def testBasicEst(self):
# list of tuples, (birth-rate, log-likelihood)
expected_results = (
# birth rate # log-likelihood
(0.02879745490817826186758, -59.41355682054444287132355),
(0.03074708092192806122012, -57.38280732060526645454956),
(0.02539588437187430269848, -63.31025321526630023072357),
(0.02261951969802362960582, -66.89924384677527768872096),
(0.02804607815688910446572, -60.23314120509648716961237),
(0.02748663302756114423797, -60.85775993426526042640035),
(0.02816256618562208019485, -60.10465085978295007862471),
(0.03592126646048716259729, -52.56123967307649991198559),
(0.02905144990609926855529, -59.14133401672411594063306),
(0.02703739196351075124714, -61.36860953277779628933786),
(0.01981322730236481297061, -71.00561162515919022553135),
)
trees = dendropy.TreeList.get_from_path(
pathmap.tree_source_path("pythonidae.reference-trees.newick"), "newick")
self.assertEqual(len(trees), len(expected_results))
for tree, expected_result in zip(trees, expected_results):
obs_result1 = birthdeath.fit_pure_birth_model(tree=tree, ultrametricity_precision=1e-5)
obs_result2 = birthdeath.fit_pure_birth_model(internal_node_ages=tree.internal_node_ages(ultrametricity_precision=1e-5))
for obs_result in (obs_result1, obs_result2):
self.assertAlmostEqual(obs_result["birth_rate"], expected_result[0], 5)
self.assertAlmostEqual(obs_result["log_likelihood"], expected_result[1], 5)
def testBasicEst(self):
# list of tuples, (birth-rate, log-likelihood)
expected_results = (
# birth rate # log-likelihood
(0.02879745490817826186758, -59.41355682054444287132355),
(0.03074708092192806122012, -57.38280732060526645454956),
(0.02539588437187430269848, -63.31025321526630023072357),
(0.02261951969802362960582, -66.89924384677527768872096),
(0.02804607815688910446572, -60.23314120509648716961237),
(0.02748663302756114423797, -60.85775993426526042640035),
(0.02816256618562208019485, -60.10465085978295007862471),
(0.03592126646048716259729, -52.56123967307649991198559),
(0.02905144990609926855529, -59.14133401672411594063306),
(0.02703739196351075124714, -61.36860953277779628933786),
(0.01981322730236481297061, -71.00561162515919022553135),
)
trees = dendropy.TreeList.get_from_path(
pathmap.tree_source_path("pythonidae.reference-trees.newick"), "newick")
self.assertEqual(len(trees), len(expected_results))
for tree, expected_result in zip(trees, expected_results):
obs_result1 = birthdeath.fit_pure_birth_model(tree=tree, ultrametricity_precision=1e-5)
obs_result2 = birthdeath.fit_pure_birth_model(internal_node_ages=tree.internal_node_ages(ultrametricity_precision=1e-5))
for obs_result in (obs_result1, obs_result2):
self.assertAlmostEqual(obs_result["birth_rate"], expected_result[0], 5)
self.assertAlmostEqual(obs_result["log_likelihood"], expected_result[1], 5)
def summarize_trees(self, trees, trees_outf=None, params=None, summaries=None):
trees = self.tree_postprocessor.process_trees(trees)
stats_fields = set()
# crucial assumption here is all trees from same landscape wrt to
# number of islands and habitats
representative_taxon = trees[0].taxon_namespace[0]
community_by_disturbed_vs_interior_habitat = {}
num_islands = len(representative_taxon.island_code)
num_habitats = len(representative_taxon.habitat_code)
# community_by_island = {}
# community_by_habitat = {}
# for i in num_islands:
# community_by_island[i] = {}
# for i in num_habitats:
# community_by_habitat[i] = {}
# community_by_disturbed_vs_interior_habitat[0] = {}
# community_by_disturbed_vs_interior_habitat[1] = {}
for tree in list(trees):
num_tips = 0
total_length = 0.0
