def find_centroids(centroids, data, labels, pairwise_distances, zero_point, C,
D):
# Get the number of points associated with each centroid
counts = np.bincount(labels, minlength=C)
# Build label masks for each centroid and sum across all the
# points assocated with each new centroid
distance_sum = 0.0
for idx in range(C):
# Boolean mask indicating where the points are for this center
centroid_mask = labels == idx
centroids[idx, :] = np.sum(np.where(centroid_mask[..., np.newaxis],
data, zero_point),
axis=0)
distance_sum += np.sum(
np.where(centroid_mask, pairwise_distances[:, idx], 0.0))
# To avoid introducing divide by zero errors
# If a centroid has no weight, we'll do no normalization
# This will keep its coordinates defined.
counts = np.maximum(counts, np.ones((1, ), dtype=np.uint64))
centroids /= counts[:, np.newaxis]
return distance_sum
def cnd(d):
A1 = 0.31938153
A2 = -0.356563782
A3 = 1.781477937
A4 = -1.821255978
A5 = 1.330274429
RSQRT2PI = 0.39894228040143267793994605993438
K = 1.0 / (1.0 + 0.2316419 * np.absolute(d))
cnd = (RSQRT2PI * np.exp(-0.5 * d * d) *
(K * (A1 + K * (A2 + K * (A3 + K * (A4 + K * A5))))))
return np.where(d > 0, 1.0 - cnd, cnd)
def test():
# np.random.seed(42)
# anp = np.array([1, 54, 4 , 4, 0, 45, 5, 58, 0, 9, 0, 4, 0, 0, 0, 5, 0])
# a = lg.array(anp)
# assert(lg.array_equal(np.where(anp), lg.where(a)))
# cnp = np.array([1, 54, 4 , 4, 0, 45, 5, 58, 0, 9, 0, 4, 0, 0, 0, 5, 0, 1]).reshape((6,3)) # noqa E501
# c = lg.array(cnp)
# bnp = np.random.randn(6,3)
# b = lg.array(bnp)
# assert(lg.array_equal(lg.extract(c, b), np.extract(cnp, bnp)))
anp = np.array([[True, False], [True, True]])
xnp = np.array([[1, 2], [3, 4]])
ynp = np.array([[9, 8], [7, 6]])
a = lg.array(anp)
x = lg.array(xnp)
y = lg.array(ynp)
assert np.array_equal(np.where(anp, xnp, ynp), lg.where(a, x, y))
def test():
np.random.seed(50)
datanp = np.random.randn(2000000, 3)
data = lg.array(datanp)
pointsnp = np.random.choice(lg.arange(len(data)), 4, False)
points = lg.array(pointsnp)
centroids = data[points]
centroidsnp = datanp[pointsnp]
sqdists = lg.zeros((4, len(data)))
sqdistsnp = np.zeros((4, len(datanp)))
for i in range(4):
vec = data - centroids[i]
vecnp = datanp - centroidsnp[i]
sqdists[i] = lg.linalg.norm(vec, axis=1)
sqdistsnp[i] = np.linalg.norm(vecnp, axis=1)
clusters = lg.argmin(sqdists, axis=0)
clustersnp = np.argmin(sqdistsnp, axis=0)
assert lg.array_equal(lg.where(clusters == 0), np.where(clustersnp == 0))
def test():
x = lg.array([[1, 2], [3, 4], [5, 6]])
assert lg.array_equal(x[[0, 1, 2], [0, 1, 0]], [1, 4, 5])
x = lg.array([[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 10, 11]])
rows = lg.array([0, 3])
columns = lg.array([0, 2])
assert lg.array_equal(x[rows[:, np.newaxis], columns], [[0, 2], [9, 11]])
zg = lg.array([[-1.2 + 0.5j, 1.2 - 2j], [-2.2 + 3.5j, 4.2 - 6.2j]])
m = lg.array([[True, False], [False, True]])
assert lg.array_equal(zg[m], [-1.2 + 0.5j, 4.2 - 6.2j])
anp = np.array([[[2, 1], [3, 2]], [[2, 4], [4, 1]]])
a = lg.array(anp)
nznp = anp < 3
nzgp = a < 3
assert lg.array_equal(anp[nznp], a[nzgp])
y = lg.array([[[True, True], [False, True]], [[True, False], [False,
True]]])
z = lg.nonzero(y)
assert lg.array_equal(a[z], lg.array([2, 1, 2, 2, 1]))
np.random.seed(42)
anp = np.random.randn(10, 10, 4)
a = lg.array(anp)
bnp = np.array([3, 4, 6])
cnp = np.array([1, 4, 5])
b = lg.array(bnp)
c = lg.array(cnp)
assert lg.array_equal(a[b], anp[bnp])
assert lg.array_equal(a[(b, c)], anp[(b, c)])
onesnp = np.zeros(10, int)
ones = lg.zeros(10, int)
dnp = np.random.randn(20, 4)
d = lg.array(dnp)
assert lg.array_equal(dnp[np.where(onesnp)], d[lg.where(ones)])