[docs] fixed miscellaneous typos in comments and documentation (#2496)

* fixed miscellaneous typos in documentation

* fix typo introduced in typo-fixing PR

R-package/R/callback.R

@@ -269,7 +269,7 @@ cb.early.stop <- function(stopping_rounds, verbose = TRUE) {
   best_msg <- NULL
   eval_len <- NULL
 
-  # Initalization function
+  # Initialization function
   init <- function(env) {
 
     # Store evaluation length

R-package/R/lgb.Dataset.R

@@ -855,7 +855,7 @@ dimnames.lgb.Dataset <- function(x) {
 #' original \code{lgb.Dataset} object
 #'
 #' @param dataset Object of class \code{lgb.Dataset}
-#' @param idxset a integer vector of indices of rows needed
+#' @param idxset an integer vector of indices of rows needed
 #' @param ... other parameters (currently not used)
 #' @return constructed sub dataset
 #'

R-package/R/lgb.interprete.R

@@ -4,7 +4,7 @@
 #'
 #' @param model object of class \code{lgb.Booster}.
 #' @param data a matrix object or a dgCMatrix object.
-#' @param idxset a integer vector of indices of rows needed.
+#' @param idxset an integer vector of indices of rows needed.
 #' @param num_iteration number of iteration want to predict with, NULL or <= 0 means use best iteration.
 #'
 #' @return

R-package/R/lightgbm.R

@@ -20,7 +20,7 @@ NULL
 
 #' @title Train a LightGBM model
 #' @name lightgbm
-#' @description Simple interface for training an LightGBM model.
+#' @description Simple interface for training a LightGBM model.
 #' @inheritParams lgb_shared_params
 #' @param label Vector of labels, used if \code{data} is not an \code{\link{lgb.Dataset}}
 #' @param weight vector of response values. If not NULL, will set to dataset

R-package/demo/boost_from_prediction.R

@@ -9,8 +9,8 @@ dtest <- lgb.Dataset.create.valid(dtrain, data = agaricus.test$data, label = aga
 
 valids <- list(eval = dtest, train = dtrain)
 #--------------------Advanced features ---------------------------
-# advanced: start from a initial base prediction
-print("Start running example to start from a initial prediction")
+# advanced: start from an initial base prediction
+print("Start running example to start from an initial prediction")
 
 # Train lightgbm for 1 round
 param <- list(num_leaves = 4,

R-package/man/lgb.interprete.Rd

@@ -11,7 +11,7 @@ lgb.interprete(model, data, idxset, num_iteration = NULL)
 
 \item{data}{a matrix object or a dgCMatrix object.}
 
-\item{idxset}{a integer vector of indices of rows needed.}
+\item{idxset}{an integer vector of indices of rows needed.}
 
 \item{num_iteration}{number of iteration want to predict with, NULL or <= 0 means use best iteration.}
 }

R-package/man/lightgbm.Rd

@@ -60,5 +60,5 @@ List of callback functions that are applied at each iteration.}
 }}
 }
 \description{
-Simple interface for training an LightGBM model.
+Simple interface for training a LightGBM model.
 }

R-package/man/slice.Rd

@@ -14,7 +14,7 @@ slice(dataset, ...)
 
 \item{...}{other parameters (currently not used)}
 
-\item{idxset}{a integer vector of indices of rows needed}
+\item{idxset}{an integer vector of indices of rows needed}
 }
 \value{
 constructed sub dataset

docs/GPU-Tutorial.rst

@@ -33,7 +33,7 @@ After installing the drivers you need to restart the server.
 
 After about 30 seconds, the server should be up again.
 
-If you are using a AMD GPU, you should download and install the `AMDGPU-Pro`_ driver and also install package ``ocl-icd-libopencl1`` and ``ocl-icd-opencl-dev``.
+If you are using an AMD GPU, you should download and install the `AMDGPU-Pro`_ driver and also install package ``ocl-icd-libopencl1`` and ``ocl-icd-opencl-dev``.
 
