不需要进行集合操作。这个问题几乎和循环K个嵌套循环一样，但你必须小心索引和边界(忽略Java和OOP的东西):

 public class CombinationsGen {
    private final int n;
    private final int k;
    private int[] buf;

    public CombinationsGen(int n, int k) {
        this.n = n;
        this.k = k;
    }

    public void combine(Consumer<int[]> consumer) {
        buf = new int[k];
        rec(0, 0, consumer);
    }

    private void rec(int index, int next, Consumer<int[]> consumer) {
        int max = n - index;

        if (index == k - 1) {
            for (int i = 0; i < max && next < n; i++) {
                buf[index] = next;
                next++;
                consumer.accept(buf);
            }
        } else {
            for (int i = 0; i < max && next + index < n; i++) {
                buf[index] = next;
                next++;
                rec(index + 1, next, consumer);
            }
        }
    }
}

像这样使用:

 CombinationsGen gen = new CombinationsGen(5, 2);

 AtomicInteger total = new AtomicInteger();
 gen.combine(arr -> {
     System.out.println(Arrays.toString(arr));
     total.incrementAndGet();
 });
 System.out.println(total);

获得预期的结果:

[0, 1]
[0, 2]
[0, 3]
[0, 4]
[1, 2]
[1, 3]
[1, 4]
[2, 3]
[2, 4]
[3, 4]
10

最后，将索引映射到您可能拥有的任何数据集。

作为迭代器对象实现的MetaTrader MQL4非常快速的组合。

代码很容易理解。

我对很多算法进行了基准测试，这个算法真的非常快——大约比大多数next_combination()函数快3倍。

class CombinationsIterator { private: int input_array[]; // 1 2 3 4 5 int index_array[]; // i j k int m_elements; // N int m_indices; // K public: CombinationsIterator(int &src_data[], int k) { m_indices = k; m_elements = ArraySize(src_data); ArrayCopy(input_array, src_data); ArrayResize(index_array, m_indices); // create initial combination (0..k-1) for (int i = 0; i < m_indices; i++) { index_array[i] = i; } } // https://stackoverflow.com/questions/5076695 // bool next_combination(int &item[], int k, int N) bool advance() { int N = m_elements; for (int i = m_indices - 1; i >= 0; --i) { if (index_array[i] < --N) { ++index_array[i]; for (int j = i + 1; j < m_indices; ++j) { index_array[j] = index_array[j - 1] + 1; } return true; } } return false; } void getItems(int &items[]) { // fill items[] from input array for (int i = 0; i < m_indices; i++) { items[i] = input_array[index_array[i]]; } } };

测试上述迭代器类的驱动程序:

//+------------------------------------------------------------------+ //| | //+------------------------------------------------------------------+ // driver program to test above class #define N 5 #define K 3 void OnStart() { int myset[N] = {1, 2, 3, 4, 5}; int items[K]; CombinationsIterator comboIt(myset, K); do { comboIt.getItems(items); printf("%s", ArrayToString(items)); } while (comboIt.advance()); }

输出: 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

我知道这个问题已经有很多答案了，但我想在JavaScript中添加我自己的贡献，它由两个函数组成——一个生成原始n元素集的所有可能不同的k子集，另一个使用第一个函数生成原始n元素集的幂集。

下面是这两个函数的代码:

//Generate combination subsets from a base set of elements (passed as an array). This function should generate an
//array containing nCr elements, where nCr = n!/[r! (n-r)!].

//Arguments:

//[1] baseSet :     The base set to create the subsets from (e.g., ["a", "b", "c", "d", "e", "f"])
//[2] cnt :         The number of elements each subset is to contain (e.g., 3)

function MakeCombinationSubsets(baseSet, cnt)
{
    var bLen = baseSet.length;
    var indices = [];
    var subSet = [];
    var done = false;
    var result = [];        //Contains all the combination subsets generated
    var done = false;
    var i = 0;
    var idx = 0;
    var tmpIdx = 0;
    var incr = 0;
    var test = 0;
    var newIndex = 0;
    var inBounds = false;
    var tmpIndices = [];
    var checkBounds = false;

    //First, generate an array whose elements are indices into the base set ...

