def clust(self, clusters, cluster_id):
# initialize the distance matrix
dist_matrix = [[10000] * len(clusters) for i in range(len(clusters))]
# save the smallest value
min_val = 10000
imin = -1
jmin = -1
# fill out the distance matrix (lower half)
for i in range(len(clusters)):
j = i - 1
while j >= 0:
# compute pairwise distances b/n clusters
pairwise_distances = clusters[i] - clusters[j]
# fill out distance matrix depending on the link
if self.link == "S":
d = min(pairwise_distances)
elif self.link == "C":
d = max(pairwise_distances)
elif self.link == "A":
d = float(
sum(pairwise_distances)) / len(pairwise_distances)
dist_matrix[i][j] = d
# save info regarding
if d < min_val:
min_val = d
imin = i
jmin = j
# decrement j
j -= 1
# make new cluster based off new information
new_cluster = cluster_node(id=cluster_id)
new_cluster.add_children(clusters[imin])
new_cluster.add_children(clusters[jmin])
new_cluster.set_height(min_val)
# add new cluster union, remove unioned clusters
clusters.append(new_cluster)
clusters.remove(clusters[imin])
clusters.remove(clusters[jmin])
def clust(self, clusters, cluster_id):
# initialize the distance matrix
dist_matrix = [[10000]*len(clusters) for i in range(len(clusters))]
# save the smallest value
min_val = 10000
imin = -1
jmin = -1
# fill out the distance matrix (lower half)
for i in range(len(clusters)):
j = i - 1
while j >= 0:
# compute pairwise distances b/n clusters
pairwise_distances = clusters[i] - clusters[j]
# fill out distance matrix depending on the link
if self.link == "S":
d = min(pairwise_distances)
elif self.link == "C":
d = max(pairwise_distances)
elif self.link == "A":
d = float( sum(pairwise_distances) ) / len(pairwise_distances)
dist_matrix[i][j] = d
# save info regarding
if d < min_val:
min_val = d
imin = i
jmin = j
# decrement j
j -= 1
# make new cluster based off new information
new_cluster = cluster_node(id = cluster_id)
new_cluster.add_children(clusters[imin])
new_cluster.add_children(clusters[jmin])
new_cluster.set_height(min_val)
# add new cluster union, remove unioned clusters
clusters.append(new_cluster)
clusters.remove(clusters[imin])
clusters.remove(clusters[jmin])
def hclust(self, genes):
# initialize the leaf clusters based off the genes
# 1st value is gene id, 2nd value is gene description, 3rd value is vector of expr values
clusters = [cluster_node(g[0], g[1], map(float, g[2:])) for g in genes]
# identifier for cluster merges
i = len(clusters) + 1
# run clustering algorithm until there is only k nodes left (specified by user
while len(clusters) > self.k:
# merge two nodes
id = "cluster_" + str(i)
self.clust(clusters, id)
# increment
i += 1
# return clusters
return clusters
def hclust(self, genes):
# initialize the leaf clusters based off the genes
# 1st value is gene id, 2nd value is gene description, 3rd value is vector of expr values
clusters = [cluster_node(g[0], g[1], map(float, g[2:])) for g in genes]
# identifier for cluster merges
i = len(clusters) + 1
# run clustering algorithm until there is only k nodes left (specified by user
while len(clusters) > self.k:
# merge two nodes
id = "cluster_" + str(i)
self.clust(clusters, id)
# increment
i += 1
# return clusters
return clusters
