TEST(naive_bayes, serialization) {
NaiveBayes bayes;
std::vector<std::string> words1{"hello", "world", "world"};
std::vector<std::string> words2{"f**k", "world", "world"};
std::vector<Example> examples = {
Example(words1, "positive"),
Example(words2, "negative")
};
bayes.fit(examples);
auto scores = bayes.scores(examples[0]);
TempFile tmp_file;
std::ofstream ofs(tmp_file.filename);
boost::archive::text_oarchive oa(ofs);
oa << bayes;
ofs.close();
NaiveBayes bayes_restore;
std::ifstream ifs(tmp_file.filename);
boost::archive::text_iarchive ia(ifs);
ia >> bayes_restore;
auto scores_restore = bayes_restore.scores(examples[0]);
EXPECT_EQ(scores.get("positive"), scores_restore.get("positive"));
EXPECT_EQ(scores.get("negative"), scores_restore.get("negative"));
}
TEST(naive_bayes, example) {
NaiveBayes bayes;
std::vector<std::string> words1{"hello", "world", "world"};
std::vector<std::string> words2{"f**k", "world", "world"};
std::vector<Example> examples = {
Example(words1, "positive"),
Example(words2, "negative")
};
bayes.fit(examples);
print_scores(bayes.scores(examples[0]));
print_scores(bayes.scores(examples[1]));
}
int main(int argc, const char * argv[]) {
DataSet train = createDataSet("/Users/Hacker/Desktop/vote_train.arff.txt");
DataSet test = createDataSet("/Users/Hacker/Desktop/vote_test.arff.txt");
vector<Instance> testData = test.instances;
vector<string> className = test.labels;
long size = testData.size();
NaiveBayes *n = new NaiveBayes(train);
n->training(train);
//Learning by NaiveBayes
long correct_count = 0;
for(long i = 0; i < size; i ++)
{
double probability = 0.00;
probability = n->classify(testData[i]);
string actualclass = className[testData[i].getlabel()];
if(probability > 0.5)
{
cout<<className[0]<<" "<<actualclass<<" ";
if(className[0] == actualclass)
{
correct_count ++;
}
printf("%.16f",probability);
}
else
{
probability = 1 - probability;
cout<<className[1]<<" "<<actualclass<<" ";
if(className[1] == actualclass)
{
correct_count ++;
}
printf("%.16f",probability);
}
cout<<endl;
}
cout<<"Number Of Correct Classification:"<<correct_count<<endl;
delete n;
return 0;
}
int mostLikely(Digit const & digit )
{
Vector<int> values(64);
for(int i = 0; i < 8; i++)
for(int j = 0; j < 8; j++)
values.append(mapColor(digit.color[i][j]));
return nb.classify(values);
}
//learns all probabilities from a digit
void learnProbColorGivenN(Digit digit)
{
Vector<int> values(64);
for(int i = 0; i < 8; i++)
for(int j = 0; j < 8; j++)
values.append(mapColor(digit.color[i][j]));
nb.learn(digit.actualDigit, values);
}
TEST(naive_bayes, nomatching_words_example) {
// When nothing in dict matches, we want an empty map returned,
// rather than smoothed class distributions.
NaiveBayes bayes;
std::vector<std::string> words1{"hello", "world"};
std::vector<std::string> words2{"good", "morning"};
std::vector<Example> examples = {
Example(words1, "positive"),
Example(words2, "negative")
};
bayes.fit(examples);
std::vector<std::string> missing_words{"escape", "notfound"};
Example missing_example(missing_words, "positive");
auto scores = bayes.scores(missing_example);
EXPECT_EQ(0, scores.size());
EXPECT_EQ(0, scores.sum());
}
TEST(naive_bayes, fast_scores) {
NaiveBayes bayes;
std::vector<std::string> words1{"hello", "world"};
std::vector<std::string> words2{"good", "morning"};
std::vector<Example> examples = {
Example(words1, "positive"),
Example(words2, "negative")
};
bayes.fit(examples);
auto scores1 = bayes.fast_scores(examples[0]);
EXPECT_EQ(1, scores1.size());
EXPECT_EQ(2, scores1.get("positive"));
auto scores2 = bayes.fast_scores(examples[1]);
EXPECT_EQ(1, scores2.size());
EXPECT_EQ(2, scores2.get("negative"));
std::vector<std::string> missing_words{"escape", "notfound"};
Example missing_example(missing_words, "positive");
auto missing_scores = bayes.fast_scores(missing_example);
EXPECT_EQ(0, missing_scores.size());
EXPECT_EQ(0, missing_scores.sum());
}
int main()
{
NaiveBayes nb;
nb.create_vocab_list();
nb.get_train_matrix();
nb.print();
nb.train_NB0();
string doc1_to_classify[] = {"love", "my", "dalmation", "null"};
string doc2_to_classify[] = {"stupid", "garbage", "null"};
