aGrUM  0.14.1
gum::learning::DatabaseTable< ALLOC > Class Template Reference

The class representing a tabular database as used by learning tasks. More...

#include <agrum/learning/database/databaseTable.h>

+ Inheritance diagram for gum::learning::DatabaseTable< ALLOC >:
+ Collaboration diagram for gum::learning::DatabaseTable< ALLOC >:

Public Member Functions

Constructors / Destructors
template<template< typename > class XALLOC>
 DatabaseTable (const MissingValType< XALLOC > &missing_symbols, const DBTranslatorSet< ALLOC > &translators=DBTranslatorSet< ALLOC >(), const allocator_type &alloc=allocator_type())
 default constructor More...
 
 DatabaseTable (const DBTranslatorSet< ALLOC > &translators=DBTranslatorSet< ALLOC >(), const allocator_type &alloc=allocator_type())
 default constructor More...
 
 DatabaseTable (const DatabaseTable< ALLOC > &from)
 copy constructor More...
 
 DatabaseTable (const DatabaseTable< ALLOC > &from, const allocator_type &alloc)
 copy constructor with a given allocator More...
 
 DatabaseTable (DatabaseTable< ALLOC > &&from)
 move constructor More...
 
 DatabaseTable (DatabaseTable< ALLOC > &&from, const allocator_type &alloc)
 move constructor with a given allocator More...
 
virtual DatabaseTable< ALLOC > * clone () const final
 virtual copy constructor More...
 
virtual DatabaseTable< ALLOC > * clone (const allocator_type &alloc) const final
 virtual copy constructor with a given allocator More...
 
virtual ~DatabaseTable ()
 destructor More...
 
Operators
DatabaseTable< ALLOC > & operator= (const DatabaseTable< ALLOC > &from)
 copy operator More...
 
DatabaseTable< ALLOC > & operator= (DatabaseTable< ALLOC > &&from)
 move constructor More...
 
Accessors / Modifiers
std::size_t insertTranslator (const DBTranslator< ALLOC > &translator, const std::size_t input_column, const bool unique_column=true)
 insert a new translator into the database table More...
 
std::size_t insertTranslator (const Variable &var, const std::size_t input_column, const bool unique_column=true)
 insert a new translator into the database table More...
 
template<template< typename > class XALLOC>
std::size_t insertTranslator (const Variable &var, const std::size_t input_column, std::vector< std::string, XALLOC< std::string > > missing_symbols, const bool unique_column=true)
 insert a new translator into the database table More...
 
void eraseTranslators (const std::size_t k, const bool k_is_input_col=false)
 erases either the kth translator or all those parsing the kth column of the input dataset More...
 
const DBTranslatorSet< ALLOC > & translatorSet () const
 returns the set of translators More...
 
const DBTranslator< ALLOC > & translator (const std::size_t k, const bool k_is_input_col=false) const
 returns either the kth translator of the database table or the first one reading the kth column of the input database More...
 
const Variablevariable (const std::size_t k, const bool k_is_input_col=false) const
 returns either the kth variable of the database table or the first one corresponding to the kth column of the input database More...
 
virtual void setVariableNames (const std::vector< std::string, ALLOC< std::string > > &names, const bool from_external_object=true) final
 sets the names of the variables More...
 
virtual void ignoreColumn (const std::size_t k, const bool from_external_object=true) final
 makes the database table ignore from now on the kth column of the input dataset or the column parsed by the kth translator More...
 
virtual const DBVector< std::size_t > ignoredColumns () const final
 returns the set of columns of the original dataset that are ignored More...
 
virtual const DBVector< std::size_t > inputColumns () const final
 returns the set of columns of the original dataset that are present in the DatabaseTable More...
 
std::size_t domainSize (const std::size_t k, const bool k_is_input_col=false) const
 returns the domain size of the kth variable of the database table or of that of the first one corresponding to the kth column of the input database More...
 
DBVector< std::size_t > domainSizes () const
 returns the domain sizes of all the variables in the database table More...
 
bool needsReordering (const std::size_t k, const bool k_is_input_col=false) const
 indicates whether a reordering is needed to sort the translations of the kth translator or those of the first translator parsing the kth column More...
 
void reorder (const std::size_t k, const bool k_is_input_col=false)
 performs a reordering of the kth translator or of the first translator parsing the kth column of the input database More...
 
void reorder ()
 performs a reordering of all the columns More...
 
virtual void insertRow (const std::vector< std::string, ALLOC< std::string > > &new_row) final
 insert a new row at the end of the database More...
 
virtual void insertRow (Row< DBTranslatedValue > &&new_row, const IsMissing contains_missing_data) final
 insert a new DBRow at the end of the database More...
 
virtual void insertRow (const Row< DBTranslatedValue > &new_row, const IsMissing contains_missing_data) final
 insert a new row at the end of the database More...
 
virtual void insertRow (const Row< DBCell > &new_row) final
 insert a new DBRow of DBCells at the end of the database More...
 
virtual void insertRow (Row< DBCell > &&new_row) final
 insert a new DBRow of DBCells at the end of the database More...
 
virtual void insertRows (Matrix< DBTranslatedValue > &&new_rows, const DBVector< IsMissing > &rows_have_missing_vals) final
 insert a set of new DBRows at the end of the database More...
 
virtual void insertRows (const Matrix< DBTranslatedValue > &new_rows, const DBVector< IsMissing > &rows_have_missing_vals) final
 insert a set of new DBRows at the end of the database More...
 
virtual void insertRows (Matrix< DBCell > &&new_rows) final
 insert a set of new DBRows at the end of the database More...
 
virtual void insertRows (const Matrix< DBCell > &new_rows) final
 insert a set of new DBRows at the end of the database More...
 
virtual void clear () final
 erase the content of the database, including the names of the variables More...
 
Iterators
iterator begin () const
 returns a new unsafe handler pointing to the beginning of the database More...
 
iterator_safe beginSafe () const
 returns a new safe handler pointing to the beginning of the database More...
 
const iteratorend () const noexcept
 returns a new unsafe handler pointing to the end of the database More...
 
const iterator_safeendSafe () const noexcept
 returns a new safe handler pointing to the end of the database More...
 
