public static int[][] GetWordIndexStemmedDocs(string[] docs, List <string> vocabulary)
{
List <int>[] wordIndex = Util.ArrayInit(docs.Length, d => new List <int>());
int docIndex = 0;
foreach (var doc in docs)
{
if (doc != null)
{
string[] parts2 = Tokenize(doc.ToLower());
List <int> wordIndexDoc = new List <int>();
foreach (string part in parts2)
{
// Strip non-alphanumeric characters.
string stripped = Regex.Replace(part, "[^a-zA-Z0-9]", "");
try
{
var english = new EnglishWord(stripped);
string stem = english.Stem;
if (vocabulary.Contains(stem))
{
wordIndexDoc.Add(vocabulary.IndexOf(stem));
}
}
catch
{
// ignored
}
}
wordIndex[docIndex] = wordIndexDoc.Distinct().ToList();
docIndex++;
}
}
return(wordIndex.Select(list => list.Select(index => index).ToArray()).ToArray());
}
/// <summary>
/// Parses and tokenizes a list of documents, returning a vocabulary of words.
/// </summary>
/// <param name="docs">string[]</param>
/// <param name="stemmedDocs">List of List of string</param>
/// <param name="vocabularyThreshold"></param>
/// <returns>Vocabulary (list of strings)</returns>
private static List <string> GetVocabulary(string[] docs, out List <List <string> > stemmedDocs, int vocabularyThreshold)
{
List <string> vocabulary = new List <string>();
Dictionary <string, int> wordCountList = new Dictionary <string, int>();
stemmedDocs = new List <List <string> >();
var stopWordsFile = File.ReadAllLines(Path.Combine("Data", "stopwords.txt"));
var stopWordsList = new List <string>(stopWordsFile).ToArray();
int docIndex = 0;
List <string> words = new List <string>();
foreach (var doc in docs)
{
List <string> stemmedDoc = new List <string>();
docIndex++;
if (docIndex % 10000 == 0)
{
Console.WriteLine("Processing " + docIndex + "/" + docs.Length);
}
string[] parts2 = Tokenize(doc.ToLower());
foreach (string part in parts2)
{
// Strip non-alphanumeric characters.
string stripped = Regex.Replace(part, "[^a-zA-Z0-9]", "");
if (!stopWordsList.Contains(stripped.ToLower()))
{
try
{
var english = new EnglishWord(stripped);
string stem = english.Original;
words.Add(stripped);
if (stem.Length > 0)
{
// Build the word count list.
if (wordCountList.ContainsKey(stem))
{
wordCountList[stem]++;
}
else
{
wordCountList.Add(stem, 0);
}
stemmedDoc.Add(stem);
}
}
catch
{
// ignored
}
}
}
stemmedDocs.Add(stemmedDoc);
}
// Get the top words.
var vocabList = wordCountList.Where(w => w.Value >= vocabularyThreshold);
foreach (var item in vocabList)
{
vocabulary.Add(item.Key);
}
return(vocabulary);
}
