public float GetDistance(TF_IDF_Vector vec1, TF_IDF_Vector vec2) { float manhattan = 0; List<string> tokenKeys = vec1.Keys.ToList<string>(); tokenKeys.AddRange(vec2.Keys.ToList<string>()); foreach (string tokenKey in tokenKeys) { float value1 = vec1.ContainsKey(tokenKey) ? vec1[tokenKey].TF_IDF : 0; value1 -= vec2.ContainsKey(tokenKey) ? vec2[tokenKey].TF_IDF : 0; manhattan += Math.Abs(value1); } return manhattan; }
public WikiPage(Page pg) { page = pg; if (page.text == null || page.text == "") { page.Load(); } title = page.text; ns = 0; id = long.Parse(page.pageID); //revid = long.Parse(page.lastRevisionID); //try { parentid = long.Parse(page.lastUserID); } //catch { } timestamp = page.timestamp; text = page.text; tf_IDF_Vec = new TF_IDF_Vector(); }
public WikiPage(XElement page) { title = page.Element(page.GetDefaultNamespace() + "title").Value; ns = int.Parse(page.Element(page.GetDefaultNamespace() + "ns").Value); id = long.Parse(page.Element(page.GetDefaultNamespace() + "id").Value); XElement revision = page.Element(page.GetDefaultNamespace() + "revision"); //revid = long.Parse(revision.Element(revision.GetDefaultNamespace() + "id").Value); //try { parentid = long.Parse(revision.Element(revision.GetDefaultNamespace() + "parentid").Value); } //catch { } timestamp = DateTime.Parse(revision.Element(revision.GetDefaultNamespace() + "timestamp").Value); text = revision.Element(revision.GetDefaultNamespace() + "text").Value; text = text.Replace("\n", "\r\n"); tf_IDF_Vec = new TF_IDF_Vector(); //this.page = new Page(); }
public WikiPage() { tf_IDF_Vec = null; page = null; }