def main():
num_clusters = 3
new_tm = TreeMixture(num_clusters=num_clusters, num_nodes=3)
new_tm.simulate_pi(None)
new_tm.simulate_trees(None)
new_tm.sample_mixtures(100)
new_samples = new_tm.samples
#samples = tm.samples
seed_val = None
directory = '/Users/filipbergentoft/Desktop/Github/DD2434/Assignment 2/2_4/'
sample_filename = directory + "data/q2_4/q2_4_tree_mixture.pkl_samples.txt"
output_filename = directory + "data/q2_4/q2_4_own_results"
real_values_filename = directory + "data/q2_4/q2_4_tree_mixture.pkl"
samples = np.loadtxt(sample_filename, delimiter="\t", dtype=np.int32)
np.random.shuffle(samples)
best_tm = sieving(n_first_mixtures=50,
n_second_mixtures=10,
n_first_iterations=10,
n_second_iterations=100,
samples=samples,
num_clusters=num_clusters)
real_tm = TreeMixture(num_clusters=3, num_nodes=5)
real_tm.load_mixture(real_values_filename)
print('best tree', mixture_likelihood(best_tm, samples))
print('best tree', best_tm.pi)
print('real tree', mixture_likelihood(real_tm, samples))
print('real tree', real_tm.pi)
print(RF_comparison(best_tm, real_tm))
for tree in new_tm.clusters:
print('Real tree topology')
print(tree.get_topology_array())
for tree in best_tm.clusters:
print('Inferred tree topology')
print(tree.get_topology_array())
sns.set_style('darkgrid')
"""
plt.subplot(121)
plt.plot(np.exp(best_tm.loglikelihood), label='Estimated')
plt.ylabel("Likelihood of Mixture")
plt.xlabel("Iterations")
plt.subplot(122)
"""
plt.plot(best_tm.loglikelihood, label='Estimated')
plt.ylabel("Log-Likelihood of Mixture")
plt.xlabel("Iterations")
plt.legend()
plt.show()
def main():
print("Hello World!")
seed_val = 123
#sample_filename = "q2_4/q2_4_tree_mixture.pkl_samples.txt"
#real_values_filename = "q2_4/q2_4_tree_mixture.pkl"
#sample_filename = "q2_4/case1.pkl_samples.txt"
#real_values_filename = "q2_4/case1.pkl"
#sample_filename = "q2_4/case2.pkl_samples.txt"
#real_values_filename = "q2_4/case2.pkl"
sample_filename = "q2_4/case3.pkl_samples.txt"
real_values_filename = "q2_4/case3.pkl"
num_clusters = 2 #need to change this fpr each case!
samples = np.loadtxt(sample_filename, delimiter="\t", dtype=np.int32)
loglikelihood, my_tm = sieving(seed_val,
samples,
num_clusters=num_clusters)
plt.figure(figsize=(8, 3))
plt.subplot(121)
plt.plot(np.exp(loglikelihood), label='Estimated')
plt.ylabel("Likelihood of Mixture")
plt.xlabel("Iterations")
plt.subplot(122)
plt.plot(loglikelihood, label='Estimated')
plt.ylabel("Log-Likelihood of Mixture")
plt.xlabel("Iterations")
plt.legend(loc=(1.04, 0))
plt.show()
if real_values_filename != "":
real = TreeMixture(0, 0)
real.load_mixture(real_values_filename)
print("\t4.1. Make the Robinson-Foulds distance analysis.\n")
tns = dendropy.TaxonNamespace()
real_trees = [i.newick for i in real.clusters]
my_trees = [i.newick for i in my_tm.clusters]
print(my_trees)
i = 0
for real_tree in real_trees:
real_den = dendropy.Tree.get(data=real_tree,
schema="newick",
taxon_namespace=tns)
j = 0
for my_tree in my_trees:
my_den = dendropy.Tree.get(data=my_tree,
schema="newick",
taxon_namespace=tns)
print(
"RF distance: $<", i, j, ">$\t=",
dendropy.calculate.treecompare.symmetric_difference(
real_den, my_den), "\\\\")
j += 1
i += 1
print("4.2. Make the likelihood comparison.\n")
real_log_hood = tm_likelihood(real, samples, len(samples),
num_clusters)
print("Real: ", real_log_hood)
print("Infered: ", loglikelihood)
def main():
# Code to process command line arguments
parser = argparse.ArgumentParser(
description='EM algorithm for likelihood of a tree GM.')
