import numpy as np, glob
from PIL import Image

files = sorted(glob.glob("an2/f*.png"))
imgs = [Image.open(f) for f in files]
print("PIL mode:", imgs[0].mode)
idx = [np.asarray(im.convert("P") if im.mode!="P" else im, dtype=np.uint8) for im in imgs]
N = len(idx); H,W = idx[0].shape; raw = H*W
print(f"frames={N} size={H}x{W} raw={raw} B/frame")

# --- per-pair change stats on the QUANTIZED stream ---
pct = np.array([100.0*np.count_nonzero(idx[i]!=idx[i-1])/raw for i in range(1,N)])
print(f"\n--- consecutive change % (24fps, quantized) ---")
print(f"mean {pct.mean():.1f}  median {np.median(pct):.1f}  p10 {np.percentile(pct,10):.1f}  p90 {np.percentile(pct,90):.1f}  max {pct.max():.1f}")
print(f"pairs under 2% changed: {np.count_nonzero(pct<2.0)}/{len(pct)}  ({100*np.count_nonzero(pct<2.0)/len(pct):.0f}%)")

# --- threshold dedupe (twos detection) ---
THRESH = 2.0
keep=[0]
for i in range(1,N):
    if 100.0*np.count_nonzero(idx[i]!=idx[keep[-1]])/raw >= THRESH:
        keep.append(i)
print(f"\n--- dedupe @ {THRESH}% ---")
print(f"unique frames: {len(keep)}/{N} -> effective {len(keep)/12.0:.1f} fps")

cp = np.array([100.0*np.count_nonzero(idx[keep[j]]!=idx[keep[j-1]])/raw for j in range(1,len(keep))])
print(f"unique-pair change %: mean {cp.mean():.1f} median {np.median(cp):.1f} p90 {np.percentile(cp,90):.1f} max {cp.max():.1f}")

def encode_size(a,b,gap=4):
    total=0
    for y in range(a.shape[0]):
        ra,rb=a[y],b[y]
        d=np.nonzero(ra!=rb)[0]
        if len(d)==0: continue
        spans=[]; s=d[0]; p=d[0]
        for x in d[1:]:
            if x-p>gap: spans.append((s,p)); s=x
            p=x
        spans.append((s,p))
        total+=2
        for s0,e0 in spans:
            seg=rb[s0:e0+1]; total+=2
            i2=0
            while i2<len(seg):
                r=1
                while i2+r<len(seg) and seg[i2+r]==seg[i2] and r<127: r+=1
                total += 2 if r>=3 else r
                i2+=r
    return total

sz=np.array([encode_size(idx[keep[j-1]],idx[keep[j]]) for j in range(1,len(keep))])
fps_eff=len(keep)/12.0
rate=sz.mean()*fps_eff
print(f"\n--- codec estimate ---")
print(f"delta bytes: mean {sz.mean():.0f} median {np.median(sz):.0f} p90 {np.percentile(sz,90):.0f} max {sz.max():.0f}")
print(f"ratio vs raw: {raw/sz.mean():.1f}:1")
print(f"stream rate : {rate/1024:.1f} KB/s")
print(f"22min video : {rate*22*60/1048576:.0f} MB")
px=cp.mean()/100*raw
print(f"blit cost   : ~{px*6.5/1000:.0f}k cycles/frame (budget 833k)")
print(f"p90 blit    : ~{np.percentile(cp,90)/100*raw*6.5/1000:.0f}k cycles")