我在excel中使用以下vb代码来计算A列和B列之间的程度相似性。它运行得很好。
我的下一步是定义首字母缩写词，以便计算出的相似度不会受到影响。 IE：如果我在A栏，“ABC LLC”和B栏“ABC有限责任公司”中，当前的vb代码将返回两列不太相似。但是，我希望他们通过定义“LLC”和“有限责任公司”实际上是相同的东西，100％相似。我能做什么以及在哪里可以将其放入代码中来实现这一目标？谢谢！
免责声明 - 是的我知道有加载项可以做到这一点。但是，我的数据集太大而无法使用它们。
Public Function Similarity(ByVal String1 As String, _
ByVal String2 As String, _
Optional ByRef RetMatch As String, _
Optional min_match = 1) As Single
'Returns percentile of similarity between 2 strings (ignores case)
'"RetMatch" returns the characters that match(in order)
'"min_match" specifies minimum number af char's in a row to match
Dim b1() As Byte, b2() As Byte
Dim lngLen1 As Long, lngLen2 As Long
Dim lngResult As Long
If UCase(String1) = UCase(String2) Then '..Exactly the same
Similarity = 1
Else '..one string is empty
lngLen1 = Len(String1)
lngLen2 = Len(String2)
If (lngLen1 = 0) Or (lngLen2 = 0) Then
Similarity = 0
Else '..otherwise find similarity
b1() = StrConv(UCase(String1), vbFromUnicode)
b2() = StrConv(UCase(String2), vbFromUnicode)
lngResult = Similarity_sub(0, lngLen1 - 1, _
0, lngLen2 - 1, _
b1, b2, _
String1, _
RetMatch, _
min_match)
Erase b1
Erase b2
If lngLen1 >= lngLen2 Then
Similarity = lngResult / lngLen1
Else
Similarity = lngResult / lngLen2
End If
End If
End If
End Function
Private Function Similarity_sub(ByVal start1 As Long, ByVal end1 As Long, _
ByVal start2 As Long, ByVal end2 As Long, _
ByRef b1() As Byte, ByRef b2() As Byte, _
ByVal FirstString As String, _
ByRef RetMatch As String, _
ByVal min_match As Long, _
Optional recur_level As Integer = 0) As Long
'* CALLED BY: Similarity * (RECURSIVE)
Dim lngCurr1 As Long, lngCurr2 As Long
Dim lngMatchAt1 As Long, lngMatchAt2 As Long
Dim i As Long
Dim lngLongestMatch As Long, lngLocalLongestMatch As Long
Dim strRetMatch1 As String, strRetMatch2 As String
If (start1 > end1) Or (start1 < 0) Or (end1 - start1 + 1 < min_match) _
Or (start2 > end2) Or (start2 < 0) Or (end2 - start2 + 1 < min_match) Then
Exit Function '(exit if start/end is out of string, or length is too short)
End If
For lngCurr1 = start1 To end1 '(for each char of first string)
For lngCurr2 = start2 To end2 '(for each char of second string)
i = 0
Do Until b1(lngCurr1 + i) <> b2(lngCurr2 + i) 'as long as chars DO match..
i = i + 1
If i > lngLongestMatch Then '..if longer than previous best, store starts & length
lngMatchAt1 = lngCurr1
lngMatchAt2 = lngCurr2
lngLongestMatch = i
End If
If (lngCurr1 + i) > end1 Or (lngCurr2 + i) > end2 Then Exit Do
Loop
Next lngCurr2
Next lngCurr1
If lngLongestMatch < min_match Then Exit Function 'no matches at all, so no point checking for sub-matches!