parser.add_argument(
'--sample_filename',
type=str,
default='data/q_2_5_tm_20node_20sample_4clusters.pkl_samples.txt',
help=
'Specify the name of the sample file (i.e data/example_samples.txt)')
parser.add_argument(
'--real_values_filename',
type=str,
default='data/q_2_5_tm_20node_20sample_4clusters.pkl',
help=
'Specify the name of the real values file (i.e data/example_tree_mixture.pkl)'
)
parser.add_argument(
'--output_filename',
type=str,
default='q_2_5_tm_20node_20sample_4clusters_result.txt',
help=
'Specify the name of the output file (i.e data/example_results.txt)')
parser.add_argument('--num_nodes',
type=int,
default=10,
help='Specify the number of nodes of trees (i.e 10)')
parser.add_argument('--num_clusters',
type=int,
default=10,
help='Specify the number of clusters (i.e 3)')
parser.add_argument(
'--seed_val',
type=int,
default=123,
help='Specify the seed value for reproducibility (i.e 42)')
parser.add_argument(
'--if_simulate',
type=bool,
default=True,
help='Specify whether the sampling is enabled (i.e False)')
parser.add_argument(
'--num_samples',
type=int,
default=50,
help='Specify the number of samples if sampling is enabled (i.e 1000)')
# You can add more default parameters if you want.
print("Hello World!")
print(
"This file demonstrates the flow of function templates of question 2.5."
)
print("\n0. Load the parameters from command line.\n")
args = parser.parse_args()
print("\tArguments are: ", args)
if args.if_simulate:
print("\n1. Make new tree and sample.\n")
tm_truth = TreeMixture(num_clusters=args.num_clusters,
num_nodes=args.num_nodes)
tm_truth.simulate_pi(seed_val=args.seed_val)
tm_truth.simulate_trees(seed_val=args.seed_val)
tm_truth.sample_mixtures(args.num_samples, seed_val=args.seed_val)
else:
print("\n1. Load true tree from file.\n")
tm_truth = TreeMixture(0, 0)
tm_truth.load_mixture(args.real_values_filename)
print("Load samples.")
samples = tm_truth.samples
num_samples, num_nodes = samples.shape
print("\tnum_samples: ", num_samples, "\tnum_nodes: ", num_nodes)
print("\tSamples: \n", samples)
print("\n2. Run EM Algorithm.\n")
loglikelihood, topology_array, theta_array, tm = em_algorithm(
args.seed_val, samples, num_clusters=args.num_clusters)
print("\n3. Save, print and plot the results.\n")
# save_results(loglikelihood, topology_array, theta_array, args.output_filename)
for i in range(args.num_clusters):
print("\n\tCluster: ", i)
print("\tTopology: \t", topology_array[i])
print("\tTheta: \t", theta_array[i])
plt.figure(figsize=(8, 3))
plt.subplot(121)
plt.plot(np.exp(loglikelihood), label='Estimated')
plt.ylabel("Likelihood of Mixture")
plt.xlabel("Iterations")
plt.subplot(122)
plt.plot(loglikelihood, label='Estimated')
plt.ylabel("Log-Likelihood of Mixture")
plt.xlabel("Iterations")
plt.legend(loc=(1.04, 0))
plt.show()
print("\n4. Retrieve real results and compare.\n")
if args.real_values_filename != "":
print(
"\n=> Compare trees and print Robinson-Foulds (RF) distance (result v.s truth):\n"
)
N = len(samples)
K = tm_truth.num_clusters
tns = dendropy.TaxonNamespace()
print("\\hline")
for k in range(K):
print(k, end=" & ")
for j in range(K):
t_0 = tm.clusters[k]
t_0.get_tree_newick()
t_0 = dendropy.Tree.get(data=t_0.newick,
schema="newick",
taxon_namespace=tns)
t_t = tm_truth.clusters[j]
t_t.get_tree_newick()
t_t = dendropy.Tree.get(data=t_t.newick,
schema="newick",
taxon_namespace=tns)
print(dendropy.calculate.treecompare.symmetric_difference(
t_0, t_t),
end=" & ")
print("\\\\")
print("\n=> Compare log-likelihood (result v.s truth):\n")
posterior = np.ones((N, K))
prior = np.ones(N)
for n, x in enumerate(samples):
for k, tree in enumerate(tm_truth.clusters):
visit_list = [tree.root]
while len(visit_list) != 0:
cur_node = visit_list[0]
visit_list = visit_list[1:]
visit_list = visit_list + cur_node.descendants
if cur_node.ancestor is None:
posterior[n, k] *= cur_node.cat[x[int(cur_node.name)]]
else:
posterior[n, k] *= cur_node.cat[x[int(
cur_node.ancestor.name)]][x[int(cur_node.name)]]
prior[n] *= np.sum(posterior[n] * tm_truth.pi)
loglikelihood_truth = np.sum(np.log(prior))
print("%f : %f" % (loglikelihood[-1], loglikelihood_truth))
def main():
# Code to process command line arguments
parser = argparse.ArgumentParser(
description='EM algorithm for likelihood of a tree GM.')
