src/scripts/temp

import os
import sys
# Add the project root directory to sys.path
project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../"))
sys.path.append(project_root)
import google.generativeai as genai

from flask import Flask, request, jsonify, render_template
from src.scripts.data_preprocessing import DataPreprocessor
from src.scripts.prediction import DiabetesPrediction

class HealthRecommendations:
    def __init__(self, api_key):
        # Configure Google GenAI
        genai.configure(api_key=api_key)
        # For this example, we'll use the gemini-pro model
        self.model = genai.GenerativeModel('gemini-pro')

    def get_recommendations(self, patient_data, prediction):
        # Create a prompt for the model
        prompt = f"""
        Given the following patient data:
        - Glucose level: {patient_data['Glucose']}
        - Blood Pressure: {patient_data['BloodPressure']}
        - BMI: {patient_data['BMI']}
        - Age: {patient_data['Age']}
        - Diabetes Prediction: {'Positive' if prediction == 1 else 'Negative'}

        Please provide specific health recommendations for this patient considering their metrics 
        and diabetes risk status. Focus on diet, exercise, and lifestyle changes.
        """

        # Generate response using Google GenAI
        response = self.model.generate_content(prompt)
        
        # Extract and return the recommendations
        return response.text

app = Flask(__name__, template_folder='src/templates')

# Initialize components
predictor = DiabetesPrediction()
health_advisor = HealthRecommendations(api_key=os.getenv('AIzaSyBMh7bQCD1tf_9w7C04zNoJocEtHg9KLjI'))  # Changed to use Google API key

@app.route('/')
def home():
    return render_template('index.html')

@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Get data from request
        data = request.json
        features = [
            float(data['pregnancies']),
            float(data['glucose']),
            float(data['bloodPressure']),
            float(data['skinThickness']),
            float(data['insulin']),
            float(data['bmi']),
            float(data['diabetesPedigree']),
            float(data['age'])
        ]
        
        # Make prediction
        prediction_result = predictor.predict(features)
        
        # Get health recommendations
        recommendations = health_advisor.get_recommendations(
            patient_data={
                'Glucose': data['glucose'],
                'BloodPressure': data['bloodPressure'],
                'BMI': data['bmi'],
                'Age': data['age']
            },
            prediction=prediction_result
        )
        
        return jsonify({
            'prediction': prediction_result,
            'recommendations': recommendations
        })
        
    except Exception as e:
        return jsonify({'error': str(e)}), 400

if __name__ == '__main__':
    app.run(debug=True)