def _best_cluster(x):
counts =[]
for ward_or_phash, unions in pw:
counts.append([])
for u in unions:
p = 0
for item in x[1][ward_or_phash]:
p += u.get(item, 0)
counts[-1].append(p)
best = list(map(np.argmax, counts))
distances = [np.sum((kPoints[i] - flatten_hist_cen(x[1]))**2) for i in range(len(kPoints))]
best.append(np.argmin(distances))
# TODO I think the following line has a typo distances[b] is what is should be.
return [(x[0], (b, 'self', distances[best[-1]], x[1]['ward'], x[1]['phash'])) for b in best]
def kmeans(config):
""" Kmeans with merging and counting of perceptive hashes and
ward hashes among clusters."""
measures = sc.pickleFile(hdfs_path(config, "map_each_image", "measures"))
data = measures.map(lambda x: (x[1]["id"], flatten_hist_cen(x[1]), x[1]["phash"], x[1]["ward"])).cache()
K = config["n_clusters_group"]
convergeDist = config["kmeans_group_converge"]
sample = data.takeSample(False, K, 1)
kPoints = [k[1] for k in sample]
tempDist = 10 * convergeDist
idx = 0
within_set_sse = []
while tempDist > convergeDist:
max_len = config["in_memory_set_len"] / K
ward_max_len = int(0.5 * max_len)
phash_max_len = int(max_len - ward_max_len)
closest = data.map(partial(km_map, kPoints))
pointStats = closest.reduceByKey(partial(reduce_dist, ward_max_len, phash_max_len))
pts_hash_union = pointStats.map(lambda (x, (y, z, u, w)): (x, (y / z, u, w)))
tempDist = pts_hash_union.map(lambda (x, (y, u, w)): np.sum((kPoints[x] - y) ** 2)).sum()
newPoints = pts_hash_union.map(lambda (x, (y, u, w)): (x, np.array(y, dtype="int32"))).collect()
idx += 1
if idx > config["max_iter_group"]:
break
print("kmeans did iteration: ", idx, file=sys.stderr)
for (x, y) in newPoints:
kPoints[x] = y
phash_unions = pts_hash_union.map(lambda (x, (y, u, w)): u)
phash_unions.saveAsPickleFile(hdfs_path(config, "km", "phash_unions"))
ward_unions = pts_hash_union.map(lambda (x, (y, u, w)): w)
ward_unions.saveAsPickleFile(hdfs_path(config, "km", "ward_unions"))
# The rest of the function deals with writing various lookup tables.
# save the fit data and the meta stats as a single item in list
kpsave = sc.parallelize([kPoints, tempDist, within_set_sse])
kpsave.saveAsPickleFile(hdfs_path(config, "km", "cluster_center_meta"))
def flat(field_to_field):
flat_map = partial(flat_map_indicators, config["phash_chunk_len"], kPoints, {field_to_field: True})
data.flatMap(lambda x: flat_map(*x)).saveAsPickleFile(hdfs_path(config, "km", field_to_field))
options = options_template.copy()
options.update(config["kmeans_output"])
for k, v in options.items():
if v:
flat(k)
def kmeans(config):
""" Kmeans with merging and counting of perceptive hashes and
ward hashes among clusters."""
measures = sc.pickleFile(hdfs_path(config, 'map_each_image', 'measures'))
data = measures.map(lambda x: (x[1]['id'], flatten_hist_cen(x[1]), x[1][
'phash'], x[1]['ward'])).cache()
K = config['n_clusters_group']
convergeDist = config['kmeans_group_converge']
sample = data.takeSample(False, K, 1)
kPoints = [k[1] for k in sample]
if convergeDist is not None:
tempDist = 10 * convergeDist
else:
tempDist = 1e12
idx = 0
within_set_sse = []
while tempDist > convergeDist:
max_len = config['in_memory_set_len'] / K
ward_max_len = int(.5 * max_len)
phash_max_len = int(max_len - ward_max_len)
closest = data.map(partial(km_map, kPoints))
pointStats = closest.reduceByKey(
partial(reduce_dist, ward_max_len, phash_max_len))
pts_hash_union = pointStats.map(lambda (x, (y, z, u, w)):
(x, (y / z, u, w)))
if convergeDist is not None:
tempDist = pts_hash_union.map(lambda (x, (y, u, w)): np.sum(
(kPoints[x] - y)**2)).sum()
newPoints = pts_hash_union.map(
lambda (x, (y, u, w)): (x, np.array(y, dtype="int32"))).collect()
idx += 1
if idx > config['max_iter_group']:
break
print('kmeans did iteration: ', idx, file=sys.stderr)
for (x, y) in newPoints:
kPoints[x] = y
phash_unions = pts_hash_union.map(lambda (x, (y, u, w)): u)
phash_unions.saveAsPickleFile(hdfs_path(config, 'km', 'phash_unions'))
ward_unions = pts_hash_union.map(lambda (x, (y, u, w)): w)
ward_unions.saveAsPickleFile(hdfs_path(config, 'km', 'ward_unions'))
# The rest of the function deals with writing various lookup tables.
# save the fit data and the meta stats as a single item in list
kpsave = sc.parallelize([
kPoints,
tempDist,
within_set_sse,
])
kpsave.saveAsPickleFile(hdfs_path(config, 'km', 'cluster_center_meta'))
def flat(field_to_field):
flat_map = partial(flat_map_indicators, config['phash_chunk_len'],
kPoints, {field_to_field: True})
data.flatMap(lambda x: flat_map(*x)).saveAsPickleFile(
hdfs_path(config, 'km', field_to_field))
options = options_template.copy()
options.update(config['kmeans_output'])
for k, v in options.items():
if v:
flat(k)