我需要计算两个字符串之间的相似度。那我具体是什么意思呢?让我举个例子:
- 正确单词:
hospital
- 错误单词:
haspita
现在我的目标是确定我需要修改多少个字符才能得到正确单词。在这个例子中,我需要修改2个字母。那么百分比是多少呢?我总是使用正确单词的长度作为分母。所以它变成了 2 / 8 = 25%,因此这两个给定的字符串 DSM 的相似度为 75%。
如何在性能成为关键考虑因素的情况下实现这一点呢?
我需要计算两个字符串之间的相似度。那我具体是什么意思呢?让我举个例子:
hospital
haspita
现在我的目标是确定我需要修改多少个字符才能得到正确单词。在这个例子中,我需要修改2个字母。那么百分比是多少呢?我总是使用正确单词的长度作为分母。所以它变成了 2 / 8 = 25%,因此这两个给定的字符串 DSM 的相似度为 75%。
如何在性能成为关键考虑因素的情况下实现这一点呢?
我几周前刚解决了这个问题。既然有人现在正在问,我将分享代码。在我的详尽测试中,即使没有提供最大距离,我的代码也比维基百科上的C#示例快约10倍。当提供最大距离时,这种性能增益增加到30倍-100倍以上。请注意一些关键点以提高性能:
ints
比 chars
更快。代码(如果在参数声明中将int []
替换为String
,则代码完全相同):
/// <summary>
/// Computes the Damerau-Levenshtein Distance between two strings, represented as arrays of
/// integers, where each integer represents the code point of a character in the source string.
/// Includes an optional threshhold which can be used to indicate the maximum allowable distance.
/// </summary>
/// <param name="source">An array of the code points of the first string</param>
/// <param name="target">An array of the code points of the second string</param>
/// <param name="threshold">Maximum allowable distance</param>
/// <returns>Int.MaxValue if threshhold exceeded; otherwise the Damerau-Leveshteim distance between the strings</returns>
public static int DamerauLevenshteinDistance(int[] source, int[] target, int threshold) {
int length1 = source.Length;
int length2 = target.Length;
// Return trivial case - difference in string lengths exceeds threshhold
if (Math.Abs(length1 - length2) > threshold) { return int.MaxValue; }
// Ensure arrays [i] / length1 use shorter length
if (length1 > length2) {
Swap(ref target, ref source);
Swap(ref length1, ref length2);
}
int maxi = length1;
int maxj = length2;
int[] dCurrent = new int[maxi + 1];
int[] dMinus1 = new int[maxi + 1];
int[] dMinus2 = new int[maxi + 1];
int[] dSwap;
for (int i = 0; i <= maxi; i++) { dCurrent[i] = i; }
int jm1 = 0, im1 = 0, im2 = -1;
for (int j = 1; j <= maxj; j++) {
// Rotate
dSwap = dMinus2;
dMinus2 = dMinus1;
dMinus1 = dCurrent;
dCurrent = dSwap;
// Initialize
int minDistance = int.MaxValue;
dCurrent[0] = j;
im1 = 0;
im2 = -1;
for (int i = 1; i <= maxi; i++) {
int cost = source[im1] == target[jm1] ? 0 : 1;
int del = dCurrent[im1] + 1;
int ins = dMinus1[i] + 1;
int sub = dMinus1[im1] + cost;
//Fastest execution for min value of 3 integers
int min = (del > ins) ? (ins > sub ? sub : ins) : (del > sub ? sub : del);
if (i > 1 && j > 1 && source[im2] == target[jm1] && source[im1] == target[j - 2])
min = Math.Min(min, dMinus2[im2] + cost);
dCurrent[i] = min;
if (min < minDistance) { minDistance = min; }
im1++;
im2++;
}
jm1++;
if (minDistance > threshold) { return int.MaxValue; }
}
int result = dCurrent[maxi];
return (result > threshold) ? int.MaxValue : result;
}
这里的Swap
是:
static void Swap<T>(ref T arg1,ref T arg2) {
T temp = arg1;
arg1 = arg2;
arg2 = temp;
}
int[]
是一场噩梦。http://i.imgur.com/mkW0aWw.png - hyankovprivate static int CalcLevenshteinDistance(string a, string b)
{
