def test_add_edge_effect_with_weight():
graph = Graph()
end = graph.add_node('coffee')
start = graph.add_node('muffin')
graph.add_edge(start, end, 44)
expected = (end, 44)
actual = graph._adjacency_list[start][0]
assert actual == expected
def test_breadth_first():
g = Graph()
v1 = g.add_node('Pandora')
v2 = g.add_node('Mordor')
g.add_nondirectional_edge(v1, v2, 110)
expected = ['Pandora', 'Mordor']
actual = g.breadth_first(v1)
assert expected == actual
def test_get_nodes():
graph = Graph()
graph.add_node('coffee')
graph.add_node('muffin')
Vertex('loner')
expected = 2
actual = len(graph.get_nodes())
assert actual == expected
def test_get_neighbors():
graph = Graph()
end = graph.add_node('coffee')
start = graph.add_node('muffin')
graph.add_edge(start, end, 44)
neighbors = graph.get_neighbors(start)
assert len(neighbors) == 1
assert neighbors[0][0].value == 'coffee'
assert isinstance(neighbors[0][0], Vertex)
assert neighbors[0][1] == 44
def erdos_renyi(n, p): g = Graph() for i in xrange(n): g.add_node(DiscreteVariable([0,1], name=str(i))) for i,j in itertools.product(xrange(n), xrange(n)): if random.random() < p: g.add_edge(g.get_node_by_name(str(i)),g.get_node_by_name(str(j))) return g
def erdos_renyi(n, p):
g = Graph()
for i in xrange(n):
g.add_node(DiscreteVariable([0, 1], name=str(i)))
for i, j in itertools.product(xrange(n), xrange(n)):
if random.random() < p:
g.add_edge(g.get_node_by_name(str(i)), g.get_node_by_name(str(j)))
return g
def test_add_edge_interloper_start():
graph = Graph()
start = Vertex('start')
end = graph.add_node('end')
with pytest.raises(KeyError):
graph.add_edge(start, end)
def test_depth_first_3():
g = Graph()
v1 = g.add_node('A')
v2 = g.add_node('B')
v3 = g.add_node('C')
v4 = g.add_node('G')
v5 = g.add_node('D')
v6 = g.add_node('E')
v7 = g.add_node('F')
v8 = g.add_node('H')
g.add_nondirectional_edge(v1, v2, 110)
g.add_nondirectional_edge(v1, v5, 43)
g.add_nondirectional_edge(v2, v3, 50)
g.add_nondirectional_edge(v2, v5, 12)
g.add_nondirectional_edge(v3, v4, 75)
g.add_nondirectional_edge(v5, v6, 21)
g.add_nondirectional_edge(v5, v8, 29)
g.add_nondirectional_edge(v5, v7, 23)
g.add_nondirectional_edge(v7, v8, 14)
actual = g.depth_first(v5)
expected = ['D', 'A', 'B', 'C', 'G', 'E', 'H', 'F']
assert actual == expected
def test_get_edges_one_vertex():
g = Graph()
v1 = g.add_node('Pandora')
v2 = g.add_node('Mordor')
v3 = g.add_node('Monstropolis')
v4 = g.add_node('Metroville')
v5 = g.add_node('Naboo')
v6 = g.add_node('Narnia')
g.add_nondirectional_edge(v1, v2, 110)
g.add_nondirectional_edge(v2, v3, 50)
g.add_nondirectional_edge(v2, v4, 12)
g.add_nondirectional_edge(v3, v5, 43)
g.add_nondirectional_edge(v4, v5, 23)
g.add_nondirectional_edge(v4, v6, 14)
g.add_nondirectional_edge(v5, v6, 21)
actual = g.get_edge(['Mordor'])
expected = (True, '$0')
assert actual == expected
from graphs import Graph
def dfs_visit(graph, source, parent, finished):
for u in graph.adj_list(source):
if u not in parent:
parent[u] = source
dfs_visit(graph, u, parent, finished)
finished.append(source)
def dfs(graph):
parent = {}
finished = []
vertices = graph.vertices()
for v in vertices:
if v not in parent:
parent[v] = None
dfs_visit(graph, v, parent, finished)
finished = list(reversed(finished))
return parent, finished
if __name__ == '__main__':
