Understand the cardinality sort

Cardinality sorting is a non-comparative integer sorting algorithm. Its principle is to cut integers into different numbers according to the digits, and then compare them according to each digit. Since integers can also express strings (such as names or dates) and floating-point numbers in specific formats, radix sorting is not limited to integers.

1. Cardinality sort vs. Count sort vs. Bucket sort

There are two methods for radix sorting:

These three sorting algorithms all use the concept of buckets, but there are obvious differences in the use of buckets:

  1. Cardinality sorting: allocate buckets according to each digit of the key value;
  2. Counting sorting: each bucket only stores a single key value;
  3. Bucket sorting: each bucket stores a certain range of values;

2. LSD cardinality sorting animation demo

Code:

JavaScript

Instance

//LSD Radix Sort
var counter = [];
function radixSort(arr, maxDigit) {
    var mod = 10;
    var dev = 1;
    for (var i = 0; i < maxDigit; i++, dev *= 10, mod *= 10) {
        for(var j = 0; j < arr.length; j++) {
            var bucket = parseInt ((arr [j]% mod) / dev);
            if(counter[bucket]==null) {
                counter[bucket] = [];
            }
            counter[bucket].push(arr[j]);
        }
        var pos = 0;
        for(var j = 0; j < counter.length; j++) {
            var value = null;
            if(counter[j]!=null) {
                while ((value = counter[j].shift()) != null) {
                      arr[pos++] = value;
                }
          }
        }
    }
    return arr;
}

Java

Instance

/**
 * Cardinality sort
 * You can also refer to the case of considering negative numbers: https://code.i-harness.com/zh-CN/q/e98fa9
 */
public class RadixSort implements IArraySort {

    @Override
    public int[] sort(int[] sourceArray) throws Exception {
        // Copy arr without changing the parameter content
        int[] arr = Arrays.copyOf(sourceArray, sourceArray.length);

        int maxDigit = getMaxDigit(arr);
        return radixSort(arr, maxDigit);
    }

    /**
     * Get the highest number of digits
     */
    private int getMaxDigit(int[] arr) {
        int maxValue = getMaxValue(arr);
        return getNumLenght(maxValue);
    }

    private int getMaxValue(int[] arr) {
        int maxValue = arr[0];
        for (int value : arr) {
            if (maxValue < value) {
                maxValue = value;
            }
        }
        return maxValue;
    }

    protected int getNumLenght(long num) {
        if (num == 0) {
            return 1;
        }
        int lenght = 0;
        for (long temp = num; temp != 0; temp /= 10) {
            lenght++;
        }
        return lenght;
    }

    private int[] radixSort(int[] arr, int maxDigit) {
        int mod = 10;
        int dev = 1;

        for (int i = 0; i < maxDigit; i++, dev *= 10, mod *= 10) {
            // Consider the case of negative numbers, here double the number of queues, where [0-9] corresponds to negative numbers, and [10-19] corresponds to positive numbers (bucket + 10)
            int[][] counter = new int[mod * 2][0];

            for (int j = 0; j < arr.length; j++) {
                int bucket = ((arr[j] % mod) / dev) + mod;
                counter[bucket] = arrayAppend(counter[bucket], arr[j]);
            }

            int pos = 0;
            for (int[] bucket : counter) {
                for (int value : bucket) {
                    arr[pos++] = value;
                }
            }
        }

        return arr;
    }

    /**
     * Automatically expand capacity and save data
     *
     * @param arr
     * @param value
     */
    private int[] arrayAppend(int[] arr, int value) {
        arr = Arrays.copyOf(arr, arr.length + 1);
        arr[arr.length - 1] = value;
        return arr;
    }
}

PHP

Instance

function radixSort($arr, $maxDigit = null)
{
    if ($maxDigit === null) {
        $maxDigit = max($arr);
    }
    $counter = [];
    for ($i = 0; $i < $maxDigit; $i++) {
        for ($j = 0; $j < count($arr); $j++) {
            preg_match_all('/\d/', (string) $arr[$j], $matches);
            $numArr = $matches[0];
            $lenTmp = count($numArr);
            $bucket = array_key_exists($lenTmp - $i - 1, $numArr)
                ? intval ($ numArr [$ lenTmp - $ i - 1])
                : 0;
            if (!array_key_exists($bucket, $counter)) {
                $counter[$bucket] = [];
            }
            $counter[$bucket][] = $arr[$j];
        }
        $pos = 0;
        for ($j = 0; $j < count($counter); $j++) {
            $value = null;
            if ($counter[$j] !== null) {
                while (($value = array_shift($counter[$j])) !== null) {
                    $arr[$pos++] = $value;
                }
          }
        }
    }