Accessors / Modifiers
const Matrix< DBTranslatedValue > & content () const noexcept
 returns the content (the records) of the database More...
 
iterator handler () const
 returns a new unsafe handler pointing to the 1st record of the database More...
 
iterator_safe handlerSafe () const
 returns a new safe handler pointing to the 1st record of the database More...
 
const DBVector< std::string > & variableNames () const noexcept
 returns the variable names for all the columns of the database More...
 
void setVariableNames (const std::vector< std::string, OTHER_ALLOC< std::string > > &names, const bool from_external_object=true)
 sets the names of the variables More...
 
const std::string & variableName (const std::size_t k) const
 returns the name of the kth column of the IDatabaseTable More...
 
std::size_t columnFromVariableName (const std::string &name) const
 returns the index of the column whose name is passed in argument More...
 
DBVector< std::size_t > columnsFromVariableName (const std::string &name) const
 returns the indices of all the columns whose name is passed in argument More...
 
std::size_t nbVariables () const noexcept
 returns the number of variables (columns) of the database More...
 
std::size_t nbRows () const noexcept
 returns the number of records (rows) in the database More...
 
std::size_t size () const noexcept
 returns the number of records (rows) in the database More...
 
bool empty () const noexcept
 indicates whether the database contains some records or not More...
 
void insertRow (const std::vector< std::string, OTHER_ALLOC< std::string > > &new_row)
 insert a new row at the end of the database More...
 
virtual void insertRow (Row< DBTranslatedValue > &&new_row, const IsMissing contains_missing_data)
 insert a new DBRow at the end of the database More...
 
virtual void insertRow (const Row< DBTranslatedValue > &new_row, const IsMissing contains_missing_data)
 insert a new row at the end of the database More...
 
virtual void insertRows (Matrix< DBTranslatedValue > &&new_rows, const DBVector< IsMissing > &rows_have_missing_vals)
 insert a set of new DBRows at the end of the database More...
 
virtual void insertRows (const Matrix< DBTranslatedValue > &new_rows, const DBVector< IsMissing > &rows_have_missing_vals)
 insert a set of new DBRows at the end of the database More...
 
void eraseRow (std::size_t index)
 erase a given row specified by its index in the table More...
 
void eraseFirstRow ()
 erase the first row More...
 
void eraseLastRow ()
 erase the last row More...
 
void eraseFirstRows (const std::size_t k)
 erase the k first rows More...
 
void eraseLastRows (const std::size_t k)
 erase the k last rows More...
 
void eraseRows (std::size_t deb, std::size_t end)
 erase the rows from the debth to the endth (not included) More...
 
void eraseAllRows ()
 erase all the rows More...
 
ALLOC< DBTranslatedValuegetAllocator () const
 returns the allocator of the database More...
 
const DBVector< std::string > & missingSymbols () const
 returns the set of missing symbols More...
 
bool hasMissingValues () const
 indicates whether the database contains some missing values More...
 
bool hasMissingValues (const std::size_t k) const
 indicates whether the kth row contains some missing values More...
 
void setMaxNbThreads (const std::size_t nb) const
 changes the max number of threads that a database can use More...
 
std::size_t nbThreads () const
 returns the number of threads used to parse the database More...
 
void setMinNbRowsPerThread (const std::size_t nb) const
 changes the number min of rows a thread should process in a multithreading context More...
 
std::size_t minNbRowsPerThread () const
 returns the minimum of rows that each thread should process More...
 
void setAllRowsWeight (const double new_weight)
 assign a given weight to all the rows of the database More...
 

Public Types

template<typename TX_DATA >
using DBVector = std::vector< TX_DATA, ALLOC< TX_DATA > >
 the type for the vectors used in the DatabaseTable More...
 
template<typename TX_DATA >
using Row = DBRow< TX_DATA, ALLOC >
 a row of the database More...
 
template<typename TX_DATA >
using Matrix = std::vector< DBRow< TX_DATA, ALLOC >, ALLOC< DBRow< TX_DATA, ALLOC > > >
 the type for the matrices stored into the database More...
 
template<template< typename > class XALLOC>
using MissingValType = std::vector< std::string, XALLOC< std::string > >
 
using Handler = typename IDatabaseTable< DBTranslatedValue, ALLOC >::Handler
 the unsafe handler type More...
 
using HandlerSafe = typename IDatabaseTable< DBTranslatedValue, ALLOC >::HandlerSafe
 the safe handler type More...
 
using IsMissing = typename IDatabaseTable< DBTranslatedValue, ALLOC >::IsMissing
 
using value_type = Row< DBTranslatedValue >
 Types for STL compliance. More...
 
using reference = value_type &
 Types for STL compliance. More...
 
using const_reference = const value_type &
 Types for STL compliance. More...
 
using pointer = value_type *
 Types for STL compliance. More...
 
using const_pointer = const value_type *
 Types for STL compliance. More...
 
using size_type = std::size_t
 Types for STL compliance. More...
 
using difference_type = std::ptrdiff_t
 Types for STL compliance. More...
 
using iterator = Handler
 Types for STL compliance. More...
 
using iterator_safe = HandlerSafe
 Types for STL compliance. More...
 
using allocator_type = ALLOC< DBTranslatedValue >
 Types for STL compliance. More...
 
using const_iterator = const Handler
 Types for STL compliance. More...
 
using const_iterator_safe = const HandlerSafe
 Types for STL compliance. More...
 

Protected Attributes

DBVector< std::string > _variable_names
 the names of the variables for each column More...
 
Matrix< DBTranslatedValue_rows
 
DBVector< std::string > _missing_symbols
 
DBVector< IsMissing_has_row_missing_val
 
std::size_t _max_nb_threads
 
std::size_t _min_nb_rows_per_thread
 

Protected Member Functions

bool _isRowSizeOK (const std::size_t size) const
 checks whether a size corresponds to the number of columns of the database More...
 

Detailed Description

template<template< typename > class ALLOC = std::allocator>
class gum::learning::DatabaseTable< ALLOC >

The class representing a tabular database as used by learning tasks.

Class DatabaseTable represents a tabular database that stores in the computer's random access memory (RAM) its content as a vector of DBRows of DBTranslatedValue instances. This class is very well suited for fast learning algorithms.

