feature_engineering/advanced_features.py

"""
Advanced Medical Feature Engineering and Clinical Metric Interpreter.
Handles 21-input scaling pipelines, BMI triage math, and multi-modal feature vectors.
"""
import pandas as pd
import numpy as np

class ClinicalFeatureEngineer:
    def __init__(self):
        # Full explicit 21-feature mapping matching the BRFSS2015 indicator topology
        self.required_features = [
            'HighBP', 'HighChol', 'CholCheck', 'BMI', 'Smoker', 'Stroke',
            'Diabetes', 'PhysActivity', 'Fruits', 'Veggies', 'HvyAlcoholConsump',
            'AnyHealthcare', 'NoDocbcCost', 'GenHlth', 'MentHlth', 'PhysHlth',
            'DiffWalk', 'Sex', 'Age', 'Education', 'Income'
        ]

    def compute_bmi_metrics(self, weight_kg, height_cm):
        """Calculates exact BMI and returns clinical classification boundaries."""
        if height_cm <= 0 or weight_kg <= 0:
            return 0.0, "Unknown Parameters"

        height_m = height_cm / 100.0
        bmi = float(weight_kg / (height_m ** 2))

        if bmi < 18.5:
            category = "Underweight (Increased Risk)"
        elif 18.5 <= bmi < 25.0:
            category = "Normal Weight (Optimal Range)"
        elif 25.0 <= bmi < 30.0:
            category = "Overweight (Monitored Base)"
        else:
            category = "Obese (Severe Cardiovascular Risk Factor)"

        return round(bmi, 2), category

    def compute_engineered_metrics(self, raw_df):
        """Maps full 21-input arrays to deep structural interaction metrics."""
        df = raw_df.copy()

        # Ensure all columns exist, fill default values if absent
        for col in self.required_features:
            if col not in df.columns:
                df[col] = 0.0

        # High-order medical risk interactions
        df['BMI_BP_Interaction'] = df['BMI'] * df['HighBP']
        df['Health_Risk_Score'] = (
            df['HighBP'] + df['HighChol'] + df['Smoker'] +
            df['Stroke'] + df['Diabetes'] + df['DiffWalk']
        ).astype(float)

        extended_columns = self.required_features + ['BMI_BP_Interaction', 'Health_Risk_Score']
        return df[extended_columns]