generate_data.py

"""
Bioweather Production Data Generator v2.0
EmpedocLabs © 2025

Generates clinically-plausible weather → headache risk data with:
  - 15 distinct biometeo conditions
  - Seasonal/geographic variation
  - Multi-trigger overlap scoring
  - Graded risk (not just if/else buckets)
  - 20,000+ samples for robust training
"""

import numpy as np
import pandas as pd


def generate_production_data(n: int = 25000, seed: int = 42) -> pd.DataFrame:
    rng = np.random.default_rng(seed)
    rows = []

    for _ in range(n):
        # ── Base weather with seasonal coherence ─────────────────────
        season = rng.choice(["winter", "spring", "summer", "autumn"],
                            p=[0.25, 0.25, 0.25, 0.25])

        if season == "winter":
            temp = rng.normal(-2, 8)
            humidity = rng.normal(70, 15)
            uv = rng.integers(0, 4)
            wind = abs(rng.normal(15, 12))
        elif season == "spring":
            temp = rng.normal(14, 7)
            humidity = rng.normal(55, 18)
            uv = rng.integers(2, 8)
            wind = abs(rng.normal(18, 10))
        elif season == "summer":
            temp = rng.normal(28, 6)
            humidity = rng.normal(55, 20)
            uv = rng.integers(5, 11)
            wind = abs(rng.normal(12, 8))
        else:  # autumn
            temp = rng.normal(12, 8)
            humidity = rng.normal(65, 15)
            uv = rng.integers(1, 6)
            wind = abs(rng.normal(16, 10))

        temp = np.clip(temp, -15, 45)
        humidity = np.clip(humidity, 8, 99)
        uv = int(np.clip(uv, 0, 11))
        wind = np.clip(wind, 0, 70)

        pressure = rng.normal(1013, 12)
        pressure = np.clip(pressure, 970, 1050)

        # Pressure change: occasional fronts
        if rng.random() < 0.10:
            p_drop = rng.normal(-8, 3)       # cold front
        elif rng.random() < 0.08:
            p_drop = rng.normal(7, 2.5)      # high pressure ridge
        else:
            p_drop = rng.normal(0, 2.5)
        p_drop = np.clip(p_drop, -15, 15)

        # Temp change: some days have big swings
        if rng.random() < 0.07:
            t_change = rng.choice([-1, 1]) * abs(rng.normal(10, 3))
        else:
            t_change = rng.normal(0, 3)
        t_change = np.clip(t_change, -15, 15)

        # ── Additive risk scoring (multiple triggers stack) ──────────
        risk = 5.0  # baseline
        condition_scores = {}  # condition_id → contribution

        # 1. Pressure drop (strongest weather trigger per literature)
        if p_drop <= -8:
            contribution = 35 + abs(p_drop) * 1.5
            condition_scores[1] = contribution
            risk += contribution
        elif p_drop <= -4:
            contribution = 15 + abs(p_drop) * 1.2
            condition_scores[10] = contribution
            risk += contribution
        elif p_drop <= -2:
            contribution = 8 + abs(p_drop) * 0.8
            condition_scores[10] = contribution
            risk += contribution

        # 2. Pressure rise
        if p_drop >= 8:
            contribution = 25 + p_drop * 1.0
            condition_scores[2] = contribution
            risk += contribution
        elif p_drop >= 4:
            contribution = 12 + p_drop * 0.7
            condition_scores[11] = contribution
            risk += contribution
        elif p_drop >= 2:
            contribution = 6 + p_drop * 0.5
            condition_scores[11] = contribution
            risk += contribution

        # 3. Sauna effect (heat + humidity)
        if temp >= 28 and humidity >= 65:
            strength = (temp - 28) * 2 + (humidity - 65) * 0.5
            condition_scores[3] = strength
            risk += strength

        # 4. Wind
        if wind >= 40:
            condition_scores[4] = 25 + (wind - 40) * 0.8
            risk += condition_scores[4]
        elif wind >= 20:
            condition_scores[12] = 10 + (wind - 20) * 0.3
            risk += condition_scores[12]

        # 5. UV glare
        if uv >= 8:
            condition_scores[5] = 20 + (uv - 8) * 3
            risk += condition_scores[5]
        elif uv >= 6 and temp > 15:
            condition_scores[5] = 8 + (uv - 6) * 2
            risk += condition_scores[5]

        # 6. Bitter cold
        if temp <= -5:
            condition_scores[6] = 25 + abs(temp + 5) * 2
            risk += condition_scores[6]
        elif temp <= 2:
            condition_scores[6] = 10 + abs(temp - 2) * 1.5
            risk += condition_scores[6]

        # 7. Drastic temp drop
        if t_change <= -8:
            condition_scores[7] = 30 + abs(t_change) * 1.5
            risk += condition_scores[7]
        elif t_change <= -5:
            condition_scores[7] = 12 + abs(t_change) * 0.8
            risk += condition_scores[7]

        # 8. Heat shock
        if t_change >= 8:
            condition_scores[8] = 28 + t_change * 1.2
            risk += condition_scores[8]
        elif t_change >= 5:
            condition_scores[8] = 10 + t_change * 0.7
            risk += condition_scores[8]

        # 9. Heavy dampness
        if humidity >= 88 and wind <= 12:
            condition_scores[9] = 15 + (humidity - 88) * 0.8
            risk += condition_scores[9]

        # 13. Dry air
        if humidity <= 25:
            condition_scores[13] = 18 + (25 - humidity) * 0.8
            risk += condition_scores[13]
        elif humidity <= 32:
            condition_scores[13] = 8 + (32 - humidity) * 0.5
            risk += condition_scores[13]

        # 14. Stagnant & gloomy
        if uv <= 2 and humidity >= 72 and wind <= 10 and temp < 18:
            condition_scores[14] = 10 + (humidity - 72) * 0.3
            risk += condition_scores[14]

        # ── Determine primary condition ──────────────────────────────
        if condition_scores:
            label = max(condition_scores, key=condition_scores.get)
        else:
            label = 0  # clear skies

        # ── Add realistic noise ──────────────────────────────────────
        risk += rng.normal(0, 2.5)
        risk = int(np.clip(round(risk), 0, 100))

        rows.append([
            round(temp, 1), round(pressure, 1), round(humidity, 1),
            round(wind, 1), uv, round(p_drop, 2), round(t_change, 2),
            risk, label,
        ])

    df = pd.DataFrame(rows, columns=[
        "temp_c", "pressure_hpa", "humidity", "wind_kph", "uv_index",
        "pressure_drop", "temp_change", "risk_score", "advice_label",
    ])

    print(f"✅ Generated {len(df):,} samples")
    print(f"   Risk: mean={df['risk_score'].mean():.1f}, std={df['risk_score'].std():.1f}")
    print(f"   Conditions: {df['advice_label'].value_counts().sort_index().to_dict()}")
    return df


if __name__ == "__main__":
    df = generate_production_data()
    df.to_csv("smart_weather_data.csv", index=False)
    print(f"💾 Saved → smart_weather_data.csv")