def test_mb_k_means(self) -> None:
s = self.scheduler()
n_clusters = 3
try:
dataset = (get_dataset("cluster:s3"), )
except TimeoutError:
print("Cannot download cluster:s3")
return
with s:
csv = CSVLoader(
dataset,
sep=" ",
skipinitialspace=True,
header=None,
index_col=False,
scheduler=s,
)
km = MBKMeans(
n_clusters=n_clusters,
random_state=42,
is_input=False,
is_greedy=False,
scheduler=s,
)
# km.input.table = csv.output.result
km.create_dependent_modules(csv)
pr = Print(proc=self.terse, scheduler=s)
pr.input[0] = km.output.result
e = Every(proc=self.terse, scheduler=s)
e.input[0] = km.output.labels
aio.run(s.start())
labels = km.labels()
assert labels is not None
self.assertEqual(len(csv.table), len(labels))
'name': cname,
'x_column': '_0',
'y_column': '_1',
'sample': mbkmeans if i == 0 else None,
'input_module': filt,
'input_slot': 'table'
})
sp = MCScatterPlot(scheduler=s, classes=classes)
sp.create_dependent_modules()
for i in range(n_clusters):
cname = f"k{i}"
sp[cname].min_value._table = PsDict({'_0': -np.inf, '_1': -np.inf})
sp[cname].max_value._table = PsDict({'_0': np.inf, '_1': np.inf})
mbkmeans.input.table = data.output.table
mbkmeans.create_dependent_modules()
sp.move_point = mbkmeans.moved_center # for input management
def myprint(d):
if d['convergence'] != 'unknown':
print(d)
else:
print('.', end='')
prn = Every(scheduler=s, proc=print)
prn.input.df = mbkmeans.output.conv
if __name__ == '__main__':
#data.start()