"""
Clinical Action and Recommendation Engine.
Generates targeted lifestyle and follow-up care steps based on patient risk attributions.
"""


class MedicalRecommendationEngine:
    def __init__(self):
        pass

    def generate_patient_guidelines(self, risk_category_string, attribution_dataframe):
        """
        Generates actionable care steps tailored to the patient's top risk contributors.
        """
        care_guidelines = []

        # Tiered care tracking based on global risk categories
        if "Severe" in risk_category_string:
            care_guidelines.append("Cardiovascular specialist review advised immediately.")
            care_guidelines.append("Monitor blood pressure and vital signs regularly.")
        elif "Moderate" in risk_category_string:
            care_guidelines.append("Schedule a follow-up clinical review within 14 business days.")
            care_guidelines.append("Begin systematic tracking of daily vitals.")
        else:
            care_guidelines.append("Maintain routine annual check-ups as scheduled.")

        # Extract and sort features to find the top risk contributors
        if not attribution_dataframe.empty and "Impact_Percentage" in attribution_dataframe.columns:
            sorted_features = attribution_dataframe.sort_values(by="Impact_Percentage", ascending=False)
            top_contributors = sorted_features["Feature"].head(2).tolist()

            for feature_name in top_contributors:
                if feature_name == "HighBP":
                    care_guidelines.append("Initiate a low-sodium dietary plan and track blood pressure daily.")
                elif feature_name == "BMI":
                    care_guidelines.append("Discuss a supervised weight management and exercise plan.")
                elif feature_name == "Smoker":
                    care_guidelines.append("Provide resources for smoking cessation and tobacco alternatives.")

        # Ensure a fallback guideline is always present
        if not care_guidelines:
            care_guidelines.append("Consult with your primary care physician for personalized health planning.")

        return care_guidelines


if __name__ == "__main__":
    import pandas as pd

    mock_attributions = pd.DataFrame({
        "Feature": ["HighBP", "BMI", "Smoker"],
        "Impact_Percentage": [18.5, 14.2, 2.1]
    })

    engine = MedicalRecommendationEngine()
    guidelines_list = engine.generate_patient_guidelines("Severe Cardiovascular Risk", mock_attributions)
    print("[SUCCESS] Actionable care guidelines generated successfully:")
    for line in guidelines_list:
        print(f" • {line}")