total_edges = 0
nodes_by_island = collections.defaultdict(list)
nodes_by_habitat = collections.defaultdict(list)
disturbed_habitat_nodes = []
interior_habitat_nodes = []
all_tips = []
for nd in tree:
# colorize
if nd.taxon is None and nd.label is None:
continue
if nd.label is not None:
self.tree_postprocessor.decode_labeled_item_biogeography(nd)
# stats
total_edges += 1
num_tips += 1
total_length += nd.edge.length
if nd.is_leaf():
all_tips.append(nd)
island_code = nd.taxon.island_code
for idx, i in enumerate(island_code):
# island_idx = len(island_code) - idx
island_idx = idx
if i == "1":
nodes_by_island[island_idx].append(nd)
habitat_code = nd.taxon.habitat_code
for idx, i in enumerate(habitat_code):
# habitat_idx = len(habitat_code) - idx
habitat_idx = idx
if i == "1":
nodes_by_habitat[habitat_idx].append(nd)
if habitat_idx == 0:
disturbed_habitat_nodes.append(nd)
else:
if nd not in interior_habitat_nodes:
interior_habitat_nodes.append(nd)
if len(nodes_by_island) < num_islands and self.drop_trees_not_occupying_all_islands:
trees.remove(tree)
continue
if len(nodes_by_habitat) < num_habitats and self.drop_trees_not_occupying_all_habitats:
trees.remove(tree)
continue
pdm = treemeasure.PatristicDistanceMatrix(tree=tree)
tree.stats = collections.defaultdict(lambda: "NA")
if params is not None:
tree.params = params.copy()
tree.stats["size"] = num_tips
tree.stats["length"] = total_length
tree.stats["edges"] = total_edges
# node_ages = tree.internal_node_ages()
# node_ages = [n/total_length for n in node_ages]
# tree.stats["est.birth.rate"] = birthdeath.fit_pure_birth_model(internal_node_ages=node_ages)["birth_rate"]
tree.stats["est.birth.rate"] = birthdeath.fit_pure_birth_model(tree=tree)["birth_rate"]
weighted_disturbed, unweighted_disturbed = self.get_mean_patristic_distance(pdm, disturbed_habitat_nodes)
weighted_interior, unweighted_interior = self.get_mean_patristic_distance(pdm, interior_habitat_nodes)
tree.stats["weighted.disturbed.habitat.pd"] = weighted_disturbed
tree.stats["unweighted.disturbed.habitat.pd"] = unweighted_disturbed
tree.stats["weighted.interior.habitat.pd"] = weighted_interior
tree.stats["unweighted.interior.habitat.pd"] = unweighted_interior
try:
tree.stats["weighted.disturbed.to.interior.habitat.pd"] = weighted_disturbed / weighted_interior
tree.stats["unweighted.disturbed.to.interior.habitat.pd"] = unweighted_disturbed / unweighted_interior
except (ZeroDivisionError, TypeError):
tree.stats["weighted.disturbed.to.interior.habitat.pd"] = "NA"
tree.stats["unweighted.disturbed.to.interior.habitat.pd"] = "NA"
rstats = self.rcalc.calc_ecological_stats(
tree=tree,
patristic_distance_matrix=pdm,
total_tree_length=total_length,
total_tree_edges=total_edges,
nodes_by_island=nodes_by_island,
nodes_by_habitat=nodes_by_habitat,
disturbed_habitat_nodes=disturbed_habitat_nodes,
interior_habitat_nodes=interior_habitat_nodes,
)
stats_fields.update(tree.stats.keys())
if summaries is not None:
sss = tree.stats.copy()
sss.update(tree.params)
summaries.append(sss)
if trees_outf is not None:
try:
trees.write_to_stream(trees_outf, "nexus")
except AttributeError:
self.write_nexus(trees, trees_outf)
return trees, stats_fields
def summarize_trees(self,
trees,
trees_outf=None,
params=None,
summaries=None):
trees = self.tree_postprocessor.process_trees(trees)
stats_fields = set()
# crucial assumption here is all trees from same landscape wrt to
# number of islands and habitats
representative_taxon = trees[0].taxon_namespace[0]
community_by_disturbed_vs_interior_habitat = {}
num_islands = len(representative_taxon.island_code)
