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

spelling, wording, and doc fixes in c++ code

Browse Source 
I was reading through the code and fixing some things in the comments.
Only a few trivial actual code changes were made to make things more
readable.
This commit is contained in:
Vadim Khotilovich 2015-12-12 21:40:12 -06:00
parent c56c1b9482
commit c70022e6c4
27 changed files with 113 additions and 108 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/data.h
View File

@ -14,7 +14,7 @@
namespace xgboost {
/*!
* \brief unsigned interger type used in boost,
* \brief unsigned integer type used in boost,
* used for feature index and row index
*/
typedef unsigned bst_uint;
@ -35,8 +35,8 @@ struct bst_gpair {
};
/*!
* \brief extra information that might needed by gbm and tree module
* these information are not necessarily presented, and can be empty
* \brief extra information that might be needed by gbm and tree module
* this information is not necessarily present, and can be empty
*/
struct BoosterInfo {
/*! \brief number of rows in the data */
@ -53,7 +53,7 @@ struct BoosterInfo {
/*! \brief number of rows, number of columns */
BoosterInfo(void) : num_row(0), num_col(0) {
}
/*! \brief get root of ith instance */
/*! \brief get root of i-th instance */
inline unsigned GetRoot(size_t i) const {
return root_index.size() == 0 ? 0 : root_index[i];
}
@ -120,13 +120,13 @@ struct ColBatch : public SparseBatch {
};
/**
* \brief interface of feature matrix, needed for tree construction
* this interface defines two way to access features,
* row access is defined by iterator of RowBatch
* col access is optional, checked by HaveColAccess, and defined by iterator of ColBatch
* this interface defines two ways to access features:
* row access is defined by iterator of RowBatch
* col access is optional, checked by HaveColAccess, and defined by iterator of ColBatch
*/
class IFMatrix {
public:
// the interface only need to ganrantee row iter
// the interface only need to guarantee row iter
// column iter is active, when ColIterator is called, row_iter can be disabled
/*! \brief get the row iterator associated with FMatrix */
virtual utils::IIterator<RowBatch> *RowIterator(void) = 0;
@ -142,7 +142,7 @@ class IFMatrix {
* \brief check if column access is supported, if not, initialize column access
* \param enabled whether certain feature should be included in column access
* \param subsample subsample ratio when generating column access
* \param max_row_perbatch auxilary information, maximum row used in each column batch
* \param max_row_perbatch auxiliary information, maximum row used in each column batch
* this is a hint information that can be ignored by the implementation
*/
virtual void InitColAccess(const std::vector<bool> &enabled,

6
src/gbm/gbm.h
View File

@ -58,7 +58,7 @@ class IGradBooster {
return false;
}
/*!
* \brief peform update to the model(boosting)
* \brief perform update to the model(boosting)
* \param p_fmat feature matrix that provide access to features
* \param buffer_offset buffer index offset of these instances, if equals -1
* this means we do not have buffer index allocated to the gbm
@ -88,7 +88,7 @@ class IGradBooster {
std::vector<float> *out_preds,
unsigned ntree_limit = 0) = 0;
/*!
* \brief online prediction funciton, predict score for one instance at a time
* \brief online prediction function, predict score for one instance at a time
* NOTE: use the batch prediction interface if possible, batch prediction is usually
* more efficient than online prediction
* This function is NOT threadsafe, make sure you only call from one thread
@ -119,7 +119,7 @@ class IGradBooster {
/*!
* \brief dump the model in text format
* \param fmap feature map that may help give interpretations of feature
* \param option extra option of the dumo model
* \param option extra option of the dump model
* \return a vector of dump for boosters
*/
virtual std::vector<std::string> DumpModel(const utils::FeatMap& fmap, int option) = 0;

6
src/gbm/gbtree-inl.hpp
View File

@ -31,7 +31,7 @@ class GBTree : public IGradBooster {
using namespace std;
if (!strncmp(name, "bst:", 4)) {
cfg.push_back(std::make_pair(std::string(name+4), std::string(val)));
// set into updaters, if already intialized
// set into updaters, if already initialized
for (size_t i = 0; i < updaters.size(); ++i) {
updaters[i]->SetParam(name+4, val);
}
@ -85,7 +85,7 @@ class GBTree : public IGradBooster {
fo.Write(BeginPtr(pred_counter), pred_counter.size() * sizeof(unsigned));
}
}
// initialize the predic buffer
// initialize the predict buffer
virtual void InitModel(void) {
pred_buffer.clear(); pred_counter.clear();
pred_buffer.resize(mparam.PredBufferSize(), 0.0f);
@ -446,7 +446,7 @@ class GBTree : public IGradBooster {
int num_roots;
/*! \brief number of features to be used by trees */
int num_feature;
/*! \brief size of predicton buffer allocated used for buffering */
/*! \brief size of prediction buffer allocated used for buffering */
int64_t num_pbuffer;
/*!
* \brief how many output group a single instance can produce

