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))
def test_mb_k_means(self):
#log_level()
s=Scheduler()
n_clusters = 3
csv = CSVLoader(get_dataset('cluster:s3'),sep=' ',skipinitialspace=True,header=None,index_col=False,scheduler=s)
km = MBKMeans(n_clusters=n_clusters, random_state=42, is_input=False, scheduler=s)
km.input.df = csv.output.df
pr = Print(scheduler=s)
pr.input.df = km.output.df
e = Every(scheduler=s)
e.input.df = km.output.labels
s.start()
self.assertEquals(len(csv.df()), len(km.labels()))
def test_mb_k_means(self):
#log_level()
s = self.scheduler()
n_clusters = 3
csv = CSVLoader(get_dataset('cluster:s3'),
sep=' ',
skipinitialspace=True,
header=None,
index_col=False,
scheduler=s)
km = MBKMeans(n_clusters=n_clusters,
random_state=42,
is_input=False,
scheduler=s)
km.input.table = csv.output.table
pr = Print(proc=self.terse, scheduler=s)
pr.input.df = km.output.table
e = Every(proc=self.terse, scheduler=s)
e.input.df = km.output.labels
s.start()
s.join()
self.assertEqual(len(csv.table()), len(km.labels()))