How can I implement Viterbi's algorithm in C # to separate connected words?

Question

In short, I want to convert the first answer to the question here from Python to C #. My current split word conjugation solution is exponential, and I would like to get a linear solution. I do not assume that there is no spacing and consistent flow around my source code.

Background

I want to convert concatenated strings such as "wickedweather" into separate words, such as "evil weather" using C #. I created a working solution, a recursive function that uses exponential time, which is simply not efficient enough for my purposes (processing at least 100 connected words). Here are the questions that I have read so far that I think may be useful, but I cannot translate their answers from Python to C #.

• How can I break up several related words?
• Need help understanding this Python Viterbi algorithm
• How to efficiently extract literary words from a sequential line?

My current recursive solution

This is for people who want to split a few words (<50) in C # and don't care about efficiency.

, . , - . , .

static public string find_words(string instring)
    {
        if (words.Contains(instring)) //where words is my dictionary of words
        {
            return instring;
        }
        if (solutions.ContainsKey(instring.ToString()))
        {
            return solutions[instring];
        }

        string bestSolution = "";
        string solution = "";

        for (int i = 1; i < instring.Length; i++)
        {
            string partOne = find_words(instring.Substring(0, i));
            string partTwo = find_words(instring.Substring(i, instring.Length - i));
            if (partOne == "" || partTwo == "")
            {
                continue;
            }
            solution = partOne + " " + partTwo;
            //if my current solution is smaller than my best solution so far (smaller solution means I have used the space to separate words fewer times, meaning the words are larger)
            if (bestSolution == "" || solution.Length < bestSolution.Length) 
            {
                bestSolution = solution;
            }
        }
        solutions[instring] = bestSolution;
        return bestSolution;
    }

( , ). , , , "" . , "wickedweatherdykjs" " d y k j s", , " dykjs".

:

    static List<string> words = File.ReadLines("E:\\words.txt").ToList(); 
    static Dictionary<char, HashSet<string>> compiledWords = buildDictionary(words);

    private void btnAutoSpacing_Click(object sender, EventArgs e)
    {
        string text = txtText.Text;
        text = RemoveSpacingandNewLines(text); //get rid of anything that breaks the algorithm
        if (text.Length > 150)
        {
            //possibly split the text up into more manageable chunks?
            //considering using textSplit() for this.
        }
        else 
        {
            txtText.Text = find_words(text);
        }
    }

    static IEnumerable<string> textSplit(string str, int chunkSize)
    {
        return Enumerable.Range(0, str.Length / chunkSize)
            .Select(i => str.Substring(i * chunkSize, chunkSize));
    }

    private static Dictionary<char, HashSet<string>> buildDictionary(IEnumerable<string> words)
    {
        var dictionary = new Dictionary<char, HashSet<string>>();

        foreach (var word in words)
        {
            var key = word[0];

            if (!dictionary.ContainsKey(key))
            {
                dictionary[key] = new HashSet<string>();
            }

            dictionary[key].Add(word);
        }

        return dictionary;
    }

    static public string find_words(string instring)
    {
        string bestSolution = "";
        string solution = "";

        if (compiledWords[instring[0]].Contains(instring))
        {
            return instring;
        }

        if (solutions.ContainsKey(instring.ToString()))
        {
            return solutions[instring];
        }

        for (int i = 1; i < instring.Length; i++)
        {
            string partOne = find_words(instring.Substring(0, i));
            string partTwo = find_words(instring.Substring(i, instring.Length - i));
            if (partOne == "" || partTwo == "")
            {
                continue;
            }
            solution = partOne + " " + partTwo;
            if (bestSolution == "" || solution.Length < bestSolution.Length)
            {
                bestSolution = solution;
            }
        }
        solutions[instring] = bestSolution;
        return bestSolution;
    }

, , , . , , - , . .

• ...

, . ,

:

, Zipf, n 1/(n log N), N - .

Generic Human, Python, , . Python #, , , . , , , , #?

Answer 1

, . , words. , . , Dictionary<char, HashSet<string>>, - :

private static Dictionary<char, HashSet<string>> buildDictionary(IEnumerable<string> words)
{
    var dictionary = new Dictionary<char, HashSet<string>>();

    foreach (var word in words)
    {
        var key = word[0];

        if (!dictionary.ContainsKey(key))
        {
            dictionary[key] = new HashSet<string>();
        }

        dictionary[key].Add(word);
    }

    return dictionary;
}

, .

, ( ), , .

. , .

Answer 2

, , . , , , , " " ( ), , , . ... , Zipf, , , .

, - .

, -log(P) log(1/P), log(index * log(N)), log(index) + log(log(N)), .