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=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, 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, 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)
]
for d in dataset:
for i in xrange(0, cls_idx):
d.tuple[i] = float(d.tuple[i] - mins[i].tuple[i]) / (maxs[i].tuple[i] -
mins[i].tuple[i])
f_norm.write(str(d.tuple))
f_norm.write('\n')
k = int(sys.argv[1])
eps = float(sys.argv[2])
cluster = dbscan.dbscan(dataset, eps, k)
if len(cluster) == 0:
print 'k:', k, 'no. of cluster:', len(cluster)
print
pure = evaluation.purity(cluster, len(dataset))
NMI = evaluation.NMI(cluster, dataset)
RI = evaluation.RI(cluster, dataset)
cp = [len(c) for c in cluster]
f_out = open("output.txt", 'w')
for i in xrange(0, len(cluster)):
print 'cluster:', i, 'no. of pt. in cluster:', cp[i]
for c in cluster[i]:
s = str(i) + " " + str(c.cls)
f_out.write(s)
f_out.write('\n')
f_out.close()
min_index=0
min_value=1e100
data=self.data[i,:]
for j in range(0,len(self.center)):
square=self.distance(self.center[j],data)
if(square<min_value):
min_index=j
min_value=square
predict_index[i]=min_index
return predict_index
if __name__ == '__main__':
clusters=20
data,label_family,label_genus,label_species,label_record=data_reader.read_frog_data()
data=PCA.pca(data,10)
print(data.shape)
label=np.argmin(-label_family,axis=1)
predictor=k_means(data,label,clusters)
predictor.init_center()
iteration=100
for i in range(0,iteration):
predictor.update()
predict=predictor.predict_data()
acc=evaluation.multi_label_accuracy(predict,label,clusters)
p=evaluation.purity(predict,label,clusters)
F_score=evaluation.F_score(predict,label,clusters)
F_score_output=evaluation.format_F_score(F_score)
print("the acc in it %d is %.4f %.4f"%(i,acc,p))
print("the Fscore is "+F_score_output)