if (String.IsNullOrEmpty(a) && String.IsNullOrEmpty(b)) {
return 0;
}
if (String.IsNullOrEmpty(a)) {
return b.Length;
}
if (String.IsNullOrEmpty(b)) {
return a.Length;
}
int lengthA = a.Length;
int lengthB = b.Length;
var distances = new int[lengthA + 1, lengthB + 1];
for (int i = 0; i <= lengthA; distances[i, 0] = i++);
for (int j = 0; j <= lengthB; distances[0, j] = j++);
for (int i = 1; i <= lengthA; i++)
for (int j = 1; j <= lengthB; j++)
{
int cost = b[j - 1] == a[i - 1] ? 0 : 1;
distances[i, j] = Math.Min
(
Math.Min(distances[i - 1, j] + 1, distances[i, j - 1] + 1),
distances[i - 1, j - 1] + cost
);
}
return distances[lengthA, lengthB];
}
[m+1][2]
数组。然而,它只在您的字符串变得相当长时才开始起作用,比如说一百个字符左右。 - Sergey Kalinichenko有许多可以使用的字符串相似度距离算法,以下列出了一些(但不是详尽列表):
一个包含所有这些实现的库称为SimMetrics,它有 java 和 c# 实现。
我发现Levenshtein和Jaro Winkler非常适合处理字符串之间的小差异,例如:
然而,当比较文章标题时,文本的大部分内容相同,但是“噪声”在边缘上时,Smith-Waterman-Gotoh效果非常好:
比较这两个标题(它们来自不同来源,但是意思相同):
一种来自大肠杆菌的内切酶,可在紫外线照射的DNA中引入单个多核苷酸链断裂
内切酶III:一种来自大肠杆菌的内切酶,可在紫外线照射的DNA中引入单个多核苷酸链断裂
此网站提供字符串算法比较结果如下:
Jaro Winkler和Levenshtein在检测相似性方面不如Smith Waterman Gotoh。如果我们比较两个标题,它们不是同一篇文章,但有一些匹配的文本:
高等植物中的脂肪代谢。酰基辅酶A和酰基载体蛋白的代谢中酰基硫酯酶的功能。 高等植物中的脂肪代谢。在复杂的脂质混合物中确定酰基载体蛋白和酰基辅酶A。正如Anastasiosyal所指出的那样,这些算法的Java代码可以在SimMetrics中找到。我成功地使用了SimMetrics中的SmithWatermanGotoh Java代码。
public static List<Mistake> OptimalStringAlignmentDistance(
string word, string correctedWord,
bool transposition = true,
int substitutionCost = 1,
int insertionCost = 1,
int deletionCost = 1,
int transpositionCost = 1)
{
int w_length = word.Length;
int cw_length = correctedWord.Length;
var d = new KeyValuePair<int, CharMistakeType>[w_length + 1, cw_length + 1];
var result = new List<Mistake>(Math.Max(w_length, cw_length));
if (w_length == 0)
{
for (int i = 0; i < cw_length; i++)
result.Add(new Mistake(i, CharMistakeType.Insertion));
return result;
}
for (int i = 0; i <= w_length; i++)
d[i, 0] = new KeyValuePair<int, CharMistakeType>(i, CharMistakeType.None);
for (int j = 0; j <= cw_length; j++)
d[0, j] = new KeyValuePair<int, CharMistakeType>(j, CharMistakeType.None);
for (int i = 1; i <= w_length; i++)
{
for (int j = 1; j <= cw_length; j++)
{
bool equal = correctedWord[j - 1] == word[i - 1];
int delCost = d[i - 1, j].Key + deletionCost;
int insCost = d[i, j - 1].Key + insertionCost;
int subCost = d[i - 1, j - 1].Key;
if (!equal)
subCost += substitutionCost;
int transCost = int.MaxValue;
if (transposition && i > 1 && j > 1 && word[i - 1] == correctedWord[j - 2] && word[i - 2] == correctedWord[j - 1])
{
transCost = d[i - 2, j - 2].Key;
if (!equal)
transCost += transpositionCost;
}
int min = delCost;
CharMistakeType mistakeType = CharMistakeType.Deletion;
if (insCost < min)
{
min = insCost;
mistakeType = CharMistakeType.Insertion;
}
if (subCost < min)
{
min = subCost;
mistakeType = equal ? CharMistakeType.None : CharMistakeType.Substitution;
}
if (transCost < min)
{
min = transCost;
mistakeType = CharMistakeType.Transposition;
}