    for (i=0; i<cnt; i++)

        indices.push(i);

    //Now create a clone of this array, to be used in the loop itself ...

        tmpIndices = [];

        tmpIndices = tmpIndices.concat(indices);

    //Now initialise the loop ...

    idx = cnt - 1;      //point to the last element of the indices array
    incr = 0;
    done = false;
    while (!done)
    {
    //Create the current subset ...

        subSet = [];    //Make sure we begin with a completely empty subset before continuing ...

        for (i=0; i<cnt; i++)

            subSet.push(baseSet[tmpIndices[i]]);    //Create the current subset, using items selected from the
                                                    //base set, using the indices array (which will change as we
                                                    //continue scanning) ...

    //Add the subset thus created to the result set ...

        result.push(subSet);

    //Now update the indices used to select the elements of the subset. At the start, idx will point to the
    //rightmost index in the indices array, but the moment that index moves out of bounds with respect to the
    //base set, attention will be shifted to the next left index.

        test = tmpIndices[idx] + 1;

        if (test >= bLen)
        {
        //Here, we're about to move out of bounds with respect to the base set. We therefore need to scan back,
        //and update indices to the left of the current one. Find the leftmost index in the indices array that
        //isn't going to  move out of bounds with respect to the base set ...

            tmpIdx = idx - 1;
            incr = 1;

            inBounds = false;       //Assume at start that the index we're checking in the loop below is out of bounds
            checkBounds = true;

            while (checkBounds)
            {
                if (tmpIdx < 0)
                {
                    checkBounds = false;    //Exit immediately at this point
                }
                else
                {
                    newIndex = tmpIndices[tmpIdx] + 1;
                    test = newIndex + incr;

                    if (test >= bLen)
                    {
                    //Here, incrementing the current selected index will take that index out of bounds, so
                    //we move on to the next index to the left ...

                        tmpIdx--;
                        incr++;
                    }
                    else
                    {
                    //Here, the index will remain in bounds if we increment it, so we
                    //exit the loop and signal that we're in bounds ...

                        inBounds = true;
                        checkBounds = false;

                    //End if/else
                    }

                //End if 
                }               
            //End while
            }
    //At this point, if we'er still in bounds, then we continue generating subsets, but if not, we abort immediately.

            if (!inBounds)
                done = true;
            else
            {
            //Here, we're still in bounds. We need to update the indices accordingly. NOTE: at this point, although a
            //left positioned index in the indices array may still be in bounds, incrementing it to generate indices to
            //the right may take those indices out of bounds. We therefore need to check this as we perform the index
            //updating of the indices array.

                tmpIndices[tmpIdx] = newIndex;

                inBounds = true;
                checking = true;
                i = tmpIdx + 1;

                while (checking)
                {
                    test = tmpIndices[i - 1] + 1;   //Find out if incrementing the left adjacent index takes it out of bounds

                    if (test >= bLen)
                    {
                        inBounds = false;           //If we move out of bounds, exit NOW ...
                        checking = false;
                    }
                    else
                    {
                        tmpIndices[i] = test;       //Otherwise, update the indices array ...

                        i++;                        //Now move on to the next index to the right in the indices array ...

                        checking = (i < cnt);       //And continue until we've exhausted all the indices array elements ...
                    //End if/else
                    }
                //End while
                }
                //At this point, if the above updating of the indices array has moved any of its elements out of bounds,
                //we abort subset construction from this point ...
                if (!inBounds)
                    done = true;
            //End if/else
            }
        }
        else
        {
        //Here, the rightmost index under consideration isn't moving out of bounds with respect to the base set when
        //we increment it, so we simply increment and continue the loop ...
            tmpIndices[idx] = test;
        //End if
        }
    //End while
    }
    return(result);
//End function
}


function MakePowerSet(baseSet)
{
    var bLen = baseSet.length;
    var result = [];
    var i = 0;
    var partialSet = [];

    result.push([]);    //add the empty set to the power set

    for (i=1; i<bLen; i++)
    {
        partialSet = MakeCombinationSubsets(baseSet, i);
        result = result.concat(partialSet);
    //End i loop
    }
    //Now, finally, add the base set itself to the power set to make it complete ...

