def predict(
self,
X,
only_topk=None,
csr_codes=None,
cond_prob=None,
normalized=False,
threads=-1,
):
assert X.shape[1] == self.nr_features
if csr_codes is None:
dense = X.dot(self.W).toarray()
if cond_prob:
dense = cond_prob.transform(dense, inplace=True)
coo = smat_util.dense_to_coo(dense)
pred_csr = smat_util.sorted_csr_from_coo(coo.shape,
coo.row,
coo.col,
coo.data,
only_topk=only_topk)
else: # csr_codes is given
assert self.C is not None, "This model does not have C"
assert X.shape[1] == self.nr_features
assert csr_codes.shape[0] == X.shape[0]
assert csr_codes.shape[1] == self.nr_codes
if (csr_codes.data == 0).sum() != 0:
# this is a trick to avoid zero entries explicit removal from the smat_dot_smat
offset = sp.absolute(csr_codes.data).max() + 1
csr_codes = smat.csr_matrix(
(csr_codes.data + offset, csr_codes.indices,
csr_codes.indptr),
shape=csr_codes.shape,
)
csr_labels = (csr_codes.dot(self.C.T)).tocsr()
csr_labels.data -= offset
else:
csr_labels = (csr_codes.dot(self.C.T)).tocsr()
nnz_of_insts = csr_labels.indptr[1:] - csr_labels.indptr[:-1]
inst_idx = sp.repeat(sp.arange(X.shape[0], dtype=sp.uint32),
nnz_of_insts)
label_idx = csr_labels.indices.astype(sp.uint32)
val = self.predict_values(X, inst_idx, label_idx, threads=threads)
if cond_prob:
val = cond_prob.transform(val, inplace=True)
val = cond_prob.combiner(val, csr_labels.data)
pred_csr = smat_util.sorted_csr_from_coo(csr_labels.shape,
inst_idx,
label_idx,
val,
only_topk=only_topk)
if normalized:
pred_csr = sk_normalize(pred_csr, axis=1, copy=False, norm="l1")
return pred_csr
def predict_with_coo_labels(self, X, inst_idx, label_idx, only_topk=None):
val = self.predict_values(X, inst_idx, label_idx)
shape = (X.shape[0], self.nr_labels)
pred_csr = smat_util.sorted_csr_from_coo(shape,
inst_idx,
label_idx,
val,
only_topk=only_topk)
return pred_csr
def predict_new(
self,
X,
only_topk=None,
csr_codes=None,
cond_prob=None,
normalized=False,
threads=-1,
):
assert X.shape[1] == self.nr_features
if csr_codes is None:
dense = X.dot(self.W).toarray()
if cond_prob:
dense = cond_prob.transform(dense, inplace=True)
coo = smat_util.dense_to_coo(dense)
pred_csr = smat_util.sorted_csr_from_coo(coo.shape,
coo.row,
coo.col,
coo.data,
only_topk=only_topk)
else: # csr_codes is given
assert self.C is not None, "This model does not have C"
assert X.shape[1] == self.nr_features
assert csr_codes.shape[0] == X.shape[0]
assert csr_codes.shape[1] == self.nr_codes
if not csr_codes.has_sorted_indices:
csr_codes = csr_codes.sorted_indices()
if (csr_codes.data == 0).sum() != 0:
# this is a trick to avoid zero entries explicit removal from the smat_dot_smat
offset = sp.absolute(csr_codes.data).max() + 1
csr_codes = smat.csr_matrix(
(csr_codes.data + offset, csr_codes.indices,
csr_codes.indptr),
shape=csr_codes.shape,
)
pZ = PyMatrix.init_from(csr_codes, self.dtype)
csr_labels, pred_csr = clib.multilabel_predict_with_codes(
X, self.pW, self.pC, pZ, threads=threads)
csr_labels.data -= offset
else:
pZ = PyMatrix.init_from(csr_codes.sorted_indices(), self.dtype)