4
src/io/io.h
View File

@ -22,7 +22,7 @@ typedef learner::DMatrix DataMatrix;
* \param silent whether print message during loading
* \param savebuffer whether temporal buffer the file if the file is in text format
* \param loadsplit whether we only load a split of input files
* such that each worker node get a split of the data
* such that each worker node get a split of the data
* \param cache_file name of cache_file, used by external memory version
* can be NULL, if cache_file is specified, this will be the temporal
* space that can be re-used to store intermediate data
@ -38,7 +38,7 @@ DataMatrix* LoadDataMatrix(const char *fname,
* note: the saved dmatrix format may not be in exactly same as input
* SaveDMatrix will choose the best way to materialize the dmatrix.
* \param dmat the dmatrix to be saved
* \param fname file name to be savd
* \param fname file name to be saved
* \param silent whether print message during saving
*/
void SaveDataMatrix(const DataMatrix &dmat, const char *fname, bool silent = false);

2
src/io/libsvm_parser.h
View File

@ -31,7 +31,7 @@ struct LibSVMPage : public SparsePage {
/*!
* \brief libsvm parser that parses the input lines
* and returns rows in input data
* factry that was used by threadbuffer template
* factory that was used by threadbuffer template
*/
class LibSVMPageFactory {
public:

10
src/io/page_fmatrix-inl.hpp
View File

@ -200,7 +200,7 @@ class FMatrixPage : public IFMatrix {
virtual bool HaveColAccess(void) const {
return col_size_.size() != 0;
}
/*! \brief get number of colmuns */
/*! \brief get number of columns */
virtual size_t NumCol(void) const {
utils::Check(this->HaveColAccess(), "NumCol:need column access");
return col_size_.size();
@ -246,7 +246,7 @@ class FMatrixPage : public IFMatrix {
return &col_iter_;
}
/*!
* \brief colmun based iterator
* \brief column based iterator
*/
virtual utils::IIterator<ColBatch> *ColIterator(const std::vector<bst_uint> &fset) {
size_t ncol = this->NumCol();
@ -290,8 +290,10 @@ class FMatrixPage : public IFMatrix {
fo->Write(col_size_);
}
/*!
* \brief intialize column data
* \brief initialize column data
* \param enabled the list of enabled columns
* \param pkeep probability to keep a row
* \param max_row_perbatch maximum row per batch
*/
inline void InitColData(const std::vector<bool> &enabled,
float pkeep, size_t max_row_perbatch) {
@ -319,7 +321,7 @@ class FMatrixPage : public IFMatrix {
bytes_write += spage;
double tnow = rabit::utils::GetTime();
double tdiff = tnow - tstart;
utils::Printf("Writting to %s in %g MB/s, %lu MB written\n",
utils::Printf("Writing to %s in %g MB/s, %lu MB written\n",
col_data_name_.c_str(),
(bytes_write >> 20UL) / tdiff,
(bytes_write >> 20UL));

4
src/io/simple_dmatrix-inl.hpp
View File

@ -51,7 +51,7 @@ class DMatrixSimple : public DataMatrix {
inline void CopyFrom(const DataMatrix &src) {
this->Clear();
this->info = src.info;
// clone data content in thos matrix
// clone data contents from src matrix
utils::IIterator<RowBatch> *iter = src.fmat()->RowIterator();
iter->BeforeFirst();
while (iter->Next()) {
@ -313,7 +313,7 @@ class DMatrixSimple : public DataMatrix {
private:
// whether is at first
bool at_first_;
// pointer to parient
// pointer to parent
DMatrixSimple *parent_;
// temporal space for batch
RowBatch batch_;

6
src/io/simple_fmatrix-inl.hpp
View File

@ -40,7 +40,7 @@ class FMatrixS : public IFMatrix {
virtual bool HaveColAccess(void) const {
return col_size_.size() != 0;
}
/*! \brief get number of colmuns */
/*! \brief get number of columns */
virtual size_t NumCol(void) const {
utils::Check(this->HaveColAccess(), "NumCol:need column access");
return col_size_.size();
@ -83,7 +83,7 @@ class FMatrixS : public IFMatrix {
return &col_iter_;
}
/*!
* \brief colmun based iterator
* \brief column based iterator
*/
virtual utils::IIterator<ColBatch> *ColIterator(const std::vector<bst_uint> &fset) {
size_t ncol = this->NumCol();
@ -112,7 +112,7 @@ class FMatrixS : public IFMatrix {
protected:
/*!
* \brief intialize column data
* \brief initialize column data
* \param enabled the list of enabled columns
* \param pkeep probability to keep a row
* \param max_row_perbatch maximum row per batch