    return $arr;
}

C++

Instance

int maxbit(int data[], int n) //Auxiliary function, find the maximum number of bits of data
{
    int maxData = data[0]; ///< maximum number
    /// First find the maximum number, and then find the number of digits, so that the number of digits is judged by each number in turn, which is slightly optimized.
    for (int i = 1; i < n; ++i)
    {
        if (maxData < data[i])
            maxData = data[i];
    }
    int d = 1;
    int p = 10;
    while (maxData >= p)
    {
        //p *= 10; // Maybe overflow
        maxData /= 10;
        ++d;
    }
    return d;
/* int d = 1; //Save the largest number of digits
    int p = 10;
    for(int i = 0; i < n; ++i)
    {
        while(data[i] >= p)
        {
            p *= 10;
            ++d;
        }
    }
    return d;*/
}
void radixsort(int data[], int n) //Radix sort
{
    int d = maxbit(data, n);
    int *tmp = new int[n];
    int *count = new int[10]; //Counter
    int i, j, k;
    int radix = 1;
    for(i = 1; i <= d; i++) //Sort d times
    {
        for(j = 0; j < 10; j++)
            count[j] = 0; //Clear the counter before each allocation
        for(j = 0; j < n; j++)
        {
            k = (data[j] / radix)% 10; //Count the number of records in each bucket
            count[k]++;
        }
        for(j = 1; j < 10; j++)
            count[j] = count[j-1] + count[j]; //Allocate the position in tmp to each bucket in turn
        for(j = n-1; j >= 0; j--) // Collect all the records in the bucket into tmp in turn
        {
            k = (data[j] / radix) % 10;
            tmp[count[k] - 1] = data[j];
            count[k]--;
        }
        for(j = 0; j <n; j++) //Copy the contents of the temporary array to data
            data[j] = tmp[j];
        radix = radix * 10;
    }
    delete []tmp;
    delete []count;
}

C

Instance

#include
#define MAX 20
//#define SHOWPASS
#define BASE 10

void print(int *a, int n) {
  int i;
  for (i = 0; i < n; i++) {
    printf("%d\t", a[i]);
  }
}

void radixsort(int *a, int n) {
  int i, b[MAX], m = a[0], exp = 1;

  for (i = 1; i < n; i++) {
    if (a[i] > m) {
      m = a[i];
    }
  }

  while (m / exp > 0) {
    int bucket[BASE] = { 0 };

    for (i = 0; i < n; i++) {
      bucket[(a[i] / exp) % BASE]++;
    }

    for (i = 1; i < BASE; i++) {
      bucket[i] += bucket[i - 1];
    }

    for (i = n - 1; i >= 0; i--) {
      b[--bucket[(a[i] / exp) % BASE]] = a[i];
    }

    for (i = 0; i < n; i++) {
      a[i] = b[i];
    }

    exp *= BASE;

#ifdef SHOWPASS
    printf("\nPASS   : ");
    print(a, n);
#endif
  }
}

int main () {
  int arr[MAX];
  int i, n;

  printf("Enter total elements (n <= %d) : ", MAX);
  scanf("%d", &n);
  n = n < MAX ? n : MAX;

  printf("Enter %d Elements : ", n);
  for (i = 0; i < n; i++) {
    scanf("%d", &arr[i]);
  }

  printf("\nARRAY  : ");
  print(&arr[0], n);

  radixsort(&arr[0], n);

  printf("\nSORTED : ");
  print(&arr[0], n);
  printf("\n");

  return 0;
}

take

Instance

- Get the median of the table
local maxBit = function (tt)
    local weight = 10; - decimal
    local bit = 1;
   
    for k, v in pairs(tt) do
        while v >= weight do
            weight = weight * 10;
            bit = bit + 1;  
        end
    end
    return bit;
end
- Cardinality sort
local radixSort = function (tt)
    local maxbit = maxBit(tt);

    local bucket = {};
    local temp = {};
    local radix = 1;
    for i = 1, maxbit do
        for j = 1, 10 do
            bucket[j] = 0; --- Empty the bucket
        end
        for k, v in pairs(tt) do
            local remainder = math.floor((v / radix)) % 10 + 1;    
            bucket[remainder] = bucket[remainder] + 1; - the number of each bucket is automatically increased by 1
        end
       
        for j = 2, 10 do
            bucket[j] = bucket[j-1] + bucket[j]; - the number of each bucket = the previous number of buckets and + own number
        end
        - Sort according to the position of the bucket--This is a bucket sort, and you must use the reverse order, because the sorting method is from small to large, and the order is down, the larger ones will be cleared on top of the smaller ones.
        for k = #tt, 1, -1 do
            local remainder = math.floor((tt[k] / radix)) % 10 + 1;
            temp[bucket[remainder]] = tt[k];
            bucket[remainder] = bucket[remainder] - 1;
        end
        for k, v in pairs(temp) do
            tt [k] = v;
        end
        radix = radix * 10;
    end
end;

Guess you like

Origin blog.csdn.net/yaxuan88521/article/details/114114672