def estimate_states(tree, outgroup, migration_matrix):
# estimate the states (by making each node trifurcating...)
root = tree.root
kids = root.GetKids()
if kids[0].name in outgroup:
true_root = kids[1]
else:
true_root = kids[0]
lik_score = ML.EstimateStates(true_root)
k = 1 + len(migration_matrix) * (len(migration_matrix.values()[0]) - 1)
aic_score = 2 * k - 2 * lik_score
return true_root, lik_score, aic_score
# wipe the likelihoods off of the tree (just to be sure)
ML.TreeWipe(tree.a_node)
# learn the likelihoods
print "Learn habitat assignments"
ML.LearnLiks(tree, mu, migration_matrix, outgroup)
# estimate the states (by making each node trifurcating...)
root = tree.root
kids = root.GetKids()
if kids[0].name in outgroup:
true_root = kids[1]
else:
true_root = kids[0]
lik_score = ML.EstimateStates(true_root)
k = 1 + len(migration_matrix) * (len(migration_matrix.values()[0]) - 1)
aic_score = 2 * k - 2 * lik_score
lik_f.write("likelihood: " + str(lik_score) + "\n")
lik_f.write("aic: " + str(aic_score) + "\n")
# write out the habitat assignment of each leaf
for leaf in true_root.leaf_nodes:
this_str = str(leaf) + "\t" + leaf.habitat
migration_f.write(this_str + "\n")
# draw out the tree
files = {}
files['full'] = full_f
if thresh_fn is not None:
stats_str += str(len(habitat_matrix)) + "\t"
stats_str += str(score) + "\t"
stats_str += str(mu) + "\t"
stats_str += str(diff) + "\t"
stats_file.write(stats_str + "\n")
stats_file.flush()
print "\t\t" + str(counter) + "\t" + str(diff)
# wipe the likelihoods off of the tree
ML.TreeWipe(tree)
# learn the likelihoods
ML.LearnLiks(tree,mu,habitat_matrix)
# estimate the states (by making each node trifurcating...)
ML.EstimateStates(tree.a_node,habitat_matrix)
# upgrade guesses for mu and habitat matrix
this_migrate = habitat_matrix
mu, habitat_matrix = ML.LearnRates(tree,mu,habitat_matrix,rateopt)
new_migrate = habitat_matrix
# stop?
old_diff = diff
score, diff = ML.CheckConverge(tree,new_migrate,this_migrate)
if diff < converge_thresh:
break
# this should break the loop if you end up bouncing back and
# forth between the same values
# wipe the likelihoods off of the tree (just to be sure)
ML.TreeWipe(tree.a_node)
# learn the likelihoods
print "Learn habitat assignments"
ML.LearnLiks(tree, mu, migration_matrix, outgroup)
# estimate the states (by making each node trifurcating...)
root = tree.root
kids = root.GetKids()
if kids[0].name in outgroup:
true_root = kids[1]
else:
true_root = kids[0]
ML.EstimateStates(true_root)
# write out the habitat assignment of each leaf
for leaf in true_root.leaf_nodes:
this_str = str(leaf) + "\t" + leaf.habitat
migration_f.write(this_str + "\n")
# draw out the tree
files = {}
files['full'] = full_f
if thresh_fn is not None:
files['cluster'] = cluster_f
files['bar'] = bars_f
files['prune'] = prune_f
files['cdist'] = cdist_f
def learn_habitats(tree, habitat_matrix, mu, rateopt,
converge_thresh, habitat_thresh):
"""Learn habitats
"""
sys.stderr.write('Learning Habitats:\n')
# setting/checking params
score = -9999.99999999
diff = 1.0
old_diff = 1.0
msg = 'The convergence threshold ({}) must be between 0 & 1'
assert 0 <= converge_thresh <= 1, msg.format(converge_thresh)
msg = 'The collapse threshold ({}) must be between 0 & 1'
assert 0 <= habitat_thresh <= 1, msg.format(habitat_thresh)
stats_header = ['counter', 'habs', 'ML_score', 'mu', 'habitat dist diff']
stats = [stats_header]
while 1:
msg = "\t{} habitats\tRefinement Steps [d(Habitat Score)]:\n"
sys.stderr.write(msg.format(len(habitat_matrix)))
counter = 0
stats_line = '{} habitats'.format(len(habitat_matrix))
stats.append([stats_line] + stats_header)
while 1:
msg = '\t\t{}\t{}\n'
sys.stderr.write(msg.format(counter, diff))
stats.append([counter, len(habitat_matrix), score, mu, diff])
# wipe the likelihoods off of the tree
ML.TreeWipe(tree)
# learn the likelihoods
ML.LearnLiks(tree,mu,habitat_matrix)
# estimate the states (by making each node trifurcating...)
ML.EstimateStates(tree.a_node,habitat_matrix)
# upgrade guesses for mu and habitat matrix
this_migrate = habitat_matrix
mu, habitat_matrix = ML.LearnRates(tree,mu,habitat_matrix,rateopt)
new_migrate = habitat_matrix
# stop?
old_diff = diff
score, diff = ML.CheckConverge(tree,new_migrate,this_migrate)
if diff < converge_thresh:
break
# this should break the loop if you end up bouncing back and
# forth between the same values
sig_figs = 8
diff1 = math.floor(diff*math.pow(10,sig_figs))
diff2 = math.floor(old_diff*math.pow(10,sig_figs))
if diff1 > 0:
if diff1 == diff2:
break
if counter > 500:
break
counter += 1
# remove similar habitats
new_habitats = remove_similar_habitats(habitat_matrix, habitat_thresh)
if len(new_habitats) == len(habitat_matrix):
break
habitat_matrix = new_habitats
if len(habitat_matrix) < 2:
break
msg = 'Learned {} habitats in {} seconds\n'
sys.stderr.write(msg.format(len(habitat_matrix), time.clock()))
return habitat_matrix, mu, stats
