mitai-jinkendo/backend/data_layer/correlation_chart_payloads.py

"""
Chart.js-kompatible Payloads für Lag-Korrelationen C1–C3 und Treiber C4.

Gemeinsame Quelle für GET /charts/* und history_overview_viz.chart_payloads (Issue 53).
"""

from __future__ import annotations

from typing import Any, Dict

from data_layer.correlations import calculate_lag_correlation, calculate_top_drivers


def build_weight_energy_correlation_chart_payload(profile_id: str, max_lag: int) -> Dict[str, Any]:
    corr_data = calculate_lag_correlation(profile_id, "energy_balance", "weight", max_lag)

    if not corr_data or corr_data.get("correlation") is None:
        msg = "Nicht genug Daten für Korrelationsanalyse"
        if isinstance(corr_data, dict):
            msg = str(corr_data.get("interpretation") or corr_data.get("reason") or msg)
        return {
            "chart_type": "scatter",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "insufficient",
                "data_points": corr_data.get("data_points", 0) if isinstance(corr_data, dict) else 0,
                "message": msg,
                "lag_details": corr_data.get("lag_details") if isinstance(corr_data, dict) else None,
                "tdee_kcal_used": corr_data.get("tdee_kcal_used") if isinstance(corr_data, dict) else None,
            },
        }

    best_lag = corr_data.get("best_lag_days", corr_data.get("best_lag", 0))
    correlation = corr_data.get("correlation", 0)

    return {
        "chart_type": "scatter",
        "data": {
            "labels": [f"Lag {best_lag} Tage"],
            "datasets": [
                {
                    "label": "Korrelation",
                    "data": [{"x": best_lag, "y": correlation}],
                    "backgroundColor": "#1D9E75",
                    "borderColor": "#085041",
                    "borderWidth": 2,
                    "pointRadius": 8,
                }
            ],
        },
        "metadata": {
            "confidence": corr_data.get("confidence", "low"),
            "correlation": round(float(correlation), 3),
            "best_lag_days": best_lag,
            "interpretation": corr_data.get("interpretation", ""),
            "data_points": corr_data.get("data_points", 0),
            "lag_details": corr_data.get("lag_details"),
            "tdee_kcal_used": corr_data.get("tdee_kcal_used"),
            "layer_1": "correlations._correlate_energy_weight",
        },
    }


def build_lbm_protein_correlation_chart_payload(profile_id: str, max_lag: int) -> Dict[str, Any]:
    corr_data = calculate_lag_correlation(profile_id, "protein", "lbm", max_lag)

    if not corr_data or corr_data.get("correlation") is None:
        msg = "Nicht genug Daten für LBM-Protein Korrelation"
        if isinstance(corr_data, dict):
            msg = str(corr_data.get("interpretation") or corr_data.get("reason") or msg)
        return {
            "chart_type": "scatter",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "insufficient",
                "data_points": corr_data.get("data_points", 0) if isinstance(corr_data, dict) else 0,
                "message": msg,
                "lag_details": corr_data.get("lag_details") if isinstance(corr_data, dict) else None,
            },
        }

    best_lag = corr_data.get("best_lag_days", corr_data.get("best_lag", 0))
    correlation = corr_data.get("correlation", 0)

    return {
        "chart_type": "scatter",
        "data": {
            "labels": [f"Lag {best_lag} Tage"],
            "datasets": [
                {
                    "label": "Korrelation",
                    "data": [{"x": best_lag, "y": correlation}],
                    "backgroundColor": "#3B82F6",
                    "borderColor": "#1E40AF",
                    "borderWidth": 2,
                    "pointRadius": 8,
                }
            ],
        },
        "metadata": {
            "confidence": corr_data.get("confidence", "low"),
            "correlation": round(float(correlation), 3),
            "best_lag_days": best_lag,
            "interpretation": corr_data.get("interpretation", ""),
            "data_points": corr_data.get("data_points", 0),
            "lag_details": corr_data.get("lag_details"),
            "layer_1": "correlations._correlate_protein_lbm",
        },
    }


def build_load_vitals_correlation_chart_payload(profile_id: str, max_lag: int) -> Dict[str, Any]:
    corr_hrv = calculate_lag_correlation(profile_id, "load", "hrv", max_lag)
    corr_rhr = calculate_lag_correlation(profile_id, "load", "rhr", max_lag)