csr_labels, pred_csr = clib.multilabel_predict_with_codes(
X, self.pW, self.pC, pZ, threads=threads)
val = pred_csr.data
if cond_prob:
val = cond_prob.transform(val, inplace=True)
val = cond_prob.combiner(val, csr_labels.data)
pred_csr = smat_util.sorted_csr(pred_csr, only_topk=only_topk)
if normalized:
pred_csr = sk_normalize(pred_csr, axis=1, copy=False, norm="l1")
return pred_csr
def predict(self,
X,
only_topk=None,
transform=None,
csr_codes=None,
cond_prob=None,
normalized=False,
threads=-1):
assert X.shape[1] == self.nr_features
if csr_codes is None:
dense = X.dot(self.W).toarray()
if transform:
dense = transform(dense, inplace=True)
coo = smat_util.dense_to_coo(dense)
pred_csr = smat_util.sorted_csr_from_coo(coo.shape,
coo.row,
coo.col,
coo.data,
only_topk=only_topk)
else: # csr_codes is given
assert self.C is not None, "This model does not have C"
assert X.shape[1] == self.nr_features
assert csr_codes.shape[0] == X.shape[0]
assert csr_codes.shape[1] == self.nr_codes
csr_labels = (csr_codes.dot(self.C.T)).tocsr()
nnz_of_insts = csr_labels.indptr[1:] - csr_labels.indptr[:-1]
inst_idx = sp.repeat(sp.arange(X.shape[0], dtype=sp.uint32),
nnz_of_insts)
label_idx = csr_labels.indices.astype(sp.uint32)
val = self.predict_values(X, inst_idx, label_idx, threads=threads)
if transform:
val = transform(val, inplace=True)
if cond_prob:
val[:] = cond_prob.combiner(val, csr_labels.data)
pred_csr = smat.csr_matrix((val, label_idx, csr_labels.indptr),
shape=csr_labels.shape)
pred_csr = smat_util.sorted_csr(pred_csr, only_topk=only_topk)
#pred_csr = self.predict_with_coo_labels(X, coo_labels.row, coo_labels.cols, only_topk)
if normalized:
pred_csr = sk_normalize(pred_csr, axis=1, copy=False, norm='l1')
return pred_csr
def predict_new(self,
X,
only_topk=None,
transform=None,
csr_codes=None,
cond_prob=None,
normalized=False,
threads=-1):
assert X.shape[1] == self.nr_features
if csr_codes is None:
dense = X.dot(self.W).toarray()
if transform:
dense = transform(dense, inplace=True)
coo = smat_util.dense_to_coo(dense)
pred_csr = smat_util.sorted_csr_from_coo(coo.shape,
coo.row,
coo.col,
coo.data,
only_topk=only_topk)
else: # csr_codes is given
assert self.C is not None, "This model does not have C"
assert X.shape[1] == self.nr_features
assert csr_codes.shape[0] == X.shape[0]
assert csr_codes.shape[1] == self.nr_codes
pZ = PyMatrix.init_from(csr_codes, self.dtype)
csr_labels, pred_csr = clib.multilabel_predict_with_codes(
X, self.pW, self.pC, pZ, threads=threads)
val = pred_csr.data
if transform:
val = transform(val, inplace=True)
if cond_prob:
val[:] = cond_prob.combiner(val, csr_labels.data)
pred_csr = smat_util.sorted_csr(pred_csr, only_topk=only_topk)
if normalized:
pred_csr = sk_normalize(pred_csr, axis=1, copy=False, norm='l1')
return pred_csr
def sorted_csr(csr, only_topk=None):
assert isinstance(csr, smat.csr_matrix)
row_idx = sp.repeat(sp.arange(csr.shape[0], dtype=sp.uint32),
csr.indptr[1:] - csr.indptr[:-1])
return smat_util.sorted_csr_from_coo(csr.shape, row_idx, csr.indices,
csr.data, only_topk)