d[i, j] = new KeyValuePair<int, CharMistakeType>(min, mistakeType);
}
}
int w_ind = w_length;
int cw_ind = cw_length;
while (w_ind >= 0 && cw_ind >= 0)
{
switch (d[w_ind, cw_ind].Value)
{
case CharMistakeType.None:
w_ind--;
cw_ind--;
break;
case CharMistakeType.Substitution:
result.Add(new Mistake(cw_ind - 1, CharMistakeType.Substitution));
w_ind--;
cw_ind--;
break;
case CharMistakeType.Deletion:
result.Add(new Mistake(cw_ind, CharMistakeType.Deletion));
w_ind--;
break;
case CharMistakeType.Insertion:
result.Add(new Mistake(cw_ind - 1, CharMistakeType.Insertion));
cw_ind--;
break;
case CharMistakeType.Transposition:
result.Add(new Mistake(cw_ind - 2, CharMistakeType.Transposition));
w_ind -= 2;
cw_ind -= 2;
break;
}
}
if (d[w_length, cw_length].Key > result.Count)
{
int delMistakesCount = d[w_length, cw_length].Key - result.Count;
for (int i = 0; i < delMistakesCount; i++)
result.Add(new Mistake(0, CharMistakeType.Deletion));
}
result.Reverse();
return result;
}
public struct Mistake
{
public int Position;
public CharMistakeType Type;
public Mistake(int position, CharMistakeType type)
{
Position = position;
Type = type;
}
public override string ToString()
{
return Position + ", " + Type;
}
}
public enum CharMistakeType
{
None,
Substitution,
Insertion,
Deletion,
Transposition
}
Public Shared Function LevenshteinDistance(ByVal v1 As String, ByVal v2 As String) As Integer
Dim cost(v1.Length, v2.Length) As Integer
If v1.Length = 0 Then
Return v2.Length 'if string 1 is empty, the number of edits will be the insertion of all characters in string 2
ElseIf v2.Length = 0 Then
Return v1.Length 'if string 2 is empty, the number of edits will be the insertion of all characters in string 1
Else
'setup the base costs for inserting the correct characters
For v1Count As Integer = 0 To v1.Length
cost(v1Count, 0) = v1Count
Next v1Count
For v2Count As Integer = 0 To v2.Length
cost(0, v2Count) = v2Count
Next v2Count
'now work out the cheapest route to having the correct characters
For v1Count As Integer = 1 To v1.Length
For v2Count As Integer = 1 To v2.Length
'the first min term is the cost of editing the character in place (which will be the cost-to-date or the cost-to-date + 1 (depending on whether a change is required)
'the second min term is the cost of inserting the correct character into string 1 (cost-to-date + 1),
'the third min term is the cost of inserting the correct character into string 2 (cost-to-date + 1) and
cost(v1Count, v2Count) = Math.Min(
cost(v1Count - 1, v2Count - 1) + If(v1.Chars(v1Count - 1) = v2.Chars(v2Count - 1), 0, 1),
Math.Min(
cost(v1Count - 1, v2Count) + 1,
cost(v1Count, v2Count - 1) + 1
)
)
Next v2Count
Next v1Count
'the final result is the cheapest cost to get the two strings to match, which is the bottom right cell in the matrix
'in the event of strings being equal, this will be the result of zipping diagonally down the matrix (which will be square as the strings are the same length)
Return cost(v1.Length, v2.Length)
End If
End Function