"""Data preparation, logistic fitting, prediction, and goodness-of-fit."""

from pathlib import Path
import numpy as np
from scipy.io import loadmat

from ..data import get_data
from .core import (
    _sigmoid_stable,
    model_p,
    design_matrix,
    nll,
    llf,
    grad_nll,
    hess_nll,
    covariance,
    standard_errors,
    fit_newton,
    goodness_of_fit,
    fit_pack,
    trim_nc_by_value,
    fit_logistic_x,
    predict_curve_x,
    plot_overlay_two_panels_final,
)


def load_dataset(project_root=None, percentile=95):
    """Load the thesis SUV predictor and binary outcome arrays."""
    root = Path(project_root) if project_root else Path(__file__).resolve().parents[1]
    suv = loadmat(root / "suv_percentilesSLOthenUWM.mat")
    flags = loadmat(root / "flags_combined.mat")
    x, y = get_data(percentile, suv, flags)
    return np.asarray(x, float).ravel(), np.asarray(y, int).ravel()


def prepare_full_trim(project_root=None, percentile=95, target=2.48122597, tol=0.05):
    """Return aligned FULL and TRIM datasets."""
    x_full, y_full = load_dataset(project_root, percentile)
    x_trim, y_trim = trim_nc_by_value(x_full, y_full, target=target, tol=tol)
    return {
        "FULL": (x_full, y_full),
        "TRIM": (x_trim, y_trim),
    }