3
src/io/sparse_batch_page.h
View File

@ -33,8 +33,7 @@ class SparsePage {
return offset.size() - 1;
}
/*!
* \brief load the by providing a list of interested segments
* only the interested segments are loaded
* \brief load only the segments we are interested in
* \param fi the input stream of the file
* \param sorted_index_set sorted index of segments we are interested in
* \return true of the loading as successful, false if end of file was reached

2
src/learner/dmatrix.h
View File

@ -35,7 +35,7 @@ struct MetaInfo {
std::vector<float> weights;
/*!
* \brief initialized margins,
* if specified, xgboost will start from this init margin
* if specified, xgboost will start from this initial margin
* can be used to specify initial prediction to boost from
*/
std::vector<float> base_margin;

34
src/learner/evaluation-inl.hpp
View File

@ -21,7 +21,7 @@
namespace xgboost {
namespace learner {
/*!
* \brief base class of elementwise evaluation
* \brief base class of element-wise evaluation
* \tparam Derived the name of subclass
*/
template<typename Derived>
@ -57,7 +57,7 @@ struct EvalEWiseBase : public IEvaluator {
*/
inline static float EvalRow(float label, float pred);
/*!
* \brief to be overide by subclas, final trasnformation
* \brief to be overridden by subclass, final transformation
* \param esum the sum statistics returned by EvalRow
* \param wsum sum of weight
*/
@ -109,7 +109,7 @@ struct EvalError : public EvalEWiseBase<EvalError> {
}
};
/*! \brief loglikelihood of poission distribution */
/*! \brief log-likelihood of Poission distribution */
struct EvalPoissionNegLogLik : public EvalEWiseBase<EvalPoissionNegLogLik> {
virtual const char *Name(void) const {
return "poisson-nloglik";
@ -174,7 +174,7 @@ struct EvalMClassBase : public IEvaluator {
const float *pred,
size_t nclass);
/*!
* \brief to be overide by subclas, final trasnformation
* \brief to be overridden by subclass, final transformation
* \param esum the sum statistics returned by EvalRow
* \param wsum sum of weight
*/
@ -367,7 +367,7 @@ struct EvalPrecisionRatio : public IEvaluator{
std::string name_;
};
/*! \brief Area under curve, for both classification and rank */
/*! \brief Area Under Curve, for both classification and rank */
struct EvalAuc : public IEvaluator {
virtual float Eval(const std::vector<float> &preds,
const MetaInfo &info,
@ -382,7 +382,7 @@ struct EvalAuc : public IEvaluator {
utils::Check(gptr.back() == info.labels.size(),
"EvalAuc: group structure must match number of prediction");
const bst_omp_uint ngroup = static_cast<bst_omp_uint>(gptr.size() - 1);
// sum statictis
// sum statistics
double sum_auc = 0.0f;
#pragma omp parallel reduction(+:sum_auc)
{
