def test_estimate_eps_10_dimension_data(selfs):
D=np.zeros((7,2))
for i in range(0, 7):
for ii in range(0, 2):
D[i,ii]=i+ii
test_average_nearest_distance=nearestneighbour.estimate_eps(D)
result=np.isclose(test_average_nearest_distance,np.sqrt(2))
assert result
def test_estimate_eps_10_dimension_data(self):
D = np.zeros((7, 2))
for i in range(0, 7):
for ii in range(0, 2):
D[i, ii] = i + ii
test_average_nearest_distance = nearestneighbour.estimate_eps(D)
result = np.isclose(test_average_nearest_distance, np.sqrt(2))
assert result
def __init__(self,D,minPts,eps=None):
self.D=D
if eps is None:
eps=nearestneighbour.estimate_eps(D)*2
print 'epsilon has been set to %d' % eps
self.eps=eps
else:
self.eps=eps
self.minPts=minPts
def __init__(self, D, minPts, eps=None):
self.D = D
self.visitedPoints = np.zeros(len(D), dtype=bool)
self.clusterByIndex = np.zeros(len(D), dtype=int)
self.clusterCount = 0
self.eps = 0.0
if eps is None:
eps = nearestneighbour.estimate_eps(D) * 2
print 'epsilon has been set to %d' % eps
self.eps = eps
else:
self.eps = eps
self.minPts = minPts
def __init__(self,D,minPts,eps=None):
self.D=D
self.visitedPoints=np.zeros(len(D),dtype=bool)
self.clusterByIndex=np.zeros(len(D), dtype=int)
self.clusterCount=0
self.eps=0.0
if eps is None:
eps=nearestneighbour.estimate_eps(D)*2
print 'epsilon has been set to %d' % eps
self.eps=eps
else:
self.eps=eps
self.minPts=minPts
def test_estimate_eps(self):
D = np.linspace(0, 10, 21)
print D
test_average_nearest_distance=nearestneighbour.estimate_eps(D)
assert test_average_nearest_distance == 0.5
def test_estimate_eps(self):
D = np.linspace(0, 10, 21)
print D
test_average_nearest_distance = nearestneighbour.estimate_eps(D)
print test_average_nearest_distance
assert test_average_nearest_distance == 0.5
