def get_consensus_edges(nwkFittestTrees):
N = len(nwkFittestTrees)
Edges = {} # track edge appearance across fittest trees
cEdges = [] # edges labeled with fraction of times they appear
for nwkTree in nwkFittestTrees:
tree = Node.from_newick(nwkTree)
tree.update_descendants()
edges = tree.get_pairs()
for edge in edges:
if edge not in Edges.keys():
Edges[edge] = 0
Edges[edge]+=1
# sort edges by value if they are numeric
clusterLabels = list(set(zip(*Edges.keys())[0] + \
zip(*Edges.keys())[1]))
# if cluster IDs are numeric, sort
if sum([x.isdigit() for x in clusterLabels]) == len(clusterLabels):
edgeKeys = sorted(Edges.keys(), \
key = lambda x: (int(x[0]),int(x[1])))
else:
edgeKeys = sorted(Edges.keys())
# prepare to return edges labeled with frequency information
for edge in edgeKeys:
cEdges.append('\t'.join(map(str, edge) +\
[str(float(Edges[edge])/N),\
str(Edges[edge]) + '/' + str(N)]))
return cEdges
def get_consensus_edges(nwkFittestTrees):
N = len(nwkFittestTrees)
Edges = {} # track edge appearance across fittest trees
cEdges = [] # edges labeled with fraction of times they appear
for nwkTree in nwkFittestTrees:
tree = Node.from_newick(nwkTree)
tree.update_descendants()
edges = tree.get_pairs()
for edge in edges:
if edge not in Edges.keys():
Edges[edge] = 0
Edges[edge] += 1
# sort edges by value if they are numeric
clusterLabels = list(set(zip(*Edges.keys())[0] + \
zip(*Edges.keys())[1]))
# if cluster IDs are numeric, sort
if sum([x.isdigit() for x in clusterLabels]) == len(clusterLabels):
edgeKeys = sorted(Edges.keys(), \
key = lambda x: (int(x[0]),int(x[1])))
else:
edgeKeys = sorted(Edges.keys())
# prepare to return edges labeled with frequency information
for edge in edgeKeys:
cEdges.append('\t'.join(map(str, edge) +\
[str(float(Edges[edge])/N),\
str(Edges[edge]) + '/' + str(N)]))
return cEdges
