def cluster_columns(self, data, parts, ordered=False):
assert len(parts.columns) == 1, "columns split is no longer supported"
assert all(var.is_continuous for var in data.domain.attributes)
col0 = parts.columns[0]
if col0.cluster is not None:
cluster = col0.cluster
else:
cluster = None
if col0.cluster_ordered is not None:
cluster_ord = col0.cluster_ordered
else:
cluster_ord = None
need_dist = cluster is None or (ordered and cluster_ord is None)
matrix = None
if need_dist:
data = Orange.distance._preprocess(data)
matrix = np.asarray(Orange.distance.PearsonR(data, axis=0))
# nan values break clustering below
matrix = np.nan_to_num(matrix)
if cluster is None:
assert matrix is not None
assert len(matrix) < self.MaxClustering
cluster = hierarchical.dist_matrix_clustering(
matrix, linkage=hierarchical.WARD)
if ordered and cluster_ord is None:
assert len(matrix) < self.MaxOrderedClustering
cluster_ord = hierarchical.optimal_leaf_ordering(cluster, matrix)
col_groups = [
col._replace(cluster=cluster, cluster_ordered=cluster_ord)
for col in parts.columns
]
return parts._replace(columns=col_groups)
def setUpClass(cls):
m = [
[],
[3],
[2, 4],
[17, 5, 4],
[2, 8, 3, 8],
[7, 5, 10, 11, 2],
[8, 4, 1, 5, 11, 13],
[4, 7, 12, 8, 10, 1, 5],
[13, 9, 14, 15, 7, 8, 4, 6],
[12, 10, 11, 15, 2, 5, 7, 3, 1],
]
cls.items = [
"Ann",
"Bob",
"Curt",
"Danny",
"Eve",
"Fred",
"Greg",
"Hue",
"Ivy",
"Jon",
]
dist = numpy.array(list(flatten(m)), dtype=float)
matrix = hierarchical.squareform(dist, mode="lower")
cls.m = m
cls.matrix = Orange.misc.DistMatrix(matrix)
cls.matrix.items = cls.items
cls.cluster = hierarchical.dist_matrix_clustering(cls.matrix)
def cluster_rows(self, data: Table, parts: 'Parts', ordered=False) -> 'Parts':
row_groups = []
for row in parts.rows:
if row.cluster is not None:
cluster = row.cluster
else:
cluster = None
if row.cluster_ordered is not None:
cluster_ord = row.cluster_ordered
else:
cluster_ord = None
if row.can_cluster:
matrix = None
need_dist = cluster is None or (ordered and cluster_ord is None)
if need_dist:
subset = data[row.indices]
matrix = Orange.distance.Euclidean(subset)
if cluster is None:
assert len(matrix) < self.MaxClustering
cluster = hierarchical.dist_matrix_clustering(
matrix, linkage=hierarchical.WARD
)
if ordered and cluster_ord is None:
assert len(matrix) < self.MaxOrderedClustering
cluster_ord = hierarchical.optimal_leaf_ordering(
cluster, matrix,
)
row_groups.append(row._replace(cluster=cluster, cluster_ordered=cluster_ord))
return parts._replace(rows=row_groups)
def cluster_data(self, matrix):
with self.progressBar():
# cluster rows
if len(matrix) > 1:
rows_distances = Euclidean(matrix)
cluster = hierarchical.dist_matrix_clustering(rows_distances)
row_order = hierarchical.optimal_leaf_ordering(
cluster, rows_distances, progress_callback=self.progressBarSet)
row_order = np.array([x.value.index for x in leaves(row_order)])
else:
row_order = np.array([0])
# cluster columns
if matrix.X.shape[1] > 1:
columns_distances = Euclidean(matrix, axis=0)
cluster = hierarchical.dist_matrix_clustering(columns_distances)
columns_order = hierarchical.optimal_leaf_ordering(
cluster, columns_distances,
progress_callback=self.progressBarSet)
columns_order = np.array([x.value.index for x in leaves(columns_order)])
else:
columns_order = np.array([0])
return row_order, columns_order
def setUpClass(cls):
m = [[],
[3],
[2, 4],
[17, 5, 4],
[2, 8, 3, 8],
[7, 5, 10, 11, 2],
[8, 4, 1, 5, 11, 13],
[4, 7, 12, 8, 10, 1, 5],
[13, 9, 14, 15, 7, 8, 4, 6],
[12, 10, 11, 15, 2, 5, 7, 3, 1]]
cls.items = ["Ann", "Bob", "Curt", "Danny", "Eve", "Fred",
"Greg", "Hue", "Ivy", "Jon"]
dist = numpy.array(list(flatten(m)), dtype=float)
matrix = hierarchical.squareform(dist, mode="lower")
cls.m = m
cls.matrix = Orange.misc.DistMatrix(matrix)
cls.matrix.items = cls.items
cls.cluster = hierarchical.dist_matrix_clustering(cls.matrix)
def _cluster_tree(self):
if self._tree is None:
self._tree = hierarchical.dist_matrix_clustering(self.matrix)
return self._tree