g = Graph()
for key in [1, 2, 3, 4]:
g.add_node(key)
g.add_edge(1, 2)
g.add_edge(2, 3)
g.add_edge(3, 4)
g.add_edge(4, 1)
print(dfs(g))
queue.append(start)
# do BFS
while(len(queue) > 0):
next_node = queue.pop(0)
for neighbor in graph.get_edges(next_node):
if neighbor not in visited:
queue.append(neighbor)
visited.append(next_node)
# print results
return {"reachable_nodes": visited}
# test
if __name__ == "__main__":
my_graph = Graph()
node1 = Node(10, 1)
node2 = Node(13, 2)
node3 = Node(20, 3)
my_graph.add_node(node1)
my_graph.add_edge((node2, node3))
my_graph.add_edge((node3, node1))
my_graph.print_nodes()
my_graph.print_edges()
print breadth_first_search(my_graph, node2)
def test_add_edge_works():
graph = Graph()
start = graph.add_node('start')
end = graph.add_node('end')
graph.add_edge(start, end)
def test_add_node():
graph = Graph()
actual = graph.add_node('testing').value
expected = 'testing'
assert actual == expected
def test_size():
graph = Graph()
graph.add_node('testing')
expected = 1
actual = graph.size()
assert actual == expected
def get_graph(my_orfs):
G = Graph(directed=True)
pgap = my_orfs.pstop
for orf in my_orfs.iter_orfs():
if(orf.frame > 0):
source = Node('CDS', 'start', orf.frame, orf.start)
target = Node('CDS', 'stop', orf.frame, orf.stop)
else:
source = Node('CDS', 'stop', orf.frame, orf.stop)
target = Node('CDS', 'start', orf.frame, orf.start)
G.add_edge(Edge(source, target, orf.weight))
#-------------------------------Check for long noncoding regions that would break the path---------#
bases = [None] * my_orfs.contig_length
for orfs in my_orfs.iter_in():
for orf in orfs:
mi = min(orf.start, orf.stop)
ma = max(orf.start, orf.stop)
for n in range(mi, min(ma, my_orfs.contig_length-1)):
try:
bases[n] = n
except:
sys.stderr.write("error in breaking region"+str(n))
break
last = 0
for base in bases:
if(base):
if(base-last > 300):
for right_node in G.iternodes():
for left_node in G.iternodes():
l = left_node.position
r = right_node.position
if(last+1 >= l > last-300 and base-1 <= r < base+300):
if(left_node.frame*right_node.frame > 0):
if(left_node.type == 'stop' and right_node.type =='start' and left_node.frame > 0):
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score))
elif(left_node.type == 'start' and right_node.type =='stop' and left_node.frame < 0):
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score ))
else:
if(left_node.type == 'stop' and right_node.type =='stop' and left_node.frame > 0):
score = score_gap(r-l-3, 'diff', pgap)
G.add_edge(Edge(left_node, right_node, score ))
elif(left_node.type == 'start' and right_node.type =='start' and left_node.frame < 0):
score = score_gap(r-l-3, 'diff',pgap)
G.add_edge(Edge(left_node, right_node, score ))
last = base
#-------------------------------Add in tRNA data---------------------------------------------------#
add_trnas(my_orfs, G)
#-------------------------------Connect the open reading frames to each other----------------------#
for right_node in G.iternodes():
r = right_node.position
if(right_node.gene == 'CDS'):
r_other = my_orfs.other_end[r]
else:
r_other = my_orfs.other_end['t'+str(r)]
for left_node in G.iternodes():
l = left_node.position
if(left_node.gene == 'CDS'):
l_other = my_orfs.other_end[l]
else:
l_other = my_orfs.other_end['t'+str(l)]
