from pylab import *
import tables
from collections import Counter

def crop_black(image):
    gray = image
    if gray.ndim==3: gray = sum(image,axis=2)
    yr = find(sum(gray,axis=1)>0)
    y0 = yr[0]
    y1 = yr[-1]
    xr = find(sum(gray,axis=0)>0)
    x0 = xr[0]
    x1 = xr[-1]
    if image.ndim==3: return image[y0:y1,x0:x1,:]
    else: return image[y0:y1,x0:x1]

hdf = tables.openFile("1k.h5","r")

image = crop_black(hdf.root.icons[60]/255.0)
imshow(image)

pixels = image.reshape(-1,3)

from scipy.cluster.vq import kmeans,vq
centers,_ = kmeans(pixels,8)
palettized,_ = vq(pixels,centers)
imshow(palettized.reshape(image.shape[:2]),cmap=cm.spectral)

quant = centers[palettized].reshape(image.shape)
subplot(121); imshow(quant)
subplot(122); imshow(image)

quant = centers[numpy.sort(palettized)].reshape(image.shape)
subplot(121); imshow(quant)
subplot(122); imshow(image)

from collections import Counter
counts = Counter(palettized)
[(centers[c],n) for c,n in counts.most_common(100)]

def color_descriptor(image,k=8):
    image = crop_black(image)
    total = 1.0*prod(image.shape[:2])
    if amax(image)>1: image = image/255.0
    pixels = image.reshape(-1,3)
    pixels = pixels[sum(pixels,axis=1)>0.01]
    centers,_ = kmeans(pixels,k)
    palettized,_ = vq(pixels,centers)  
    counts = Counter(palettized)
    return [(centers[c],n/total) for c,n in counts.most_common(k)]
color_descriptor(hdf.root.icons[1])

descriptors = [color_descriptor(hdf.root.icons[i]) for i in range(len(hdf.root.icons))]

def cdmatch(desc1,desc2,delta=0.25):
    delta2 = delta**2
    total = 0.0
    for v,p in desc1:
        for w,q in desc2:
            d = maximum(1-norm(v-w)**2/delta2,0)
            total += d * minimum(p,q)
    return total

print cdmatch(descriptors[1],descriptors[1])
print cdmatch(descriptors[1],descriptors[2])

def cddissim(desc1,desc2,delta=0.25):
    score = cdmatch(desc1,desc2,delta)
    score1 = cdmatch(desc1,desc1,delta)
    score2 = cdmatch(desc2,desc2,delta)
    return 1-score/max(score1,score2,1e-6)

scores = [cddissim(descriptors[5],descriptors[i]) for i in range(100)]
print scores[:8]
argsort(scores)

scores = [cddissim(descriptors[5],descriptors[i]) for i in range(100)]
for i,j in enumerate(argsort(scores)[:6]):
    subplot(1,6,i+1); axis("off"); imshow(hdf.root.icons[j]); title("%d %.2f"%(j,scores[j]))

subplot(121); hist(scores)
subplot(122); plot(sorted(scores)[:30])

scores = [cddissim(descriptors[22],descriptors[i]) for i in range(100)]
for i,j in enumerate(argsort(scores)[:6]):
    subplot(1,6,i+1); axis("off"); imshow(hdf.root.icons[j]); title("%d %.2f"%(j,scores[j]))

scores = [cddissim(descriptors[60],descriptors[i]) for i in range(100)]
for i,j in enumerate(argsort(scores)[:6]):
    subplot(1,6,i+1); axis("off"); imshow(hdf.root.icons[j]); title("%d %.2f"%(j,scores[j]))

subplot(121); hist(scores)
subplot(122); plot(sorted(scores)[:30])

h,w,_ = image.shape
scale = 3.0
rs,cs = mgrid[:h,:w]*scale/max(h,w)
augmented = array(list(transpose(image,[2,0,1]))+[rs,cs])
augmented = transpose(augmented,[1,2,0])

apixels = augmented.reshape(-1,5)
apixels[:10]

acenters,_ = kmeans(apixels,64)
apalettized,_ = vq(apixels,acenters)
imshow(apalettized.reshape(image.shape[:2]))

aquant = acenters[apalettized].reshape(h,w,5)
subplot(121); imshow(aquant[:,:,:3])
subplot(122); imshow(image)

counts = Counter(apalettized)
[(acenters[c],n) for c,n in counts.most_common(100)]