num_habitats = len(representative_taxon.habitat_code)
# community_by_island = {}
# community_by_habitat = {}
# for i in num_islands:
# community_by_island[i] = {}
# for i in num_habitats:
# community_by_habitat[i] = {}
# community_by_disturbed_vs_interior_habitat[0] = {}
# community_by_disturbed_vs_interior_habitat[1] = {}
for tree in list(trees):
num_tips = 0
total_length = 0.0
total_edges = 0
nodes_by_island = collections.defaultdict(list)
nodes_by_habitat = collections.defaultdict(list)
disturbed_habitat_nodes = []
interior_habitat_nodes = []
all_tips = []
for nd in tree:
# colorize
if nd.taxon is None and nd.label is None:
continue
if nd.label is not None:
self.tree_postprocessor.decode_labeled_item_biogeography(nd)
# stats
total_edges += 1
num_tips += 1
total_length += nd.edge.length
if nd.is_leaf():
all_tips.append(nd)
island_code = nd.taxon.island_code
for idx, i in enumerate(island_code):
# island_idx = len(island_code) - idx
island_idx = idx
if i == "1":
nodes_by_island[island_idx].append(nd)
habitat_code = nd.taxon.habitat_code
for idx, i in enumerate(habitat_code):
# habitat_idx = len(habitat_code) - idx
habitat_idx = idx
if i == "1":
nodes_by_habitat[habitat_idx].append(nd)
if habitat_idx == 0:
disturbed_habitat_nodes.append(nd)
else:
if nd not in interior_habitat_nodes:
interior_habitat_nodes.append(nd)
if len(nodes_by_island) < num_islands and self.drop_trees_not_occupying_all_islands:
trees.remove(tree)
continue
if len(nodes_by_habitat) < num_habitats and self.drop_trees_not_occupying_all_habitats:
trees.remove(tree)
continue
pdm = treemeasure.PatristicDistanceMatrix(tree=tree)
tree.stats = collections.defaultdict(lambda:"NA")
if params is not None:
tree.params = params.copy()
tree.stats["size"] = num_tips
tree.stats["length"] = total_length
tree.stats["edges"] = total_edges
# node_ages = tree.internal_node_ages()
# node_ages = [n/total_length for n in node_ages]
# tree.stats["est.birth.rate"] = birthdeath.fit_pure_birth_model(internal_node_ages=node_ages)["birth_rate"]
tree.stats["est.birth.rate"] = birthdeath.fit_pure_birth_model(tree=tree)["birth_rate"]
weighted_disturbed, unweighted_disturbed = self.get_mean_patristic_distance(pdm, disturbed_habitat_nodes)
weighted_interior, unweighted_interior = self.get_mean_patristic_distance(pdm, interior_habitat_nodes)
tree.stats["weighted.disturbed.habitat.pd"] = weighted_disturbed
tree.stats["unweighted.disturbed.habitat.pd"] = unweighted_disturbed
tree.stats["weighted.interior.habitat.pd"] = weighted_interior
tree.stats["unweighted.interior.habitat.pd"] = unweighted_interior
try:
tree.stats["weighted.disturbed.to.interior.habitat.pd"] = weighted_disturbed/weighted_interior
tree.stats["unweighted.disturbed.to.interior.habitat.pd"] = unweighted_disturbed/unweighted_interior
except (ZeroDivisionError, TypeError):
tree.stats["weighted.disturbed.to.interior.habitat.pd"] = "NA"
tree.stats["unweighted.disturbed.to.interior.habitat.pd"] = "NA"
rstats = self.rcalc.calc_ecological_stats(
tree=tree,
patristic_distance_matrix=pdm,
total_tree_length=total_length,
total_tree_edges=total_edges,
nodes_by_island=nodes_by_island,
nodes_by_habitat=nodes_by_habitat,
disturbed_habitat_nodes=disturbed_habitat_nodes,
interior_habitat_nodes=interior_habitat_nodes,
)
stats_fields.update(tree.stats.keys())
if summaries is not None:
sss = tree.stats.copy()
sss.update(tree.params)
summaries.append(sss)
if trees_outf is not None:
try:
trees.write_to_stream(trees_outf, "nexus")
except AttributeError:
self.write_nexus(trees, trees_outf)
return trees, stats_fields