Usage example:
// create the database from a CSV. This is not compulsory for
// DatabaseTable instances, but this is how we usually create
// DatabaseTable instances
gum::learning::DBInitializerFromCSV<> initializer ( "asia.csv" );
const auto& var_names = initializer.variableNames ();
for ( std::size_t i = 0; i < var_names.size(); ++i )
translator_set.insertTranslator ( translator, i );
gum::learning::DatabaseTable<> database ( translator_set );
database.setVariableNames( initializer.variableNames () );
// here, database contains the content of the asia.csv file.
// determine how many columns and rows the database contains
std::size_t nb_rows = database.nbRows();
std::size_t nb_cols = database.nbVariables ();
// manually add a new row into the database
std::vector<std::string> row( 8, "toto" ); // asia has 8 columns
database.insertRow ( row );
dbrow ( 8, gum::learning::DBTranslatedValue { std::size_t(0) } );
database.insertRow ( dbrow );
// insert 4 rows in a single call:
database.insertRows(
( 4, dbrow ) );
// erase some rows
database.eraseRow ( 12 ); // erase the 13th row of the database
database.eraseFirstRow (); // erase the first row of the database
database.eraseLastRow (); // erase the last row of the database
database.eraseFirstRows ( 2 ); // erase the first two rows
database.eraseLastRows ( 3 ); // erase the last three rows
database.eraseRows ( 2,4 ); // erase rows indexed from 2 to 4 (excluded)
// parse the content of the database, the usual way
for ( const auto& dbrow : database )
std::cout << dbrow.row() << " weight: " << dbrow.weight() << std::endl;
// ignore some columns of the database, i.e., remove them
database.ignoreColumn ( 3 ); // remove the column X3 of the CSV file
// now, the database contains columns 0, 1, 2, 4, 5, 6, 7 of the
// CSV file. If we wish to remove Column X5 of the CSV file:
database.ignoreColumn ( 5 ); // remove the column X5 of the CSV file
// now, the database contains columns 0, 1, 2, 4, 6, 7 of the CSV file.
// if we wish to remove the 5th column of the DatabaseTable, i.e.,
// column #4 of the CSV, either we determine that this actually correspond
// to column X6 of the CSV and we use database.ignoreColumn ( 6 ) or
// we call:
database.ignoreColumn ( 4, false ); // false => 4 = the 5th column of
// the DatabaseTable, not the 5th column/variable of the CSV file
// (remember that all column numbers start from 0).
// display the columns of the CSV that were ignored and those that
// were kept:
std::vector<std::size_t> ignored_cols = database.ignoredColumns ();
std::vector<std::size_t> kept_cols = database.inputColumns ();
// parse the content of the database using handlers
typename gum::learning::DatabaseTable<>::Handler uhandler( database );
// by default, the handlers range over the whole database
// change the range of rows handled by the DBHandler
std::cout << handler.setRange ( 1, 40 ); // now parses rows [1,40)
std::cout << handler.size (); // displays 39: rows 1,...,39
std::cout << handler.DBSize (); // shows the number of rows in the database
std::cout << handler.numRow (); // displays 0: the handler currently
// points on the first row of its managed area [1,40)
// move the handler to the next row
handler.nextRow();
std::cout << handler.numRow (); // displays 1: the handler points now
// on the second row of its managed area. This corresponds to the third
// DBRow of the database since the range of handler is [1,40)
++handler; // move again to the next row
std::cout << handler.numRow (); // displays 2
handler += 4; // advances the pointer by 4 rows
std::cout << handler.numRow (); // displays 6
// get the DBRow pointed to by the handler: this is the 7th DBRow
// of the database
const auto& xrow7 = handler.row (); // get the DBRow, unsafe version
const auto& yrow7 = handler.rowSafe (); // get the DBRow, safe version
const std::vector<gum::learning::DBCell>& xrow = xrow7.row ();
const double xweight = xrow27.weight ();
// another way to access the row
const auto& zrow7 = *handler; // get the DBRow, unsafe version
// check whether there exist other rows managed by the handler after
// the current row
bool has_rows = handler.hasRows (); // true: there remains 33 rows
// makes the handler point again on the 2nd row of the database
handler.reset (); // the handler points to the beginning of its area
std::cout << handler.numRow (); // displays 0: the handler currently
// points on the first row of its managed area [1,40)
// see the variables' names, i.e., the names of the database's columns
const auto& vars = handler.variableNames();
// parse all the rows managed
handler.reset ();
for ( auto end = handler.end (); handler != end; ++handler )
std::cout << handler.row ().weight () << std::endl;
// another possibility:
for ( const auto& row : handler )
std::cout << row.weight () << std::endl;
// clear the content of the database and update the database's
// handlers
database.clear ();

Definition at line 184 of file databaseTable.h.

Member Typedef Documentation

◆ allocator_type

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::allocator_type = ALLOC< DBTranslatedValue >

Types for STL compliance.

Definition at line 223 of file databaseTable.h.

◆ const_iterator

Types for STL compliance.

Definition at line 771 of file IDatabaseTable.h.

◆ const_iterator_safe

Types for STL compliance.

Definition at line 772 of file IDatabaseTable.h.

◆ const_pointer

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::const_pointer = const value_type*

Types for STL compliance.

Definition at line 218 of file databaseTable.h.

◆ const_reference

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::const_reference = const value_type&

Types for STL compliance.

Definition at line 216 of file databaseTable.h.

◆ DBVector

template<template< typename > class ALLOC = std::allocator>
template<typename TX_DATA >
using gum::learning::DatabaseTable< ALLOC >::DBVector = std::vector< TX_DATA, ALLOC< TX_DATA > >

the type for the vectors used in the DatabaseTable

Definition at line 188 of file databaseTable.h.

◆ difference_type

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::difference_type = std::ptrdiff_t

Types for STL compliance.

Definition at line 220 of file databaseTable.h.

◆ Handler

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::Handler = typename IDatabaseTable< DBTranslatedValue, ALLOC >::Handler

the unsafe handler type

Definition at line 203 of file databaseTable.h.

◆ HandlerSafe

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::HandlerSafe = typename IDatabaseTable< DBTranslatedValue, ALLOC >::HandlerSafe

the safe handler type

Definition at line 207 of file databaseTable.h.

◆ IsMissing

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::IsMissing = typename IDatabaseTable< DBTranslatedValue, ALLOC >::IsMissing

Definition at line 210 of file databaseTable.h.

◆ iterator

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::iterator = Handler

Types for STL compliance.

Definition at line 221 of file databaseTable.h.

◆ iterator_safe

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::iterator_safe = HandlerSafe

Types for STL compliance.

Definition at line 222 of file databaseTable.h.