@ -404,13 +404,16 @@ struct EvalAuc : public IEvaluator {
// keep bucketing predictions in same bucket
if (j != 0 && rec[j].first != rec[j - 1].first) {
sum_pospair += buf_neg * (sum_npos + buf_pos *0.5);
sum_npos += buf_pos; sum_nneg += buf_neg;
sum_npos += buf_pos;
sum_nneg += buf_neg;
buf_neg = buf_pos = 0.0f;
}
buf_pos += ctr * wt; buf_neg += (1.0f - ctr) * wt;
buf_pos += ctr * wt;
buf_neg += (1.0f - ctr) * wt;
}
sum_pospair += buf_neg * (sum_npos + buf_pos *0.5);
sum_npos += buf_pos; sum_nneg += buf_neg;
sum_npos += buf_pos;
sum_nneg += buf_neg;
// check weird conditions
utils::Check(sum_npos > 0.0 && sum_nneg > 0.0,
"AUC: the dataset only contains pos or neg samples");
@ -443,7 +446,8 @@ struct EvalRankList : public IEvaluator {
utils::Check(preds.size() == info.labels.size(),
"label size predict size not match");
// quick consistency when group is not available
std::vector<unsigned> tgptr(2, 0); tgptr[1] = static_cast<unsigned>(preds.size());
std::vector<unsigned> tgptr(2, 0);
tgptr[1] = static_cast<unsigned>(preds.size());
const std::vector<unsigned> &gptr = info.group_ptr.size() == 0 ? tgptr : info.group_ptr;
utils::Assert(gptr.size() != 0, "must specify group when constructing rank file");
utils::Assert(gptr.back() == preds.size(),
@ -468,7 +472,7 @@ struct EvalRankList : public IEvaluator {
float dat[2];
dat[0] = static_cast<float>(sum_metric);
dat[1] = static_cast<float>(ngroup);
// approximately estimate auc using mean
// approximately estimate the metric using mean
rabit::Allreduce<rabit::op::Sum>(dat, 2);
return dat[0] / dat[1];
} else {
@ -500,14 +504,14 @@ struct EvalRankList : public IEvaluator {
bool minus_;
};
/*! \brief Precison at N, for both classification and rank */
/*! \brief Precision at N, for both classification and rank */
struct EvalPrecision : public EvalRankList{
public:
explicit EvalPrecision(const char *name) : EvalRankList(name) {}
protected:
virtual float EvalMetric(std::vector< std::pair<float, unsigned> > &rec) const {
// calculate Preicsion
// calculate Precision
std::sort(rec.begin(), rec.end(), CmpFirst);
unsigned nhit = 0;
for (size_t j = 0; j < rec.size() && j < this->topn_; ++j) {
@ -517,7 +521,7 @@ struct EvalPrecision : public EvalRankList{
}
};
/*! \brief NDCG */
/*! \brief NDCG: Normalized Discounted Cumulative Gain at N */
struct EvalNDCG : public EvalRankList{
public:
explicit EvalNDCG(const char *name) : EvalRankList(name) {}
@ -549,7 +553,7 @@ struct EvalNDCG : public EvalRankList{
}
};
/*! \brief Precison at N, for both classification and rank */
/*! \brief Mean Average Precision at N, for both classification and rank */
struct EvalMAP : public EvalRankList {
public:
explicit EvalMAP(const char *name) : EvalRankList(name) {}

