def __init__(self, data):
drange = self.__diameter(data)
dcount = data.shape[0]
# run clustering
clusterer = hcluster(compute_full_tree=True)
clusterer.fit(data.copy())
hc_children = clusterer.children_
# setup leaf clusters
clusters = {i: Cluster(i, None, None, data=np.array([data[i, :]]), count=1, range=0) for i in range(data.shape[0])}
leaves = {}
# setup tree
if drange != 0:
minrange = 1
for idx in range(hc_children.shape[0]):
children = hc_children[idx]
left_child, right_child = clusters[children[0]], clusters[children[1]]
id = idx + data.shape[0]
cluster = Cluster(id, left_child, right_child)
cluster.data = np.vstack((left_child.data, right_child.data))
cluster.range = self.__diameter(cluster.data) / (drange)
if cluster.range < minrange: minrange = cluster.range
cluster.count = left_child.count + right_child.count
left_child.parent = cluster
right_child.parent = cluster
clusters[id] = cluster
for id in clusters:
cluster = clusters[id]
leaf = (cluster.count == 1)
while (cluster.parent is not None and cluster.parent.range == 0):
cluster = cluster.parent
clusters[id] = cluster
if cluster.range == 0 and cluster.parent is not None and cluster.parent.range != 0:
if cluster.items is None:
cluster.items = set()
if leaf:
leaves[id] = cluster
cluster.items.add(id)
# clear "clusters" from original leaves
# set true leaves children to empty
cids = clusters.keys()
for id in cids:
cluster = clusters[id]
if cluster.id != id:
del clusters[id]
elif cluster.range == 0:
cluster.left, cluster.right = None, None
for id in clusters:
cluster = clusters[id]
if cluster.range == 0:
if minrange < 0.1:
cluster.range = minrange
else:
cluster.range = 1e-4
cluster.count = cluster.count * 1.0 / dcount
else:
big_cluster = Cluster(data.shape[0], None, None, data=np.array(data[0, :]), count=data.shape[0], range=1e-4)
big_cluster.items = set(range(data.shape[0]))
for i in range(data.shape[0]):
leaves[i] = big_cluster
clusters = {data.shape[0]: big_cluster}
# setup leaf levels
for lid in leaves:
lcluster = leaves[lid]
lcluster.level = 1
# compute all tree levels
computed = set([leaves[lid].id for lid in leaves.keys()])
for lid in leaves:
cluster = leaves[lid]
while (cluster is not None and (cluster.right is None or cluster.right.id in computed) and (cluster.left is None or cluster.left.id in computed)):
if (cluster.id not in computed):
cluster.level = max(cluster.right.level, cluster.left.level) + 1
computed.add(cluster.id)
cluster = cluster.parent
del computed
# set tree state variables
biggest, max_level = 0, 0
test_cl = leaves[0]
while (test_cl.parent is not None):
test_cl = test_cl.parent
self.root = test_cl
self.max_level = test_cl.level
self.data = data
self.clusters = clusters
self.leaves = leaves
self.__drange = drange
self.__dcount = dcount
def __init__(self, data):
drange = self.__diameter(data)
dcount = data.shape[0]
# run clustering
clusterer = hcluster(compute_full_tree=True)
clusterer.fit(data.copy())
hc_children = clusterer.children_
# setup leaf clusters
clusters = {
i: Cluster(i,
None,
None,
data=np.array([data[i, :]]),
count=1,
range=0)
for i in range(data.shape[0])
}
leaves = {}
# setup tree
if drange != 0:
minrange = 1
for idx in range(hc_children.shape[0]):
children = hc_children[idx]
left_child, right_child = clusters[children[0]], clusters[
children[1]]
id = idx + data.shape[0]
cluster = Cluster(id, left_child, right_child)
cluster.data = np.vstack((left_child.data, right_child.data))
cluster.range = self.__diameter(cluster.data) / (drange)
if cluster.range < minrange: minrange = cluster.range
cluster.count = left_child.count + right_child.count
left_child.parent = cluster
right_child.parent = cluster
clusters[id] = cluster
for id in clusters:
cluster = clusters[id]
leaf = (cluster.count == 1)
while (cluster.parent is not None
and cluster.parent.range == 0):
cluster = cluster.parent
clusters[id] = cluster