◆ Matrix

template<template< typename > class ALLOC = std::allocator>
template<typename TX_DATA >
using gum::learning::DatabaseTable< ALLOC >::Matrix = std::vector< DBRow< TX_DATA, ALLOC >, ALLOC< DBRow< TX_DATA, ALLOC > > >

the type for the matrices stored into the database

Definition at line 197 of file databaseTable.h.

◆ MissingValType

template<template< typename > class ALLOC = std::allocator>
template<template< typename > class XALLOC>
using gum::learning::DatabaseTable< ALLOC >::MissingValType = std::vector< std::string, XALLOC< std::string > >

Definition at line 200 of file databaseTable.h.

◆ pointer

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::pointer = value_type*

Types for STL compliance.

Definition at line 217 of file databaseTable.h.

◆ reference

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::reference = value_type&

Types for STL compliance.

Definition at line 215 of file databaseTable.h.

◆ Row

template<template< typename > class ALLOC = std::allocator>
template<typename TX_DATA >
using gum::learning::DatabaseTable< ALLOC >::Row = DBRow< TX_DATA, ALLOC >

a row of the database

Definition at line 192 of file databaseTable.h.

◆ size_type

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::size_type = std::size_t

Types for STL compliance.

Definition at line 219 of file databaseTable.h.

◆ value_type

template<template< typename > class ALLOC = std::allocator>
using gum::learning::DatabaseTable< ALLOC >::value_type = Row< DBTranslatedValue >

Types for STL compliance.

Definition at line 214 of file databaseTable.h.

Constructor & Destructor Documentation

◆ DatabaseTable() [1/6]

template<template< typename > class ALLOC = std::allocator>
template<template< typename > class XALLOC>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( const MissingValType< XALLOC > &  missing_symbols,
const DBTranslatorSet< ALLOC > &  translators = DBTranslatorSet< ALLOC >(),
const allocator_type alloc = allocator_type() 
)

default constructor

◆ DatabaseTable() [2/6]

template<template< typename > class ALLOC = std::allocator>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( const DBTranslatorSet< ALLOC > &  translators = DBTranslatorSet< ALLOC >(),
const allocator_type alloc = allocator_type() 
)

default constructor

◆ DatabaseTable() [3/6]

template<template< typename > class ALLOC = std::allocator>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( const DatabaseTable< ALLOC > &  from)

copy constructor

◆ DatabaseTable() [4/6]

template<template< typename > class ALLOC = std::allocator>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( const DatabaseTable< ALLOC > &  from,
const allocator_type alloc 
)

copy constructor with a given allocator

◆ DatabaseTable() [5/6]

template<template< typename > class ALLOC = std::allocator>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( DatabaseTable< ALLOC > &&  from)

move constructor

◆ DatabaseTable() [6/6]

template<template< typename > class ALLOC = std::allocator>
gum::learning::DatabaseTable< ALLOC >::DatabaseTable ( DatabaseTable< ALLOC > &&  from,
const allocator_type alloc 
)

move constructor with a given allocator

◆ ~DatabaseTable()

template<template< typename > class ALLOC = std::allocator>
virtual gum::learning::DatabaseTable< ALLOC >::~DatabaseTable ( )
virtual

destructor

Member Function Documentation

◆ _isRowSizeOK()

bool gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_isRowSizeOK ( const std::size_t  size) const
protectedinherited

checks whether a size corresponds to the number of columns of the database

◆ begin()

iterator gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::begin ( ) const
inherited

returns a new unsafe handler pointing to the beginning of the database

◆ beginSafe()

iterator_safe gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::beginSafe ( ) const
inherited

returns a new safe handler pointing to the beginning of the database

◆ clear()

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::clear ( )
finalvirtual

erase the content of the database, including the names of the variables

Reimplemented from gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ clone() [1/2]

template<template< typename > class ALLOC = std::allocator>
virtual DatabaseTable< ALLOC >* gum::learning::DatabaseTable< ALLOC >::clone ( ) const
finalvirtual

virtual copy constructor

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ clone() [2/2]

template<template< typename > class ALLOC = std::allocator>
virtual DatabaseTable< ALLOC >* gum::learning::DatabaseTable< ALLOC >::clone ( const allocator_type alloc) const
finalvirtual

virtual copy constructor with a given allocator

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ columnFromVariableName()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::columnFromVariableName ( const std::string &  name) const
inherited

returns the index of the column whose name is passed in argument

Warning
If several columns correspond to the name, only the column with the lowest index is returned. If you wish to retrieve all the columns, use method columnsFromVariableName
Exceptions
UndefinedElementis raised if there exists no column with the given name

◆ columnsFromVariableName()

DBVector< std::size_t > gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::columnsFromVariableName ( const std::string &  name) const
inherited

returns the indices of all the columns whose name is passed in argument

It may happen that several columns correspond to a given variable name. In this case, the function returns the indices of all the columns of the IDatabase that match the name.

◆ content()

const Matrix< DBTranslatedValue >& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::content ( ) const
noexceptinherited

returns the content (the records) of the database

◆ domainSize()

template<template< typename > class ALLOC = std::allocator>
std::size_t gum::learning::DatabaseTable< ALLOC >::domainSize ( const std::size_t  k,
const bool  k_is_input_col = false 
) const

returns the domain size of the kth variable of the database table or of that of the first one corresponding to the kth column of the input database

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., the index of one of these two columns. When k_is_input_col is set to true, the variable is that of the translator that parses the kth column of the input database.

Exceptions
UndefinedElementis raised if there is no translator corresponding to k.

◆ domainSizes()

template<template< typename > class ALLOC = std::allocator>
DBVector< std::size_t > gum::learning::DatabaseTable< ALLOC >::domainSizes ( ) const

returns the domain sizes of all the variables in the database table

Referenced by gum::learning::genericBNLearner::Database::Database().

+ Here is the caller graph for this function:

◆ empty()

bool gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::empty ( ) const
noexceptinherited

indicates whether the database contains some records or not

◆ end()

const iterator& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::end ( ) const
noexceptinherited

returns a new unsafe handler pointing to the end of the database

◆ endSafe()

const iterator_safe& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::endSafe ( ) const
noexceptinherited

returns a new safe handler pointing to the end of the database

◆ eraseAllRows()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseAllRows ( )
inherited

erase all the rows

◆ eraseFirstRow()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseFirstRow ( )
inherited

erase the first row

Warning
if the row does not exist, nothing is done. In particular, no exception is raised.

