这是一种“惰性”方法，可扩展到 n=10000，使用“仅”4gb 内存，每次调用在 10 秒左右完成。最坏情况复杂度为 O(n^3)，但对于随机数据，预期性能为 O(n^2)。乍一看，您似乎需要 O(n^3) 次操作；每行组合至少需要生产和检查一次。但是我们不需要查看整行。相反，我们可以对行对的比较执行早期退出策略，一旦明确它们对我们没有用处；对于随机数据，我们可能会在考虑一行中的所有列之前很久就得出这个结论。
import numpy as np
n = 10
#also works for non-square A
A = np.random.randint(2, size=(n*2,n)).astype(np.int8)
#force the inclusion of some hits, to keep our algorithm on its toes
##A[0] = A[1]
def base_pack_lazy(a, base, dtype=np.uint64):
"""
pack the last axis of an array as minimal base representation
lazily yields packed columns of the original matrix
"""
a = np.ascontiguousarray( np.rollaxis(a, -1))
init = np.zeros(a.shape[1:], dtype)
packing = int(np.dtype(dtype).itemsize * 8 / (float(base) / 2))
for columns in np.array_split(a, (len(a)-1)//packing+1):
yield reduce(
lambda acc,inc: acc*base+inc,
columns,
init)
def unique_count(a):
"""returns counts of unique elements"""
unique, inverse = np.unique(a, return_inverse=True)
count = np.zeros(len(unique), np.int)
np.add.at(count, inverse, 1) #note; this scatter operation requires numpy 1.8; use a sparse matrix otherwise!
return unique, count, inverse
def has_identical_row_sums_lazy(A, combinations_index):
"""
compute the existence of combinations of rows summing to the same vector,
given an nxm matrix A and an index matrix specifying all combinations
naively, we need to compute the sum of each row combination at least once, giving n^3 computations
however, this isnt strictly required; we can lazily consider the columns, giving an early exit opportunity
all nicely vectorized of course
"""
multiplicity, combinations = combinations_index.shape
#list of indices into combinations_index, denoting possibly interacting combinations
active_combinations = np.arange(combinations, dtype=np.uint32)
for packed_column in base_pack_lazy(A, base=multiplicity+1): #loop over packed cols
#compute rowsums only for a fixed number of columns at a time.
#this is O(n^2) rather than O(n^3), and after considering the first column,
#we can typically already exclude almost all rowpairs
partial_rowsums = sum(packed_column[I[active_combinations]] for I in combinations_index)
#find duplicates in this column
unique, count, inverse = unique_count(partial_rowsums)
#prune those pairs which we can exclude as having different sums, based on columns inspected thus far
active_combinations = active_combinations[count[inverse] > 1]
#early exit; no pairs
if len(active_combinations)==0:
return False
return True
def has_identical_triple_row_sums(A):
n = len(A)
idx = np.array( [(i,j,k)
for i in xrange(n)
for j in xrange(n)
for k in xrange(n)
if i<j and j<k], dtype=np.uint16)
idx = np.ascontiguousarray( idx.T)
return has_identical_row_sums_lazy(A, idx)
def has_identical_double_row_sums(A):
n = len(A)
idx = np.array(np.tril_indices(n,-1), dtype=np.int32)
return has_identical_row_sums_lazy(A, idx)
from time import clock
t = clock()
for i in xrange(10):
print has_identical_double_row_sums(A)
print has_identical_triple_row_sums(A)
print clock()-t
如您在上面所问的，已扩展为包括对三组行总和的计算。对于 n=100，这仍然只需要大约 0.2s
编辑：一些清理；编辑2：更多清理