    def _abs_corr(c: Any) -> float:
        if not c or c.get("correlation") is None:
            return -1.0
        try:
            return abs(float(c["correlation"]))
        except (TypeError, ValueError):
            return -1.0

    if _abs_corr(corr_hrv) < 0 and _abs_corr(corr_rhr) < 0:
        msg = "Nicht genug Daten für Load-Vitals Korrelation"
        h_msg = corr_hrv.get("interpretation") if isinstance(corr_hrv, dict) else None
        r_msg = corr_rhr.get("interpretation") if isinstance(corr_rhr, dict) else None
        if h_msg or r_msg:
            msg = f"HRV: {h_msg or '—'} · RHR: {r_msg or '—'}"
        return {
            "chart_type": "scatter",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "insufficient",
                "data_points": 0,
                "message": msg,
                "lag_details_hrv": corr_hrv.get("lag_details") if isinstance(corr_hrv, dict) else None,
                "lag_details_rhr": corr_rhr.get("lag_details") if isinstance(corr_rhr, dict) else None,
            },
        }

    if _abs_corr(corr_hrv) >= _abs_corr(corr_rhr):
        corr_data = corr_hrv
        metric_name = "HRV"
    else:
        corr_data = corr_rhr
        metric_name = "RHR"

    if not corr_data or corr_data.get("correlation") is None:
        return {
            "chart_type": "scatter",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "insufficient",
                "data_points": 0,
                "message": str(corr_data.get("interpretation") or "Nicht genug Daten für Load-Vitals Korrelation"),
            },
        }

    best_lag = corr_data.get("best_lag_days", corr_data.get("best_lag", 0))
    correlation = corr_data.get("correlation", 0)

    return {
        "chart_type": "scatter",
        "data": {
            "labels": [f"Load → {metric_name} (Lag {best_lag}d)"],
            "datasets": [
                {
                    "label": "Korrelation",
                    "data": [{"x": best_lag, "y": correlation}],
                    "backgroundColor": "#F59E0B",
                    "borderColor": "#D97706",
                    "borderWidth": 2,
                    "pointRadius": 8,
                }
            ],
        },
        "metadata": {
            "confidence": corr_data.get("confidence", "low"),
            "correlation": round(float(correlation), 3),
            "best_lag_days": best_lag,
            "metric": metric_name,
            "interpretation": corr_data.get("interpretation", ""),
            "data_points": corr_data.get("data_points", 0),
            "lag_details": corr_data.get("lag_details"),
            "layer_1": "correlations._correlate_load_vitals",
        },
    }


def build_recovery_performance_chart_payload(profile_id: str) -> Dict[str, Any]:
    drivers = calculate_top_drivers(profile_id)

    if not drivers or len(drivers) == 0:
        return {
            "chart_type": "bar",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "insufficient",
                "data_points": 0,
                "message": "Nicht genug Daten für Driver-Analyse",
            },
        }

    hindering = [d for d in drivers if d.get("impact", "") == "hindering"]
    helpful = [d for d in drivers if d.get("impact", "") == "helpful"]

    top_hindering = hindering[:3]
    top_helpful = helpful[:3]

    labels = []
    values = []
    colors = []

    for d in top_hindering:
        labels.append(f"❌ {d.get('factor', '')}")
        values.append(-abs(d.get("score", 0)))
        colors.append("#EF4444")

    for d in top_helpful:
        labels.append(f"✅ {d.get('factor', '')}")
        values.append(abs(d.get("score", 0)))
        colors.append("#1D9E75")

    if not labels:
        return {
            "chart_type": "bar",
            "data": {"labels": [], "datasets": []},
            "metadata": {
                "confidence": "low",
                "data_points": 0,
                "message": "Keine signifikanten Treiber gefunden",
            },
        }

    return {
        "chart_type": "bar",
        "data": {
            "labels": labels,
            "datasets": [
                {
                    "label": "Impact Score",
                    "data": values,
                    "backgroundColor": colors,
                    "borderColor": "#085041",
                    "borderWidth": 1,
                }
            ],
        },
        "metadata": {
            "confidence": "medium",
            "hindering_count": len(top_hindering),
            "helpful_count": len(top_helpful),
            "total_factors": len(drivers),
        },
    }