def do_kr(x, y, nclusters=4, verbose=1, use_global_attr_count=1, n_init=10):
kr = k_center1.KRepresentative(n_clusters=nclusters,
init='random',
n_init=n_init,
verbose=verbose,
use_global_attr_count=use_global_attr_count)
kr.fit_predict(x)
ari = evaluation.rand(kr.labels_, y)
nmi = evaluation.nmi(kr.labels_, y)
purity = evaluation.purity(kr.labels_, y)
homogenity, completeness, v_measure = homogeneity_completeness_v_measure(
y, kr.labels_)
if verbose == 1:
print("Purity = {:8.3f}".format(purity))
print("NMI = {:8.3f}".format(nmi))
print("Homogenity = {:8.3f}".format(homogenity))
print("Completeness = {:8.3f}".format(completeness))
print("V-measure = {:8.3f}".format(v_measure))
return [
round(purity, 3),
round(nmi, 3),
round(homogenity, 3),
round(completeness, 3),
round(v_measure, 3)
]
def do_kr(x, y, nclusters, verbose, use_global_attr_count, n_init):
start_time = time()
tracemalloc.start()
categorical = [0, 3, 4, 5, 6, 8, 9, 11, 12]
kr = KCMM(categorical, n_clusters = nclusters, init='random',
n_init = n_init, verbose = verbose, use_global_attr_count = use_global_attr_count)
kr.fit_predict(x)
# print(kr.labels_)
ari = evaluation.rand(kr.labels_, y)
nmi = evaluation.nmi(kr.labels_, y)
purity = evaluation.purity(kr.labels_, y)
homogenity, completeness, v_measure = homogeneity_completeness_v_measure(y, kr.labels_)
end_time = time()
elapsedTime = timedelta(seconds=end_time - start_time).total_seconds()
memoryUsage = tracemalloc.get_tracemalloc_memory() / 1024 / 1024
if verbose == 1:
print("Purity = {:8.3f}" . format(purity))
print("NMI = {:8.3f}" . format(nmi))
print("Homogenity = {:8.3f}" . format(homogenity))
print("Completeness = {:8.3f}" . format(completeness))
print("V-measure = {:8.3f}" . format(v_measure))
print("Elapsed Time = {:8.3f} secs".format(elapsedTime))
print("Memory usage = {:8.3f} MB".format(memoryUsage))
tracemalloc.stop()
return [round(purity,3),round(nmi,3),round(homogenity,3),round(completeness,3),round(v_measure,3),round(elapsedTime,3),round(memoryUsage,3)]
def do_kr(x, y, nclusters=4, verbose=1, n_init=10):
kr = kmodes.KModes(n_clusters=nclusters,
max_iter=1,
init='Huang',
n_init=n_init,
verbose=verbose)
kr.fit_predict(x)
ari = evaluation.rand(kr.labels_, y)
nmi = evaluation.nmi(kr.labels_, y)
purity = evaluation.purity(kr.labels_, y)
homogenity, completeness, v_measure = homogeneity_completeness_v_measure(
y, kr.labels_)
if verbose == 1:
print("Purity = {:8.3f}".format(purity))
print("NMI = {:8.3f}".format(nmi))
print("Homogenity = {:8.3f}".format(homogenity))
print("Completeness = {:8.3f}".format(completeness))
print("V-measure = {:8.3f}".format(v_measure))
return [
round(purity, 3),
round(nmi, 3),
round(homogenity, 3),
round(completeness, 3),
round(v_measure, 3)
]
def do_kr(x, y, nclusters, verbose, n_init):
start_time = time()
tracemalloc.start()
# Fill in missing values in numeric attributes in advances
xDataFrame = pd.DataFrame(x)
attrList = [0, 3, 4, 5, 6, 8, 9, 11, 12]
numOfRows = x.shape[0]
numOfCols = x.shape[1]
for i in range(0, numOfCols):
if i not in attrList:
colTmp = x[:, i].copy()
colTmp.sort()
if "?" not in colTmp:
continue
missIndex = colTmp.tolist().index("?")
colTmp = list(map(float, colTmp[0:missIndex]))
average = round(mean(colTmp), 2)
for j in range(0, numOfRows):
if xDataFrame.iloc[j, i] == "?":
xDataFrame.iloc[j, i] = average
x = np.asarray(xDataFrame)
kr = kpro.KPrototypes(n_clusters=nclusters,
max_iter=1,
init='random',
n_init=n_init,
verbose=verbose)
kr.fit_predict(x, categorical=attrList)
ari = evaluation.rand(kr.labels_, y)
nmi = evaluation.nmi(kr.labels_, y)
purity = evaluation.purity(kr.labels_, y)
homogenity, completeness, v_measure = homogeneity_completeness_v_measure(
y, kr.labels_)
end_time = time()
elapsedTime = timedelta(seconds=end_time - start_time).total_seconds()
memoryUsage = tracemalloc.get_tracemalloc_memory() / 1024 / 1024
if verbose == 1:
print("Purity = {:8.3f}".format(purity))
print("NMI = {:8.3f}".format(nmi))
print("Homogenity = {:8.3f}".format(homogenity))
print("Completeness = {:8.3f}".format(completeness))
print("V-measure = {:8.3f}".format(v_measure))
print("Elapsed Time = {:8.3f} secs".format(elapsedTime))
print("Memory usage = {:8.3f} MB".format(memoryUsage))
# snapshot = tracemalloc.take_snapshot()
# top_stats = snapshot.statistics('lineno')
# print("[ Top 10 ]")
# for stat in top_stats[:10]:
# print(stat)
tracemalloc.stop()
return [
round(purity, 3),
round(nmi, 3),
round(homogenity, 3),
round(completeness, 3),
round(v_measure, 3),
round(elapsedTime, 3),
round(memoryUsage, 3)
]