def test_count():
slt = SortedList(load=7)
assert slt.count(0) == 0
for iii in range(100):
for jjj in range(iii):
slt.add(iii)
slt._check()
for iii in range(100):
assert slt.count(iii) == iii
def test_count():
slt = SortedList(load=7)
assert slt.count(0) == 0
for iii in range(100):
for jjj in range(iii):
slt.add(iii)
slt._check()
for iii in range(100):
assert slt.count(iii) == iii
def save_remove_n_edges(edges: pandas.DataFrame, n):
"""
removes n edges from 'edges' so that no node is removed in the process, i.e. the total number
of nodes in 'edges' stays the same
:param edges: original edges
:param n: number of how many edges should be removed
:return:
"""
if n < 1:
return edges
all_edges = SortedList(
list(edges[globConst.NODE1_ID_COL_NAME].append(
edges[globConst.NODE2_ID_COL_NAME])))
edges_list = set(all_edges)
edges_count_dict = {x: all_edges.count(x) for x in edges_list}
i = 0
for _ in range(1000):
drop_indices_candidates = random.sample(
edges.index.values.tolist(), n)
drop_indices = []
for drop_index in tqdm(drop_indices_candidates):
if i == n:
break
drop_edge_candidate = edges.loc[drop_index]
if edges_count_dict[drop_edge_candidate[globConst.NODE1_ID_COL_NAME]]>1 \
and edges_count_dict[drop_edge_candidate[globConst.NODE2_ID_COL_NAME]]>1:
drop_indices.append(drop_index)
i += 1
edges.drop(inplace=True, index=drop_indices)
if i == n:
break
edges.reset_index(drop=True, inplace=True)
return edges
def _test5():
"""
网址：http://www.grantjenks.com/docs/sortedcontainers/sortedlist.html
"""
from sortedcontainers import SortedList
# 定义
sl = SortedList(key=lambda x: -x) # 降序
sl = SortedList([3, 1, 2, 1, 5, 4]) # 升序
print(sl) # SortedList([1, 1, 2, 3, 4, 5])
# 插入、删除元素
sl.add(3)
sl.add(3)
sl.discard(2) # SortedList([1, 1, 3, 3, 3, 4, 5])
print(sl)
# 统计某个元素出现的次数
print(sl.count(3)) # 3
# 返回第一个和最后一个元素
print(sl[0]) # 1
print(sl[-1]) # 5
# 遍历 set
for e in sl:
print(e, end=", ") # 1, 1, 3, 3, 3, 4, 5,
print()
# 判断某元素是否存在
print(2 in sl) # False
# bisect_left() / bisect_right()
print(sl.bisect_left(3)) # 返回大于等于3的最小元素对应的下标 2
print(sl.bisect_right(3)) # 返回大于3的最小元素对应的下标 5
# 清空
sl.clear()
print(len(sl)) # 0
print(len(sl) == 0) # True
def save_remove_n_edges(edges: pandas.DataFrame, n):
"""
removes n edges from 'edges' so that no node is removed in the process, i.e. the total number
of nodes in 'edges' stays the same
:param edges: original edges
:param n: number of how many edges should be removed
:return:
"""
if n < 1:
return edges
print("Ensuring same size (Positive/Negative)...")