6
src/learner/helper_utils.h
View File

@ -45,7 +45,7 @@ inline static int FindMaxIndex(const std::vector<float>& rec) {
return FindMaxIndex(BeginPtr(rec), rec.size());
}
// perform numerical safe logsum
// perform numerically safe logsum
inline float LogSum(float x, float y) {
if (x < y) {
return y + std::log(std::exp(x - y) + 1.0f);
@ -53,7 +53,7 @@ inline float LogSum(float x, float y) {
return x + std::log(std::exp(y - x) + 1.0f);
}
}
// numerical safe logsum
// numerically safe logsum
inline float LogSum(const float *rec, size_t size) {
float mx = rec[0];
for (size_t i = 1; i < size; ++i) {
@ -66,11 +66,11 @@ inline float LogSum(const float *rec, size_t size) {
return mx + std::log(sum);
}
// comparator functions for sorting pairs in descending order
inline static bool CmpFirst(const std::pair<float, unsigned> &a,
const std::pair<float, unsigned> &b) {
return a.first > b.first;
}
inline static bool CmpSecond(const std::pair<float, unsigned> &a,
const std::pair<float, unsigned> &b) {
return a.second > b.second;

22
src/learner/learner-inl.hpp
View File

@ -22,8 +22,8 @@ namespace xgboost {
/*! \brief namespace for learning algorithm */
namespace learner {
/*!
* \brief learner that takes do gradient boosting on specific objective functions
* and do training and prediction
* \brief learner that performs gradient boosting for a specific objective function.
* It does training and prediction.
*/
class BoostLearner : public rabit::Serializable {
public:
@ -258,7 +258,7 @@ class BoostLearner : public rabit::Serializable {
}
/*!
* \brief check if data matrix is ready to be used by training,
* if not intialize it
* if not initialize it
* \param p_train pointer to the matrix used by training
*/
inline void CheckInit(DMatrix *p_train) {
@ -283,7 +283,7 @@ class BoostLearner : public rabit::Serializable {
/*!
* \brief update the model for one iteration
* \param iter current iteration number
* \param p_train pointer to the data matrix
* \param train reference to the data matrix
*/
inline void UpdateOneIter(int iter, const DMatrix &train) {
if (seed_per_iteration != 0 || rabit::IsDistributed()) {
@ -342,6 +342,7 @@ class BoostLearner : public rabit::Serializable {
* \param out_preds output vector that stores the prediction
* \param ntree_limit limit number of trees used for boosted tree
* predictor, when it equals 0, this means we are using all the trees
* \param pred_leaf whether to only predict the leaf index of each tree in a boosted tree predictor
*/
inline void Predict(const DMatrix &data,
bool output_margin,
@ -358,7 +359,7 @@ class BoostLearner : public rabit::Serializable {
}
}
/*!
* \brief online prediction funciton, predict score for one instance at a time
* \brief online prediction function, predict score for one instance at a time
* NOTE: use the batch prediction interface if possible, batch prediction is usually
* more efficient than online prediction
* This function is NOT threadsafe, make sure you only call from one thread
@ -367,7 +368,6 @@ class BoostLearner : public rabit::Serializable {
* \param output_margin whether to only predict margin value instead of transformed prediction
* \param out_preds output vector to hold the predictions
* \param ntree_limit limit the number of trees used in prediction
* \param root_index the root index
* \sa Predict
*/
inline void Predict(const SparseBatch::Inst &inst,
@ -452,7 +452,7 @@ class BoostLearner : public rabit::Serializable {
float base_score;
/* \brief number of features */
unsigned num_feature;
/* \brief number of class, if it is multi-class classification */
/* \brief number of classes, if it is multi-class classification */
int num_class;
/*! \brief whether the model itself is saved with pbuffer */
int saved_with_pbuffer;
@ -495,7 +495,7 @@ class BoostLearner : public rabit::Serializable {
int updater_mode;
// cached size of predict buffer
size_t pred_buffer_size;
// maximum buffred row value
// maximum buffered row value
float prob_buffer_row;
// evaluation set
EvalSet evaluator_;
@ -505,13 +505,13 @@ class BoostLearner : public rabit::Serializable {
gbm::IGradBooster *gbm_;
// name of gbm model used for training
std::string name_gbm_;
// objective fnction
// objective function
IObjFunction *obj_;
// name of objective function
std::string name_obj_;
// configurations
std::vector< std::pair<std::string, std::string> > cfg_;
// temporal storages for prediciton
// temporal storages for prediction
std::vector<float> preds_;
// gradient pairs
std::vector<bst_gpair> gpair_;
@ -527,7 +527,7 @@ class BoostLearner : public rabit::Serializable {
CacheEntry(const DMatrix *mat, size_t buffer_offset, size_t num_row)
:mat_(mat), buffer_offset_(buffer_offset), num_row_(num_row) {}
};
// find internal bufer offset for certain matrix, if not exist, return -1
// find internal buffer offset for certain matrix, if not exist, return -1
inline int64_t FindBufferOffset(const DMatrix &mat) const {
for (size_t i = 0; i < cache_.size(); ++i) {
if (cache_[i].mat_ == &mat && mat.cache_learner_ptr_ == this) {

2
src/learner/objective-inl.hpp
View File

@ -84,7 +84,7 @@ struct LossType {
* \return second order gradient
*/
inline float SecondOrderGradient(float predt, float label) const {
// cap second order gradient to postive value
// cap second order gradient to positive value
const float eps = 1e-16f;
switch (loss_type) {
case kLinearSquare: return 1.0f;

2
src/learner/objective.h
View File

@ -68,7 +68,7 @@ class IObjFunction{
// factory function
namespace xgboost {
namespace learner {
/*! \brief factory funciton to create objective function by name */
/*! \brief factory function to create objective function by name */
inline IObjFunction* CreateObjFunction(const char *name) {
using namespace std;
if (!strcmp("reg:linear", name)) return new RegLossObj(LossType::kLinearSquare);

