Dataset

class Dataset

holds variable type data.

Public Functions

Dataset operator()(const vector<size_t> &idx) const

return a slice of the data using indices idx

void init()

call init at the end of constructors to define metafeatures of the data.

map<string, State> make_features(const ArrayXXf &X, const map<string, State> &Z = {}, const vector<string> &vn = {}, const vector<string> &ft = {})

turns input data into a feature map

map<string, State> copy_and_make_features(const ArrayXXf &X, const Dataset &ref_dataset, const vector<string> &vn = {})

turns input into a feature map, with feature types copied from a reference

inline Dataset(std::map<string, State> &d, const Ref<const ArrayXf> &y_ = ArrayXf(), bool c = false, float validation_size = 0.0, float batch_size = 1.0, bool shuffle_split = false)

1. initialize data from a map.

inline Dataset(const ArrayXXf &X, const Ref<const ArrayXf> &y_ = ArrayXf(), const vector<string> &vn = {}, const map<string, State> &Z = {}, const vector<string> &ft = {}, bool c = false, float validation_size = 0.0, float batch_size = 1.0, bool shuffle_split = false)

1. initialize data from a matrix with feature columns.

inline Dataset(const ArrayXXf &X, const vector<string> &vn, const vector<string> &ft = {}, bool c = false, float validation_size = 0.0, float batch_size = 1.0, bool shuffle_split = false)

1. initialize data from X and feature names

inline Dataset(const ArrayXXf &X, const Dataset &ref_dataset, const vector<string> &vn)

inline void print() const

inline auto get_X() const

Dataset get_training_data() const

Dataset get_validation_data() const

inline int get_n_samples() const

inline int get_n_features() const

Dataset get_batch() const

select random subset of data for training weights.

float get_batch_size()

void set_batch_size(float new_size)

inline DataType get_feature_type(const string &name) const

std::array<Dataset, 2> split(const ArrayXb &mask) const

inline State operator[](std::string name) const

Public Members

std::vector<DataType> unique_data_types

keeps track of the unique data types in the dataset.

std::vector<DataType> feature_types

types of data in the features.

std::vector<string> feature_names

names of the feature types as string representations.

std::unordered_map<DataType, vector<string>> features_of_type

map from data types to features having that type.

std::map<string, State> features

dataset features, as key value pairs

ArrayXf y

length N array, the target label

bool classification

whether this is a classification problem

std::optional<std::reference_wrapper<const ArrayXXf>> Xref

float validation_size

percentage of original data used for train. if 0.0, then all data is used for train and validation

bool use_validation

bool shuffle_split

float batch_size

percentage of training data size to use in each batch. if 1.0, then all data is used

bool use_batch