Relintai/pmlpp
1
0
Fork 0
mirror of https://github.com/Relintai/pmlpp.git synced 2024-12-31 16:17:10 +01:00
Code Issues Packages Projects Releases Wiki Activity

Cleanups to tests.

Browse Source
This commit is contained in:
Relintai 2023-12-28 18:00:52 +01:00
parent ece344400c
commit f409265513
2 changed files with 54 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

109
test/mlpp_tests.cpp
View File

@ -882,40 +882,31 @@ void MLPPTests::test_convolution_tensors_etc() {
ERR_PRINT(conv.convolve_2d(conv.gaussian_filter_2d(5, 1), laplacian, 1)->to_string()); ERR_PRINT(conv.convolve_2d(conv.gaussian_filter_2d(5, 1), laplacian, 1)->to_string());
} }
void MLPPTests::test_pca_svd_eigenvalues_eigenvectors(bool ui) { void MLPPTests::test_pca_svd_eigenvalues_eigenvectors(bool ui) {
/*
MLPPLinAlg alg; MLPPLinAlg alg;
// PCA, SVD, eigenvalues & eigenvectors const real_t input_set_arr[] = {
std::vector<std::vector<real_t>> inputSet = { { 1, 1 }, { 1, 1 } }; 1, 1, //
1, 1 //
};
MLPPLinAlg::EigenResultOld eigen = alg.eigen_old(inputSet); Ref<MLPPMatrix> input_set = Ref<MLPPMatrix>(memnew(MLPPMatrix(input_set_arr, 2, 2)));
std::cout << "Eigenvectors:" << std::endl; // eigenvalues & eigenvectors
alg.printMatrix(eigen.eigen_vectors);
std::cout << std::endl;
std::cout << "Eigenvalues:" << std::endl;
alg.printMatrix(eigen.eigen_values);
std::cout << "SVD OLD START" << std::endl; MLPPLinAlg::EigenResult eigen = alg.eigen(input_set);
MLPPLinAlg::SVDResultOld svd_old = alg.SVD(inputSet); PLOG_MSG("== Eigen ==");
std::cout << "U:" << std::endl; PLOG_MSG("Eigenvectors:");
alg.printMatrix(svd_old.U); PLOG_MSG(eigen.eigen_vectors->to_string());
std::cout << "S:" << std::endl; PLOG_MSG("Eigenvalues:");
alg.printMatrix(svd_old.S); PLOG_MSG(eigen.eigen_values->to_string());
std::cout << "Vt:" << std::endl;
alg.printMatrix(svd_old.Vt);
std::cout << "SVD OLD FIN" << std::endl; // SVD
Ref<MLPPMatrix> input_set; PLOG_MSG("== SVD ==");
input_set.instance();
input_set->set_from_std_vectors(inputSet);
*/
/* String str_svd;
String str_svd = "SVD\n";
MLPPLinAlg::SVDResult svd = alg.svd(input_set); MLPPLinAlg::SVDResult svd = alg.svd(input_set);
@ -928,17 +919,10 @@ void MLPPTests::test_pca_svd_eigenvalues_eigenvectors(bool ui) {
str_svd += "\n"; str_svd += "\n";
PLOG_MSG(str_svd); PLOG_MSG(str_svd);
*/
/* // PCA
std::cout << "PCA" << std::endl;
// PCA done using Jacobi's method to approximate eigenvalues and eigenvectors. PLOG_MSG("== PCA ==");
MLPPPCAOld dr_old(inputSet, 1); // 1 dimensional representation.
std::cout << std::endl;
std::cout << "OLD Dimensionally reduced representation:" << std::endl;
alg.printMatrix(dr_old.principalComponents());
std::cout << "SCORE: " << dr_old.score() << std::endl;
// PCA done using Jacobi's method to approximate eigenvalues and eigenvectors. // PCA done using Jacobi's method to approximate eigenvalues and eigenvectors.
MLPPPCA dr(input_set, 1); // 1 dimensional representation. MLPPPCA dr(input_set, 1); // 1 dimensional representation.
@ -947,47 +931,54 @@ void MLPPTests::test_pca_svd_eigenvalues_eigenvectors(bool ui) {
str += dr.principal_components()->to_string(); str += dr.principal_components()->to_string();
str += "\nSCORE: " + String::num(dr.score()) + "\n"; str += "\nSCORE: " + String::num(dr.score()) + "\n";
PLOG_MSG(str); PLOG_MSG(str);
*/
} }
void MLPPTests::test_nlp_and_data(bool ui) { void MLPPTests::test_nlp_and_data(bool ui) {