20
src/tree/model.h
View File

@ -321,9 +321,9 @@ class TreeModel {
*/
inline void SaveModel(utils::IStream &fo) const { // NOLINT(*)
utils::Assert(param.num_nodes == static_cast<int>(nodes.size()),
"Tree::SaveModel");
"TreeModel::SaveModel");
utils::Assert(param.num_nodes == static_cast<int>(stats.size()),
"Tree::SaveModel");
"TreeModel::SaveModel");
fo.Write(&param, sizeof(Param));
utils::Assert(param.num_nodes != 0, "invalid model");
fo.Write(BeginPtr(nodes), sizeof(Node) * nodes.size());
@ -462,7 +462,7 @@ class TreeModel {
/*! \brief node statistics used in regression tree */
struct RTreeNodeStat {
/*! \brief loss chg caused by current split */
/*! \brief loss change caused by current split */
float loss_chg;
/*! \brief sum of hessian values, used to measure coverage of data */
float sum_hess;
@ -485,7 +485,7 @@ class RegTree: public TreeModel<bst_float, RTreeNodeStat>{
public:
/*!
* \brief dense feature vector that can be taken by RegTree
* to do tranverse efficiently
* to do traverse efficiently
* and can be construct from sparse feature vector
*/
struct FVec {
@ -498,7 +498,7 @@ class RegTree: public TreeModel<bst_float, RTreeNodeStat>{
int flag;
};
std::vector<Entry> data;
/*! \brief intialize the vector with size vector */
/*! \brief initialize the vector with size vector */
inline void Init(size_t size) {
Entry e; e.flag = -1;
data.resize(size);
@ -529,14 +529,14 @@ class RegTree: public TreeModel<bst_float, RTreeNodeStat>{
};
/*!
* \brief get the leaf index
* \param feats dense feature vector, if the feature is missing the field is set to NaN
* \param root_gid starting root index of the instance
* \param feat dense feature vector, if the feature is missing the field is set to NaN
* \param root_id starting root index of the instance
* \return the leaf index of the given feature
*/
inline int GetLeafIndex(const FVec&feat, unsigned root_id = 0) const {
inline int GetLeafIndex(const FVec &feat, unsigned root_id = 0) const {
// start from groups that belongs to current data
int pid = static_cast<int>(root_id);
// tranverse tree
// traverse tree
while (!(*this)[ pid ].is_leaf()) {
unsigned split_index = (*this)[pid].split_index();
pid = this->GetNext(pid, feat.fvalue(split_index), feat.is_missing(split_index));
@ -546,7 +546,7 @@ class RegTree: public TreeModel<bst_float, RTreeNodeStat>{
/*!
* \brief get the prediction of regression tree, only accepts dense feature vector
* \param feats dense feature vector, if the feature is missing the field is set to NaN
* \param root_gid starting root index of the instance
* \param root_id starting root index of the instance
* \return the leaf index of the given feature
*/
inline float Predict(const FVec &feat, unsigned root_id = 0) const {

22
src/tree/param.h
View File

@ -32,7 +32,7 @@ struct TrainParam{
// default direction choice
int default_direction;
// maximum delta update we can add in weight estimation
// this parameter can be used to stablize update
// this parameter can be used to stabilize update
// default=0 means no constraint on weight delta
float max_delta_step;
// whether we want to do subsample
@ -51,7 +51,7 @@ struct TrainParam{
int size_leaf_vector;
// option for parallelization
int parallel_option;
// option to open cacheline optimizaton
// option to open cacheline optimization
int cache_opt;
// number of threads to be used for tree construction,
// if OpenMP is enabled, if equals 0, use system default
@ -132,7 +132,7 @@ struct TrainParam{
}
}
}
// calculate cost of loss function with four stati
// calculate cost of loss function with four statistics
inline double CalcGain(double sum_grad, double sum_hess,
double test_grad, double test_hess) const {
double w = CalcWeight(sum_grad, sum_hess);
@ -167,7 +167,7 @@ struct TrainParam{
inline bool need_backward_search(float col_density, bool indicator) const {
return this->default_direction != 2;
}
/*! \brief given the loss change, whether we need to invode prunning */
/*! \brief given the loss change, whether we need to invoke pruning */
inline bool need_prune(double loss_chg, int depth) const {
return loss_chg < this->min_split_loss;
}
@ -235,7 +235,7 @@ struct GradStats {
const bst_gpair &b = gpair[ridx];
this->Add(b.grad, b.hess);
}
/*! \brief caculate leaf weight */
/*! \brief calculate leaf weight */
inline double CalcWeight(const TrainParam &param) const {
return param.CalcWeight(sum_grad, sum_hess);
}
@ -362,10 +362,10 @@ struct SplitEntry{
/*! \brief constructor */
SplitEntry(void) : loss_chg(0.0f), sindex(0), split_value(0.0f) {}
/*!
* \brief decides whether a we can replace current entry with the statistics given
* This function gives better priority to lower index when loss_chg equals
* not the best way, but helps to give consistent result during multi-thread execution
* \param loss_chg the loss reduction get through the split
* \brief decides whether we can replace current entry with the given statistics
* This function gives better priority to lower index when loss_chg == new_loss_chg.
* Not the best way, but helps to give consistent result during multi-thread execution.
* \param new_loss_chg the loss reduction get through the split
* \param split_index the feature index where the split is on
*/
inline bool NeedReplace(bst_float new_loss_chg, unsigned split_index) const {
@ -392,9 +392,9 @@ struct SplitEntry{
}
/*!
* \brief update the split entry, replace it if e is better
* \param loss_chg loss reduction of new candidate
* \param new_loss_chg loss reduction of new candidate
* \param split_index feature index to split on
* \param split_value the split point
* \param new_split_value the split point
* \param default_left whether the missing value goes to left
* \return whether the proposed split is better and can replace current split
*/

