MiniBatchKmeans.py

import time
import numpy as np
from sklearn import datasets
from sklearn.cluster import MiniBatchKMeans
from sklearn.feature_extraction.image import extract_patches_2d
faces = datasets. fetch_olivetti_faces( )
print('Learning the dictionary...')
rng = np.random.RandomState(0)
kmeans = MiniBatchKMeans(n_clusters=81, random_state=rng, verbose=True)
patch_size = (20, 20)

buffer = []
to = time.time()
# The online Learning part: cycle over the whole dataset 6 times
index = 0
for _ in range(6):
    for img in faces.images:
        data = extract_patches_2d(img, patch_size, max_patches=50,random_state=rng)
        data = np. reshape(data, (len(data), -1))
        buffer.append (data)
        index += 1
        if index % 10 == 0:
            data = np.concatenate(buffer, axis=0)
            data -= np.mean(data, axis=0)
            data /= np.std(data, axis=0)
            kmeans . partial_fit(data)
            buffer = []

        if index % 100 == 0:
            print('Partial fit of %4i out of %i' %(index,6*len(faces.images)))
dt = time.time() - to
print( 'done in %.2fs.' %dt)