frecuencia de palabras
Publicado por salazar (1 intervención) el 21/05/2007 20:10:44
hay alguna manera de tomar un documento de word y buscar con que frecuencia se repite una palabra??
Gracias
Gracias
Valora esta pregunta
0
Sub WordFrequency()
Dim SingleWord As String 'Raw word pulled from doc
Const maxwords = 9000 'Maximum unique words allowed
Dim Words(maxwords) As String 'Array to hold unique words
Dim Freq(maxwords) As Integer 'Frequency counter for unique words
Dim WordNum As Integer 'Number of unique words
Dim ByFreq As Boolean 'Flag for sorting order
Dim ttlwds As Long 'Total words in the document
Dim Excludes As String 'Words to be excluded
Dim Found As Boolean 'Temporary flag
Dim j As Integer 'Temporary variables
Dim k As Integer '
Dim l As Integer '
Dim Temp As Integer '
Dim tword As String '
' Set up excluded words
Excludes = "[the][a][of][is][to][for][this][that][by][be][and][are]"
' Find out how to sort
ByFreq = True
ans = InputBox$("Sort by WORD or by FREQ?", "Sort order", "WORD")
If ans = "" Then End
If UCase(ans) = "WORD" Then
ByFreq = False
End If
Selection.HomeKey Unit:=wdStory
System.Cursor = wdCursorWait
WordNum = 0
ttlwds = ActiveDocument.Words.Count
' Control the repeat
For Each aword In ActiveDocument.Words
SingleWord = Trim(LCase(aword))
If SingleWord < "a" Or SingleWord > "z" Then SingleWord = "" 'Out of range?
If InStr(Excludes, "[" & SingleWord & "]") Then SingleWord = "" 'On exclude list?
If Len(SingleWord) > 0 Then
Found = False
For j = 1 To WordNum
If Words(j) = SingleWord Then
Freq(j) = Freq(j) + 1
Found = True
Exit For
End If
Next j
If Not Found Then
WordNum = WordNum + 1
Words(WordNum) = SingleWord
Freq(WordNum) = 1
End If
If WordNum > maxwords - 1 Then
j = MsgBox("The maximum array size has been exceeded. _Increase maxwords.", vbOKOnly)
Exit For
End If
End If
ttlwds = ttlwds - 1
StatusBar = "Remaining: " & ttlwds & " Unique: " & WordNum
Next aword
' Now sort it into word order
For j = 1 To WordNum - 1
k = j
For l = j + 1 To WordNum
If (Not ByFreq And Words(l) < Words(k)) Or (ByFreq And Freq(l) > Freq(k)) Then k = l
Next l
If k <> j Then
tword = Words(j)
Words(j) = Words(k)
Words(k) = tword
Temp = Freq(j)
Freq(j) = Freq(k)
Freq(k) = Temp
End If
StatusBar = "Sorting: " & WordNum - j
Next j
' Now write out the results
tmpName = ActiveDocument.AttachedTemplate.FullName
Documents.Add Template:=tmpName, NewTemplate:=False
Selection.ParagraphFormat.TabStops.ClearAll
With Selection
For j = 1 To WordNum
.TypeText Text:=Trim(Str(Freq(j))) & vbTab & Words(j) & vbCrLf
Next j
End With
System.Cursor = wdCursorNormal
j = MsgBox("There were " & Trim(Str(WordNum)) & _
" different words ", vbOKOnly, "Finished")
End Sub