6
src/tree/updater.h
View File

@ -26,11 +26,11 @@ class IUpdater {
*/
virtual void SetParam(const char *name, const char *val) = 0;
/*!
* \brief peform update to the tree models
* \brief perform update to the tree models
* \param gpair the gradient pair statistics of the data
* \param p_fmat feature matrix that provide access to features
* \param info extra side information that may be need, such as root index
* \param trees pointer to the trees to be updated, upater will change the content of the tree
* \param trees references the trees to be updated, updater will change the content of trees
* note: all the trees in the vector are updated, with the same statistics,
* but maybe different random seeds, usually one tree is passed in at a time,
* there can be multiple trees when we train random forest style model
@ -53,7 +53,7 @@ class IUpdater {
virtual ~IUpdater(void) {}
};
/*!
* \brief create a updater based on name
* \brief create an updater based on name
* \param name name of updater
* \return return the updater instance
*/

2
src/tree/updater_colmaker-inl.hpp
View File

@ -17,7 +17,7 @@
namespace xgboost {
namespace tree {
/*! \brief colunwise update to construct a tree */
/*! \brief column-wise update to construct a tree */
template<typename TStats>
class ColMaker: public IUpdater {
public:

6
src/tree/updater_prune-inl.hpp
View File

@ -14,7 +14,7 @@
namespace xgboost {
namespace tree {
/*! \brief pruner that prunes a tree after growing finishs */
/*! \brief pruner that prunes a tree after growing finishes */
class TreePruner: public IUpdater {
public:
virtual ~TreePruner(void) {}
@ -56,7 +56,7 @@ class TreePruner: public IUpdater {
return npruned;
}
}
/*! \brief do prunning of a tree */
/*! \brief do pruning of a tree */
inline void DoPrune(RegTree &tree) { // NOLINT(*)
int npruned = 0;
// initialize auxiliary statistics
@ -69,7 +69,7 @@ class TreePruner: public IUpdater {
}
}
if (silent == 0) {
utils::Printf("tree prunning end, %d roots, %d extra nodes, %d pruned nodes ,max_depth=%d\n",
utils::Printf("tree pruning end, %d roots, %d extra nodes, %d pruned nodes ,max_depth=%d\n",
tree.param.num_roots, tree.num_extra_nodes(), npruned, tree.MaxDepth());
}
}

4
src/utils/base64-inl.h
View File

@ -91,7 +91,7 @@ class Base64InStream: public IStream {
* call this function before actually start read
*/
inline void InitPosition(void) {
// get a charater
// get a character
do {
tmp_ch = reader_.GetChar();
} while (isspace(tmp_ch));
@ -223,7 +223,7 @@ class Base64OutStream: public IStream {
}
/*!
* \brief finish writing of all current base64 stream, do some post processing
* \param endch charater to put to end of stream, if it is EOF, then nothing will be done
* \param endch character to put to end of stream, if it is EOF, then nothing will be done
*/
inline void Finish(char endch = EOF) {
using base64::EncodeTable;

2
src/utils/fmap.h
View File

@ -58,7 +58,7 @@ class FeatMap {
}
/*! \brief return type of specific feature */
const Type& type(size_t idx) const {
utils::Assert(idx < names_.size(), "utils::FMap::name feature index exceed bound");
utils::Assert(idx < names_.size(), "utils::FMap::type feature index exceed bound");
return types_[idx];
}

2
src/utils/iterator.h
View File

@ -23,7 +23,7 @@ class IIterator {
* \param val value of parameter
*/
virtual void SetParam(const char *name, const char *val) {}
/*! \brief initalize the iterator so that we can use the iterator */
/*! \brief initialize the iterator so that we can use the iterator */
virtual void Init(void) {}
/*! \brief set before first of the item */
virtual void BeforeFirst(void) = 0;

