def factorize(self, show_progress=False, compute_w=True, compute_h=True,
compute_err=True, niter=1):
""" Factorize s.t. WH = data
Parameters
----------
show_progress : bool
print some extra information to stdout.
compute_h : bool
iteratively update values for H.
compute_w : bool
iteratively update values for W.
compute_err : bool
compute Frobenius norm |data-WH| after each update and store
it to .ferr[k].
Updated Values
--------------
.W : updated values for W.
.H : updated values for H.
.ferr : Frobenius norm |data-WH|.
"""
AA.factorize(self, niter=1, show_progress=show_progress,
compute_w=compute_w, compute_h=compute_h,
compute_err=compute_err)
def factorize(self,
show_progress=False,
compute_w=True,
compute_h=True,
compute_err=True,
niter=1):
""" Factorize s.t. WH = data
Parameters
----------
show_progress : bool
print some extra information to stdout.
compute_h : bool
iteratively update values for H.
compute_w : bool
iteratively update values for W.
compute_err : bool
compute Frobenius norm |data-WH| after each update and store
it to .ferr[k].
Updated Values
--------------
.W : updated values for W.
.H : updated values for H.
.ferr : Frobenius norm |data-WH|.
"""
AA.factorize(self,
niter=1,
show_progress=show_progress,
compute_w=compute_w,
compute_h=compute_h,
compute_err=compute_err)
def factorize(self,
show_progress=False,
compute_w=True,
compute_h=True,
compute_err=True,
robust_cluster=3,
niter=1,
robust_nselect=-1):
""" Factorize s.t. WH = data
Parameters
----------
show_progress : bool
print some extra information to stdout.
False, default
compute_h : bool
iteratively update values for H.
True, default
compute_w : bool
iteratively update values for W.
default, True
compute_err : bool
compute Frobenius norm |data-WH| after each update and store
it to .ferr[k].
robust_cluster : int, optional
set the number of clusters for robust map selection.
3, default
robust_nselect : int, optional
set the number of samples to consider for robust map
selection.
-1, default (automatically determine suitable number)
Updated Values
--------------
.W : updated values for W.
.H : updated values for H.
.ferr : Frobenius norm |data-WH|.
"""
self._robust_cluster = robust_cluster
self._robust_nselect = robust_nselect
if self._robust_nselect == -1:
self._robust_nselect = np.round(np.log(self.data.shape[1]) * 2)
AA.factorize(self,
niter=1,
show_progress=show_progress,
compute_w=compute_w,
compute_h=compute_h,
compute_err=compute_err)
def update_w(self):
""" compute new W """
def select_hull_points(data, n=3):
""" select data points for pairwise projections of the first n
dimensions """
# iterate over all projections and select data points
idx = np.array([])
# iterate over some pairwise combinations of dimensions
for i in combinations(range(n), 2):
# sample convex hull points in 2D projection
convex_hull_d = quickhull(data[i, :].T)
# get indices for convex hull data points
idx = np.append(idx, vq(data[i, :], convex_hull_d.T))
idx = np.unique(idx)
return np.int32(idx)
# determine convex hull data points using either PCA or random
# projections
method = 'randomprojection'
if method == 'pca':
pcamodel = PCA(self.data)
pcamodel.factorize(show_progress=False)
proj = pcamodel.H
else:
R = np.random.randn(self._base_sel, self._data_dimension)
proj = np.dot(R, self.data)
self._hull_idx = select_hull_points(proj, n=self._base_sel)
aa_mdl = AA(self.data[:, self._hull_idx], num_bases=self._num_bases)
# determine W
aa_mdl.factorize(niter=50,
compute_h=True,
compute_w=True,
compute_err=True,
show_progress=False)
self.W = aa_mdl.W
self._map_w_to_data()
def updateW(self):
def selectHullPoints(data, n=3):
""" select data points for pairwise projections of the first n
dimensions """
# iterate over all projections and select data points
idx = np.array([])
# iterate over some pairwise combinations of dimensions
for i in combinations(range(n), 2):
# sample convex hull points in 2D projection
convex_hull_d = quickhull(data[i, :].T)
# get indices for convex hull data points
idx = np.append(idx, vq(data[i, :], convex_hull_d.T))
idx = np.unique(idx)
return np.int32(idx)
# determine convex hull data points only if the total
# amount of available data is >50
#if self.data.shape[1] > 50:
pcamodel = PCA(self.data, show_progress=self._show_progress)
pcamodel.factorize()
self._hull_idx = selectHullPoints(pcamodel.H, n=self._base_sel)
#else:
# self._hull_idx = range(self.data.shape[1])
aa_mdl = AA(self.data[:, self._hull_idx],
num_bases=self._num_bases,
niter=self._niter,
show_progress=self._show_progress,
compW=True)
# initialize W, H, and beta
aa_mdl.initialization()
# determine W
aa_mdl.factorize()
self.W = aa_mdl.W
def factorize(self, show_progress=False, compute_w=True, compute_h=True,
compute_err=True, robust_cluster=3, niter=1, robust_nselect=-1):
""" Factorize s.t. WH = data
Parameters
----------
show_progress : bool
print some extra information to stdout.
False, default
compute_h : bool
iteratively update values for H.
True, default
compute_w : bool
iteratively update values for W.
default, True
compute_err : bool
compute Frobenius norm |data-WH| after each update and store
it to .ferr[k].
robust_cluster : int, optional
set the number of clusters for robust map selection.
3, default
robust_nselect : int, optional
set the number of samples to consider for robust map
selection.
-1, default (automatically determine suitable number)
Updated Values
--------------
.W : updated values for W.
.H : updated values for H.
.ferr : Frobenius norm |data-WH|.
"""
self._robust_cluster = robust_cluster
self._robust_nselect = robust_nselect
if self._robust_nselect == -1:
self._robust_nselect = np.round(np.log(self.data.shape[1])*2)
AA.factorize(self, niter=1, show_progress=show_progress,
compute_w=compute_w, compute_h=compute_h,
compute_err=compute_err)
def update_w(self):
""" compute new W """
def select_hull_points(data, n=3):
""" select data points for pairwise projections of the first n
dimensions """
# iterate over all projections and select data points
idx = np.array([])
# iterate over some pairwise combinations of dimensions
for i in combinations(range(n), 2):
# sample convex hull points in 2D projection
convex_hull_d = quickhull(data[i, :].T)
# get indices for convex hull data points
idx = np.append(idx, vq(data[i, :], convex_hull_d.T))
idx = np.unique(idx)
return np.int32(idx)
# determine convex hull data points using either PCA or random
# projections
method = 'randomprojection'
if method == 'pca':
pcamodel = PCA(self.data)
pcamodel.factorize(show_progress=False)
proj = pcamodel.H
else:
R = np.random.randn(self._base_sel, self._data_dimension)
proj = np.dot(R, self.data)
self._hull_idx = select_hull_points(proj, n=self._base_sel)
aa_mdl = AA(self.data[:, self._hull_idx], num_bases=self._num_bases)
# determine W
aa_mdl.factorize(niter=50, compute_h=True, compute_w=True,
compute_err=True, show_progress=False)
self.W = aa_mdl.W
self._map_w_to_data()