all_edges = SortedList(
list(edges[globConst.NODE1_ID_COL_NAME].append(
edges[globConst.NODE2_ID_COL_NAME])))
edges_list = set(all_edges)
edges_count_dict = {x: all_edges.count(x) for x in edges_list}
i = 0
for _ in range(1000):
drop_indices_candidates = random.sample(
edges.index.values.tolist(), n)
drop_indices = []
tqdmbuffer = TqdmBuffer() if globConst.GUI_MODE else None
for drop_index in tqdm(drop_indices_candidates, file=tqdmbuffer):
if i == n:
break
drop_edge_candidate = edges.loc[drop_index]
if (edges_count_dict[drop_edge_candidate[
globConst.NODE1_ID_COL_NAME]] > 1
and edges_count_dict[drop_edge_candidate[
globConst.NODE2_ID_COL_NAME]] > 1):
edges_count_dict[drop_edge_candidate[
globConst.NODE1_ID_COL_NAME]] = edges_count_dict[
drop_edge_candidate[
globConst.NODE1_ID_COL_NAME]] - 1
edges_count_dict[drop_edge_candidate[
globConst.NODE2_ID_COL_NAME]] = edges_count_dict[
drop_edge_candidate[
globConst.NODE2_ID_COL_NAME]] - 1
drop_indices.append(drop_index)
i += 1
edges.drop(inplace=True, index=drop_indices)
if i == n:
break
edges.reset_index(drop=True, inplace=True)
return edges
################################################
l1 = [(1, 10), (2, 100), (2, -5), (1, -100)]
l1.sort(key=lambda x: (x[0], x[1]))
print(l1)
################################################
l2 = [i for i in range(10)]
bisect.bisect(l2, 5) # binary search
from sortedcontainers import SortedList # treemap
sl = SortedList(['e', 'a', 'c', 'd', 'b'])
sl
SortedList(['a', 'b', 'c', 'd', 'e'])
sl *= 10_000_000
sl.count('c')
10000000
sl[-3:]
['e', 'e', 'e']
from sortedcontainers import SortedDict
sd = SortedDict({'c': 3, 'a': 1, 'b': 2})
sd
SortedDict({'a': 1, 'b': 2, 'c': 3})
sd.popitem(index=-1)
('c', 3)
from sortedcontainers import SortedSet
ss = SortedSet('abracadabra')
ss
SortedSet(['a', 'b', 'c', 'd', 'r'])
# http://www.grantjenks.com/docs/sortedcontainers/
from sortedcontainers import SortedList
sl = SortedList(['e', 'a', 'c', 'd', 'b'])
print(sl)
sl *= 10000000
print(sl.count('c'))
print(sl[-3:])
['e', 'e', 'e']
from sortedcontainers import SortedDict
sd = SortedDict({'c': 3, 'a': 1, 'b': 2})
print(sd)
SortedDict({'a': 1, 'b': 2, 'c': 3})
print(sd.popitem())
from sortedcontainers import SortedSet
ss = SortedSet('abracadabra')
print(ss)
print(ss.bisect_left('c'))
一款纯python写的对列表、字典、集合排序的模块
下面显示的所有操作都比线性时间快
>>> from sortedcontainers import SortedList
>>> sl = SortedList(['e', 'a', 'c', 'd', 'b'])
>>> sl
SortedList(['a', 'b', 'c', 'd', 'e'])
>>> sl *= 10_000_000
>>> sl.count('c')
10000000
>>> sl[-3:]
['e', 'e', 'e']
>>> from sortedcontainers import SortedDict
>>> sd = SortedDict({'c': 3, 'a': 1, 'b': 2})
>>> sd
SortedDict({'a': 1, 'b': 2, 'c': 3})
>>> sd.popitem(index=-1)
('c', 3)
>>> from sortedcontainers import SortedSet
>>> ss = SortedSet('abracadabra')
>>> ss
SortedSet(['a', 'b', 'c', 'd', 'r'])
>>> ss.bisect_left('c')
2
# pip install sortedcontainers
from sortedcontainers import SortedList
sl = SortedList(['e', 'a', 'c', 'd', 'b'])
print(sl)
SortedList(['a', 'b', 'c', 'd', 'e'])
sl *= 10_000_000
print(sl.count('c'))
print(sl[-3:])
from sortedcontainers import SortedDict
sd = SortedDict({'c': 3, 'a': 1, 'b': 2})
print(sd)
SortedDict({'a': 1, 'b': 2, 'c': 3})
print(sd.popitem(index=-1))
from sortedcontainers import SortedSet
ss = SortedSet('abracadabra')
print(ss)
SortedSet(['a', 'b', 'c', 'd', 'r'])
print(ss.bisect_left('c'))
