/*
* This method sentence-tokenizes all top level comments
* The best sentences are those where the words in the sentence
* occur in the most number of subtree items within the current
* top level comment
*/
public List <SentenceObj> GetTopSentences(int N)
{
List <SentenceObj> topSentenceObjs = new List <SentenceObj>();
List <string> topSentences = new List <string>();
Dictionary <string, double> sentenceScores = new Dictionary <string, double>();
Dictionary <string, string> sentenceAuthors = new Dictionary <string, string>();
Dictionary <string, string> sentenceCommentTrees = new Dictionary <string, string>();
Dictionary <string, int> sentenceIds = new Dictionary <string, int>();
foreach (children child in children)
{
try
{
Dictionary <string, HashSet <int> > wordIDMapping = GetWordIDMapping(child);
string text = child.text;
List <string> currSentences = SentenceTokenizer.Tokenize(Util.StripTagsCharArray(text));
string bestSentence = currSentences[0];
double currMax = double.MinValue;
foreach (string sentence in currSentences)
{
string[] allWords = GetAllWords(sentence);
bool goodSentence = (allWords.Length > 2) && (stopWords.Where(x => !allWords.Contains(x.ToLower())).Count() > 2);
if (goodSentence)
{
double weightedScore = 0;
int totalIDCount = 0;
foreach (string word in allWords)
{
if (!stopWords.Contains(word.ToLower()))
{
string stemmedWord = Stemmer.GetStem(word);
if (wordIDMapping.ContainsKey(stemmedWord))
{
HashSet <int> idsContainingWord = wordIDMapping[stemmedWord];
totalIDCount += idsContainingWord.Count;
weightedScore += idsContainingWord.Count * 1.0 / (CommonWords.GetFrequency(word) + 1);
}
}
}
//add some weighting so that longer sentences have more weight
weightedScore = weightedScore * (1 - (1 / (Math.Pow(1.25, allWords.Length))));
double avgScore = weightedScore / allWords.Length;
if (avgScore > currMax)
{
currMax = avgScore;
bestSentence = sentence;
}
}
}
sentenceScores[bestSentence] = currMax;
sentenceAuthors[bestSentence] = child.author;
sentenceCommentTrees[bestSentence] = JsonConvert.SerializeObject(GetCommentTreeString(child));
sentenceIds[bestSentence] = child.id;
}
catch (Exception ex)
{
}
}
topSentences = sentenceScores.OrderByDescending(x => x.Value).Take(N).Where(y => !string.IsNullOrWhiteSpace(y.Key)).Select(x => x.Key).ToList();
foreach (var sent in topSentences)
{
SentenceObj sentenceObj = new SentenceObj()
{
Author = sentenceAuthors[sent], Sentence = sent, SentenceCommentTree = sentenceCommentTrees[sent], Id = sentenceIds[sent], StoryId = this.id
};
topSentenceObjs.Add(sentenceObj);
}
topSentenceObjs = topSentenceObjs.OrderByDescending(x => GetChildCount(GetNodeById(x.Id))).ToList();
return(topSentenceObjs);
}
/*
* This method sentence-tokenizes all top level comments
* The best sentences are those where the words in the sentence
* occur in the most number of subtree items within the current
* top level comment
*/
public List<SentenceObj> GetTopSentences(int N)
{
List<SentenceObj> topSentenceObjs = new List<SentenceObj>();
List<string> topSentences = new List<string>();
Dictionary<string,double> sentenceScores = new Dictionary<string, double>();
Dictionary<string,string> sentenceAuthors = new Dictionary<string, string>();
Dictionary<string,string> sentenceCommentTrees = new Dictionary<string, string>();
Dictionary<string,int> sentenceIds = new Dictionary<string, int>();
foreach (children child in children)
{
try
{
Dictionary<string, HashSet<int>> wordIDMapping = GetWordIDMapping(child);
string text = child.text;
List<string> currSentences = SentenceTokenizer.Tokenize(Util.StripTagsCharArray(text));
string bestSentence = currSentences[0];
double currMax = double.MinValue;
foreach (string sentence in currSentences)
{
string[] allWords = GetAllWords(sentence);
bool goodSentence = (allWords.Length > 2) && (stopWords.Where(x => !allWords.Contains(x.ToLower())).Count() > 2);
if (goodSentence)
{
double weightedScore = 0;
int totalIDCount = 0;
foreach (string word in allWords)
{
if (!stopWords.Contains(word.ToLower()))
{
string stemmedWord = Stemmer.GetStem(word);
if (wordIDMapping.ContainsKey(stemmedWord))
{
HashSet<int> idsContainingWord = wordIDMapping[stemmedWord];
totalIDCount += idsContainingWord.Count;
weightedScore += idsContainingWord.Count * 1.0/(CommonWords.GetFrequency(word) + 1);
}
}
}
//add some weighting so that longer sentences have more weight
weightedScore = weightedScore*(1 - (1/(Math.Pow(1.25, allWords.Length))));
double avgScore = weightedScore / allWords.Length;
if (avgScore > currMax)
{
currMax = avgScore;
bestSentence = sentence;
}
}
}
sentenceScores[bestSentence] = currMax;
sentenceAuthors[bestSentence] = child.author;
sentenceCommentTrees[bestSentence] = JsonConvert.SerializeObject(GetCommentTreeString(child));
sentenceIds[bestSentence] = child.id;
}
catch (Exception ex)
{
}
}
topSentences = sentenceScores.OrderByDescending(x => x.Value).Take(N).Where(y=>!string.IsNullOrWhiteSpace(y.Key)).Select(x=>x.Key).ToList();
foreach (var sent in topSentences)
{
SentenceObj sentenceObj = new SentenceObj()
{
Author = sentenceAuthors[sent], Sentence = sent, SentenceCommentTree = sentenceCommentTrees[sent],Id = sentenceIds[sent],StoryId = this.id
};
topSentenceObjs.Add(sentenceObj);
}
topSentenceObjs = topSentenceObjs.OrderByDescending(x => GetChildCount(GetNodeById(x.Id))).ToList();
return topSentenceObjs;
}