if cluster.range == 0 and cluster.parent is not None and cluster.parent.range != 0:
if cluster.items is None:
cluster.items = set()
if leaf:
leaves[id] = cluster
cluster.items.add(id)
# clear "clusters" from original leaves
# set true leaves children to empty
cids = clusters.keys()
for id in cids:
cluster = clusters[id]
if cluster.id != id:
del clusters[id]
elif cluster.range == 0:
cluster.left, cluster.right = None, None
for id in clusters:
cluster = clusters[id]
if cluster.range == 0:
if minrange < 0.1:
cluster.range = minrange
else:
cluster.range = 1e-4
cluster.count = cluster.count * 1.0 / dcount
else:
big_cluster = Cluster(data.shape[0],
None,
None,
data=np.array(data[0, :]),
count=data.shape[0],
range=1e-4)
big_cluster.items = set(range(data.shape[0]))
for i in range(data.shape[0]):
leaves[i] = big_cluster
clusters = {data.shape[0]: big_cluster}
# setup leaf levels
for lid in leaves:
lcluster = leaves[lid]
lcluster.level = 1
# compute all tree levels
computed = set([leaves[lid].id for lid in leaves.keys()])
for lid in leaves:
cluster = leaves[lid]
while (cluster is not None
and (cluster.right is None or cluster.right.id in computed)
and (cluster.left is None or cluster.left.id in computed)):
if (cluster.id not in computed):
cluster.level = max(cluster.right.level,
cluster.left.level) + 1
computed.add(cluster.id)
cluster = cluster.parent
del computed
# set tree state variables
biggest, max_level = 0, 0
test_cl = leaves[0]
while (test_cl.parent is not None):
test_cl = test_cl.parent
self.root = test_cl
self.max_level = test_cl.level
self.data = data
self.clusters = clusters
self.leaves = leaves
self.__drange = drange
self.__dcount = dcount
def __init__(self, data):
# NOTE: assumes data is 1-d numpy array
pos = data.argsort()
data = data[pos]
data = data.reshape(data.shape[0], 1)
drange = data[-1,0] - data[0,0]
dcount = data.shape[0]
# run clustering
# clusterer = hcluster(compute_full_tree=True)
clusterer = hcluster(compute_full_tree=True, linkage='complete')
clusterer.fit(data)
hc_children = clusterer.children_
# setup leaf clusters
clusters = {i: Cluster(i, None, None, data=(data[i, 0], data[i, 0]), count=1, range=0) for i in range(data.shape[0])}
leaves = {}
# setup tree
if drange != 0:
minrange = 1
for idx in range(hc_children.shape[0]):
children = hc_children[idx]
lc, rc = clusters[children[0]], clusters[children[1]]
check = 0 if lc.data[-1] < rc.data[0] else 1
left_child, right_child = clusters[children[check]], clusters[children[1-check]]
id = idx + data.shape[0]
cluster = Cluster(id, left_child, right_child)
cluster.data = (min(left_child.data), max(right_child.data))
cluster.range = (cluster.data[-1] - cluster.data[0]) / (drange)
if cluster.range < minrange: minrange = cluster.range
cluster.count = left_child.count + right_child.count
left_child.parent = cluster
right_child.parent = cluster
clusters[id] = cluster
for id in clusters:
cluster = clusters[id]
leaf = (cluster.count == 1)
while (cluster.parent is not None and cluster.parent.range == 0):
cluster = cluster.parent
clusters[id] = cluster
if cluster.range == 0 and cluster.parent is not None and cluster.parent.range != 0:
if cluster.items is None:
cluster.items = set()
if leaf:
leaves[id] = cluster
cluster.items.add(id)
cids = clusters.keys()
for id in cids:
cluster = clusters[id]
if cluster.id != id:
del clusters[id]
elif cluster.range == 0:
cluster.left, cluster.right = None, None
for id in clusters:
cluster = clusters[id]
if cluster.range == 0:
if minrange < 0.1:
cluster.range = minrange
else:
cluster.range = 1e-4
cluster.count = cluster.count * 1.0 / dcount
else:
big_cluster = Cluster(data.shape[0], None, None, data=(data[0,0], data[0,0]), count=data.shape[0], range=1e-4)
big_cluster.items = set(range(data.shape[0]))
for i in range(data.shape[0]):
leaves[i] = big_cluster
clusters = {data.shape[0]: big_cluster}
# setup leaf levels
for lid in leaves:
lcluster = leaves[lid]
lcluster.level = 1