/*
MLPPLinAlg alg; MLPPLinAlg alg;
MLPPData data; MLPPData data;
// NLP/DATA // NLP/DATA
std::string verbText = "I am appearing and thinking, as well as conducting."; String verb_text = "I am appearing and thinking, as well as conducting.";
std::cout << "Stemming Example:" << std::endl;
std::cout << data.stemming(verbText) << std::endl;
std::cout << std::endl;
std::vector<std::string> sentences = { "He is a good boy", "She is a good girl", "The boy and girl are good" }; data.load_default_suffixes();
std::cout << "Bag of Words Example:" << std::endl; data.load_default_stop_words();
alg.printMatrix(data.BOW(sentences, "Default"));
std::cout << std::endl;
std::cout << "TFIDF Example:" << std::endl;
alg.printMatrix(data.TFIDF(sentences));
std::cout << std::endl;
std::cout << "Tokenization:" << std::endl; PLOG_MSG("Stemming Example:");
alg.printVector(data.tokenize(verbText)); PLOG_MSG(data.stemming(verb_text));
std::cout << std::endl;
std::cout << "Word2Vec:" << std::endl; Vector<String> sentences = String("He is a good boy|She is a good girl|The boy and girl are good").split("|");
std::string textArchive = { "He is a good boy. She is a good girl. The boy and girl are good." };
std::vector<std::string> corpus = data.splitSentences(textArchive);
MLPPData::WordsToVecResult wtvres = data.word_to_vec(corpus, "CBOW", 2, 2, 0.1, 10000); // Can use either CBOW or Skip-n-gram. PLOG_MSG("Bag of Words Example (BAG_OF_WORDS_TYPE_DEFAULT):");
PLOG_MSG(data.bag_of_words(sentences, MLPPData::BAG_OF_WORDS_TYPE_DEFAULT)->to_string());
alg.printMatrix(wtvres.word_embeddings); PLOG_MSG("Bag of Words Example (BAG_OF_WORDS_TYPE_BINARY):");
std::cout << std::endl; PLOG_MSG(data.bag_of_words(sentences, MLPPData::BAG_OF_WORDS_TYPE_BINARY)->to_string());
std::vector<std::string> textArchive2 = { "pizza", "pizza hamburger cookie", "hamburger", "ramen", "sushi", "ramen sushi" }; PLOG_MSG("TFIDF Example:");
PLOG_MSG(data.tfidf(sentences)->to_string());
alg.printMatrix(data.LSA(textArchive2, 2)); PLOG_MSG("Tokenization:");
//alg.printMatrix(data.BOW(textArchive, "Default")); PLOG_MSG(String(Variant(data.tokenize(verb_text))));
std::cout << std::endl;
String text_archive = "He is a good boy. She is a good girl. The boy and girl are good.";
Vector<String> corpus = data.split_sentences(text_archive);
PLOG_MSG("Word2Vec (WORD_TO_VEC_TYPE_CBOW):");
MLPPData::WordsToVecResult wtvres = data.word_to_vec(corpus, MLPPData::WORD_TO_VEC_TYPE_CBOW, 2, 2, 0.1, 10000); // Can use either CBOW or Skip-n-gram.
PLOG_MSG(wtvres.word_embeddings->to_string());
PLOG_MSG("Word2Vec (WORD_TO_VEC_TYPE_SKIPGRAM):");
MLPPData::WordsToVecResult wtvres2 = data.word_to_vec(corpus, MLPPData::WORD_TO_VEC_TYPE_SKIPGRAM, 2, 2, 0.1, 10000); // Can use either CBOW or Skip-n-gram.
PLOG_MSG(wtvres2.word_embeddings->to_string());
Vector<String> text_archive2 = String("pizza|pizza hamburger cookie|hamburger|ramen|sushi|ramen sushi").split("|");
PLOG_MSG("LSA:");
PLOG_MSG(data.lsa(text_archive2, 2)->to_string());
/*
std::vector<std::vector<real_t>> inputSet = { { 1, 2 }, { 2, 3 }, { 3, 4 }, { 4, 5 }, { 5, 6 } }; std::vector<std::vector<real_t>> inputSet = { { 1, 2 }, { 2, 3 }, { 3, 4 }, { 4, 5 }, { 5, 6 } };
std::cout << "Feature Scaling Example:" << std::endl; std::cout << "Feature Scaling Example:" << std::endl;
alg.printMatrix(data.featureScaling(inputSet)); alg.printMatrix(data.featureScaling(inputSet));

