"""Table VI: HC flag rate by firm under any-pair (deployed) vs strict same-pair rule.
same-pair dHash = Hamming distance between a signature's dHash and its cosine-closest
same-accountant partner (closest_match_file). Reproduces from signature_analysis.db."""
import sqlite3
from collections import defaultdict
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')
FM={'勤業眾信聯合':'A','安侯建業聯合':'B','資誠聯合':'C','安永聯合':'D'}
con=sqlite3.connect(DB);cur=con.cursor()
cur.execute("SELECT image_filename, dhash_vector FROM signatures WHERE dhash_vector IS NOT NULL")
dh={fn:bytes(b) for fn,b in cur.fetchall()}
ham=lambda a,b: bin(int.from_bytes(a,'big')^int.from_bytes(b,'big')).count('1')
cur.execute(f"""SELECT excel_firm,max_similarity_to_same_accountant,min_dhash_independent,closest_match_file,image_filename
 FROM signatures WHERE is_valid=1 AND max_similarity_to_same_accountant IS NOT NULL
   AND min_dhash_independent IS NOT NULL AND excel_firm IN ({','.join('?'*4)})""",BIG4)
st=defaultdict(lambda:[0,0,0])
for firm,cos,mindh,cmf,imf in cur.fetchall():
    f=FM[firm]; st[f][0]+=1
    st[f][1]+= (cos>0.95 and mindh<=5)
    sp=ham(dh[imf],dh[cmf]) if (cmf in dh and imf in dh) else 99
    st[f][2]+= (cos>0.95 and sp<=5)
con.close()
print(f"{'firm':5}{'n':>8}{'any-pair%':>11}{'same-pair%':>12}")
T=[0,0,0]
for f in 'ABCD':
    n,a,s=st[f]; T=[T[0]+n,T[1]+a,T[2]+s]
    print(f"{f:5}{n:>8}{100*a/n:>10.1f}%{100*s/n:>11.1f}%")
n,a,s=T; print(f"{'all':5}{n:>8}{100*a/n:>10.1f}%{100*s/n:>11.1f}%")