◆ eraseFirstRows()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseFirstRows ( const std::size_t  k)
inherited

erase the k first rows

Warning
if there are fewer than k rows in the database, the database is completely emptied

◆ eraseLastRow()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseLastRow ( )
inherited

erase the last row

Warning
if the row does not exist, nothing is done. In particular, no exception is raised.

◆ eraseLastRows()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseLastRows ( const std::size_t  k)
inherited

erase the k last rows

Warning
if there are fewer than k rows in the database, the database is completely emptied

◆ eraseRow()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseRow ( std::size_t  index)
inherited

erase a given row specified by its index in the table

In the database, rows are indexed, starting from 0.

Warning
If the row does not exist, nothing is done. In particular, no exception is raised.

◆ eraseRows()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::eraseRows ( std::size_t  deb,
std::size_t  end 
)
inherited

erase the rows from the debth to the endth (not included)

In the database, rows are indexed, starting from 0.

◆ eraseTranslators()

template<template< typename > class ALLOC = std::allocator>
void gum::learning::DatabaseTable< ALLOC >::eraseTranslators ( const std::size_t  k,
const bool  k_is_input_col = false 
)

erases either the kth translator or all those parsing the kth column of the input dataset

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., to the index of one of these two output columns. When k_is_input_col is set to true, the translators to be erased are all those that parse the kth column of the input database.

Warning
if the translator does not exists, nothing is done. In particular, no exception is raised.

◆ getAllocator()

ALLOC< DBTranslatedValue > gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::getAllocator ( ) const
inherited

returns the allocator of the database

◆ handler()

iterator gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::handler ( ) const
inherited

returns a new unsafe handler pointing to the 1st record of the database

◆ handlerSafe()

iterator_safe gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::handlerSafe ( ) const
inherited

returns a new safe handler pointing to the 1st record of the database

◆ hasMissingValues() [1/2]

bool gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::hasMissingValues ( ) const
inherited

indicates whether the database contains some missing values

◆ hasMissingValues() [2/2]

bool gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::hasMissingValues ( const std::size_t  k) const
inherited

indicates whether the kth row contains some missing values

◆ ignoreColumn()

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::ignoreColumn ( const std::size_t  k,
const bool  from_external_object = true 
)
finalvirtual

makes the database table ignore from now on the kth column of the input dataset or the column parsed by the kth translator

This method can be called in two different ways: either k refers to the current kth column of the database table (in this case parameter from_external_object is set to false), or k corresponds to the kth column of an original database used to fill the database table (in this case from_external_object is set to true). Depending on from_external_object's value, the ignored columns may differ. As an example, imagine that the database table is created from a CSV file with 5 columns named X0, X1, X2, X3 and X4 respectivly. Then a call to ignoreColumn ( 1, true ) will exclude column X1 from the database table. As a result, the database table columns are X0, X2, X3 and X4. Therefore, subsequently calling ignoreColumn ( 1, false ) will result in excluding X2 since X2 is the 2nd column (columns are indexed starting from 0). So, now the database table's columns are X0, X3 and X4. If, now, we call ignoreColumn ( 3, true ), this will remove column X3 because, in the original database, X3 was the 4th column.

The method also erases all the translators corresponding to column k, if any. If the DatabaseTable contains some rows, then their column corresponding to k is removed. If the resulting DatabaseTable contains only empty rows, then those are removed.

Parameters
kthe column to remove. See Method setVariableNames for a detailed description on how k is computed.
from_external_objectindicates whether k refers to the kth column of an original external database (true) or to the current kth column of the DatabaseTable (false).
Exceptions
UndefinedElementis raised if k refers to the position of a translator that does not exist (k >= number of translators).

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ ignoredColumns()

template<template< typename > class ALLOC = std::allocator>
virtual const DBVector< std::size_t > gum::learning::DatabaseTable< ALLOC >::ignoredColumns ( ) const
finalvirtual

returns the set of columns of the original dataset that are ignored

In this vector, all the column indices greater than or equal to its last element are also ignored.

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ inputColumns()

template<template< typename > class ALLOC = std::allocator>
virtual const DBVector< std::size_t > gum::learning::DatabaseTable< ALLOC >::inputColumns ( ) const
finalvirtual

returns the set of columns of the original dataset that are present in the DatabaseTable

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

◆ insertRow() [1/8]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRow ( const std::vector< std::string, ALLOC< std::string > > &  new_row)
finalvirtual

insert a new row at the end of the database

The new_row passed in argument is supposed to come from an external database. So it must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the DatabaseTable because its size does not allow a matching with the columns of the DatabaseTable (taking into account the ignored columns)
UnknownLabelInDatabaseis raised if the translation of an element in the new row cannot be found and the corresponding translator is not in an editable dictionary mode.
SizeErroris raised if the number of entries in the dictionary of a translator has already reached its maximum.
OperationNotAllowedexception is raised if the translation of an element in new_row cannot be found and the insertion of the string into the corresponding translator's dictionary fails because it would induce incoherent behavior (e.g., a DBTranslator4ContinuousVariable that contains a variable whose domain is [x,y] as well as a missing value symbol z \(\in\) [x,y]).
TypeErroris raised if the translation of an element in new_row cannot be found and the insertion of the string into the translator's dictionary fails due to str being impossible to be converted into an appropriate type.

Referenced by gum::learning::BNDatabaseGenerator< GUM_SCALAR >::toDatabaseTable().

+ Here is the caller graph for this function:

◆ insertRow() [2/8]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRow ( Row< DBTranslatedValue > &&  new_row,
const IsMissing  contains_missing_data 
)
finalvirtual

insert a new DBRow at the end of the database

Unlike methods insertRow for data whose type is different from DBTranslatedValue, this method assumes that the new row passed in argument does not contain any data of the ignored columns. So, basically, it could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of the new_row is not equal to the number of translators of the DatabaseTable is raised if at least one element of new_row does not belong to the domain of its corresponding translator.

◆ insertRow() [3/8]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRow ( const Row< DBTranslatedValue > &  new_row,
const IsMissing  contains_missing_data 
)
finalvirtual

insert a new row at the end of the database

Unlike methods insertRow for data whose type is different from DBTranslatedValue, this method assumes that the new row passed in argument does not contain any data of the ignored columns. So, basically, it could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of the new_row is not equal to the number of translators of the DatabaseTable is raised if at least one element of new_row does not belong to the domain of its corresponding translator.