# compute all tree levels
computed = set([leaves[lid].id for lid in leaves.keys()])
for lid in leaves:
cluster = leaves[lid]
while (cluster is not None and \
((cluster.data[0] == cluster.data[1]) or \
(cluster.right.id in computed and cluster.left.id in computed))):
if (cluster.id not in computed):
cluster.level = max(cluster.right.level, cluster.left.level) + 1
computed.add(cluster.id)
cluster = cluster.parent
del computed
# set tree state variables
biggest, max_level = 0, 0
for id in clusters:
if id > biggest: biggest = id
if clusters[id].level > max_level: max_level = clusters[id].level
self.data = data
self.root = clusters[biggest]
self.max_level = max_level
self.clusters = clusters
self.leaves = leaves
self.__dindex = pos
self.__findex = np.argsort(pos)
self.__drange = drange
self.__dcount = dcount
def __init__(self, data):
# NOTE: assumes data is 1-d numpy array
pos = data.argsort()
data = data[pos]
data = data.reshape(data.shape[0], 1)
drange = data[-1, 0] - data[0, 0]
dcount = data.shape[0]
# run clustering
# clusterer = hcluster(compute_full_tree=True)
clusterer = hcluster(compute_full_tree=True, linkage='complete')
clusterer.fit(data)
hc_children = clusterer.children_
# setup leaf clusters
clusters = {
i: Cluster(i,
None,
None,
data=(data[i, 0], data[i, 0]),
count=1,
range=0)
for i in range(data.shape[0])
}
leaves = {}
# setup tree
if drange != 0:
minrange = 1
for idx in range(hc_children.shape[0]):
children = hc_children[idx]
lc, rc = clusters[children[0]], clusters[children[1]]
check = 0 if lc.data[-1] < rc.data[0] else 1
left_child, right_child = clusters[children[check]], clusters[
children[1 - check]]
id = idx + data.shape[0]
cluster = Cluster(id, left_child, right_child)
cluster.data = (min(left_child.data), max(right_child.data))
cluster.range = (cluster.data[-1] - cluster.data[0]) / (drange)
if cluster.range < minrange: minrange = cluster.range
cluster.count = left_child.count + right_child.count
left_child.parent = cluster
right_child.parent = cluster
clusters[id] = cluster
for id in clusters:
cluster = clusters[id]
leaf = (cluster.count == 1)
while (cluster.parent is not None
and cluster.parent.range == 0):
cluster = cluster.parent
clusters[id] = cluster
if cluster.range == 0 and cluster.parent is not None and cluster.parent.range != 0:
if cluster.items is None:
cluster.items = set()
if leaf:
leaves[id] = cluster
cluster.items.add(id)
cids = clusters.keys()
for id in cids:
cluster = clusters[id]
if cluster.id != id:
del clusters[id]
elif cluster.range == 0:
cluster.left, cluster.right = None, None
for id in clusters:
cluster = clusters[id]
if cluster.range == 0:
if minrange < 0.1:
cluster.range = minrange
else:
cluster.range = 1e-4
cluster.count = cluster.count * 1.0 / dcount
else:
big_cluster = Cluster(data.shape[0],
None,
None,
data=(data[0, 0], data[0, 0]),
count=data.shape[0],
range=1e-4)
big_cluster.items = set(range(data.shape[0]))
for i in range(data.shape[0]):
leaves[i] = big_cluster
clusters = {data.shape[0]: big_cluster}
# setup leaf levels
for lid in leaves:
lcluster = leaves[lid]
lcluster.level = 1
# compute all tree levels
computed = set([leaves[lid].id for lid in leaves.keys()])
for lid in leaves:
cluster = leaves[lid]
while (cluster is not None and \
((cluster.data[0] == cluster.data[1]) or \
(cluster.right.id in computed and cluster.left.id in computed))):
if (cluster.id not in computed):
cluster.level = max(cluster.right.level,
cluster.left.level) + 1
computed.add(cluster.id)
cluster = cluster.parent
del computed
# set tree state variables
biggest, max_level = 0, 0
for id in clusters:
if id > biggest: biggest = id
if clusters[id].level > max_level: max_level = clusters[id].level
self.data = data
self.root = clusters[biggest]
self.max_level = max_level
self.clusters = clusters
self.leaves = leaves
self.__dindex = pos
self.__findex = np.argsort(pos)
self.__drange = drange
self.__dcount = dcount
