gpmp::ml::BayesClf Class Reference

Bayes Classifier Class based on assumptions of independence. More...

#include <bayes_clf.hpp>

Public Member Functions
	BayesClf (double alpha_param=1.0, bool fit_prior_param=true, const std::vector< double > &class_prior={})
	Constructor for BayesClf class. More...
	~BayesClf ()
	Destructor for BayesClf class. More...
void	train (const std::vector< std::vector< double >> &data, const std::vector< std::string > &labels)
	Train the classifier with a set of labeled data. More...
std::string	predict (const std::vector< double > &newData) const
	Predict the class of a new data point. More...
void	display () const
	Display the learned probabilities. More...

Public Attributes
double	alpha
	Additive smoothing parameter. More...
bool	fit_prior
	Whether to learn class prior probabilities or not. More...
std::unordered_map< std::string, double >	class_probs
	Map of class labels to their probabilities. More...
std::unordered_map< std::string, std::vector< double > >	feature_probs
	Map of class labels to their feature probabilities. More...
std::vector< double >	class_log_prior
	Vector of class log priors. More...

Detailed Description

Bayes Classifier Class based on assumptions of independence.

Definition at line 53 of file bayes_clf.hpp.

Constructor & Destructor Documentation

BayesClf()

gpmp::ml::BayesClf::BayesClf	(	double	alpha_param = 1.0,
		bool	fit_prior_param = true,
		const std::vector< double > &	class_prior = {}
	)

Constructor for BayesClf class.

Parameters

alpha	Additive (Laplace/Lidstone) smoothing parameter
fit_prior	Whether to learn class prior probabilities or not
class_prior	Prior probabilities of the classes

Definition at line 42 of file bayes_clf.cpp.

    : alpha(alpha_param), fit_prior(fit_prior_param),
      class_log_prior(class_prior.begin(), class_prior.end()) {
}

~BayesClf()

gpmp::ml::BayesClf::~BayesClf

(

)

Destructor for BayesClf class.

Definition at line 49 of file bayes_clf.cpp.

                          {
}

Member Function Documentation

display()

void gpmp::ml::BayesClf::display

(

)

const

Display the learned probabilities.

Note

This method is for debugging purposes

Definition at line 135 of file bayes_clf.cpp.

                                   {
    std::cout << "Class Probabilities:\n";
    for (const auto &entry : class_probs) {
        std::cout << entry.first << ": " << entry.second << "\n";
    }
 
    std::cout << "\nFeature Probabilities:\n";
    for (const auto &class_entry : feature_probs) {
        std::cout << class_entry.first << ":\n";
        for (size_t j = 0; j < class_entry.second.size(); ++j) {
            std::cout << "  Feature " << j << ": " << class_entry.second[j]
                      << "\n";
        }
    }
 
    std::cout << "\nClass Log Priors:\n";
    for (const auto &logPrior : class_log_prior) {
        std::cout << logPrior << "\n";
    }
}

predict()

std::string gpmp::ml::BayesClf::predict

(

const std::vector< double > &

newData

)

const

Predict the class of a new data point.

Parameters

newData

A vector of doubles representing the features of the new data point

Returns

The predicted class label as a string

Definition at line 114 of file bayes_clf.cpp.

                                                               {
    double max_prob = -std::numeric_limits<double>::infinity();
    std::string predicted_class;
 
    for (const auto &entry : class_probs) {
        const std::string &label = entry.first;
        double probability = log(entry.second);
 
        for (size_t j = 0; j < new_data.size(); ++j) {
            probability += new_data[j] * log(feature_probs.at(label).at(j));
        }
 
        if (probability > max_prob) {
            max_prob = probability;
            predicted_class = label;
        }
    }
 
    return predicted_class;
}

train()

void gpmp::ml::BayesClf::train	(	const std::vector< std::vector< double >> &	data,
		const std::vector< std::string > &	labels
	)

Train the classifier with a set of labeled data.

Parameters

data	A vector of vectors representing the training instances
labels	A vector of strings representing the corresponding class labels

Definition at line 52 of file bayes_clf.cpp.

                                                                   {
    // count class occurrences
    for (const auto &label : labels) {
        class_probs[label] += 1.0;
    }
 
    // count feature occurrences for each class
    for (size_t i = 0; i < data.size(); ++i) {
        const std::string &label = labels[i];
        const std::vector<double> &features = data[i];
 
        class_probs[label] += 1.0;
 
        // initialize feature_probs[label] if not present
        if (feature_probs.find(label) == feature_probs.end()) {
            feature_probs[label] = std::vector<double>(features.size(), 0.0);
        }
 
        for (size_t j = 0; j < features.size(); ++j) {
            feature_probs[label][j] += features[j];
        }
    }
 
    // calculate class probabilities and feature probabilities
    double smoothing_factor = alpha * 2.0;
    for (const auto &entry : class_probs) {
        const std::string &label = entry.first;
        double class_count = entry.second;
 
        // calculate class probability
        class_probs[label] =
            (class_count + alpha) / (data.size() + smoothing_factor);
 
        // calculate feature probabilities
        for (size_t j = 0; j < feature_probs[label].size(); ++j) {
            feature_probs[label][j] = (feature_probs[label][j] + alpha) /
                                      (class_count + smoothing_factor);
        }
    }
 
    // calculate class log priors
    if (fit_prior) {
        double total = std::accumulate(
            class_probs.begin(),
            class_probs.end(),
            0.0,
            [](double sum, const auto &entry) { return sum + entry.second; });
 
        for (auto &entry : class_probs) {
            entry.second /= total;
        }
 
        std::transform(
            class_probs.begin(),
            class_probs.end(),
            class_log_prior.begin(),
            [total](const auto &entry) { return log(entry.second); });
    }
}

Referenced by main().

Member Data Documentation

alpha

double gpmp::ml::BayesClf::alpha

Additive smoothing parameter.

Definition at line 58 of file bayes_clf.hpp.

class_log_prior

std::vector<double> gpmp::ml::BayesClf::class_log_prior

Vector of class log priors.

Definition at line 75 of file bayes_clf.hpp.

class_probs

std::unordered_map<std::string, double> gpmp::ml::BayesClf::class_probs

Map of class labels to their probabilities.

Definition at line 67 of file bayes_clf.hpp.

feature_probs

std::unordered_map<std::string, std::vector<double> > gpmp::ml::BayesClf::feature_probs

Map of class labels to their feature probabilities.

Definition at line 71 of file bayes_clf.hpp.

fit_prior

bool gpmp::ml::BayesClf::fit_prior

Whether to learn class prior probabilities or not.

Definition at line 63 of file bayes_clf.hpp.

---

The documentation for this class was generated from the following files:

• include/openGPMP/ml/bayes_clf.hpp
• modules/ml/bayes_clf.cpp