Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,308 Bytes
7968cb0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import random
class cached_property(object):
"""
Descriptor (non-data) for building an attribute on-demand on first use.
"""
def __init__(self, factory):
"""
<factory> is called such: factory(instance) to build the attribute.
"""
self._attr_name = factory.__name__
self._factory = factory
def __get__(self, instance, owner):
# Build the attribute.
attr = self._factory(instance)
# Cache the value; hide ourselves.
setattr(instance, self._attr_name, attr)
return attr
def get_inds(expected_num, clu_nums, cid2clu, seq2ind):
cur_len, cur_idx, query_cids, query_idx = 0, 0, [], []
while cur_len < expected_num:
cid, l = clu_nums[cur_idx % (len(clu_nums))]
cur_idx += 1
# check if this cluster has been selected
if cid in query_cids:
continue
if random.random() > 0.5:
for seq in cid2clu[cid]:
# seq2ind: ensure it is in limited lengths
if seq in seq2ind.keys():
query_idx.append(seq2ind[seq])
cur_len += 1
query_cids.append(cid)
return query_cids, query_idx
def get_num(N, valid_num=100):
train_n, valid_n = int(0.9 * N), min(valid_num, int(0.05 * N))
test_n = N - train_n - valid_n
return train_n, valid_n, test_n
def get_full_inds(expected_num, clu_nums, cid2clu, full_seq2ind):
cur_len, cur_idx, query_cids, query_idx = 0, 0, [], {}
# build query_idx for each dataset
for dataname in full_seq2ind.keys():
if dataname not in query_idx.keys():
query_idx[dataname] = []
cur_idx_lst = list(range(len(clu_nums)))
while cur_len < expected_num:
cur_idx = random.choice(cur_idx_lst)
cid, l = clu_nums[cur_idx]
# check if this cluster has been selected
if cid in query_cids:
continue
for seq in set(cid2clu[cid]):
# seq2ind: ensure it is in limited lengths
for dataname in full_seq2ind.keys():
if seq in full_seq2ind[dataname].keys():
query_idx[dataname].append(full_seq2ind[dataname][seq])
cur_len += 1
query_cids.append(cid)
cur_idx_lst.remove(cur_idx)
return query_cids, query_idx
def get_inds(expected_num, clu_nums, cid2clu, seq2ind):
cur_len, query_cids, query_idx = 0, [], []
cur_idx_lst = list(range(len(clu_nums)))
while cur_len < expected_num:
try:
cur_idx = random.choice(cur_idx_lst)
cid, l = clu_nums[cur_idx]
# check if this cluster has been selected
if cid in query_cids:
continue
# check if this cluster is too big
pre = abs(expected_num - cur_len)
aft = abs(cur_len + l - expected_num)
if pre < aft:
continue
for seq in cid2clu[cid]:
# seq2ind: ensure it is in limited lengths
if seq in seq2ind.keys():
query_idx.append(seq2ind[seq])
cur_len += 1
query_cids.append(cid)
cur_idx_lst.remove(cur_idx)
except:
break
return query_cids, query_idx
|