◆ insertRow() [4/8]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRow ( const Row< DBCell > &  new_row)
finalvirtual

insert a new DBRow of DBCells at the end of the database

The new_row passed in argument is supposed to come from an external database. So it must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the DatabaseTable because its size does not allow a matching with the columns of the DatabaseTable (taking into account the ignored columns)

◆ insertRow() [5/8]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRow ( Row< DBCell > &&  new_row)
finalvirtual

insert a new DBRow of DBCells at the end of the database

The new_row passed in argument is supposed to come from an external database. So it must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the DatabaseTable because its size does not allow a matching with the columns of the DatabaseTable (taking into account the ignored columns)

◆ insertRow() [6/8]

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::insertRow ( const std::vector< std::string, OTHER_ALLOC< std::string > > &  new_row)
inherited

insert a new row at the end of the database

The new_row passed in argument is supposed to come from an external database. So it must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the IDatabaseTable because its size does not allow a matching with the columns of the IDatabaseTable (taking into account the ignored columns)

◆ insertRow() [7/8]

virtual void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::insertRow ( Row< DBTranslatedValue > &&  new_row,
const IsMissing  contains_missing_data 
)
virtualinherited

insert a new DBRow at the end of the database

Unlike methods insertRow for data whose type is different from T_DATA, this method assumes that the new row passed in argument does not contain any data of the ignored columns. So, basically, it could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of the new_row is not equal to the number of columns retained in the IDatabaseTable

◆ insertRow() [8/8]

virtual void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::insertRow ( const Row< DBTranslatedValue > &  new_row,
const IsMissing  contains_missing_data 
)
virtualinherited

insert a new row at the end of the database

Unlike methods insertRow for data whose type is different from T_DATA, this method assumes that the new row passed in argument does not contain any data of the ignored columns. So, basically, it could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of the new_row is not equal to the number of columns retained in the IDatabaseTable

◆ insertRows() [1/6]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRows ( Matrix< DBTranslatedValue > &&  new_rows,
const DBVector< IsMissing > &  rows_have_missing_vals 
)
finalvirtual

insert a set of new DBRows at the end of the database

Unlike methods insertRows for data whose type is different from DBTranslatedValue, this method assumes that the new rows passed in argument do not contain any data of the ignored columns. So, basically, these rows could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of at least one row in new_rows is not equal to the number of translators in the DatabaseTable is raised if at least one element of new_row does not belong to the domain of its corresponding translator.

◆ insertRows() [2/6]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRows ( const Matrix< DBTranslatedValue > &  new_rows,
const DBVector< IsMissing > &  rows_have_missing_vals 
)
finalvirtual

insert a set of new DBRows at the end of the database

Unlike methods insertRows for data whose type is different from DBTranslatedValue, this method assumes that the new rows passed in argument do not contain any data of the ignored columns. So, basically, these rows could be copied as is into the database table.

Exceptions
SizeErroris raised if the size of at least one row in new_rows is not equal to the number of translators in the DatabaseTable is raised if at least one element of new_row does not belong to the domain of its corresponding translator.

◆ insertRows() [3/6]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRows ( Matrix< DBCell > &&  new_rows)
finalvirtual

insert a set of new DBRows at the end of the database

The new rows passed in argument are supposed to come from an external database. So they must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the DatabaseTable because its size does not allow a matching with the columns of the DatabaseTable (taking into account the ignored columns)

◆ insertRows() [4/6]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::insertRows ( const Matrix< DBCell > &  new_rows)
finalvirtual

insert a set of new DBRows at the end of the database

The new rows passed in argument are supposed to come from an external database. So they must contain data for the ignored columns.

Exceptions
SizeErroris raised if the vector of string cannot be inserted in the DatabaseTable because its size does not allow a matching with the columns of the DatabaseTable (taking into account the ignored columns)

◆ insertRows() [5/6]

virtual void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::insertRows ( Matrix< DBTranslatedValue > &&  new_rows,
const DBVector< IsMissing > &  rows_have_missing_vals 
)
virtualinherited

insert a set of new DBRows at the end of the database

Unlike methods insertRows for data whose type is different from T_DATA, this method assumes that the new rows passed in argument do not contain any data of the ignored columns. So, basically, these rows could be copied as is into the database table.

Parameters
new_rowsthe new set of rows to be copied as is
rows_have_missing_valsa vector of the same size as new_rows that indicates, for each new row, whether it contains some missing value or not
Exceptions
SizeErroris raised if the size of at least one row in new_rows is not equal to the number of columns retained in the IDatabaseTable. A SizeError exception will also be raised if the number of new rows is not identical to the size of vector rows_have_missing_vals.

◆ insertRows() [6/6]

virtual void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::insertRows ( const Matrix< DBTranslatedValue > &  new_rows,
const DBVector< IsMissing > &  rows_have_missing_vals 
)
virtualinherited

insert a set of new DBRows at the end of the database

Unlike methods insertRows for data whose type is different from T_DATA, this method assumes that the new rows passed in argument do not contain any data of the ignored columns. So, basically, these rows could be copied as is into the database table.

Parameters
new_rowsthe new set of rows to be copied as is
rows_have_missing_valsa vector of the same size as new_rows that indicates, for each new row, whether it contains some missing value or not
Exceptions
SizeErroris raised if the size of at least one row in new_rows is not equal to the number of columns retained in the IDatabaseTable. A SizeError exception will also be raised if the number of new rows is not identical to the size of vector rows_have_missing_vals.

◆ insertTranslator() [1/3]

template<template< typename > class ALLOC = std::allocator>
std::size_t gum::learning::DatabaseTable< ALLOC >::insertTranslator ( const DBTranslator< ALLOC > &  translator,
const std::size_t  input_column,
const bool  unique_column = true 
)

insert a new translator into the database table

Parameters
translatorThis translator is copied into the DatabaseTable
input_columnindicates which column in the original dataset (usually a CSV file) the translator will read
unique_columnindicates whether the input column can be read by several translators.
Returns
the index of the translator within the set of translators
Exceptions
OperationNotAllowedif the input column is marked as ignored
DuplicateElementif there already exists a translator reading the input column passed in argument, and if the unique_column is set to true
Warning
if the database is not empty, i.e., it contains some records, all the column of the database corresponding to the new translator is filled with missing values.

Referenced by gum::learning::genericBNLearner::Database::Database(), and gum::learning::BNDatabaseGenerator< GUM_SCALAR >::toDatabaseTable().

