superkart_api = Flask("SuperKart Sales Predictor")

# def transform_input_for_model(df_raw):
#     # Binning
#     df_raw['Product_MRP_bin'] = pd.qcut(df_raw['Product_MRP'], q=5, duplicates='drop')
#     df_raw['Product_Weight_bin'] = pd.qcut(df_raw['Product_Weight'], q=5, duplicates='drop')

#     df_raw['Product_Type_Binned'] = bin_categorical(df_raw['Product_Type'])
#     df_raw['Store_Type_Binned'] = bin_categorical(df_raw['Store_Type'])
#     df_raw['Store_Location_City_Type_Binned'] = bin_categorical(df_raw['Store_Location_City_Type'])

#     # Dummy encoding
#     df_encoded = pd.get_dummies(df_raw, columns=[
#         'Product_Type_Binned', 'Store_Type_Binned',
#         'Store_Location_City_Type_Binned',
#         'Product_MRP_bin', 'Product_Weight_bin'
#     ], drop_first=False)

#     # Drop original fields
#     df_encoded = df_encoded.select_dtypes(include=['number']).copy()

#     return df_encoded


# Load the trained model
@st.cache_resource
def load_model():
    return model

model = load_model()

# Define root endpoint
@superkart_api.get('/')
def home():
    return jsonify({"okay": "Welcome to the SuperKart Sales Prediction API!"})

# Endpoint for single record prediction
@superkart_api.post('/v1/predict')
def predict_sales():
    if model is None:
      return jsonify({"error": "Model not loaded"}), 500

    try:
        input_json = request.get_json()
        expected_fields = [
            'Product_Type', 'Store_Type', 'Store_Location_City_Type',
            'Store_Size', 'Product_Sugar_Content', 'Product_Weight',
            'Product_MRP', 'Product_Allocated_Area', 'Store_Establishment_Year'
        ]
        missing = [f for f in expected_fields if f not in input_json]
        if missing:
            return jsonify({
                'error': 'Missing required input fields.',
                'missing_fields': missing,
                'received_fields': list(input_json.keys())
            }), 400

        # Extract relevant inputs (must match training columns)
        features = {
            'Product_Type': input_json['Product_Type'],
            'Store_Type': input_json['Store_Type'],
            'Store_Location_City_Type': input_json['Store_Location_City_Type'],
            'Store_Size': input_json['Store_Size'],
            'Product_Sugar_Content': input_json['Product_Sugar_Content'],
            'Product_Weight': input_json['Product_Weight'],
            'Product_MRP': input_json['Product_MRP'],
            'Product_Allocated_Area': input_json['Product_Allocated_Area'],
            'Store_Establishment_Year': input_json['Store_Establishment_Year'],
        }

        input_df = pd.DataFrame([features])
        # df_transformed = transform_input_for_model(input_df)
        prediction = model.predict(input_df)[0]
        return jsonify({'Predicted_Store_Sales_Total': round(float(prediction), 2)})

    except Exception as e:
        print(f"Error during single prediction: {e}") # Added print for debugging
        return jsonify({"error": str(e), "message": "Prediction failed"}), 500 # Return error message and status code


# Endpoint for batch prediction using CSV
@superkart_api.post('/v1/batch')
def predict_sales_batch():
    try:
        uploaded_file = request.files['file']
        input_df = pd.read_csv(uploaded_file)
        expected_fields = [
            'Product_Type', 'Store_Type', 'Store_Location_City_Type',
            'Store_Size', 'Product_Sugar_Content', 'Product_Weight',
            'Product_MRP', 'Product_Allocated_Area', 'Store_Establishment_Year'
        ]
        missing = [f for f in expected_fields if f not in input_df.columns]
        if missing:
            return jsonify({
                'error': 'Missing required columns in uploaded CSV.',
                'missing_columns': missing,
                'received_columns': list(input_df.columns)
            }), 400
        # df_transformed = transform_input_for_model(input_df)
        predictions = model.predict(input_df).tolist()
        rounded_preds = [round(float(p), 2) for p in predictions]
        return jsonify({'Predicted_Store_Sales_Total': rounded_preds})

        # Optional: use product-store pair if available
        # if 'Product_Id' in df_transformed.columns and 'Store_Id' in df_transformed.columns:
        #     keys = df_transformed['Product_Id'].astype(str) + "_" + df_transformed['Store_Id'].astype(str)
        # else:
        #     keys = [f"row_{i}" for i in range(len(df_transformed))]

        # return jsonify(dict(zip(keys, rounded_preds)))

    except Exception as e:
        print(f"Error during batch prediction: {e}") # Added print for debugging
        return jsonify({"error": str(e), "message": "Prediction failed"}), 500

# Run the Flask app
if __name__ == '__main__':
    superkart_api.run(host="0.0.0.0", port=7860)