我想写一个函数，它以一个字母数组作为参数，并从中选择一些字母。
假设您提供了一个包含8个字母的数组，并希望从中选择3个字母。那么你应该得到:
8! / ((8 - 3)! * 3!) = 56
数组(或单词)，每个数组由3个字母组成。
当前回答
假设你的字母数组是这样的:"ABCDEFGH"。你有三个下标(i, j, k)来表示你要用哪个字母来表示当前单词。
A B C D E F G H ^ ^ ^ i j k
首先你改变k，所以下一步看起来像这样:
A B C D E F G H ^ ^ ^ i j k
如果你到达终点，你继续改变j和k。
A B C D E F G H ^ ^ ^ i j k A B C D E F G H ^ ^ ^ i j k
一旦j达到G, i也开始变化。
A B C D E F G H ^ ^ ^ i j k A B C D E F G H ^ ^ ^ i j k ...
用代码写出来是这样的
void print_combinations(const char *string)
{
int i, j, k;
int len = strlen(string);
for (i = 0; i < len - 2; i++)
{
for (j = i + 1; j < len - 1; j++)
{
for (k = j + 1; k < len; k++)
printf("%c%c%c\n", string[i], string[j], string[k]);
}
}
}
其他回答
我可以给出这个问题的递归Python解决方案吗?
def choose_iter(elements, length):
for i in xrange(len(elements)):
if length == 1:
yield (elements[i],)
else:
for next in choose_iter(elements[i+1:], length-1):
yield (elements[i],) + next
def choose(l, k):
return list(choose_iter(l, k))
使用示例:
>>> len(list(choose_iter("abcdefgh",3)))
56
我喜欢它的简洁。
假设你的字母数组是这样的:"ABCDEFGH"。你有三个下标(i, j, k)来表示你要用哪个字母来表示当前单词。
A B C D E F G H ^ ^ ^ i j k
首先你改变k，所以下一步看起来像这样:
A B C D E F G H ^ ^ ^ i j k
如果你到达终点，你继续改变j和k。
A B C D E F G H ^ ^ ^ i j k A B C D E F G H ^ ^ ^ i j k
一旦j达到G, i也开始变化。
A B C D E F G H ^ ^ ^ i j k A B C D E F G H ^ ^ ^ i j k ...
用代码写出来是这样的
void print_combinations(const char *string)
{
int i, j, k;
int len = strlen(string);
for (i = 0; i < len - 2; i++)
{
for (j = i + 1; j < len - 1; j++)
{
for (k = j + 1; k < len; k++)
printf("%c%c%c\n", string[i], string[j], string[k]);
}
}
}
像Andrea Ambu一样用Python写的，但不是硬编码来选择三个。
def combinations(list, k):
"""Choose combinations of list, choosing k elements(no repeats)"""
if len(list) < k:
return []
else:
seq = [i for i in range(k)]
while seq:
print [list[index] for index in seq]
seq = get_next_combination(len(list), k, seq)
def get_next_combination(num_elements, k, seq):
index_to_move = find_index_to_move(num_elements, seq)
if index_to_move == None:
return None
else:
seq[index_to_move] += 1
#for every element past this sequence, move it down
for i, elem in enumerate(seq[(index_to_move+1):]):
seq[i + 1 + index_to_move] = seq[index_to_move] + i + 1
return seq
def find_index_to_move(num_elements, seq):
"""Tells which index should be moved"""
for rev_index, elem in enumerate(reversed(seq)):
if elem < (num_elements - rev_index - 1):
return len(seq) - rev_index - 1
return None
在Python中，利用递归的优势和所有事情都是通过引用完成的事实。对于非常大的集合，这将占用大量内存，但其优点是初始集合可以是一个复杂的对象。它只会找到唯一的组合。
import copy
def find_combinations( length, set, combinations = None, candidate = None ):
# recursive function to calculate all unique combinations of unique values
# from [set], given combinations of [length]. The result is populated
# into the 'combinations' list.
#
if combinations == None:
combinations = []
if candidate == None:
candidate = []
for item in set:
if item in candidate:
