public void TestEmptySource()
{
wordsDataSource = new SimpleWordsDataSource();
WordProbability wp = wordsDataSource.GetWordProbability("myWord");
Assert.IsNull(wp);
}
public void TestAddMultipleNonMatches()
{
wordsDataSource = new SimpleWordsDataSource();
string word = "myWord";
int count = 10;
for (int i = 0; i < count; i++)
wordsDataSource.AddNonMatch(word);
WordProbability wp = wordsDataSource.GetWordProbability(word);
Assert.IsNotNull(wp);
Assert.AreEqual(count, wp.NonMatchingCount);
}
public void TestMultipleWrites()
{
wordsDataSource = new SimpleWordsDataSource();
string word = "myWord";
int count = 500;
for (int i = 0; i < count; i++)
{
wordsDataSource.AddNonMatch(word + count);
}
}
public void TestMultipleWrites()
{
wordsDataSource = new SimpleWordsDataSource();
var word = "myWord";
var count = 500;
for (var i = 0; i < count; i++)
{
wordsDataSource.AddNonMatch(word + count);
}
}
public void TestAddMatch()
{
wordsDataSource = new SimpleWordsDataSource();
wordsDataSource.AddMatch("myWord");
WordProbability wp = wordsDataSource.GetWordProbability("myWord");
Assert.IsNotNull(wp);
Assert.AreEqual(1, wp.MatchingCount);
Assert.AreEqual(0, wp.NonMatchingCount);
wordsDataSource.AddMatch("myWord");
Assert.AreEqual(2, wp.MatchingCount);
Assert.AreEqual(0, wp.NonMatchingCount);
}
public BayesianClassifier(IWordsDataSource wd, ITokenizer tokenizer, IStopWordProvider swp)
{
if (wd == null)
throw new ArgumentNullException("IWordsDataSource cannot be null.");
_wordsData = wd;
if (tokenizer == null)
throw new ArgumentNullException("ITokenizer cannot be null.");
_tokenizer = tokenizer;
if (swp == null)
throw new ArgumentNullException("IStopWordProvider cannot be null.");
_stopWordProvider = swp;
}
public void TestAddMultipleNonMatches()
{
wordsDataSource = new SimpleWordsDataSource();
string word = "myWord";
int count = 10;
for (int i = 0; i < count; i++)
{
wordsDataSource.AddNonMatch(word);
}
WordProbability wp = wordsDataSource.GetWordProbability(word);
Assert.IsNotNull(wp);
Assert.AreEqual(count, wp.NonMatchingCount);
}
public void TestAddMatch()
{
wordsDataSource = new SimpleWordsDataSource();
wordsDataSource.AddMatch("myWord");
WordProbability wp = wordsDataSource.GetWordProbability("myWord");
Assert.IsNotNull(wp);
Assert.AreEqual(1, wp.MatchingCount);
Assert.AreEqual(0, wp.NonMatchingCount);
wordsDataSource.AddMatch("myWord");
Assert.AreEqual(2, wp.MatchingCount);
Assert.AreEqual(0, wp.NonMatchingCount);
}
public void TestAddMultipleMatches()
{
wordsDataSource = new SimpleWordsDataSource();
var word = "myWord";
var count = 10;
for (var i = 0; i < count; i++)
{
wordsDataSource.AddMatch(word);
}
var wp = wordsDataSource.GetWordProbability(word);
Assert.IsNotNull(wp);
Assert.AreEqual(count, wp.MatchingCount);
}
public BayesianClassifier(IWordsDataSource wd, ITokenizer tokenizer, IStopWordProvider swp)
{
if (wd == null)
{
throw new ArgumentNullException("IWordsDataSource cannot be null.");
}
_wordsData = wd;
if (tokenizer == null)
{
throw new ArgumentNullException("ITokenizer cannot be null.");
}
_tokenizer = tokenizer;
if (swp == null)
{
throw new ArgumentNullException("IStopWordProvider cannot be null.");
}
_stopWordProvider = swp;
}
public BayesianClassifier(IWordsDataSource wordsDataSource, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
if (wordsDataSource == null)
{
throw new ArgumentNullException("wordsDataSource");
}
_wordsData = wordsDataSource;
if (tokenizer == null)
{
throw new ArgumentNullException("tokenizer");
}
_tokenizer = tokenizer;
if (stopWordProvider == null)
{
throw new ArgumentNullException("stopWordProvider");
}
_stopWordProvider = stopWordProvider;
}
public BayesianClassifier(IWordsDataSource wordsDataSource, ITokenizer tokenizer, IStopWordProvider stopWordProvider)
{
if (wordsDataSource == null)
{
throw new ArgumentNullException("wordsDataSource");
}
_wordsData = wordsDataSource;
if (tokenizer == null)
{
throw new ArgumentNullException("tokenizer");
}
_tokenizer = tokenizer;
if (stopWordProvider == null)
{
throw new ArgumentNullException("stopWordProvider");
}
_stopWordProvider = stopWordProvider;
}
public BayesianClassifier(IWordsDataSource wd, ITokenizer tokenizer)
: this(wd, tokenizer, new DefaultStopWordProvider())
{
}
public BayesianClassifier(IWordsDataSource wd)
: this(wd, new DefaultTokenizer(DefaultTokenizer.BREAK_ON_WORD_BREAKS))
{
}
public BayesianClassifier(IWordsDataSource wordsDataSource) : this(wordsDataSource, new DefaultTokenizer(DefaultTokenizer.BREAK_ON_WORD_BREAKS))
{
}
public BayesianClassifier(IWordsDataSource wordsDataSource, ITokenizer tokenizer) : this(wordsDataSource, tokenizer, new DefaultStopWordProvider())
{
}
public void TestMultipleWrites()
{
wordsDataSource = new SimpleWordsDataSource();
string word = "myWord";
int count = 500;
for (int i =0; i < count; i++)
wordsDataSource.AddNonMatch(word + count);
}
public void TestEmptySource()
{
wordsDataSource = new SimpleWordsDataSource();
WordProbability wp = wordsDataSource.GetWordProbability("myWord");
Assert.IsNull(wp);
}