if(0 < r-l < 300):
if(l in my_orfs and my_orfs.other_end[l] in my_orfs[l]):
o1 = my_orfs.get_orf(my_orfs.other_end[l], l).pstop
elif(l in my_orfs):
o1 = my_orfs.get_orf(l, my_orfs.other_end[l]).pstop
else:
o1 = pgap
if(r in my_orfs and my_orfs.other_end[r] in my_orfs[r]):
o2 = my_orfs.get_orf(my_orfs.other_end[r], r).pstop
elif(r in my_orfs):
o2 = my_orfs.get_orf(r, my_orfs.other_end[r]).pstop
else:
o2 = pgap
pstop = ave([o1, o2])
#trna
if(left_node.gene == 'tRNA' or right_node.gene == 'tRNA'):
if(left_node.frame*right_node.frame > 0 and left_node.type != right_node.type):
if(left_node.frame > 0 and left_node.type == 'stop') or (left_node.frame < 0 and left_node.type == 'start'):
if not G.has_edge(Edge(left_node, right_node, 1)):
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score ))
elif(left_node.frame*right_node.frame < 0 and left_node.type == right_node.type):
if(left_node.frame > 0 and left_node.type == 'stop') or (left_node.frame < 0 and left_node.type == 'start'):
if not G.has_edge(Edge(left_node, right_node, 1)):
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score ))
# same directions
elif(left_node.frame*right_node.frame > 0):
if(left_node.type == 'stop' and right_node.type =='start'):
if(left_node.frame > 0):
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score ))
else:
if(left_node.frame != right_node.frame):
if(r < l_other and r_other < l):
score = score_overlap(r-l+3, 'same', pstop)
G.add_edge(Edge(right_node, left_node, score ))
if(left_node.type == 'start' and right_node.type =='stop'):
if(left_node.frame > 0):
if(left_node.frame != right_node.frame):
if(r < l_other and r_other < l):
score = score_overlap(r-l+3, 'same', pstop)
G.add_edge(Edge(right_node, left_node, score ))
else:
score = score_gap(r-l-3, 'same', pgap)
G.add_edge(Edge(left_node, right_node, score ))
# different directions
else:
if(left_node.type == 'stop' and right_node.type =='stop'):
if(right_node.frame > 0):
if(r_other+3 < l and r < l_other):
score = score_overlap(r-l+3, 'diff', pstop)
G.add_edge(Edge(right_node, left_node, score ))
else:
score = score_gap(r-l-3, 'diff', pgap)
G.add_edge(Edge(left_node, right_node, score ))
if(left_node.type == 'start' and right_node.type =='start'):
if(right_node.frame > 0 and r-l > 2):
score = score_gap(r-l-3, 'diff', pgap)
G.add_edge(Edge(left_node, right_node, score ))
elif(right_node.frame < 0):
#print(r_other, l, r, l_other)
if(r_other < l and r < l_other):
score = score_overlap(r-l+3, 'diff', pstop)
G.add_edge(Edge(right_node, left_node, score ))
#-------------------------------Connect open reading frames at both ends to a start and stop-------#
source = Node('source', 'source', 0, 0)
target = Node('target', 'target', 0, my_orfs.contig_length+1)
G.add_node(source)
G.add_node(target)
for node in G.iternodes():
if(node.position <= 2000):
if( (node.type == 'start' and node.frame > 0) or (node.type =='stop' and node.frame < 0) ):
score = score_gap(node.position, 'same', pgap)
G.add_edge(Edge(source, node, score))
if(my_orfs.contig_length - node.position <= 2000):
if( (node.type == 'start' and node.frame < 0) or (node.type =='stop' and node.frame > 0) ):
score = score_gap(my_orfs.contig_length-node.position, 'same', pgap)
G.add_edge(Edge(node, target, score))
return G