+ Here is the caller graph for this function:

◆ insertTranslator() [2/3]

template<template< typename > class ALLOC = std::allocator>
std::size_t gum::learning::DatabaseTable< ALLOC >::insertTranslator ( const Variable var,
const std::size_t  input_column,
const bool  unique_column = true 
)

insert a new translator into the database table

Parameters
varthe variable that will be contained into the translator
input_columnindicates which column in the original dataset (usually a CSV file) the translator will read
unique_columnindicates whether the input column can be read by several translators
missing_symbolsthe set of symbols in the database representing missing values
Returns
the index of the translator within the set of translators
Exceptions
OperationNotAllowedif the input column is marked as ignored
DuplicateElementif there already exists a translator reading the input column passed in argument, and if the unique_column is set to true
ifthe database is not empty, i.e., it contains some records, all the columns of the database corresponding to the new translator should be filled with missing values, which is impossible since we do not know which symbols correspond to missing values. Therefore, we raise a MissingValueInDatabase exception. If you do not want such a behavior, use method insertTranslator in which you specify the set of missing symbols.

◆ insertTranslator() [3/3]

template<template< typename > class ALLOC = std::allocator>
template<template< typename > class XALLOC>
std::size_t gum::learning::DatabaseTable< ALLOC >::insertTranslator ( const Variable var,
const std::size_t  input_column,
std::vector< std::string, XALLOC< std::string > >  missing_symbols,
const bool  unique_column = true 
)

insert a new translator into the database table

Parameters
varthe variable that will be contained into the translator
input_columnindicates which column in the original dataset (usually a CSV file) the translator will read
unique_columnindicates whether the input column can be read by several translators
missing_symbolsthe set of symbols in the database representing missing values
Returns
the index of the translator within the set of translators
Exceptions
OperationNotAllowedif the input column is marked as ignored
DuplicateElementif there already exists a translator reading the input column passed in argument, and if the unique_column is set to true
Warning
if the database is not empty, i.e., it contains some records, all the column of the database corresponding to the new translator is filled with missing values.

◆ minNbRowsPerThread()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::minNbRowsPerThread ( ) const
inherited

returns the minimum of rows that each thread should process

◆ missingSymbols()

const DBVector< std::string >& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::missingSymbols ( ) const
inherited

returns the set of missing symbols

◆ nbRows()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::nbRows ( ) const
noexceptinherited

returns the number of records (rows) in the database

◆ nbThreads()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::nbThreads ( ) const
inherited

returns the number of threads used to parse the database

◆ nbVariables()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::nbVariables ( ) const
noexceptinherited

returns the number of variables (columns) of the database

◆ needsReordering()

template<template< typename > class ALLOC = std::allocator>
bool gum::learning::DatabaseTable< ALLOC >::needsReordering ( const std::size_t  k,
const bool  k_is_input_col = false 
) const

indicates whether a reordering is needed to sort the translations of the kth translator or those of the first translator parsing the kth column

For a given translator, if the strings represented by the translations are only numbers, the translations are considered to be sorted if and only if they are sorted by increasing number. If the strings do not only represent numbers, then translations are considered to be sorted if and only if they are sorted lexicographically.

When constructing dynamically its dictionary, the translator may assign wrong DBTranslatedValue values to strings. For instance, a translator reading sequentially integer strings 4, 1, 3, may map 4 into DBTranslatedValue{std::size_t(0)}, 1 into DBTranslatedValue{std::size_t(1)} and 3 into DBTranslatedValue{std::size_t(2)}, resulting in random variables having domain {4,1,3}. The user may prefer having domain {1,3,4}, i.e., a domain specified with increasing values. This requires a reordering. Method needsReodering() returns a Boolean indicating whether such a reordering should be performed or whether the current order is OK.

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., the index of one of these two columns. When k_is_input_col is set to true, the translator to be reordered is that which parses the kth column of the input database.

Exceptions
UndefinedElementis raised if there is no translator corresponding to k.

◆ operator=() [1/2]

template<template< typename > class ALLOC = std::allocator>
DatabaseTable< ALLOC >& gum::learning::DatabaseTable< ALLOC >::operator= ( const DatabaseTable< ALLOC > &  from)

copy operator

◆ operator=() [2/2]

template<template< typename > class ALLOC = std::allocator>
DatabaseTable< ALLOC >& gum::learning::DatabaseTable< ALLOC >::operator= ( DatabaseTable< ALLOC > &&  from)

move constructor

◆ reorder() [1/2]

template<template< typename > class ALLOC = std::allocator>
void gum::learning::DatabaseTable< ALLOC >::reorder ( const std::size_t  k,
const bool  k_is_input_col = false 
)

performs a reordering of the kth translator or of the first translator parsing the kth column of the input database

For a given translator, if the strings represented by the translations are only numbers, the translations are considered to be sorted if and only if they are sorted by increasing number. If the strings do not only represent numbers, then translations are considered to be sorted if and only if they are sorted lexicographically.

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., the index of one of these two columns. When k_is_input_col is set to true, the translator to be reordered is that which parses the kth column of the input database.

Exceptions
UndefinedElementis raised if there is no translator corresponding to k.

Referenced by gum::learning::genericBNLearner::__readFile().

+ Here is the caller graph for this function:

◆ reorder() [2/2]

template<template< typename > class ALLOC = std::allocator>
void gum::learning::DatabaseTable< ALLOC >::reorder ( )

performs a reordering of all the columns

For a given translator, if the strings represented by the translations are only numbers, the translations are considered to be sorted if and only if they are sorted by increasing number. If the strings do not only represent numbers, then translations are considered to be sorted if and only if they are sorted lexicographically.

◆ setAllRowsWeight()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::setAllRowsWeight ( const double  new_weight)
inherited

assign a given weight to all the rows of the database

◆ setMaxNbThreads()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::setMaxNbThreads ( const std::size_t  nb) const
inherited

changes the max number of threads that a database can use

Within databases, some methods can be processed in a parallel fashion. This methods indicates the maximum number of threads that can be run in parallel at the same time.

◆ setMinNbRowsPerThread()

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::setMinNbRowsPerThread ( const std::size_t  nb) const
inherited

changes the number min of rows a thread should process in a multithreading context

When a method executes several threads to perform actions on the rows of the database, the MinNbRowsPerThread indicates how many rows each thread should at least process. This is used to compute the number of threads actually run. This number is equal to the min between the max number of threads allowed and the number of records in the database divided by nb.