    partialSet = [];
    partialSet.push(baseSet);
    result = result.concat(partialSet);

    return(result);
    //End function
}

我用集合["a"， "b"， "c"， "d"， "e"， "f"]作为基本集进行了测试，并运行代码以产生以下幂集:

[]
["a"]
["b"]
["c"]
["d"]
["e"]
["f"]
["a","b"]
["a","c"]
["a","d"]
["a","e"]
["a","f"]
["b","c"]
["b","d"]
["b","e"]
["b","f"]
["c","d"]
["c","e"]
["c","f"]
["d","e"]
["d","f"]
["e","f"]
["a","b","c"]
["a","b","d"]
["a","b","e"]
["a","b","f"]
["a","c","d"]
["a","c","e"]
["a","c","f"]
["a","d","e"]
["a","d","f"]
["a","e","f"]
["b","c","d"]
["b","c","e"]
["b","c","f"]
["b","d","e"]
["b","d","f"]
["b","e","f"]
["c","d","e"]
["c","d","f"]
["c","e","f"]
["d","e","f"]
["a","b","c","d"]
["a","b","c","e"]
["a","b","c","f"]
["a","b","d","e"]
["a","b","d","f"]
["a","b","e","f"]
["a","c","d","e"]
["a","c","d","f"]
["a","c","e","f"]
["a","d","e","f"]
["b","c","d","e"]
["b","c","d","f"]
["b","c","e","f"]
["b","d","e","f"]
["c","d","e","f"]
["a","b","c","d","e"]
["a","b","c","d","f"]
["a","b","c","e","f"]
["a","b","d","e","f"]
["a","c","d","e","f"]
["b","c","d","e","f"]
["a","b","c","d","e","f"]

只要复制粘贴这两个函数“原样”，你就有了提取n元素集的不同k子集所需的基本知识，并生成该n元素集的幂集(如果你愿意的话)。

我并不是说这很优雅，只是说它在经过大量的测试(并在调试阶段将空气变为蓝色:)之后可以工作。

也许我错过了重点(你需要的是算法，而不是现成的解决方案)，但看起来scala已经开箱即用了(现在):

def combis(str:String, k:Int):Array[String] = {
  str.combinations(k).toArray 
}

使用这样的方法:

  println(combis("abcd",2).toList)

会产生:

  List(ab, ac, ad, bc, bd, cd)

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' ]
]

下面是c++中的迭代算法，它不使用STL，也不使用递归，也不使用条件嵌套循环。这样更快，它不执行任何元素交换，也不会给堆栈带来递归负担，还可以通过分别用mallloc()、free()和printf()替换new、delete和std::cout轻松地移植到ANSI C。

如果你想用不同或更长的字母显示元素，那么改变*字母参数以指向不同于"abcdefg"的字符串。

void OutputArrayChar(unsigned int* ka, size_t n, const char *alphabet) {
    for (int i = 0; i < n; i++)
        std::cout << alphabet[ka[i]] << ",";
    std::cout << endl;
}
    

void GenCombinations(const unsigned int N, const unsigned int K, const char *alphabet) {
    unsigned int *ka = new unsigned int [K];  //dynamically allocate an array of UINTs
    unsigned int ki = K-1;                    //Point ki to the last elemet of the array
    ka[ki] = N-1;                             //Prime the last elemet of the array.
    
    while (true) {
        unsigned int tmp = ka[ki];  //Optimization to prevent reading ka[ki] repeatedly

        while (ki)                  //Fill to the left with consecutive descending values (blue squares)
            ka[--ki] = --tmp;
        OutputArrayChar(ka, K, alphabet);
    
        while (--ka[ki] == ki) {    //Decrement and check if the resulting value equals the index (bright green squares)
            OutputArrayChar(ka, K, alphabet);
            if (++ki == K) {      //Exit condition (all of the values in the array are flush to the left)
                delete[] ka;
                return;
            }                   
        }
    }
}
    

int main(int argc, char *argv[])
{
    GenCombinations(7, 4, "abcdefg");
    return 0;
}

重要提示:字母参数*必须指向至少N个字符的字符串。你也可以传递一个在其他地方定义的字符串地址。

组合:从“7选4”中选择。