"""Figure 6: two-measure sensitivity surface over the (cosine cut x dHash cut) plane.
Panel A: clean-group (B/C/D) flag rate -- how permissive the operating point is.
Panel B: Firm A minus B/C/D flag-rate contrast (pp) -- discrimination across the plane.
Shows the chosen HC point (0.95, dHash<=5) is not a cherry-picked threshold and exposes
the weaker MC band (dHash<=15). Reproduces from signature_analysis.db (DB columns only).
"""
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import numpy as np
import sqlite3

DB = "/Volumes/NV2/PDF-Processing/signature-analysis/signature_analysis.db"
BIG4 = ('勤業眾信聯合', '資誠聯合', '安侯建業聯合', '安永聯合')

con = sqlite3.connect(DB); cur = con.cursor()
cur.execute(f"""SELECT CASE WHEN excel_firm='勤業眾信聯合' THEN 1 ELSE 0 END isA,
  max_similarity_to_same_accountant c, min_dhash_independent d
FROM signatures WHERE is_valid=1 AND excel_firm IN ({','.join('?'*4)})
  AND max_similarity_to_same_accountant IS NOT NULL AND min_dhash_independent IS NOT NULL""", BIG4)
rows = cur.fetchall(); con.close()
isA = np.array([r[0] for r in rows], bool)
c = np.array([r[1] for r in rows]); d = np.array([r[2] for r in rows])
cA, dA = c[isA], d[isA]; cB, dB = c[~isA], d[~isA]

cos_cuts = np.arange(0.85, 0.9901, 0.0025)
dh_cuts = np.arange(0, 21, 1)
A = np.zeros((len(dh_cuts), len(cos_cuts)))
B = np.zeros_like(A)
for j, cc in enumerate(cos_cuts):
    for i, dd in enumerate(dh_cuts):
        A[i, j] = 100 * np.mean((cA > cc) & (dA <= dd))
        B[i, j] = 100 * np.mean((cB > cc) & (dB <= dd))
contrast = A - B

extent = [cos_cuts[0], cos_cuts[-1], dh_cuts[0], dh_cuts[-1]]
fig, axes = plt.subplots(1, 2, figsize=(10.5, 4.3))

for ax, Z, title, cmap, lab in [
    (axes[0], B, '(a) Clean group (B/C/D) flag rate', 'viridis', 'flag rate (%)'),
    (axes[1], contrast, '(b) Firm A − B/C/D contrast', 'magma', 'contrast (pp)')]:
    im = ax.imshow(Z, origin='lower', aspect='auto', extent=extent, cmap=cmap)
    cb = fig.colorbar(im, ax=ax, pad=0.02); cb.set_label(lab, fontsize=8); cb.ax.tick_params(labelsize=7)
    # operating points
    ax.scatter([0.95], [5], marker='*', s=180, color='white', edgecolor='black', zorder=5,
               label='HC operating point (0.95, dHash≤5)')
    ax.axhline(15, color='white', ls=':', lw=1.0)
    ax.text(0.853, 15.4, 'MC upper bound (dHash≤15)', color='white', fontsize=6.5, va='bottom')
    ax.set_xlabel('cosine cut', fontsize=9)
    ax.set_ylabel('dHash cut (≤)', fontsize=9)
    ax.set_title(title, fontsize=9)
    ax.tick_params(labelsize=7.5)
    ax.legend(loc='lower left', fontsize=6.5, framealpha=0.85)

fig.suptitle('Figure 6. Sensitivity surface of the deployed rule over the two-measure threshold plane (Big-4, n=%d).' % len(c),
             fontsize=9, y=1.02)
fig.tight_layout()
out = '/Volumes/NV2/pdf_recognize/paper/v13_build/figures/fig6.png'
fig.savefig(out, dpi=200, bbox_inches='tight')
plt.close(fig)
print(f"fig6 OK n={len(c)}; HC(0.95,5) contrast={contrast[5, np.argmin(abs(cos_cuts-0.95))]:.1f}pp; written {out}")