def test_inf_deathtime(self):
dgm = np.array([[1, 2]])
empty = np.array([[0, np.inf]])
with pytest.warns(UserWarning,
match="dgm1 has points with non-finite death") as w:
dist1 = wasserstein(empty, dgm)
with pytest.warns(UserWarning,
match="dgm2 has points with non-finite death") as w:
dist2 = wasserstein(dgm, empty)
assert (np.allclose(dist1,
np.sqrt(2) / 2)) and (np.allclose(
dist2,
np.sqrt(2) / 2))
def test_single(self):
d = wasserstein(
np.array([[0.5, 1]]),
np.array([[0.5, 1.1]])
)
# These are very loose bounds
assert d == pytest.approx(0.1, 0.001)
def test_matching_to_self(self):
# Matching a diagram to itself should yield 0
pd = np.array([[0. , 1.71858561],
[0. , 1.74160683],
[0. , 2.43430877],
[0. , 2.56949258]])
dist = wasserstein(pd, pd)
assert dist == 0
def mainp(queue, res_queue, df, rfs):
print("thread initiated")
while not queue.empty():
try:
i = queue.get(True, 15)
res_queue.put((i, df[0].apply(lambda x: wasserstein(x, rfs[i]))))
# f = np.vectorize(lambda x:wasserstein(x, rfs[i]))
# res_queue.put((i,f(rfs)))
except Exception as err:
print("process down")
break
if queue.empty():
quit()
break
def test_matching(self):
dgm1 = np.array([[0.5, 1], [0.6, 1.1]])
dgm2 = np.array([
[0.5, 1.1],
[0.6, 1.1],
[0.8, 1.1],
[1.0, 1.1],
])
d, m = wasserstein(dgm1, dgm2, matching=True)
u1 = np.unique(m[:, 0])
u1 = u1[u1 >= 0]
u2 = np.unique(m[:, 1])
u2 = u2[u2 >= 0]
assert u1.size == dgm1.shape[0] and u2.size == dgm2.shape[0]
print "\tSize:", curData.shape
str(bn) + "," + str(h) + "," + str(ws) + ","
#if(a == 0)
# for i in range(0,d0_count):
# outdata = np.vstack([outdata, [0,0,epsilon]])
if (len(curData.data) > 0):
print "Metric", len(curData), a
bn = persim.bottleneck(comparePers,
curData,
matching=False)
h = persim.heat(comparePers, curData)
ws = persim.wasserstein(comparePers, curData)
outString += str(bn) + "," + str(h) + "," + str(ws) + ","
end = time.time()
stat_time = (end - start)
outfile = file(os.getcwd() + "/aggResults.csv", 'a')
outfile.write(outString + str(stat_time) + ",")
outfile.close()
else:
print "ripser processing failed"
''' LHF configuration and execution '''
if (tdaType == "LHF"):
#try:
start = time.time()
def test_one_empty(self):
dgm1 = np.array([[1, 2]])
empty = np.array([])
dist = wasserstein(dgm1, empty)
assert np.allclose(dist, np.sqrt(2) / 2)
def test_single_point_same(self):
dgm = np.array([[0.11371516, 4.45734882]])
dist = wasserstein(dgm, dgm)
assert dist == 0
def match_wasserstein(dgms1, dgms2):
return wasserstein(dgms1[1], dgms2[1], matching=True)
try:
upscalePers = np.genfromtxt(outDir + "/upscaledPersistence.csv",
delimiter=',')
except:
upscalePers = np.genfromtxt(outDir + "/ripser_Output.csv", delimiter=',')
start = time.time()
print "Computing bottlenecks..."
bn = persim.bottleneck(originalPers, comparePers, matching=False)
bn_u = persim.bottleneck(originalPers, upscalePers, matching=False)
print "Computing heat kernel distance..."
h = persim.heat(originalPers, comparePers)
h_u = persim.heat(originalPers, upscalePers)
print "Computing wasserstein..."
ws = persim.wasserstein(originalPers, comparePers)
ws_u = persim.wasserstein(originalPers, upscalePers)
end = time.time()
#gh = persim.gromov_hausdorff(originalPers, comparePers)
#gh_u = persim.gromov_hausdorff(originalPers, upscalePers)
print bn, bn_u, h, h_u, ws, ws_u
stat_time = (end - start)
with open("upscaleStats.csv", 'a') as f:
f.write(SourcePers + "," + outDir +
",".join(str(x)
for x in [bn, bn_u, h, h_u, ws, ws_u, stat_time]) + "\n")
def test_repeated(self):
dgm1 = np.array([[0, 10], [0, 10]])
dgm2 = np.array([[0, 10]])
dist = wasserstein(dgm1, dgm2)
assert dist == 5 * np.sqrt(2)