这是我的解决方案，可以扩展为做我认为你想做的事。但这并不完全清楚。可以得到任意数量的行对总和相同；其中可能存在总和相同的行的唯一子集。例如：
鉴于这组总和相同的行对
[[19 19 30 30]
[11 16 11 16]]
这些行中存在一个唯一的子集，仍可被视为有效；但应该吗？
[[19 30]
[16 11]]
无论如何，我希望这些细节很容易处理，给定下面的代码。
import numpy as np
n = 20
#also works for non-square A
A = np.random.randint(2, size=(n*6,n)).astype(np.int8)
##A = np.array( [[0, 0, 0], [1, 1, 1], [1, 1 ,1]], np.uint8)
##A = np.zeros((6,6))
#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))
packing = int(np.dtype(dtype).itemsize * 8 / (float(base) / 2))
for columns in np.array_split(a, (len(a)-1)//packing+1):
R = np.zeros(a.shape[1:], dtype)
for col in columns:
R *= base
R += col
yield R
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 voidview(arr):
"""view the last axis of an array as a void object. can be used as a faster form of lexsort"""
return np.ascontiguousarray(arr).view(np.dtype((np.void, arr.dtype.itemsize * arr.shape[-1]))).reshape(arr.shape[:-1])
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)
#keep all packed columns; we might need them later
columns = []
for packed_column in base_pack_lazy(A, base=multiplicity+1): #loop over packed cols
columns.append(packed_column)
#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 combinations
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 combinations 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
"""
we now have a small set of relevant combinations, but we have lost the details of their particulars
to see which combinations of rows does sum to the same value, we do need to consider rows as a whole
we can simply apply the same mechanism, but for all columns at the same time,
but only for the selected subset of row combinations known to be relevant
"""
#construct full packed matrix
B = np.ascontiguousarray(np.vstack(columns).T)
#perform all relevant sums, over all columns
rowsums = sum(B[I[active_combinations]] for I in combinations_index)
#find the unique rowsums, by viewing rows as a void object
unique, count, inverse = unique_count(voidview(rowsums))
#if not, we did something wrong in deciding on active combinations
assert(np.all(count>1))
#loop over all sets of rows that sum to an identical unique value
for i in xrange(len(unique)):
#set of indexes into combinations_index;
#note that there may be more than two combinations that sum to the same value; we grab them all here
combinations_group = active_combinations[inverse==i]
#associated row-combinations
#array of shape=(mulitplicity,group_size)
row_combinations = combinations_index[:,combinations_group]
#if no duplicate rows involved, we have a match
if len(np.unique(row_combinations[:,[0,-1]])) == multiplicity*2:
print row_combinations
return True
#none of identical rowsums met uniqueness criteria
return False
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(1):
## print has_identical_double_row_sums(A)
print has_identical_triple_row_sums(A)
print clock()-t
编辑：代码清理