int main()
{
// build a naive bayes classifier
Classifier classifier;
// test for accuracy
classifier.test();
return 0;
}
void check_split(Index& idx, Classifier& c, double min_accuracy)
{
// create splits
std::vector<doc_id> docs = idx.docs();
std::mt19937 gen(47);
std::shuffle(docs.begin(), docs.end(), gen);
size_t split_idx = docs.size() / 8;
std::vector<doc_id> train_docs{docs.begin() + split_idx, docs.end()};
std::vector<doc_id> test_docs{docs.begin(), docs.begin() + split_idx};
// train and test
c.train(train_docs);
classify::confusion_matrix mtx = c.test(test_docs);
ASSERT_GREATER(mtx.accuracy(), min_accuracy);
ASSERT_LESS(mtx.accuracy(), 100.0);
}
