def main():
args = kmeans_args()
rand = np.random.randint(10000000)
data_train, data_test = pre_processed_data(args, rand)
label_train, label_test = pre_processed_label(args, rand)
print('data loaded')
switch_choice = {'k': lambda: 'k-means++', 'r': lambda: 'random',
'm': lambda: mean_image(label_train, data_train)}
kmeans = KMeans(n_clusters=10, random_state=0,
init=switch_choice[args.init]()) \
.fit(extract_col(data_train, args.columns))
predicted = kmeans.predict(extract_col(data_test, args.columns))
print('kmeans done')
compare_class(predicted, label_test)
if args.create_mean:
create_images_from_rows('km', mean_image(predicted, data_test))
def main():
args = arg.preprocess_args()
rand = random.randint(0, 9999999)
data, _ = helper.pre_processed_data(args, rand, dry=False)
# data = data.reshape(-1,48,48)
if args.mean:
label, _ = helper.pre_processed_label(args, rand, dry=False)
data = preprocess.mean_image(label, data)
elif args.split is not None or args.randomize:
label, _ = helper.pre_processed_label(args, rand, dry=False)
helper.write_data_to_file(
(args.folder or helper.FOLDER) + (args.name or 'processed_data') +
'_l' + helper.EXT,
label,
fmt='%d',
h='0')
# for i in range(4):
# for j in range(4):
helper.write_data_to_file(
(args.folder or helper.FOLDER) +
(args.name or 'processed_data') # + str(i) + str(j)
+ helper.EXT,
data,
# [k[i*12:(i*12)+12,j*12:(j*12)+12].flatten() for k in data],
h=', '.join(str(i) for i in range(len(data[0]))))
def spectralclustering(data_train, data_test, label_train, label_test, args):
print('spectral clustering')
SC = SpectralClustering(n_clusters=10, affinity='nearest_neighbors').fit(data_train)
predict = SC.fit_predict(data_test)
print('spectral clustering done')
compare_class(predict, label_test)
if args.create_mean:
create_images_from_rows('SC', mean_image(SC.labels_, data_test))
def birch(data_train, data_test, label_train, label_test, args):
print('birch')
birch = Birch(n_clusters=10).fit(data_train)
predict = birch.predict(data_test)
print('birch done')
compare_class(predict, label_test)
if args.create_mean:
create_images_from_rows('bi', mean_image(predict, data_test))
def main():
args = arg.preprocess_args()
rand = 0
data, _ = helper.pre_processed_data_all(args, rand, dry=False)
if args.mean:
rand = random.randint(0, 9999999)
label, _ = helper.pre_processed_label_all(args, rand, dry=False)
data = preprocess.mean_image(label, data)
helper.create_images_from_rows((args.name or 'img'), data)
def featureagglomeration(data_train, data_test, label_train, label_test, args):
print('feature agglomeration')
FA = FeatureAgglomeration(n_clusters=10).fit(data_train)
transformation = FA.transform(data_test)
agglomeration = find_highest(transformation)
print('feature agglomeration done')
compare_class(agglomeration, label_test)
if args.create_mean:
create_images_from_rows('fa', mean_image(agglomeration, data_test))
def minibatchkmeans(data_train, data_test, label_train, label_test, args):
print('mini batch kmeans')
switch_choice = {'k': lambda: 'k-means++', 'r': lambda: 'random',
'm': lambda: mean_image(label_train, data_train)}
MKMeans = MiniBatchKMeans(n_clusters=10, init=switch_choice[args.init](), n_init=10).fit(data_train)
predict = MKMeans.predict(data_test)
print('mini batch kmeans done')
compare_class(predict, label_test)
if args.create_mean:
create_images_from_rows('mbkm', MKMeans.cluster_centers_)
def kmeans(data_train, data_test, label_train, label_test, args):
print('kmeans')
switch_choice = {'k': lambda: 'k-means++', 'r': lambda: 'random',
'm': lambda: mean_image(label_train, data_train)}
kmeans = KMeans(n_clusters=10, random_state=0, n_init=10,
init=switch_choice[args.init]()).fit(data_train)
predicted = kmeans.predict(data_test)
print('kmeans done')
compare_class(predicted, label_test)
if args.create_mean:
create_images_from_rows('km', kmeans.cluster_centers_)
def bayes(name_nb, fn_label, data_train, data_test, cm, col):
label_train, label_test = fn_label()
print('using all class')
print('****%s****' % NB[name_nb]['name'])
res = []
res.append(
sk_bayes(NB[name_nb]['fn'], data_train, label_train, data_test,
label_test, col))
for i in range(10):
print('=======')
label_train, label_test = fn_label(sep=SEP, i=i)
print('class %d' % i)
res.append(
sk_bayes(NB[name_nb]['fn'], data_train, label_train, data_test,
label_test, col))
if cm:
for i in range(len(res)):
create_images_from_rows('%d_b' % i,
mean_image(res[i][1], res[i][0]))
def main():
args = arg.preprocess_args()
rand = random.randint(0, 9999999)
data, _ = helper.pre_processed_data_all(args, rand, dry=False)
if args.mean:
label, _ = helper.pre_processed_label_all(args, rand, dry=False)
data = preprocess.mean_image(label, data)
elif args.split is not None or args.randomize:
label, _ = helper.pre_processed_label(args, rand, dry=False)
helper.write_data_to_file(
(args.folder or helper.FOLDER) + (args.name or 'processed_data') +
'_l' + helper.EXT,
label,
fmt='%d',
h='0')
# for i in range(4):
# for j in range(4):
helper.write_data_to_file((args.folder or helper.FOLDER) +
(args.name or 'processed_data') + helper.EXT,
data,
h=', '.join(str(i) for i in range(len(data[0]))))