Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

lack include

Browse Source
This commit is contained in:
antinucleon 2014-08-18 13:33:36 -06:00
parent 9da2ced8a2
commit 0b36c8295d
1 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
src/data.h
View File

@ -9,6 +9,7 @@
#include <vector> #include <vector>
#include <limits> #include <limits>
#include <climits> #include <climits>
#include <cstring>
#include <algorithm> #include <algorithm>
#include "utils/io.h" #include "utils/io.h"
#include "utils/utils.h" #include "utils/utils.h"
@ -16,9 +17,9 @@
#include "utils/matrix_csr.h" #include "utils/matrix_csr.h"
namespace xgboost { namespace xgboost {
/*! /*!
* \brief unsigned interger type used in boost, * \brief unsigned interger type used in boost,
* used for feature index and row index * used for feature index and row index
*/ */
typedef unsigned bst_uint; typedef unsigned bst_uint;
/*! \brief float type, used for storing statistics */ /*! \brief float type, used for storing statistics */
@ -82,7 +83,7 @@ struct SparseBatch {
/** /**
* \brief This is a interface convention via template, defining the way to access features, * \brief This is a interface convention via template, defining the way to access features,
* column access rule is defined by template, for efficiency purpose, * column access rule is defined by template, for efficiency purpose,
* row access is defined by iterator of sparse batches * row access is defined by iterator of sparse batches
* \tparam Derived type of actual implementation * \tparam Derived type of actual implementation
*/ */
@ -122,9 +123,9 @@ class FMatrixInterface {
* \return number of columns * \return number of columns
*/ */
inline size_t NumCol(void) const; inline size_t NumCol(void) const;
/*! /*!
* \brief check if column access is supported, if not, initialize column access * \brief check if column access is supported, if not, initialize column access
* \param max_rows maximum number of rows allowed in constructor * \param max_rows maximum number of rows allowed in constructor
*/ */
inline void InitColAccess(void); inline void InitColAccess(void);
/*! \return whether column access is enabled */ /*! \return whether column access is enabled */
@ -133,8 +134,8 @@ class FMatrixInterface {
inline size_t GetColSize(size_t cidx) const; inline size_t GetColSize(size_t cidx) const;
/*! /*!
* \breif return #entries-in-col / #rows * \breif return #entries-in-col / #rows
* \param cidx column index * \param cidx column index
* this function is used to help speedup, * this function is used to help speedup,
* doese not necessarily implement it if not sure, return 0.0; * doese not necessarily implement it if not sure, return 0.0;
* \return column density * \return column density
*/ */
@ -204,9 +205,9 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
return ColIter(&col_data_[col_ptr_[cidx]] - 1, return ColIter(&col_data_[col_ptr_[cidx]] - 1,
&col_data_[col_ptr_[cidx + 1]] - 1); &col_data_[col_ptr_[cidx + 1]] - 1);
} }
/*! /*!
* \brief get reversed col iterator, * \brief get reversed col iterator,
* this function will be deprecated at some point * this function will be deprecated at some point
*/ */
inline ColBackIter GetReverseSortedCol(size_t cidx) const { inline ColBackIter GetReverseSortedCol(size_t cidx) const {
utils::Assert(cidx < this->NumCol(), "col id exceed bound"); utils::Assert(cidx < this->NumCol(), "col id exceed bound");
@ -226,8 +227,8 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
if (this->HaveColAccess()) return; if (this->HaveColAccess()) return;
this->InitColData(max_nrow); this->InitColData(max_nrow);
} }
/*! /*!
* \brief get the row iterator associated with FMatrix * \brief get the row iterator associated with FMatrix
* this function is not threadsafe, returns iterator stored in FMatrixS * this function is not threadsafe, returns iterator stored in FMatrixS
*/ */
inline utils::IIterator<SparseBatch>* RowIterator(void) const { inline utils::IIterator<SparseBatch>* RowIterator(void) const {
@ -287,19 +288,19 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
size_t nrow; size_t nrow;
utils::Check(fi.Read(&nrow, sizeof(size_t)) != 0, "invalid input file format"); utils::Check(fi.Read(&nrow, sizeof(size_t)) != 0, "invalid input file format");
out_ptr->resize(nrow + 1); out_ptr->resize(nrow + 1);
utils::Check(fi.Read(&(*out_ptr)[0], out_ptr->size() * sizeof(size_t)) != 0, utils::Check(fi.Read(&(*out_ptr)[0], out_ptr->size() * sizeof(size_t)) != 0,
"invalid input file format"); "invalid input file format");
out_data->resize(out_ptr->back()); out_data->resize(out_ptr->back());
if (out_data->size() != 0) { if (out_data->size() != 0) {
utils::Assert(fi.Read(&(*out_data)[0], out_data->size() * sizeof(SparseBatch::Entry)) != 0, utils::Assert(fi.Read(&(*out_data)[0], out_data->size() * sizeof(SparseBatch::Entry)) != 0,
"invalid input file format"); "invalid input file format");
} }
} }
protected: protected:
/*! /*!
* \brief intialize column data * \brief intialize column data
* \param max_nrow maximum number of rows supported * \param max_nrow maximum number of rows supported
*/ */
inline void InitColData(size_t max_nrow) { inline void InitColData(size_t max_nrow) {
// note: this part of code is serial, todo, parallelize this transformer // note: this part of code is serial, todo, parallelize this transformer