def get_trees(tree_type, tree_size, tree_path):
if tree_type == "binary":
tree = utils.balanced_binary(tree_size)
elif tree_type == "catepillar":
tree = utils.lopsided_tree(tree_size)
elif tree_type == "birthdeath":
tree = utils.unrooted_birth_death_tree(tree_size)
elif tree_type == "kingman":
tree = utils.unrooted_pure_kingman_tree(tree_size)
elif tree_type == "path":
tree = dendropy.Tree.get(path=args.path, schema="nexus")
return tree
jc = generation.Jukes_Cantor(num_classes=2)
mutation_rate = jc.p2t(0.9)
snj = reconstruct_tree.SpectralNeighborJoining(
reconstruct_tree.JC_similarity_matrix)
nj = reconstruct_tree.NeighborJoining(reconstruct_tree.JC_similarity_matrix)
treesvd = reconstruct_tree.TreeSVD()
methods = [snj, treesvd]
#results = compare_methods.experiment([reference_tree], jc, N_vec, methods=methods,\
# mutation_rates = [mutation_rate], reps_per_tree=num_reps)
df = pd.DataFrame(
columns=['method', 'runtime', 'RF', 'n', 'cherries_ref', 'cherries_res'])
for i in np.arange(num_reps):
print(i)
reference_tree = utils.unrooted_pure_kingman_tree(num_taxa)
ch_ref = cherry_count_for_tree(reference_tree)
for n in N_vec:
observations, taxa_meta = generation.simulate_sequences(
n,
tree_model=reference_tree,
seq_model=jc,
mutation_rate=mutation_rate,
alphabet="DNA")
# Tree svd
t_s = time.time()
tree_svd_rec = treesvd(observations, taxa_meta)
runtime_treesvd = time.time() - t_s
RF_svd, F1 = reconstruct_tree.compare_trees(tree_svd_rec,
reference_tree)
#num_taxa = [128,256,512,1024,2048,4096]
num_taxa = np.arange(200, 2000, 200)
n_itr = 10
#num_taxa = [8,16,32]
N = 1000
jc = generation.Jukes_Cantor()
mutation_rate = jc.p2t(0.95)
nj = reconstruct_tree.NeighborJoining(reconstruct_tree.JC_similarity_matrix)
raxml = reconstruct_tree.RAxML()
#tree_list = [utils.balanced_binary(m) for m in num_taxa]
df = pd.DataFrame(columns=['method', 'runtime', 'RF', 'm'])
for m in num_taxa:
for n_itr in range(n_itr):
reference_tree = utils.unrooted_pure_kingman_tree(m)
observations, taxa_meta = generation.simulate_sequences(
N,
tree_model=reference_tree,
seq_model=jc,
mutation_rate=mutation_rate,
alphabet="DNA")
# NJ
time_s = time.time()
tree_rec = nj(observations, taxa_meta)
runtime = time.time() - time_s
RF, F1 = reconstruct_tree.compare_trees(reference_tree, tree_rec)
print('NJ iteration: ', n_itr, ' num_taxa: ', m, ' time: ', runtime)
df = df.append({
