LightGBM::TextReader< INDEX_T > Class Template Reference

Read text data from file. More...

#include <text_reader.h>

Public Member Functions
	TextReader (const char *filename, bool is_skip_first_line)
	Constructor.
	~TextReader ()
	Destructor.
void	Clear ()
	Clear cached data.
std::string	first_line ()
	return first line of data
std::vector< std::string > &	Lines ()
	Get text data that read from file.
INDEX_T	ReadAllAndProcess (const std::function< void(INDEX_T, const char *, size_t)> &process_fun)
INDEX_T	ReadAllLines ()
	Read all text data from file in memory.
std::vector< char >	ReadContent (size_t *out_len)
INDEX_T	SampleFromFile (Random &random, INDEX_T sample_cnt, std::vector< std::string > *out_sampled_data)
INDEX_T	ReadAndFilterLines (const std::function< bool(INDEX_T)> &filter_fun, std::vector< INDEX_T > *out_used_data_indices)
	Read part of text data from file in memory, use filter_fun to filter data.
INDEX_T	SampleAndFilterFromFile (const std::function< bool(INDEX_T)> &filter_fun, std::vector< INDEX_T > *out_used_data_indices, Random &random, INDEX_T sample_cnt, std::vector< std::string > *out_sampled_data)
INDEX_T	CountLine ()
INDEX_T	ReadAllAndProcessParallelWithFilter (const std::function< void(INDEX_T, const std::vector< std::string > &)> &process_fun, const std::function< bool(INDEX_T, INDEX_T)> &filter_fun)
INDEX_T	ReadAllAndProcessParallel (const std::function< void(INDEX_T, const std::vector< std::string > &)> &process_fun)
INDEX_T	ReadPartAndProcessParallel (const std::vector< INDEX_T > &used_data_indices, const std::function< void(INDEX_T, const std::vector< std::string > &)> &process_fun)

Detailed Description

template<typename INDEX_T>
class LightGBM::TextReader< INDEX_T >

Read text data from file.

Constructor & Destructor Documentation

TextReader()

template<typename INDEX_T >

LightGBM::TextReader< INDEX_T >::TextReader ( const char *  filename, bool  is_skip_first_line  )

inline

Constructor.

Parameters

filename	Filename of data
is_skip_first_line	True if need to skip header

Member Function Documentation

Lines()

template<typename INDEX_T >

std::vector< std::string > & LightGBM::TextReader< INDEX_T >::Lines ( )

inline

Get text data that read from file.

Returns

Text data, store in std::vector by line

ReadAllLines()

template<typename INDEX_T >

INDEX_T LightGBM::TextReader< INDEX_T >::ReadAllLines ( )

inline

Read all text data from file in memory.

Returns

number of lines of text data

ReadAndFilterLines()

template<typename INDEX_T >

INDEX_T LightGBM::TextReader< INDEX_T >::ReadAndFilterLines ( const std::function< bool(INDEX_T)> &  filter_fun, std::vector< INDEX_T > *  out_used_data_indices  )

inline

Read part of text data from file in memory, use filter_fun to filter data.

Parameters

filter_fun	Function that perform data filter
out_used_data_indices	Store line indices that read text data

Returns

The number of total data

---

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

• External/LightGBM_2.2.3/LightGBM-2.2.3/include/LightGBM/utils/text_reader.h