さて、これが取引の人々です。私は持っていtwo text filesます。それぞれに500行（文）が含まれています。
memoryそれらを独自の配列にロードしました（データ型：文字列）。に名前を付けましょうarray A & B。
次に in を取得しfirst sentence、単語を取得するために区切り文字として使用しarray Aて別のファイルに分割します。array CSPACE
次に、 の各文を区切り文字として使用しarray Bて分割し、単語を取得して、 の各単語と各単語を比較し、2 つの文の一致率を計算します。array DSPACEarray Carray D
array Aのすべての文に対するの最初の文の平均一致率を計算しarray Bます。
Array E次に、すべての文array Aとその平均一致率を含むに保存します。
first sentence配列 A のすべてのタイトルに対して上記と同じことを行います。
問題は、配列 A のすべてのタイトルを処理するのに約 15 秒かかることです。とにかく、この時間を最適化して高速化することはできますか?
ハードウェア: AMD Phenom I 32 ビット クアッド コア
コード：
Imports System.IO
Imports System.Object
Imports System.Xml
Imports System.Text.RegularExpressions
Module Module1
Sub Main()
'Important File Paths
Dim titlesFilePath As String = Environment.CurrentDirectory & "\titles.txt"
Dim xmlTitlesFilePath As String = Environment.CurrentDirectory & "\extractedTitles.txt"
Dim stopWordsFilePath As String = Environment.CurrentDirectory & "\stopWords.txt"
'Import Important Data From Files -> Memory
Dim titles As Array = FileToArray(titlesFilePath)
Dim stopWords As Array = FileToArray(stopWordsFilePath)
Dim xmlDataUnprocessed As Array = FileToArray(xmlTitlesFilePath)
'Delimters To Filter Titles For
Dim userDefinedDelimeters(4, 1)
userDefinedDelimeters(0, 0) = "-"
userDefinedDelimeters(0, 1) = " "
userDefinedDelimeters(1, 0) = ","
userDefinedDelimeters(1, 1) = " "
userDefinedDelimeters(2, 0) = "—"
userDefinedDelimeters(2, 1) = " "
userDefinedDelimeters(3, 0) = "'s"
userDefinedDelimeters(3, 1) = ""
userDefinedDelimeters(4, 0) = "'"
userDefinedDelimeters(4, 1) = " "
'Declare Important Variables
Dim xmlData(xmlDataUnprocessed.Length / 2, 1)
Dim xmlTurn = 0
Dim xmlDataCount = 0
'Create Feed Title/URL Array
For i = 0 To (xmlDataUnprocessed.Length - 1)
If xmlTurn = 0 Then
xmlData(xmlDataCount, 0) = xmlDataUnprocessed(i)
xmlTurn = 1
Else
xmlData(xmlDataCount, 1) = xmlDataUnprocessed(i)
xmlTurn = 0
xmlDataCount += 1
End If
Next
'CPU-Intensive Stuff Occurs
Dim xmlTitle As String
Dim xmlTitleWords As Array
Dim savedTitleWords As Array
Dim titleResults(xmlData.GetUpperBound(0) - 1, 1)
Dim titlePercentageMatch As Integer
Dim numberOfTitlesMatched As Integer
For i = 0 To xmlData.GetUpperBound(0) - 1
Console.WriteLine("Working On Title No. " & i & " Out Of " & xmlData.GetUpperBound(0) - 1)
titlePercentageMatch = 0
numberOfTitlesMatched = 0
xmlTitle = xmlData(i, 0)
xmlTitle = processTitle(stopWords, userDefinedDelimeters, xmlTitle)
xmlTitleWords = xmlTitle.Split(" ")
For Each title In titles
title = processTitle(stopWords, userDefinedDelimeters, title)
savedTitleWords = title.split(" ")
Dim compareResult = compareTitle(xmlTitleWords, savedTitleWords)
If compareResult > 0 Then
titlePercentageMatch += compareResult
numberOfTitlesMatched += 1
End If
Next
titleResults(i, 0) = xmlData(i, 0)
titleResults(i, 1) = (titlePercentageMatch / numberOfTitlesMatched)
Next
For i = 0 To titleResults.GetUpperBound(0) - 1
Console.WriteLine(titleResults(i, 0) & " ---> " & titleResults(i, 1) & vbCrLf)
Next
Console.Read()
End Sub
Function compareTitle(ByRef xmlTitleWords As Array, ByRef savedTitleWords As Array)
Dim NumberOfMatches = 0
For Each xmlWord In xmlTitleWords
For Each savedWord In savedTitleWords
If (xmlWord.ToString.ToLower = savedWord.ToString.ToLower) Then
NumberOfMatches += 1
End If
Next
Next
Return ((NumberOfMatches / xmlTitleWords.Length) * 100)
End Function
Function processTitle(ByRef stopWordArray As Array, ByRef delimArray As Array, ByVal title As String)
title = removeStopWords(stopWordArray, title)
title = removeDelims(delimArray, title)
Return title
End Function
Function removeStopWords(ByRef stopWordsArray As Array, ByVal sentence As String)
For i = 0 To stopWordsArray.Length - 1
If sentence.ToLower.Contains(" " & stopWordsArray(i).ToString.ToLower & " ") = True Then
sentence = Microsoft.VisualBasic.Strings.Replace(sentence, " " & stopWordsArray(i) & " ", " ", 1, -1, Constants.vbTextCompare)
'ElseIf sentence.ToLower.Contains(stopWordsArray(i).ToString.ToLower & " ") = True Then
'sentence = Microsoft.VisualBasic.Strings.Replace(sentence, stopWordsArray(i) & " ", "", 1, -1, Constants.vbTextCompare)
End If
sentence = Regex.Replace(sentence, "\s+", " ")
Dim Words = sentence.ToLower.Split(" ")
If Words(0).ToString.ToLower & " " = stopWordsArray(i).ToString.ToLower & " " Then
sentence = sentence.Remove(0, stopWordsArray(i).ToString.ToLower.Length + 1)
End If
Words = sentence.ToLower.Split(" ")
Dim LastWord = Words(Words.Length - 1)
'Console.WriteLine(LastWord & "++")
If " " & LastWord.ToString.ToLower = " " & stopWordsArray(i).ToString.ToLower Then
sentence = sentence.Remove(sentence.Length - 1 - LastWord.Length, stopWordsArray(i).ToString.ToLower.Length + 1)
End If
Next
sentence = Regex.Replace(sentence, "\s+", " ")
Return sentence
End Function
Function removeDelims(ByRef delimArray As Array, ByVal sentence As String)
For i = 0 To delimArray.GetUpperBound(0) - 1
sentence = sentence.Replace(delimArray(i, 0), delimArray(i, 1))
Next
sentence = Regex.Replace(sentence, "\s+", " ")
Return sentence
End Function
Function FileToArray(ByVal filePath As String) As String()
Dim content As String
Dim lines As New ArrayList
Dim sr As System.IO.StreamReader
' read the file's lines into an ArrayList
Try
sr = New System.IO.StreamReader(filePath)
Do While sr.Peek() >= 0
lines.Add(sr.ReadLine())
Loop
Finally
If Not sr Is Nothing Then sr.Close()
End Try
' convert from ArrayList to a String array
Return CType(lines.ToArray(GetType(String)), String())
End Function
End Module
編集：あまり混乱しないことを願っています。ごめんなさい！ 編集2：提供されたソース：P