cout << "doc1 classified as : " << nb.classify_NB( doc1_to_classify ) << endl;
cout << "doc2 classified as : " << nb.classify_NB( doc2_to_classify ) << endl;
return 0;
}
bool ex_model(void *arg) {
Trainer::SetLogLevel (SSI_LOG_LEVEL_DEBUG);
ssi_size_t n_classes = 4;
ssi_size_t n_samples = 50;
ssi_size_t n_streams = 1;
ssi_real_t train_distr[][3] = { 0.25f, 0.25f, 0.1f, 0.25f, 0.75f, 0.1f, 0.75f, 0.75f, 0.1f, 0.75f, 0.75f, 0.1f };
ssi_real_t test_distr[][3] = { 0.5f, 0.5f, 0.5f };
SampleList strain;
SampleList sdevel;
SampleList stest;
ModelTools::CreateTestSamples (strain, n_classes, n_samples, n_streams, train_distr, "user");
ModelTools::CreateTestSamples (sdevel, n_classes, n_samples, n_streams, train_distr, "user");
ModelTools::CreateTestSamples (stest, 1, n_samples * n_classes, n_streams, test_distr, "user");
ssi_char_t string[SSI_MAX_CHAR];
for (ssi_size_t n_class = 1; n_class < n_classes; n_class++) {
ssi_sprint (string, "class%02d", n_class);
stest.addClassName (string);
}
// train svm
{
SVM *model = ssi_create(SVM, 0, true);
model->getOptions()->seed = 1234;
Trainer trainer(model);
trainer.train(strain);
trainer.save("svm");
}
// evaluation
{
Trainer trainer;
Trainer::Load(trainer, "svm");
Evaluation eval;
eval.eval(&trainer, sdevel);
eval.print();
trainer.cluster(stest);
ModelTools::PlotSamples(stest, "svm (internal normalization)", ssi_rect(650, 0, 400, 400));
}
// train knn
{
KNearestNeighbors *model = ssi_create(KNearestNeighbors, 0, true);
model->getOptions()->k = 5;
//model->getOptions()->distsum = true;
Trainer trainer (model);
trainer.train (strain);
trainer.save ("knn");
}
// evaluation
{
Trainer trainer;
Trainer::Load (trainer, "knn");
Evaluation eval;
eval.eval (&trainer, sdevel);
eval.print ();
trainer.cluster (stest);
ModelTools::PlotSamples(stest, "knn", ssi_rect(650, 0, 400, 400));
}
// train naive bayes
{
NaiveBayes *model = ssi_create(NaiveBayes, 0, true);
model->getOptions()->log = true;
Trainer trainer (model);
trainer.train (strain);
trainer.save ("bayes");
}
// evaluation
{
Trainer trainer;
Trainer::Load (trainer, "bayes");
Evaluation eval;
eval.eval (&trainer, sdevel);
eval.print ();
trainer.cluster (stest);
ModelTools::PlotSamples(stest, "bayes", ssi_rect(650, 0, 400, 400));
}
// training
{
LDA *model = ssi_create(LDA, "lda", true);
Trainer trainer (model);
trainer.train (strain);
model->print();
trainer.save ("lda");
}
// evaluation
{
Trainer trainer;
Trainer::Load (trainer, "lda");
Evaluation eval;
eval.eval (&trainer, sdevel);
eval.print ();
trainer.cluster (stest);
ModelTools::PlotSamples(stest, "lda", ssi_rect(650, 0, 400, 400));
}
ssi_print ("\n\n\tpress a key to contiue\n");
getchar ();
return true;
}
int main()
{
ifstream infile("NaiveBayes-samples.txt");
vector<vector<int>> sample_points;
vector<int> sample_values, temp(2);
int v,cnt = 0;
while (infile >> v)
{
if (v == -1) break;
temp[cnt++] = v;
if (cnt == 2)
{
sample_points.push_back(temp);
infile >> v;
sample_values.push_back(v);
cnt = 0;
}
}
NaiveBayes nb;
vector<int> fv = { 3, 3 };
nb.create(fv, 2, 1.0);
nb.train(sample_points, sample_values);
double p;
vector<int> data = { 1, 0 };
int k = nb.compute(data, p);
cout << "Class: " << k << " Probability: " << p << endl;
getchar();
return 0;
}
void exe_naive_bayes()
{
NaiveBayes nb = NaiveBayes();
nb.set_training_data_file(std::string("training.dat"));
nb.add_training_data("Buy cheap viagra SPAM");
nb.add_training_data("Buy cheap airlines airlines tickets HAM");
nb.add_training_data("Dear friend I am the king of Persia king SPAM");
nb.add_training_data("Hello friend I am from Persia you must be from New York HAM");
nb.add_training_data("Hi friend how are you doing I love you HAM");
nb.add_training_data("New York is a big city HAM");
nb.get_training_data();
nb.train();
std::string class_ = nb.classify(std::string("Buy cheap viagra tickets"));
std::cout << "Your message is " << class_ << std::endl;
class_ = nb.classify(std::string("Hello friend how are you"));
std::cout << "Your message is " << class_ << std::endl;
class_ = nb.classify(std::string("Dhaka is a big city"));
std::cout << "Your message is " << class_ << std::endl;
}