lngLocalLongestMatch = lngLongestMatch 'call again for BEFORE + AFTER
RetMatch = ""
'Find longest match BEFORE the current position
lngLongestMatch = lngLongestMatch _
+ Similarity_sub(start1, lngMatchAt1 - 1, _
start2, lngMatchAt2 - 1, _
b1, b2, _
FirstString, _
strRetMatch1, _
min_match, _
recur_level + 1)
If strRetMatch1 <> "" Then
RetMatch = RetMatch & strRetMatch1 & "*"
Else
RetMatch = RetMatch & IIf(recur_level = 0 _
And lngLocalLongestMatch > 0 _
And (lngMatchAt1 > 1 Or lngMatchAt2 > 1) _
, "*", "")
End If
'add local longest
RetMatch = RetMatch & Mid$(FirstString, lngMatchAt1 + 1, lngLocalLongestMatch)
'Find longest match AFTER the current position
lngLongestMatch = lngLongestMatch _
+ Similarity_sub(lngMatchAt1 + lngLocalLongestMatch, end1, _
lngMatchAt2 + lngLocalLongestMatch, end2, _
b1, b2, _
FirstString, _
strRetMatch2, _
min_match, _
recur_level + 1)
If strRetMatch2 <> "" Then
RetMatch = RetMatch & "*" & strRetMatch2
Else
RetMatch = RetMatch & IIf(recur_level = 0 _
And lngLocalLongestMatch > 0 _
And ((lngMatchAt1 + lngLocalLongestMatch < end1) _
Or (lngMatchAt2 + lngLocalLongestMatch < end2)) _
, "*", "")
End If
'Return result
Similarity_sub = lngLongestMatch
End Function
答案 0 :(得分：4)
如果没有太多参与您的解决方案，这是您自己的责任，我可以建议一些方法来合并缩写。然而。 请请注意，此方法无法保证100％成功，但您已处于模糊世界。
假设我们有Dictionary其中：
在比较两个字符串之前，我们通过用缩写替换每个出现的长短语来最小化两个字符串。然后我们可以将它们与方法Similarity的其余部分（或任何其他方法）进行比较。
' Fills an abbreviation dictionary
Sub InitializeDict(ByRef abbrev As Scripting.Dictionary)
abbrev("limited liability company") = "LLC"
abbrev("United Kingdom") = "U.K."
'... Add all abbreviations into dict
' Instead of harcoding, you can better load the key/value
' pairs from a dedicated worksheet...
End Sub
' Minimizes s by putting abbreviations
Sub Abbreviate(ByRef s As String)
Static abbrev As Scripting.Dictionary ' <-- static, inititlized only once
If abbrev Is Nothing Then
Set abbrev = CreateObject("Scripting.Dictionary")
abbrev.CompareMode = vbTextCompare
InitializeDict abbrev
End If
Dim phrase
For Each phrase In abbrev.Keys
s = Replace(s, phrase, abbrev(phrase), vbTextCompare)
Next
End Sub
' A small amendment to this function: abbreviate strings before comparing
Public Function Similarity(ByVal String1 As String, _
ByVal String2 As String, _
Optional ByRef RetMatch As String, _
Optional min_match = 1) As Single
Abbreviate String1
Abbreviate String2
' ... Rest of the routine
End Function
答案 1 :(得分：0)
检查字符串是否Like可能更容易。例如
If "ABC limited liability company" Like "ABC L*L*C*" Then
为True，因为*匹配任何0个或更多字符。
Option Compare Text ' makes string comparisons case insensitive
Function areLike(str1 As String, str2 As String) As Single
If str1 = str2 Then areLike = 1: Exit Function
Dim pattern As String, temp As String
If LenB(str1) < LenB(str2) Then
pattern = str1
temp = str2
Else
pattern = str2
temp = str1
End If
pattern = StrConv(pattern, vbUnicode) ' "ABC LLC" to "A␀B␀C␀ ␀L␀L␀C␀"
pattern = Replace(pattern, vbNullChar, "*") ' "A*B*C* *L*L*C*"
pattern = Replace(pattern, " *", " ") ' "A*B*C* L*L*C*"
If temp Like pattern Then areLike = 1: Exit Function
' else areLike = some other similarity function
End Function