# this item already appears in the current combination somewhere.
# skip it
continue
attempt = copy.deepcopy(candidate)
attempt.append(item)
# sorting the subset is what gives us completely unique combinations,
# so that [1, 2, 3] and [1, 3, 2] will be treated as equals
attempt.sort()
if len(attempt) < length:
# the current attempt at finding a new combination is still too
# short, so add another item to the end of the set
# yay recursion!
find_combinations( length, set, combinations, attempt )
else:
# the current combination attempt is the right length. If it
# already appears in the list of found combinations then we'll
# skip it.
if attempt in combinations:
continue
else:
# otherwise, we append it to the list of found combinations
# and move on.
combinations.append(attempt)
continue
return len(combinations)
你可以这样使用它。传递'result'是可选的，所以你可以用它来获取可能组合的数量…尽管这样做效率很低(最好通过计算来完成)。
size = 3
set = [1, 2, 3, 4, 5]
result = []
num = find_combinations( size, set, result )
print "size %d results in %d sets" % (size, num)
print "result: %s" % (result,)
您应该从测试数据中得到以下输出:
size 3 results in 10 sets
result: [[1, 2, 3], [1, 2, 4], [1, 2, 5], [1, 3, 4], [1, 3, 5], [1, 4, 5], [2, 3, 4], [2, 3, 5], [2, 4, 5], [3, 4, 5]]
如果你的集合是这样的，它也会工作得很好:
set = [
[ 'vanilla', 'cupcake' ],
[ 'chocolate', 'pudding' ],
[ 'vanilla', 'pudding' ],
[ 'chocolate', 'cookie' ],
[ 'mint', 'cookie' ]
]
我的实现在c/c++
#include <unistd.h>
#include <stdio.h>
#include <iconv.h>
#include <string.h>
#include <errno.h>
#include <stdlib.h>
int main(int argc, char **argv)
{
int opt = -1, min_len = 0, max_len = 0;
char ofile[256], fchar[2], tchar[2];
ofile[0] = 0;
fchar[0] = 0;
tchar[0] = 0;
while((opt = getopt(argc, argv, "o:f:t:l:L:")) != -1)
{
switch(opt)
{
case 'o':
strncpy(ofile, optarg, 255);
break;
case 'f':
strncpy(fchar, optarg, 1);
break;
case 't':
strncpy(tchar, optarg, 1);
break;
case 'l':
min_len = atoi(optarg);
break;
case 'L':
max_len = atoi(optarg);
break;
default:
printf("usage: %s -oftlL\n\t-o output file\n\t-f from char\n\t-t to char\n\t-l min seq len\n\t-L max seq len", argv[0]);
}
}
if(max_len < 1)
{
printf("error, length must be more than 0\n");
return 1;
}
if(min_len > max_len)
{
printf("error, max length must be greater or equal min_length\n");
return 1;
}
if((int)fchar[0] > (int)tchar[0])
{
printf("error, invalid range specified\n");
return 1;
}
FILE *out = fopen(ofile, "w");
if(!out)
{
printf("failed to open input file with error: %s\n", strerror(errno));
return 1;
}
int cur_len = min_len;
while(cur_len <= max_len)
{
char buf[cur_len];
for(int i = 0; i < cur_len; i++)
buf[i] = fchar[0];
fwrite(buf, cur_len, 1, out);
fwrite("\n", 1, 1, out);
while(buf[0] != (tchar[0]+1))
{
while(buf[cur_len-1] < tchar[0])
{
(int)buf[cur_len-1]++;
fwrite(buf, cur_len, 1, out);
fwrite("\n", 1, 1, out);
}
if(cur_len < 2)
break;
if(buf[0] == tchar[0])
{
bool stop = true;
for(int i = 1; i < cur_len; i++)
{
if(buf[i] != tchar[0])
{
stop = false;
break;
}
}
if(stop)
break;
}
int u = cur_len-2;
for(; u>=0 && buf[u] >= tchar[0]; u--)
;
(int)buf[u]++;
for(int i = u+1; i < cur_len; i++)
buf[i] = fchar[0];
fwrite(buf, cur_len, 1, out);
fwrite("\n", 1, 1, out);
}
cur_len++;
}
fclose(out);
return 0;
}
这里我的实现在c++，它写所有的组合到指定的文件，但行为可以改变，我在生成各种字典，它接受最小和最大长度和字符范围，目前只有ANSI支持，它足以满足我的需求
