Added MLPPDataOld.

This commit is contained in:
Relintai 2023-02-13 17:31:34 +01:00
parent 478044e7b3
commit eeba478639
3 changed files with 1478 additions and 0 deletions

1
SCsub
View File

@ -83,6 +83,7 @@ sources = [
"mlpp/stat/stat_old.cpp",
"mlpp/lin_alg/lin_alg_old.cpp",
"mlpp/hypothesis_testing/hypothesis_testing_old.cpp",
"mlpp/data/data_old.cpp",
"test/mlpp_tests.cpp",
]

1276
mlpp/data/data_old.cpp Normal file

File diff suppressed because it is too large Load Diff

201
mlpp/data/data_old.h Normal file
View File

@ -0,0 +1,201 @@
#ifndef MLPP_DATA_OLD_H
#define MLPP_DATA_OLD_H
//
// Data.hpp
// MLP
//
// Created by Marc Melikyan on 11/4/20.
//
#include "core/math/math_defs.h"
#include "core/string/ustring.h"
#include "core/variant/array.h"
#include "core/object/reference.h"
#include "../lin_alg/mlpp_matrix.h"
#include "../lin_alg/mlpp_vector.h"
#include <string>
#include <tuple>
#include <vector>
class MLPPDataOldESimple : public Reference {
GDCLASS(MLPPDataOldESimple, Reference);
public:
Ref<MLPPVector> get_input();
void set_input(const Ref<MLPPVector> &val);
Ref<MLPPVector> get_output();
void set_output(const Ref<MLPPVector> &val);
void instance_data();
protected:
static void _bind_methods();
Ref<MLPPVector> _input;
Ref<MLPPVector> _output;
};
class MLPPDataOldSimple : public Reference {
GDCLASS(MLPPDataOldSimple, Reference);
public:
Ref<MLPPMatrix> get_input();
void set_input(const Ref<MLPPMatrix> &val);
Ref<MLPPVector> get_output();
void set_output(const Ref<MLPPVector> &val);
void instance_data();
protected:
static void _bind_methods();
Ref<MLPPMatrix> _input;
Ref<MLPPVector> _output;
};
class MLPPDataOldComplex : public Reference {
GDCLASS(MLPPDataOldComplex, Reference);
public:
Ref<MLPPMatrix> get_input();
void set_input(const Ref<MLPPMatrix> &val);
Ref<MLPPMatrix> get_output();
void set_output(const Ref<MLPPMatrix> &val);
void instance_data();
protected:
static void _bind_methods();
Ref<MLPPMatrix> _input;
Ref<MLPPMatrix> _output;
};
class MLPPDataOld : public Reference {
GDCLASS(MLPPDataOld, Reference);
public:
// Load Datasets
Ref<MLPPDataOldSimple> load_breast_cancer(const String &path);
Ref<MLPPDataOldSimple> load_breast_cancer_svc(const String &path);
Ref<MLPPDataOldComplex> load_iris(const String &path);
Ref<MLPPDataOldComplex> load_wine(const String &path);
Ref<MLPPDataOldComplex> load_mnist_train(const String &path);
Ref<MLPPDataOldComplex> load_mnist_test(const String &path);
Ref<MLPPDataOldSimple> load_california_housing(const String &path);
Ref<MLPPDataOldESimple> load_fires_and_crime(const String &path);
void set_data_supervised(int k, const String &file_name, Ref<MLPPMatrix> input_set, Ref<MLPPVector> output_set);
void set_data_unsupervised(int k, const String &file_name, Ref<MLPPMatrix> input_set);
void set_data_simple(const String &file_name, Ref<MLPPVector> input_set, Ref<MLPPVector> output_set);
struct SplitComplexData {
Ref<MLPPDataOldComplex> train;
Ref<MLPPDataOldComplex> test;
};
SplitComplexData train_test_split(Ref<MLPPDataOldComplex> data, real_t test_size);
Array train_test_split_bind(const Ref<MLPPDataOldComplex> &data, real_t test_size);
// Load Datasets
std::tuple<std::vector<std::vector<real_t>>, std::vector<real_t>> loadBreastCancer();
std::tuple<std::vector<std::vector<real_t>>, std::vector<real_t>> loadBreastCancerSVC();
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>> loadIris();
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>> loadWine();
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>> loadMnistTrain();
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>> loadMnistTest();
std::tuple<std::vector<std::vector<real_t>>, std::vector<real_t>> loadCaliforniaHousing();
std::tuple<std::vector<real_t>, std::vector<real_t>> loadFiresAndCrime();
