Browse Source

Add initial word-level support

master
Starbeamrainbowlabs 2 years ago
parent
commit
face693554
Signed by: sbrl GPG Key ID: 1BE5172E637709C2
4 changed files with 33 additions and 15 deletions
  1. +28
    -11
      MarkovGrams/NGrams.cs
  2. +3
    -2
      MarkovGrams/Program.cs
  3. +1
    -1
      MarkovGrams/UnweightedMarkovChain.cs
  4. +1
    -1
      MarkovGrams/WeightedMarkovChain.cs

+ 28
- 11
MarkovGrams/NGrams.cs View File

@ -15,6 +15,8 @@ namespace MarkovGrams
/// </summary>
public static class NGrams
{
public static bool Verbose { get; set; } = true;
/// <summary>
/// Generates a unique list of n-grams that the given list of words.
/// </summary>
@ -38,7 +40,7 @@ namespace MarkovGrams
/// <param name="str">The string to n-gram-ise.</param>
/// <param name="order">The order of n-gram to generate.</param>
/// <returns>A unique list of n-grams found in the specified string.</returns>
public static IEnumerable<string> GenerateFlat(string str, int order, GenerationMode mode)
private static IEnumerable<string> GenerateFlat(string str, int order, GenerationMode mode)
{
List<string> results = new List<string>();
if (mode == GenerationMode.CharacterLevel) {
@ -62,9 +64,15 @@ namespace MarkovGrams
/// <returns>The weighted dictionary of ngrams.</returns>
public static Dictionary<string, int> GenerateWeighted(IEnumerable<string> words, int order, GenerationMode mode)
{
List<string> wordList = new List<string>(words);
int wordCount = wordList.Count();
Dictionary<string, int> results = new Dictionary<string, int>();
foreach(string word in words)
GenerateWeighted(word, order, mode);
int i = 0;
foreach (string word in wordList) {
GenerateWeighted(word, order, mode, ref results);
i++;
}
Console.WriteLine(" - done");
return results;
}
/// <summary>
@ -73,15 +81,24 @@ namespace MarkovGrams
/// <param name="str">The string to n-gram-ise.</param>
/// <param name="order">The order of n-grams to generate.</param>
/// <returns>The weighted dictionary of ngrams.</returns>
public static void GenerateWeighted(string str, int order, GenerationMode mode, Dictionary<string, int> results)
private static void GenerateWeighted(string str, int order, GenerationMode mode, ref Dictionary<string, int> results)
{
string[] parts = mode == GenerationMode.WordLevel ? str.Split(" ".ToCharArray()) : null;
for(int i = 0; i < str.Length - order; i++)
{
string ngram = mode == GenerationMode.CharacterLevel ? str.Substring(i, order) : string.Join(" ", parts.Skip(i).Take(order));
if(!results.ContainsKey(ngram))
results[ngram] = 0;
results[ngram]++;
if (mode == GenerationMode.CharacterLevel) {
for (int i = 0; i < str.Length - order; i++) {
string ngram = str.Substring(i, order);
if (!results.ContainsKey(ngram))
results[ngram] = 0;
results[ngram]++;
}
}
else {
string[] parts = str.Split(" ".ToCharArray());
for (int i = 0; i < parts.Length - order; i++) {
string ngram = string.Join(" ", parts.Skip(i).Take(order));
if (!results.ContainsKey(ngram))
results[ngram] = 0;
results[ngram]++;
}
}
}
}


+ 3
- 2
MarkovGrams/Program.cs View File

@ -65,6 +65,7 @@ namespace MarkovGrams
break;
case "words":
generationMode = GenerationMode.WordLevel;
splitOnWhitespace = false;
break;
case "help":
operationMode = Mode.Help;
@ -141,9 +142,9 @@ namespace MarkovGrams
Console.WriteLine(" --help Show this message");
Console.WriteLine(" --wordlist {filename} Read the wordlist from the specified filename instead of stdin");
Console.WriteLine(" --order {number} Use the specified order when generating n-grams (default: 3)");
Console.WriteLine(" --length {number} The target length of word to generate (Not available in ngrams mode)");
Console.WriteLine(" --length {number} The target length of word to generate (Not available in ngrams mode; instead specifies the number of words to generate with --words)");
Console.WriteLine(" --count {number} The number of words to generate (Not valid in ngrams mode)");
Console.WriteLine(" --words Generate ngrams on word-level instead of character-level (Applies to all modes)");
Console.WriteLine(" --words Generate ngrams on word-level instead of character-level (Applies to all modes; implies --no-split)");
Console.WriteLine(" --no-split Don't split input words on whitespace - treat each line as a single word");
Console.WriteLine(" --lowercase Convert the input to lowercase before processing");
Console.WriteLine(" --start-uppercase Start the generating a word only with n-grams that start with a capital letter");


+ 1
- 1
MarkovGrams/UnweightedMarkovChain.cs View File

@ -69,7 +69,7 @@ namespace MarkovGrams
{
string result = RandomNgram();
string lastNgram = result;
while(result.Length < length)
while((Mode == GenerationMode.CharacterLevel ? result.Length : result.Split(' ').Length) < length)
{
// The substring that the next ngram in the chain needs to start with
string nextStartsWith = Mode == GenerationMode.CharacterLevel ? lastNgram.Substring(1) : lastNgram.Split(' ')[0];


+ 1
- 1
MarkovGrams/WeightedMarkovChain.cs View File

@ -83,7 +83,7 @@ namespace MarkovGrams
{
string result = RandomNgram();
string lastNgram = result;
while(result.Length < length)
while((Mode == GenerationMode.CharacterLevel ? result.Length : result.Split(' ').Length) < length)
{
wrandom.ClearContents();
// The substring that the next ngram in the chain needs to start with


Loading…
Cancel
Save