def load_tree(path_to_file, path_to_param=None, bias=None):
if path_to_param is not None:
with open(path_to_param, "r") as fin:
real_nr_features = int(fin.readline())
for i in range(6): # bypassing uncessary features
fin.readline()
bias = float(fin.readline)
if bias is None:
bias = 1.0 # the bias term is default to 1.0 in the parabel package
'''Load a single tree model obtained from Parabel Package'''
with open(path_to_file, "r") as fin:
nr_features = int(
fin.readline()) - 1 if bias <= 0 else 0 # remove the bias term
nr_labels = int(fin.readline())
nr_nodes = int(fin.readline())
max_depth = int(sp.log2(nr_nodes + 1))
Clist, Wlist = [], []
for depth in range(max_depth):
nr_nodes_with_depth = 2**depth
if depth != max_depth - 1:
C = smat_util.coo_appender((2**(depth + 1), 2**depth))
W = smat_util.coo_appender((nr_features, 2**(depth + 1)))
else:
C = smat_util.coo_appender((nr_labels, 2**depth))
W = smat_util.coo_appender((nr_features, nr_labels))
child_offset = 2**(depth + 1) - 1
for nid in range(nr_nodes_with_depth):
is_leaf = int(fin.readline().strip())
left, right = [
int(x) - child_offset
for x in fin.readline().strip().split()
]
cur_depth = int(fin.readline().strip())
assert cur_depth == depth
tmp = fin.readline().strip().split()
labels = [int(y) for y in tmp[1:]]
nr_childs = int(fin.readline().strip().split()[0])
if is_leaf != 1:
labels = [left, right]
for y in labels:
C.append(y, nid, 1.0)
for iv in fin.readline().strip().split():
iv = iv.split(':')
col = y
row = int(iv[0])
if row >= nr_features:
continue
v = float(iv[1])
W.append(row, col, v)
Clist += [C.tocsr()]
Wlist += [W.tocsr()]
return HierarchicalMLModel(
[MLModel(w, c) for w, c in zip(Wlist, Clist)], bias)
def load_tree(path_to_file):
with open(path_to_file, "r") as fin:
nr_features = int(
fin.readline()) - 2 # remove the zero and bias term
nr_labels = int(fin.readline())
nr_nodes = int(fin.readline())
max_depth = int(sp.log2(nr_nodes + 1))
Clist, Wlist = [], []
for depth in range(max_depth):
nr_nodes_with_depth = 2**depth
if depth != max_depth - 1:
C = smat_util.coo_appender((2**(depth + 1), 2**depth))
W = smat_util.coo_appender((nr_features, 2**(depth + 1)))
else:
C = smat_util.coo_appender((nr_labels, 2**depth))
W = smat_util.coo_appender((nr_features, nr_labels))
child_offset = 2**(depth + 1) - 1
for nid in range(nr_nodes_with_depth):
is_leaf = int(fin.readline().strip())
left, right = [
int(x) - child_offset
for x in fin.readline().strip().split()
]
cur_depth = int(fin.readline().strip())
assert cur_depth == depth
tmp = fin.readline().strip().split()
labels = [int(y) for y in tmp[1:]]
nr_childs = int(fin.readline().strip().split()[0])
if is_leaf != 1:
labels = [left, right]
for y in labels:
C.append(y, nid, 1.0)
for iv in fin.readline().strip().split():
iv = iv.split(':')
col = y
row = int(iv[0]) - 1
if row >= nr_features:
continue
v = float(iv[1])
W.append(row, col, v)
Clist += [C.tocsr()]
Wlist += [W.tocsr()]
return HierarchicalMLModel(
[MLModel(w, c) for w, c in zip(Wlist, Clist)])
def load_prediction(path_to_file, only_topk=None):
with open(path_to_file, 'r') as fin:
nr_insts, nr_labels = [
int(x) for x in fin.readline().strip().split()
]
coo = smat_util.coo_appender((nr_insts, nr_labels))
for i in range(nr_insts):
for iv in fin.readline().strip().split():
iv = iv.split(':')
j = int(iv[0])
v = float(iv[1])
coo.append(i, j, v)
return smat_util.sorted_csr(coo.tocsr(), only_topk=only_topk)
