def sig_test1(shape, iters = 20):
result = np.zeros(iters)
for i in np.arange(iters):
X = np.random.rand(shape[0], shape[1])
p = sigclust(X, verbose = False)[0]
result[i] = p
return result
def sig_test_1(shape=(50, 50), iters=20):
"""
Run sigclust on randomly generated datasets and print results.
:Parameters:
shape : tuple
Shape of randomly generated datasets
iters : int
Number of iterations
"""
result = np.zeros(iters)
for i in np.arange(iters):
print("Simulating random data of shape %r..." % str(shape))
X = np.random.rand(shape[0], shape[1])
print("Running sigclust on generated data...")
p = sigclust(X)[0]
result[i] = p
mu = np.mean(result)
sig = np.std(result)
print("The set of %d p-values had\nmean: %f and\n"
"standard deviation: %f\n" %
(iters, mu, sig))
assert(mu < .98,
"Warning: High average p-value for input matrices of random "
"normal data.")
assert(mu > .01,
"Warning: Low average p-value for input matrices of random "
"normal data.")
def sig_test_1(shape=(50, 50), iters=20):
"""
Run sigclust on randomly generated datasets and print results.
:Parameters:
shape : tuple
Shape of randomly generated datasets
iters : int
Number of iterations
"""
result = np.zeros(iters)
for i in np.arange(iters):
print("Simulating random data of shape %r..." % str(shape))
X = np.random.rand(shape[0], shape[1])
print("Running sigclust on generated data...")
p = sigclust(X)[0]
result[i] = p
mu = np.mean(result)
sig = np.std(result)
print("The set of %d p-values had\nmean: %f and\n"
"standard deviation: %f\n" % (iters, mu, sig))
assert (mu < .98,
"Warning: High average p-value for input matrices of random "
"normal data.")
assert (mu > .01,
"Warning: Low average p-value for input matrices of random "
"normal data.")
def RSC(file, rids=True, verbose = True, scale = False):
rid_col, X = get_mat(file, rids = rids)
while(True):
p, clust = sigclust(X, verbose = verbose, scale = scale)
print("p-value: %f" % p)
s = sum(clust)
n_samps = X.shape[0]
print("The clusters have sizes %d, %d" %
(n_samps - s, s))
in0 = input("Remove all points in smallest cluster and re-run sigclust? (Enter 'n' to terminate.):")
if in0 is 'n':
break
sec_small = s < (n_samps / 2)
print("Removing %s cluster (of size %d)." %
("SECOND" if sec_small else "FIRST",
s if sec_small else n_samps - s))
f_clust = clust.astype(bool)
if sec_small:
to_remove = np.where(f_clust)[0]
else:
to_remove = np.where(~f_clust)[0]
print("Now removing samples with the following indices:")
print(to_remove)
print("These samples correspond to the following rev ids:")
rem_rids = rid_col[to_remove]
print(rem_rids)
X = np.delete(X, to_remove, axis = 0)
subpop_ind = popul_ind[subpop_bool]
# Sizes of two populations
BIG = ids.shape[0]
SMALL = subpop_ind.shape[0]
# The incoming data restricted
# to the subpopulation
ids_sub = ids[subpop_bool]
features_sub = features[subpop_bool, :]
labels_sub = labels[subpop_bool]
# First we cluster the whole population
print("Computing p-value for population.")
p, clust = sigclust(features, mc_iters=ITERS_B)
print("p-value for population: %f" % p)
clust0_bool = clust == 0
clust0_ind = popul_ind[clust0_bool]
clust1_bool = ~clust0_bool
clust1_ind = popul_ind[clust1_bool]
ss_of_clust0_bool = clust0_bool & subpop_bool
ss_of_clust1_bool = clust1_bool & subpop_bool
"""
The clusters of the whole population
determine two subsets (their respective
intersections with the subpopulation)"""
subpop_ind = popul_ind[subpop_bool]
#Sizes of two populations
BIG = ids.shape[0]
SMALL = subpop_ind.shape[0]
# The incoming data restricted
# to the subpopulation
ids_sub = ids[subpop_bool]
features_sub = features[subpop_bool,:]
labels_sub = labels[subpop_bool]
#First we cluster the whole population
print("Computing p-value for population.")
p, clust = sigclust(features,
mc_iters = ITERS_B)
print("p-value for population: %f" % p)
clust0_bool = clust == 0
clust0_ind = popul_ind[clust0_bool]
clust1_bool = ~clust0_bool
clust1_ind = popul_ind[clust1_bool]
"""
The clusters of the whole population
determine two subsets (their respective
intersections with the subpopulation)"""
ss_of_clust0_bool = clust0_bool & subpop_bool
