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
Download Patch File Download Diff File Expand all files Collapse all files

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);