◆ setVariableNames() [1/2]

template<template< typename > class ALLOC = std::allocator>
virtual void gum::learning::DatabaseTable< ALLOC >::setVariableNames ( const std::vector< std::string, ALLOC< std::string > > &  names,
const bool  from_external_object = true 
)
finalvirtual

sets the names of the variables

This method can be called in two different ways: either the names correspond precisely to the columns stored into the database table (in this case, parameter from_external_object is equal to false), or they correspond to the columns of an external database (e.g., a CSV file) from which we potentially excluded some columns and, consequently, the latter should not be taken into account (in this case, parameter from_external_object is equal to true). As an example, imagine that the database table is created from a CSV file with 5 columns named X0, X1, X2, X3 and X4 respectivly. Suppose that we asked the database table to ignore columns X1 and X3. Then setVariableNames( { "X0", "X1", "X2", "X3", "X4" }, true ) will set the columns of the database table as { "X0", "X2", "X4" }. The same result could be obtained by executing setVariableNames( { "X0", "X2", "X4" }, false ), which specifies directly the set of names to retain in the database table.

Parameters
namesthe names of all the columns, including the ignored columns if from_external_object is set to true, else excluding them (i.e., this should precisely correspond to the columns stored into the database table).
from_external_objecta Boolean indicating whether parameter names includes the columns ignored by the database table (true) or not (false).
Exceptions
SizeErroris raised if the names passed in arguments cannot be assigned to the columns of the DatabaseTable because the size of their vector is inadequate.

Implements gum::learning::IDatabaseTable< DBTranslatedValue, ALLOC >.

Referenced by gum::learning::genericBNLearner::__readFile(), and gum::learning::readFile().

+ Here is the caller graph for this function:

◆ setVariableNames() [2/2]

void gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::setVariableNames ( const std::vector< std::string, OTHER_ALLOC< std::string > > &  names,
const bool  from_external_object = true 
)
inherited

sets the names of the variables

This method can be called in two different ways: either the names correspond precisely to the columns stored into the database table (in this case, parameter from_external_object is equal to false), or they corresponds to the columns of an external database (e.g., a CSV file) from which we potentially excluded some columns and, consequently, the latter should not be taken into account (in this case, parameter from_external_object is equal to true). As an example, imagine that the database table is created from a CSV file with 5 columns named X0, X1, X2, X3 and X4 respectively. Suppose that we asked the database table to ignore columns X1 and X3. Then setVariableNames( { "X0", "X1", "X2", "X3", "X4" }, true ) will set the columns of the database table as { "X0", "X2", "X4" }. The same result could be obtained by executing setVariableNames( { "X0", "X2", "X4" }, false ), which specifies directly the set of names to retain in the database table.

Parameters
namesthe names of all the columns, including the ignored columns if from_external_object is set to true, else excluding them (i.e., this should precisely correspond to the columns stored into the database table).
from_external_objecta Boolean indicating whether parameter names includes the columns ignored by the database table (true) or not (false).
Exceptions
SizeErroris raised if the names passed in arguments cannot be assigned to the columns of the IDatabaseTable because the size of their vector is inadequate.

◆ size()

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::size ( ) const
noexceptinherited

returns the number of records (rows) in the database

◆ translator()

template<template< typename > class ALLOC = std::allocator>
const DBTranslator< ALLOC >& gum::learning::DatabaseTable< ALLOC >::translator ( const std::size_t  k,
const bool  k_is_input_col = false 
) const

returns either the kth translator of the database table or the first one reading the kth column of the input database

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., the index of one of these two columns. When k_is_input_col is set to true, the translator returned is the first one that parses the kth column of the input database.

Exceptions
UndefinedElementis raised if there is no translator corresponding to k.

Referenced by gum::learning::BNDatabaseGenerator< GUM_SCALAR >::toDatabaseTable().

+ Here is the caller graph for this function:

◆ translatorSet()

template<template< typename > class ALLOC = std::allocator>
const DBTranslatorSet< ALLOC >& gum::learning::DatabaseTable< ALLOC >::translatorSet ( ) const

returns the set of translators

◆ variable()

template<template< typename > class ALLOC = std::allocator>
const Variable& gum::learning::DatabaseTable< ALLOC >::variable ( const std::size_t  k,
const bool  k_is_input_col = false 
) const

returns either the kth variable of the database table or the first one corresponding to the kth column of the input database

Translators read an input dataset that is not necessarily the same as the content of the DatabaseTable. For instance, a CSV may contain 10 columns, but if a DatabaseTable only contains two translators reading columns 3 and 5 respectively, then the DatabaseTable only contains 2 columns. When k_is_input_col is set to false, Parameter k passed in argument corresponds to either 0 or 1, i.e., the index of one of these two columns. When k_is_input_col is set to true, the variable is that of the translator that parses the kth column of the input database.

Exceptions
UndefinedElementis raised if there is no translator corresponding to k.

Referenced by gum::learning::genericBNLearner::Database::__BNVars(), and gum::learning::genericBNLearner::Database::Database().

+ Here is the caller graph for this function:

◆ variableName()

const std::string& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::variableName ( const std::size_t  k) const
inherited

returns the name of the kth column of the IDatabaseTable

Exceptions
OutOfBoundsis raised if the IDatabaseTable contains fewer than k columns.

◆ variableNames()

const DBVector< std::string >& gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::variableNames ( ) const
noexceptinherited

returns the variable names for all the columns of the database

The names do not include the ignored columns.

Member Data Documentation

◆ _has_row_missing_val

DBVector< IsMissing > gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_has_row_missing_val
protectedinherited

Definition at line 1147 of file IDatabaseTable.h.

◆ _max_nb_threads

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_max_nb_threads
mutableprotectedinherited

Definition at line 1150 of file IDatabaseTable.h.

◆ _min_nb_rows_per_thread

std::size_t gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_min_nb_rows_per_thread
mutableprotectedinherited

Definition at line 1155 of file IDatabaseTable.h.

◆ _missing_symbols

DBVector< std::string > gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_missing_symbols
protectedinherited

Definition at line 1144 of file IDatabaseTable.h.

◆ _rows

Definition at line 1141 of file IDatabaseTable.h.

◆ _variable_names

DBVector< std::string > gum::learning::IDatabaseTable< DBTranslatedValue , ALLOC >::_variable_names
protectedinherited

the names of the variables for each column

Definition at line 1138 of file IDatabaseTable.h.


The documentation for this class was generated from the following file: