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

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。

其他回答

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   

用c#的另一个解决方案:

 static List<List<T>> GetCombinations<T>(List<T> originalItems, int combinationLength)
    {
        if (combinationLength < 1)
        {
            return null;
        }

        return CreateCombinations<T>(new List<T>(), 0, combinationLength, originalItems);
    }

 static List<List<T>> CreateCombinations<T>(List<T> initialCombination, int startIndex, int length, List<T> originalItems)
    {
        List<List<T>> combinations = new List<List<T>>();
        for (int i = startIndex; i < originalItems.Count - length + 1; i++)
        {
            List<T> newCombination = new List<T>(initialCombination);
            newCombination.Add(originalItems[i]);
            if (length > 1)
            {
                List<List<T>> newCombinations = CreateCombinations(newCombination, i + 1, length - 1, originalItems);
                combinations.AddRange(newCombinations);
            }
            else
            {
                combinations.Add(newCombination);
            }
        }

        return combinations;
    }

用法示例:

   List<char> initialArray = new List<char>() { 'a','b','c','d'};
   int combinationLength = 3;
   List<List<char>> combinations = GetCombinations(initialArray, combinationLength);

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' ]
]

Haskell中的简单递归算法

import Data.List

combinations 0 lst = [[]]
combinations n lst = do
    (x:xs) <- tails lst
    rest   <- combinations (n-1) xs
    return $ x : rest

我们首先定义特殊情况,即选择零元素。它产生一个单一的结果,这是一个空列表(即一个包含空列表的列表)。

对于n> 0, x遍历列表中的每一个元素xs是x之后的每一个元素。

Rest通过对组合的递归调用从xs中选取n - 1个元素。该函数的最终结果是一个列表,其中每个元素都是x: rest(即对于x和rest的每个不同值,x为头部,rest为尾部的列表)。

> combinations 3 "abcde"
["abc","abd","abe","acd","ace","ade","bcd","bce","bde","cde"]

当然,由于Haskell是懒惰的,列表是根据需要逐渐生成的,因此您可以部分计算指数级的大组合。

> let c = combinations 8 "abcdefghijklmnopqrstuvwxyz"
> take 10 c
["abcdefgh","abcdefgi","abcdefgj","abcdefgk","abcdefgl","abcdefgm","abcdefgn",
 "abcdefgo","abcdefgp","abcdefgq"]

下面是一个coffeescript实现

combinations: (list, n) ->
        permuations = Math.pow(2, list.length) - 1
        out = []
        combinations = []

        while permuations
            out = []

            for i in [0..list.length]
                y = ( 1 << i )
                if( y & permuations and (y isnt permuations))
                    out.push(list[i])

            if out.length <= n and out.length > 0
                combinations.push(out)

            permuations--

        return combinations