14
src/utils/quantile.h
View File

@ -214,7 +214,7 @@ struct WQSummary {
/*!
* \brief set current summary to be merged summary of sa and sb
* \param sa first input summary to be merged
* \param sb second input summar to be merged
* \param sb second input summary to be merged
*/
inline void SetCombine(const WQSummary &sa,
const WQSummary &sb) {
@ -329,7 +329,7 @@ struct WQSummary {
}
};
/*! \brief try to do efficient prunning */
/*! \brief try to do efficient pruning */
template<typename DType, typename RType>
struct WXQSummary : public WQSummary<DType, RType> {
// redefine entry type
@ -364,7 +364,7 @@ struct WXQSummary : public WQSummary<DType, RType> {
RType mrange = 0;
{
// first scan, grab all the big chunk
// moviing block index
// moving block index
size_t bid = 0;
for (size_t i = 1; i < src.size; ++i) {
if (CheckLarge(src.data[i], chunk)) {
@ -574,7 +574,7 @@ struct GKSummary {
};
/*!
* \brief template for all quantle sketch algorithm
* \brief template for all quantile sketch algorithm
* that uses merge/prune scheme
* \tparam DType type of data content
* \tparam RType type of rank
@ -605,7 +605,7 @@ class QuantileSketchTemplate {
}
/*!
* \brief set the space to be merge of all Summary arrays
* \param begin begining position in th summary array
* \param begin beginning position in the summary array
* \param end ending position in the Summary array
*/
inline void SetMerge(const Summary *begin,
@ -664,7 +664,7 @@ class QuantileSketchTemplate {
}
};
/*!
* \brief intialize the quantile sketch, given the performance specification
* \brief initialize the quantile sketch, given the performance specification
* \param maxn maximum number of data points can be feed into sketch
* \param eps accuracy level of summary
*/
@ -688,7 +688,7 @@ class QuantileSketchTemplate {
}
/*!
* \brief add an element to a sketch
* \param x the elemented added to the sketch
* \param x the element added to the sketch
*/
inline void Push(DType x, RType w = 1) {
if (w == static_cast<RType>(0)) return;

2
src/utils/random.h
View File

@ -27,7 +27,7 @@ inline void Seed(unsigned seed) {
inline double Uniform(void) {
return static_cast<double>(rand()) / (static_cast<double>(RAND_MAX)+1.0); // NOLINT(*)
}
/*! \brief return a real numer uniform in (0,1) */
/*! \brief return a real number uniform in (0,1) */
inline double NextDouble2(void) {
return (static_cast<double>(rand()) + 1.0) / (static_cast<double>(RAND_MAX)+2.0); // NOLINT(*)
}

8
src/utils/thread_buffer.h
View File

@ -21,8 +21,8 @@ namespace utils {
#if !defined(XGBOOST_STRICT_CXX98_)
/*!
* \brief buffered loading iterator that uses multithread
* this template method will assume the following paramters
* \tparam Elem elememt type to be buffered
* this template method will assume the following parameters
* \tparam Elem element type to be buffered
* \tparam ElemFactory factory type to implement in order to use thread buffer
*/
template<typename Elem, typename ElemFactory>
@ -45,7 +45,7 @@ class ThreadBuffer {
/*!
* \brief initalize the buffered iterator
* \param param a initialize parameter that will pass to factory, ignore it if not necessary
* \return false if the initlization can't be done, e.g. buffer file hasn't been created
* \return false if the initialization can't be done, e.g. buffer file hasn't been created
*/
inline bool Init(void) {
if (!factory.Init()) return false;
@ -61,7 +61,7 @@ class ThreadBuffer {
inline void BeforeFirst(void) {
// wait till last loader end
loading_end.Wait();
// critcal zone
// critical zone
current_buf = 1;
factory.BeforeFirst();
// reset terminate limit

6
src/utils/utils.h
View File

@ -62,7 +62,7 @@ const int kPrintBuffer = 1 << 12;
#ifndef XGBOOST_CUSTOMIZE_MSG_
/*!
* \brief handling of Assert error, caused by in-apropriate input
* \brief handling of Assert error, caused by inappropriate input
* \param msg error message
*/
inline void HandleAssertError(const char *msg) {
@ -70,7 +70,7 @@ inline void HandleAssertError(const char *msg) {
exit(-1);
}
/*!
* \brief handling of Check error, caused by in-apropriate input
* \brief handling of Check error, caused by inappropriate input
* \param msg error message
*/
inline void HandleCheckError(const char *msg) {
@ -157,7 +157,7 @@ inline std::FILE *FopenCheck(const char *fname, const char *flag) {
return fp;
}
} // namespace utils
// easy utils that can be directly acessed in xgboost
// easy utils that can be directly accessed in xgboost
/*! \brief get the beginning address of a vector */
template<typename T>
inline T *BeginPtr(std::vector<T> &vec) { // NOLINT(*)