def _compare_clusters(**datasets):
for name, dataset in datasets.items():
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
instances = _kmeans()
for instance in instances:
instance.fit(dataset)
# reduce to 2d for visualisation
draw_cluster_2d(instance, X,
filename="%s-kmeans-%s.png" % (name, instance.k))
ms_instances = _meanshift(dataset)
for instance in ms_instances:
instance.fit(dataset)
compare_pies(
[_get_distribution(i) for i in instances] +
[_get_distribution(i) for i in ms_instances],
["KMeans(%s)" % i.k for i in instances] +
["MeanShift(%s)" % round(i.bandwidth) for i in ms_instances],
filename="%s-pie.png" % name)
def _compare_clusters(**datasets):
for name, dataset in datasets.items():
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
instances = _kmeans()
for instance in instances:
instance.fit(dataset)
# reduce to 2d for visualisation
draw_cluster_2d(instance,
X,
filename="%s-kmeans-%s.png" %
(name, instance.k))
ms_instances = _meanshift(dataset)
for instance in ms_instances:
instance.fit(dataset)
compare_pies(
[_get_distribution(i) for i in instances] +
[_get_distribution(i) for i in ms_instances],
["KMeans(%s)" % i.k for i in instances] +
["MeanShift(%s)" % round(i.bandwidth) for i in ms_instances],
filename="%s-pie.png" % name)
def _draw(dataset, filename, title):
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
draw_2d(X, filename, title)
def _draw(dataset, filename, title):
pca = RandomizedPCA(2)
pca.fit(dataset)
X = pca.transform(dataset)
draw_2d(X, filename, title)
def lininit(self):
"""X = UsigmaWT, XTX = Wsigma^2WT, T = XW = Usigma
Further, we can get lower ranks by using just few of the eigen vevtors
T(2) = U(2)sigma(2) = XW(2) ---> 2 is the number of selected
eigenvectors
This is how we initialize the map, just by using the first two first
eigen vals and eigenvectors
Further, we create a linear combination of them in the new map by giving
values from -1 to 1 in each
Direction of SOM map
It shoud be noted that here, X is the covariance matrix of original data
"""
msize = getattr(self, 'mapsize')
rows = msize[0]
cols = msize[1]
nnodes = getattr(self, 'nnodes')
if np.min(msize) > 1:
coord = np.zeros((nnodes, 2))
for i in range(0, nnodes):
coord[i, 0] = int(i / cols) # x
coord[i, 1] = int(i % cols) # y
mx = np.max(coord, axis=0)
mn = np.min(coord, axis=0)
coord = (coord - mn) / (mx - mn)
coord = (coord - .5) * 2
data = getattr(self, 'data')
me = np.mean(data, 0)
data = (data - me)
codebook = np.tile(me, (nnodes, 1))
pca = RandomizedPCA(n_components=2) # Randomized PCA is scalable
# pca = PCA(n_components=2)
pca.fit(data)
eigvec = pca.components_
eigval = pca.explained_variance_
norms = np.sqrt(np.einsum('ij, ij->i', eigvec, eigvec))
eigvec = ((eigvec.T / norms) * eigval).T; eigvec.shape
for j in range(nnodes):
for i in range(eigvec.shape[0]):
codebook[j, :] = codebook[j, :] + coord[j, i] * eigvec[i, :]
return np.around(codebook, decimals=6)
elif np.min(msize) == 1:
coord = np.zeros((nnodes, 1))
for i in range(0, nnodes):
# coord[i, 0] = int(i / cols) # x
coord[i, 0] = int(i % cols) # y
mx = np.max(coord, axis=0)
mn = np.min(coord, axis=0)
# print coord
coord = (coord - mn) / (mx - mn)
coord = (coord - 0.5) * 2
# print coord
data = getattr(self, 'data')
me = np.mean(data, 0)
data = (data - me)
codebook = np.tile(me, (nnodes, 1))
pca = RandomizedPCA(n_components=1) # Randomized PCA is scalable
# pca = PCA(n_components=2)
pca.fit(data)
eigvec = pca.components_
eigval = pca.explained_variance_
norms = np.sqrt(np.einsum('ij, ij->i', eigvec, eigvec))
eigvec = ((eigvec.T / norms) * eigval).T; eigvec.shape
for j in range(nnodes):
for i in range(eigvec.shape[0]):
codebook[j, :] = codebook[j, :] + coord[j, i] & eigvec[i, :]
return np.around(codebook, decimals=6)