app.py

import joblib
import pandas as pd
from flask import Flask, request, jsonify

# Initialize Flask app with a name
#revenue_predictor_api = Flask("SuperKart Revenue Predictor")
backend_predictor_api = Flask("Backend Predictor")

# Load the trained prediction model
model = joblib.load("personal_loan.joblib")

# Define a route for the home page
@backend_predictor_api.get('/')
def home():
    return "Welcome to the Backend Prediction API!"

# Define an endpoint to predict for a single data
@backend_predictor_api.post('/v1/dijakbn')
def predict_dijak_backend():
    # Get JSON data from the request
    backend_data = request.get_json()

    # Extract relevant backend features from the input data
    sample = {
        'ID': backend_data['ID'],
        'Age': backend_data['Age'],
        'Experience': backend_data['Experience'],
        'Income': backend_data['Income'],
        'ZIPCode': backend_data['ZIPCode'],
        'Family': backend_data['Family'],
        'CCAvg': backend_data['CCAvg'],
        'Education': backend_data['Education'],
        'Mortgage': backend_data['Mortgage'],
        'Securities_Account': backend_data['Securities_Account'],
        'CD_Account': backend_data['CD_Account'],
        'Online': backend_data['Online'],
        'CreditCard': backend_data['CreditCard']
    }

    # Convert the extracted data into a DataFrame
    input_data = pd.DataFrame([sample])

    # Make a prediction using the trained model
    prediction = model.predict(input_data).tolist()[0]

    # Return the prediction as a JSON response
    return jsonify({'Prediction': prediction})

# Define an endpoint to predict for a batch of input
@backend_predictor_api.post('/v1/dijakbnbatch')
def predict_dijak_backend_batch():
    # Get the uploaded CSV file from the request
    file = request.files['file']

    # Read the file into a DataFrame
    input_data = pd.read_csv(file)

    # Drop Product_Id before prediction
    features = input_data.drop("Personal_Loan", axis=1)

    # Make predictions
    predictions = model.predict(features).tolist()

    # Build structured output with Product_Id, Store_Id, and rounded output
    output_list = []
    for i in range(len(predictions)):
        output_list.append({
            #"Product_Id": input_data.loc[i, "Product_Id"],
            #"Store_Id": input_data.loc[i, "Store_Id"],
            "Prediction": round(predictions[i], 2)
        })

    return jsonify(output_list)

# Run the Flask app in debug mode
if __name__ == '__main__':
    app.run(debug=True)