def blend_svd(mats, factors=None, k=50):
'''
Special optimized version of blend for doing just an SVD.
Like matrix.svd, returns a triple of:
- U as a dense labeled matrix
- S, a dense vector representing the diagonal of Sigma
- V as a dense labeled matrix
'''
if factors is None:
factors = [blend_factor(mat) for mat in mats]
# Align matrices.
# FIXME: only works for fully labeleed matrices right now.
# TODO: could micro-optimize by using the first ordered set's indices.
from csc_utils.ordered_set import OrderedSet
row_labels, row_mappings = OrderedSet(), []
for mat in mats:
row_mappings.append(
np.array([row_labels.add(item) for item in mat.row_labels],
dtype=np.uint64))
col_labels, col_mappings = OrderedSet(), []
for mat in mats:
col_mappings.append(
np.array([col_labels.add(item) for item in mat.col_labels],
dtype=np.uint64))
# Elide zero row tests, etc.
from divisi2._svdlib import svd_sum
from divisi2 import DenseMatrix
Ut, S, Vt = svd_sum(mats, k, factors, row_mappings, col_mappings)
U = DenseMatrix(Ut.T, row_labels, None)
V = DenseMatrix(Vt.T, col_labels, None)
return U, S, V
def load_model(self, filename):
"""
Loads SVD transformation (U, Sigma and V matrices) from a ZIP file
:param filename: path to the SVD matrix transformation (a ZIP file)
:type filename: string
"""
try:
zip = zipfile.ZipFile(filename, allowZip64=True)
except:
zip = zipfile.ZipFile(filename + '.zip', allowZip64=True)
# Options file
options = dict()
for line in zip.open('README'):
data = line.strip().split('\t')
options[data[0]] = data[1]
try:
k = int(options['k'])
except:
k = 100 #TODO: nasty!!!
# Load U, S, and V
"""
#Python 2.6 only:
#self._U = loads(zip.open('.U').read())
#self._S = loads(zip.open('.S').read())
#self._V = loads(zip.open('.V').read())
"""
try:
self._U = loads(zip.read('.U'))
except:
matrix = fromfile(zip.extract('.U', TMPDIR))
vectors = []
i = 0
while i < len(matrix) / k:
v = DenseVector(matrix[k * i:k * (i + 1)])
vectors.append(v)
i += 1
try:
idx = [
int(idx.strip())
for idx in zip.read('.row_ids').split('\n') if idx
]
except:
idx = [
idx.strip() for idx in zip.read('.row_ids').split('\n')
if idx
]
#self._U = DenseMatrix(vectors)
self._U = DenseMatrix(vectors, OrderedSet(idx), None)
try:
self._V = loads(zip.read('.V'))
except:
matrix = fromfile(zip.extract('.V', TMPDIR))
vectors = []
i = 0
while i < len(matrix) / k:
v = DenseVector(matrix[k * i:k * (i + 1)])
vectors.append(v)
i += 1
try:
idx = [
int(idx.strip())
for idx in zip.read('.col_ids').split('\n') if idx
]
except:
idx = [
idx.strip() for idx in zip.read('.col_ids').split('\n')
if idx
]
#self._V = DenseMatrix(vectors)
self._V = DenseMatrix(vectors, OrderedSet(idx), None)
self._S = loads(zip.read('.S'))
# Shifts for Mean Centerer Matrix
self._shifts = None
if '.shifts.row' in zip.namelist():
self._shifts = [
loads(zip.read('.shifts.row')),
loads(zip.read('.shifts.col')),
loads(zip.read('.shifts.total'))
]
self._reconstruct_matrix(shifts=self._shifts, force=True)
self._reconstruct_similarity(force=True)
