def main(datafile, threshold):
filename = "out{}{}.hrc".format(os.sep, os.path.basename(datafile.name))
if not os.path.isfile(filename):
header = datafile.readline()
collist = [i for i, toggle in enumerate(header.split(",")) if toggle != "0"]
datafile.seek(0)
data = pd.read_csv(datafile, usecols=collist).as_matrix()
pipeline = Pipeline([("clf", Hierarchical())])
pipeline.set_params(**{})
pipeline.fit(data)
clf = pipeline.get_params()["clf"]
hierarchy = clf.hierarchy_
with open(filename, "wb") as fh:
fh.write(ET.tostring(hierarchy.to_xml()))
else:
with open(filename, "rb") as fh:
hierarchy = Cluster.from_xml(ET.parse(fh).getroot())
print(ET.tostring(hierarchy.to_xml()).decode("utf-8"))
if threshold != None:
clusters = hierarchy.cut(threshold)
print("\n".join(c.to_str(i) for i, c in enumerate(clusters)))
dump_graph(clusters)
def test_from_xml_small2(self):
expected = Cluster([
Cluster([np.array([3,0,4])]),
Cluster([np.array([0,0,0])])
])
actual = Cluster.from_xml(
ET.fromstring('<tree height="5.0"><leaf data="[3, 0, 4]"/><leaf data="[0, 0, 0]"/></tree>')
)
self.assertEqual(actual, expected)
def test_from_xml(self):
actual = Cluster.from_xml(self.xml)
expected = self.tree
self.assertEqual(actual, expected)
def test_from_xml_small(self):
expected = Cluster([np.array([7,4,8])])
actual = Cluster.from_xml(
ET.fromstring('<tree height="0.0"><leaf data="[7, 4, 8]"/></tree>')
)
self.assertEqual(actual, expected)