def test_partition_clustering():
# tractable subset
pdb_ids = [276, 39299, 38031]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
sim_matrix = cluster.similarity_matrix(active_sites)
assert cluster.cluster_by_partitioning([], {}) == []
assert cluster.cluster_by_partitioning([active_sites[0]],
{}) == [[active_sites[0]]]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701, 10701,10814,13052,14181,15813]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb"%id)
active_sites.append(io.read_active_site(filepath))
cluster.get_order_residues(active_sites)
# update this assertion
assert len(cluster.cluster_by_partitioning(active_sites,2)[0]) == 2
assert len(cluster.cluster_by_partitioning(active_sites,3)[0]) == 3
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert cluster.cluster_by_partitioning(active_sites) == [["276"], ["4629"],
["10701"]]
# check empty active sites doesn't crash
assert cluster.cluster_by_partitioning(None) is None
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb"%id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
#Slice out clusters that have an assignment
clusters_out = cluster.cluster_by_partitioning(active_sites)
non_empty_clusters = [i for i in clusters_out if len(i) > 1]
distances_from_centroids = [i[1][1] for i in non_empty_clusters]
print('non-empty clusters for k-means is', non_empty_clusters)
print('non-empty cluster distance from centroids are', distances_from_centroids)
#Check that the length of non-empty cluster list is <= 3 (in case where e.g. two or three residues get assigned to same cluster)
assert len(non_empty_clusters) <= 3
#For my particular variant of k-means, check that the distance between the cluster residue
#and the centroid is >= 0 (nonnegativity)
for i in distances_from_centroids:
assert i >= 0
def test_compareTwoMethods():
allPossible = []
for filename in os.listdir("data"):
allPossible.append(int(filename.split(".")[0]))
hierTotal = 0
partTotal = 0
iterations = 100
numPDBs = 15
for i in range(0, iterations):
indices = random.sample(range(0, len(allPossible)), numPDBs)
pdb_ids = []
for j in indices:
pdb_ids.append(allPossible[j])
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
hierScore = cluster.qualityMetric(
cluster.cluster_hierarchically(active_sites))
partScore = cluster.qualityMetric(
cluster.cluster_by_partitioning(active_sites))
hierTotal += hierScore
partTotal += partScore
print("hierScoreAverage: ", hierTotal / float(iterations))
print("partScoreAverage: ", partTotal / float(iterations))
def test_hierarchical_clustering():
# tractable subset
# pdb_ids = [276, 4629, 10701]
pdb_ids = [276, 1806, 3458, 3733, 10814, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert [] not in cluster.cluster_by_partitioning(active_sites)
assert len(cluster.cluster_by_partitioning(active_sites)) == 3
pdb_ids = [276]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert len(cluster.cluster_by_partitioning(active_sites)) == 1
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
clustering = cluster.cluster_by_partitioning(active_sites, [2])
# clusters more similar clusters together
assert get_names(flatten(clustering[0])) in [['276', '4629'], ['10701']]
assert get_names(flatten(clustering[1])) in [['276', '4629'], ['10701']]
# len(clustered_list.unique()==k)
active_sites = read_active_sites("data")
assert len(cluster.cluster_by_partitioning(active_sites, [2])) == 2
assert len(cluster.cluster_by_partitioning(active_sites, [3])) == 3
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert len(cluster.cluster_by_partitioning(active_sites).keys()) >= 2
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
assert cluster.cluster_by_partitioning(active_sites) == [[2], [], [0, 1]]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
assert cluster.test_format_part(
cluster.cluster_by_partitioning(active_sites, 2)) == [[276],
[4629, 10701]]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
clusters = cluster.cluster_by_partitioning(active_sites, 1)[0]
assert [int(c.name) for c in clusters] == [276, 4629, 10701]
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# clusters produce k number of final labels
assert len(
cluster.cluster_by_partitioning(active_sites)) == 3 #k = 3 in my code
def test_partition_clustering():
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
# checking the the three sites cluster as expected
assert np.array_equal(
cluster.cluster_by_partitioning(active_sites, 2)[0], [1, 1, 0])
def test_partition_clustering():
random.seed(40)
# tractable subset
pdb_ids = [276, 4629, 10701]
active_sites = []
for id in pdb_ids:
filepath = os.path.join("data", "%i.pdb" % id)
active_sites.append(io.read_active_site(filepath))
# update this assertion
label = cluster.cluster_by_partitioning(active_sites, 2)
#assert cluster.cluster_by_partitioning(active_sites) == []
assert all(label[1] == [0, 0, 1])
from matplotlib import pyplot as plt
import pandas as pd
active_sites = io.read_active_sites('./data')
number_clusters = []
p_sil_scores = []
h_sil_scores = []
r_sil_scores = []
for i in range(2,10):
# clustering all sites by partition
print('Finding %d clusters by partitioning'% i)
p_clusters, p_distances = cluster.cluster_by_partitioning(active_sites, i)
# clustering all sites hierarchically
print('Finding %d clusters hierarchically'% i)
h_clusters, h_distances = cluster.cluster_hierarchically(active_sites, i)
# generating random clusters labels
print('Generating %d random cluster labels'% i)
r_clusters = np.random.choice(range(0,i), 136)
# to evaluate the clusters I will get the silhouette score for each method of clustering
# as well as randomly generated cluster labels
p_sil_scores.append(silhouette_score(p_distances, p_clusters))
h_sil_scores.append(silhouette_score(h_distances, h_clusters))
r_sil_scores.append(silhouette_score(p_distances, r_clusters))
#from .utils import Atom, Residue, ActiveSite
from hw2skeleton import io
from hw2skeleton import cluster
import matplotlib.pyplot as plt
import numpy as np
active_sites = io.read_active_sites(
"C:\\Users\Zoë\Documents\GitHub\hw2-skeleton\data")
#site1 = active_sites[5]
#site2 = active_sites[7]
#print('site1: ', site1.categories)
#print('site2: ', site2.categories)
#sim = cluster.compute_similarity(site1,site2)
# Run for one clustering by kmeans
Pclusters, PmaxDistance = cluster.cluster_by_partitioning(active_sites)
##for i in clusters:
## print(i.toStr())
io.write_clustering("clusterPk=10", Pclusters)
# Run for just one clustering by agglomerative clustering
Hclusters, distH = cluster.cluster_hierarchically(active_sites)
io.write_clustering("clusterHcutoff=0.3", Hclusters)
## Run for one clustering by agglomerative clustering
#Hclusters, HmaxDist, Hclusterings = cluster.cluster_hierarchically(active_sites)
#io.write_mult_clusterings("clusteringsH1", Hclusterings)
#%%
## Clusterings of multiple k values in kmeans
#kvals = [2,3,4,5,6,7,8,9,10,20,30,40,50,60,70,80,90,100,120,130,136]