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>, std::vector<std::vector<real_t>>> trainTestSplit(std::vector<std::vector<real_t>> inputSet, std::vector<std::vector<real_t>> outputSet, real_t testSize);
// Supervised
void setData(int k, std::string fileName, std::vector<std::vector<real_t>> &inputSet, std::vector<real_t> &outputSet);
void printData(std::vector<std::string> inputName, std::string outputName, std::vector<std::vector<real_t>> inputSet, std::vector<real_t> outputSet);
// Unsupervised
void setData(int k, std::string fileName, std::vector<std::vector<real_t>> &inputSet);
void printData(std::vector<std::string> inputName, std::vector<std::vector<real_t>> inputSet);
// Simple
void setData(std::string fileName, std::vector<real_t> &inputSet, std::vector<real_t> &outputSet);
void printData(std::string &inputName, std::string &outputName, std::vector<real_t> &inputSet, std::vector<real_t> &outputSet);
// Images
std::vector<std::vector<real_t>> rgb2gray(std::vector<std::vector<std::vector<real_t>>> input);
std::vector<std::vector<std::vector<real_t>>> rgb2ycbcr(std::vector<std::vector<std::vector<real_t>>> input);
std::vector<std::vector<std::vector<real_t>>> rgb2hsv(std::vector<std::vector<std::vector<real_t>>> input);
std::vector<std::vector<std::vector<real_t>>> rgb2xyz(std::vector<std::vector<std::vector<real_t>>> input);
std::vector<std::vector<std::vector<real_t>>> xyz2rgb(std::vector<std::vector<std::vector<real_t>>> input);
// Text-Based & NLP
std::string toLower(std::string text);
std::vector<char> split(std::string text);
std::vector<std::string> splitSentences(std::string data);
std::vector<std::string> removeSpaces(std::vector<std::string> data);
std::vector<std::string> removeNullByte(std::vector<std::string> data);
std::vector<std::string> segment(std::string text);
std::vector<real_t> tokenize(std::string text);
std::vector<std::string> removeStopWords(std::string text);
std::vector<std::string> removeStopWords(std::vector<std::string> segmented_data);
std::string stemming(std::string text);
std::vector<std::vector<real_t>> BOW(std::vector<std::string> sentences, std::string = "Default");
std::vector<std::vector<real_t>> TFIDF(std::vector<std::string> sentences);
std::tuple<std::vector<std::vector<real_t>>, std::vector<std::string>> word2Vec(std::vector<std::string> sentences, std::string type, int windowSize, int dimension, real_t learning_rate, int max_epoch);
struct WordsToVecResult {
std::vector<std::vector<real_t>> word_embeddings;
std::vector<std::string> word_list;
};
WordsToVecResult word_to_vec(std::vector<std::string> sentences, std::string type, int windowSize, int dimension, real_t learning_rate, int max_epoch);
std::vector<std::vector<real_t>> LSA(std::vector<std::string> sentences, int dim);
std::vector<std::string> createWordList(std::vector<std::string> sentences);
// Extra
void setInputNames(std::string fileName, std::vector<std::string> &inputNames);
std::vector<std::vector<real_t>> featureScaling(std::vector<std::vector<real_t>> X);
std::vector<std::vector<real_t>> meanNormalization(std::vector<std::vector<real_t>> X);
std::vector<std::vector<real_t>> meanCentering(std::vector<std::vector<real_t>> X);
std::vector<std::vector<real_t>> oneHotRep(std::vector<real_t> tempOutputSet, int n_class);
std::vector<real_t> reverseOneHot(std::vector<std::vector<real_t>> tempOutputSet);
Ref<MLPPMatrix> mean_centering(const Ref<MLPPMatrix> &X);
Ref<MLPPMatrix> one_hot_rep(const Ref<MLPPVector> &temp_output_set, int n_class);
template <class T>
std::vector<T> vecToSet(std::vector<T> inputSet) {
std::vector<T> setInputSet;
for (uint32_t i = 0; i < inputSet.size(); i++) {
bool new_element = true;
for (uint32_t j = 0; j < setInputSet.size(); j++) {
if (setInputSet[j] == inputSet[i]) {
new_element = false;
}
}
if (new_element) {
setInputSet.push_back(inputSet[i]);
}
}
return setInputSet;
}
protected:
static void _bind_methods();
};
#endif /* Data_hpp */