static void Main(string[] args)
{
IDictionary <string, string> trainingFiles = new Dictionary <string, string>();
trainingFiles["English"] = @"D:\Dropbox\Code\NaiveBayes\NaiveBayes\datasets\training.language.en.txt";
trainingFiles["French"] = @"D:\Dropbox\Code\NaiveBayes\NaiveBayes\datasets\training.language.fr.txt";
trainingFiles["German"] = @"D:\Dropbox\Code\NaiveBayes\NaiveBayes\datasets\training.language.de.txt";
//loading examples in memory
IDictionary <string, String[]> trainingExamples = new Dictionary <string, String[]>();
foreach (KeyValuePair <string, string> entry in trainingFiles)
{
trainingExamples[entry.Key] = readLines(entry.Value);
}
//train classifier
NaiveBayes nb = new NaiveBayes();
nb.ChisquareCriticalValue = 6.63; //0.01 pvalue
nb.train(trainingExamples);
//get trained classifier knowledgeBase
NaiveBayesKnowledgeBase knowledgeBase = nb.KnowledgeBase;
nb = null;
trainingExamples = null;
//Use classifier
nb = new NaiveBayes(knowledgeBase);
string exampleEn = "Hello, my name is ed and I like to eat bagels. Please don't hurt me, the apples are in my soul.";
string outputEn = nb.predict(exampleEn);
Console.WriteLine("The sentence \"{0}\" was classified as \"{1}\"", exampleEn, outputEn);
string exampleFr = "Bonjour, mon nom est Ed et moi aiment manger des bagels. S'il vous plaît ne me fait pas de mal, les pommes sont dans mon âme.";
string outputFr = nb.predict(exampleFr);
Console.Write("The sentence \"{0}\" was classified as \"{1}\"", exampleFr, outputFr);
string exampleDe = "Hallo, mein Name ist ed und Ich mag Bagels essen. Bitte tu mir nicht weh, die Äpfel sind in meiner Seele.";
string outputDe = nb.predict(exampleDe);
Console.Write("The sentence \"{0}\" was classified as \"{1}\"", exampleDe, outputDe);
}
/// <summary>
/// This constructor is used when we load an already train classifier
/// </summary>
/// <param name="knowledgeBase"> </param>
public NaiveBayes(NaiveBayesKnowledgeBase knowledgeBase)
{
this.knowledgeBase = knowledgeBase;
}
/// <summary>
/// Trains a Naive Bayes classifier by using the Multinomial Model by passing
/// the trainingDataset and the prior probabilities.
/// </summary>
/// <param name="trainingDataset"> </param>
/// <param name="categoryPriors"> </param>
/// <exception cref="IllegalArgumentException"> </exception>
public virtual void train(IDictionary <string, String[]> trainingDataset, IDictionary <string, double> categoryPriors)
{
//preprocess the given dataset
IList <Document> dataset = preprocessDataset(trainingDataset);
//produce the feature stats and select the best features
FeatureStats featureStats = selectFeatures(dataset);
//intiliaze the knowledgeBase of the classifier
knowledgeBase = new NaiveBayesKnowledgeBase();
knowledgeBase.n = featureStats.n; //number of observations
knowledgeBase.d = featureStats.featureCategoryJointCount.Count; //number of features
//check is prior probabilities are given
if (categoryPriors == null)
{
//if not estimate the priors from the sample
knowledgeBase.c = featureStats.categoryCounts.Count; //number of cateogries
knowledgeBase.logPriors = new Dictionary <string, double>();
string category;
int count;
foreach (KeyValuePair <string, int> entry in featureStats.categoryCounts)
{
category = entry.Key;
count = entry.Value;
knowledgeBase.logPriors[category] = Math.Log((double)count / knowledgeBase.n);
}
}
else
{
//if they are provided then use the given priors
knowledgeBase.c = categoryPriors.Count;
//make sure that the given priors are valid
if (knowledgeBase.c != featureStats.categoryCounts.Count)
{
throw new System.ArgumentException("Invalid priors Array: Make sure you pass a prior probability for every supported category.");
}
string category;
double priorProbability;
foreach (KeyValuePair <string, double> entry in categoryPriors)
{
category = entry.Key;
priorProbability = entry.Value;
if (priorProbability == null)
{
throw new System.ArgumentException("Invalid priors Array: Make sure you pass a prior probability for every supported category.");
}
else if (priorProbability < 0 || priorProbability > 1)
{
throw new System.ArgumentException("Invalid priors Array: Prior probabilities should be between 0 and 1.");
}
knowledgeBase.logPriors[category] = Math.Log(priorProbability);
}
}
//We are performing laplace smoothing (also known as add-1). This requires to estimate the total feature occurrences in each category
IDictionary <string, double> featureOccurrencesInCategory = new Dictionary <string, double>();
int occurrences;
double featureOccSum;
foreach (string category in knowledgeBase.logPriors.Keys)
{
featureOccSum = 0.0;
foreach (IDictionary <string, int> categoryListOccurrences in featureStats.featureCategoryJointCount.Values)
{
if (categoryListOccurrences.ContainsKey(category))
{
occurrences = categoryListOccurrences[category];
featureOccSum += occurrences;
}
}
featureOccurrencesInCategory[category] = featureOccSum;
}
//estimate log likelihoods
string feature;
int likelycount;
IDictionary <string, int> featureCategoryCounts;
double logLikelihood;
foreach (string category in knowledgeBase.logPriors.Keys)
{
foreach (KeyValuePair <string, IDictionary <string, int> > entry in featureStats.featureCategoryJointCount)
{
feature = entry.Key;
featureCategoryCounts = entry.Value;
if (featureCategoryCounts.ContainsKey(category) != true)
{
likelycount = 0;
}
else
{
likelycount = featureCategoryCounts[category];
}
logLikelihood = Math.Log((likelycount + 1.0) / (featureOccurrencesInCategory[category] + knowledgeBase.d));
if (knowledgeBase.logLikelihoods.ContainsKey(feature) == false)
{
knowledgeBase.logLikelihoods[feature] = new Dictionary <string, double>();
}
knowledgeBase.logLikelihoods[feature][category] = logLikelihood;
}
}
featureOccurrencesInCategory = null;
}
