def test_clustering(d,
clusters,
vlmcs,
out_directory,
cluster_class=MSTClustering,
do_draw_graph=True):
metadata = get_metadata_for([vlmc.name for vlmc in vlmcs])
clustering = cluster_class(vlmcs, d, metadata)
for i in range(clusters + 0, clusters - 1, -1):
print(i)
clustering_metrics = clustering.cluster(i)
if do_draw_graph:
plot_largest_components(clustering_metrics, i, out_directory)
pictures = [('Family', 'family'), ('Genus', 'genus'),
('Host', 'hosts'), ('Baltimore', 'baltimore')]
for name, key in pictures:
draw_graph(clustering_metrics, name, key, i, out_directory)
print_connected_components(clustering_metrics)
print_cluster_metrics(clustering_metrics, i)
def test_clustering(d, vlmcs, cluster_class):
metadata = get_metadata_for([vlmc.name for vlmc in vlmcs])
metrics = np.zeros([len(vlmcs), 7], dtype=np.float32)
clustering = cluster_class(vlmcs, d, metadata)
for i in range(len(vlmcs) - 1, 0, -1):
print(i)
clustering_metrics = clustering.cluster(i)
metrics[i, 0] = clustering_metrics.average_silhouette()
metrics[i, 1] = clustering_metrics.average_percent_same_taxonomy(
'organism')
metrics[i,
2] = clustering_metrics.average_percent_same_taxonomy('family')
metrics[i,
3] = clustering_metrics.average_percent_same_taxonomy('genus')
fam_sensitivity, fam_specificity = clustering_metrics.sensitivity_specificity(
'family')
metrics[i, 4] = fam_sensitivity
metrics[i, 5] = fam_specificity
metrics[i, 6] = clustering_metrics.get_latest_merge_distance()
return metrics
def test_distance_function(d,
tree_dir,
out_dir,
plot_distances=False,
plot_boxes=False):
parse_trees_to_json.parse_trees(tree_dir)
vlmcs = VLMC.from_json_dir(tree_dir)
metadata = get_metadata_for([vlmc.name for vlmc in vlmcs])
test_dir = tree_dir + "_test"
if os.path.isdir(test_dir):
parse_trees_to_json.parse_trees(test_dir)
test_vlmcs = VLMC.from_json_dir(test_dir)
else:
test_vlmcs = vlmcs
if out_dir is not None:
try:
os.stat(out_dir)
except:
os.mkdir(out_dir)
return test_distance_function_(d, vlmcs, test_vlmcs, metadata, out_dir,
True, False, plot_distances, plot_boxes)
parser.add_argument('--intersection', action='store_true')
parser.add_argument('--occurrence-probability-labels', action='store_true')
parser.add_argument(
'--directory',
type=str,
default='../trees_pst_better',
help='The directory which contains the vlmcs to be printed.')
parser.add_argument(
'--out-directory',
type=str,
default='../images',
help='The directory to where the images should be written.')
args = parser.parse_args()
try:
os.stat(args.out_directory)
except:
os.mkdir(args.out_directory)
parse_trees(args.directory, args.deltas)
vlmcs = VLMC.from_json_dir(args.directory)
metadata = get_metadata_for([vlmc.name for vlmc in vlmcs])
if args.intersection:
save_intersection(vlmcs, metadata, args.out_directory)
else:
save(vlmcs, metadata, args.out_directory, args.deltas,
args.occurrence_probability_labels)