8
test/mlpp_tests_old.cpp
View File

@ -348,7 +348,7 @@ void MLPPTestsOld::test_pca_svd_eigenvalues_eigenvectors(bool ui) {
void MLPPTestsOld::test_nlp_and_data(bool ui) { void MLPPTestsOld::test_nlp_and_data(bool ui) {
MLPPLinAlgOld alg; MLPPLinAlgOld alg;
MLPPData data; MLPPDataOld data;
// NLP/DATA // NLP/DATA
std::string verbText = "I am appearing and thinking, as well as conducting."; std::string verbText = "I am appearing and thinking, as well as conducting.";
@ -372,15 +372,15 @@ void MLPPTestsOld::test_nlp_and_data(bool ui) {
std::string textArchive = { "He is a good boy. She is a good girl. The boy and girl are good." }; std::string textArchive = { "He is a good boy. She is a good girl. The boy and girl are good." };
std::vector<std::string> corpus = data.splitSentences(textArchive); std::vector<std::string> corpus = data.splitSentences(textArchive);
MLPPData::WordsToVecResult wtvres = data.word_to_vec(corpus, "CBOW", 2, 2, 0.1, 10000); // Can use either CBOW or Skip-n-gram. std::tuple<std::vector<std::vector<real_t>>, std::vector<std::string>> wtvres = data.word2Vec(corpus, "CBOW", 2, 2, 0.1, 10000); // Can use either CBOW or Skip-n-gram.
alg.printMatrix(wtvres.word_embeddings); alg.printMatrix(std::get<0>(wtvres));
std::cout << std::endl; std::cout << std::endl;
std::vector<std::string> textArchive2 = { "pizza", "pizza hamburger cookie", "hamburger", "ramen", "sushi", "ramen sushi" }; std::vector<std::string> textArchive2 = { "pizza", "pizza hamburger cookie", "hamburger", "ramen", "sushi", "ramen sushi" };
alg.printMatrix(data.LSA(textArchive2, 2)); alg.printMatrix(data.LSA(textArchive2, 2));
//alg.printMatrix(data.BOW(textArchive, "Default")); alg.printMatrix(data.BOW(textArchive2, "Default"));
std::cout << std::endl; std::cout << std::endl;
std::vector<std::vector<real_t>> inputSet = { { 1, 2 }, { 2, 3 }, { 3, 4 }, { 4, 5 }, { 5, 6 } }; std::vector<std::vector<real_t>> inputSet = { { 1, 2 }, { 2, 3 }, { 3, 4 }, { 4, 5 }, { 5, 6 } };