parser.add_argument(
'sample_filename',
type=str,
help=
'Specify the name of the sample file (i.e data/example_samples.txt)')
parser.add_argument(
'output_filename',
type=str,
help=
'Specify the name of the output file (i.e data/example_results.txt)')
parser.add_argument('num_clusters',
type=int,
help='Specify the number of clusters (i.e 3)')
parser.add_argument(
'--seed_val',
type=int,
default=42,
help='Specify the seed value for reproducibility (i.e 42)')
parser.add_argument(
'--real_values_filename',
type=str,
default="",
help=
'Specify the name of the real values file (i.e data/example_tree_mixture.pkl)'
)
# You can add more default parameters if you want.
print("Hello World!")
print(
"This file demonstrates the flow of function templates of question 2.5."
)
print("\n0. Load the parameters from command line.\n")
args = parser.parse_args()
print("\tArguments are: ", args)
print("\n1. Load samples from txt file.\n")
samples = np.loadtxt(args.sample_filename, delimiter="\t", dtype=np.int32)
num_samples, num_nodes = samples.shape
print("\tnum_samples: ", num_samples, "\tnum_nodes: ", num_nodes)
print("\tSamples: \n", samples)
print("\n2. Run EM Algorithm.\n")
loglikelihood, topology_array, theta_array = em_algorithm(
args.seed_val, samples, num_clusters=args.num_clusters)
print("\n3. Save, print and plot the results.\n")
save_results(loglikelihood, topology_array, theta_array,
args.output_filename)
for i in range(args.num_clusters):
print("\n\tCluster: ", i)
print("\tTopology: \t", topology_array[i])
print("\tTheta: \t", theta_array[i])
plt.figure(figsize=(8, 3))
plt.subplot(121)
plt.plot(np.exp(loglikelihood), label='Estimated')
plt.ylabel("Likelihood of Mixture")
plt.xlabel("Iterations")
plt.subplot(122)
plt.plot(loglikelihood, label='Estimated')
plt.ylabel("Log-Likelihood of Mixture")
plt.xlabel("Iterations")
plt.legend(loc=(1.04, 0))
plt.show()
print("\n4. Retrieve real results and compare.\n")
if args.real_values_filename != "":
print("\tComparing the results with real values...")
actual_tm = TreeMixture(args.num_clusters, num_nodes)
actual_tm.load_mixture(args.real_values_filename)
inferred_tm = TreeMixture(args.num_clusters, num_nodes)
inferred_tm.load_mixture(args.output_filename)
print("\t4.1. Make the Robinson-Foulds distance analysis.\n")
diff = compute_tree_mix_diff(actual_tm, inferred_tm)
print("Total Robinson-Foulds distance: " + str(diff))
print("\t4.2. Make the likelihood comparison.\n")
actual_lik = actual_tm.likelihood_dataset(samples)
inferred_lik = inferred_tm.likelihood_dataset(samples)
print("Log-Likelihood of actual tree: " + str(actual_lik) +
", inferred tree: " + str(inferred_lik))