 Build LightGBM
 --------------

docs/Parameters.rst

@@ -370,7 +370,7 @@ Learning Control Parameters
 
    -  used for the categorical features
 
-   -  L2 regularization in categorcial split
+   -  L2 regularization in categorical split
 
 -  ``cat_smooth`` :raw-html:`<a id="cat_smooth" title="Permalink to this parameter" href="#cat_smooth">&#x1F517;&#xFE0E;</a>`, default = ``10.0``, type = double, constraints: ``cat_smooth >= 0.0``
 

include/LightGBM/application.h

@@ -33,7 +33,7 @@ class Application {
   /*! \brief Destructor */
   ~Application();
 
-  /*! \brief To call this funciton to run application*/
+  /*! \brief To call this function to run application*/
   inline void Run();
 
  private:

include/LightGBM/bin.h

@@ -122,7 +122,7 @@ class BinMapper {
   */
   size_t SizesInByte() const;
   /*!
-  * \brief Mapping feature value into bin 
+  * \brief Mapping feature value into bin
   * \param value
   * \return bin for this feature value
   */
@@ -137,7 +137,7 @@ class BinMapper {
   }
   /*!
   * \brief Construct feature value to bin mapper according feature values
-  * \param values (Sampled) values of this feature, Note: not include zero. 
+  * \param values (Sampled) values of this feature, Note: not include zero.
   * \param num_values number of values.
   * \param total_sample_cnt number of total sample count, equal with values.size() + num_zeros
   * \param max_bin The maximal number of bin
@@ -159,13 +159,13 @@ class BinMapper {
   static int SizeForSpecificBin(int bin);
 
   /*!
-  * \brief Seirilizing this object to buffer
+  * \brief Serializing this object to buffer
   * \param buffer The destination
   */
   void CopyTo(char* buffer) const;
 
   /*!
-  * \brief Deserilizing this object from buffer
+  * \brief Deserializing this object from buffer
   * \param buffer The source
   */
   void CopyFrom(const char* buffer);
@@ -205,7 +205,7 @@ class BinMapper {
   std::unordered_map<int, unsigned int> categorical_2_bin_;
   /*! \brief Mapper from bin to categorical */
   std::vector<int> bin_2_categorical_;
-  /*! \brief minimal feature vaule */
+  /*! \brief minimal feature value */
   double min_val_;
   /*! \brief maximum feature value */
   double max_val_;
@@ -217,7 +217,7 @@ class BinMapper {
 * \brief Interface for ordered bin data. efficient for construct histogram, especially for sparse bin
 *        There are 2 advantages by using ordered bin.
 *        1. group the data by leafs to improve the cache hit.
-*        2. only store the non-zero bin, which can speed up the histogram consturction for sparse features.
+*        2. only store the non-zero bin, which can speed up the histogram construction for sparse features.
 *        However it brings additional cost: it need re-order the bins after every split, which will cost much for dense feature.
 *        So we only using ordered bin for sparse situations.
 */
@@ -239,8 +239,8 @@ class OrderedBin {
   *        Note: Unlike Bin, OrderedBin doesn't use ordered gradients and ordered hessians.
   *        Because it is hard to know the relative index in one leaf for sparse bin, since we skipped zero bins.
   * \param leaf Using which leaf's data to construct
-  * \param gradients Gradients, Note:non-oredered by leaf
-  * \param hessians Hessians, Note:non-oredered by leaf
+  * \param gradients Gradients, Note:non-ordered by leaf
+  * \param hessians Hessians, Note:non-ordered by leaf
   * \param out Output Result
   */
   virtual void ConstructHistogram(int leaf, const score_t* gradients,
@@ -251,7 +251,7 @@ class OrderedBin {
   *        Note: Unlike Bin, OrderedBin doesn't use ordered gradients and ordered hessians.
   *        Because it is hard to know the relative index in one leaf for sparse bin, since we skipped zero bins.
   * \param leaf Using which leaf's data to construct
-  * \param gradients Gradients, Note:non-oredered by leaf
+  * \param gradients Gradients, Note:non-ordered by leaf
   * \param out Output Result
   */
   virtual void ConstructHistogram(int leaf, const score_t* gradients, HistogramBinEntry* out) const = 0;
@@ -379,7 +379,7 @@ class Bin {
   * \brief Split data according to threshold, if bin <= threshold, will put into left(lte_indices), else put into right(gt_indices)
   * \param min_bin min_bin of current used feature
   * \param max_bin max_bin of current used feature
-  * \param default_bin defualt bin if bin not in [min_bin, max_bin]
+  * \param default_bin default bin if bin not in [min_bin, max_bin]
   * \param missing_type missing type
   * \param default_left missing bin will go to left child
   * \param threshold The split threshold.
@@ -398,7 +398,7 @@ class Bin {
   * \brief Split data according to threshold, if bin <= threshold, will put into left(lte_indices), else put into right(gt_indices)
   * \param min_bin min_bin of current used feature
   * \param max_bin max_bin of current used feature
-  * \param default_bin defualt bin if bin not in [min_bin, max_bin]
+  * \param default_bin default bin if bin not in [min_bin, max_bin]
   * \param threshold The split threshold.
   * \param num_threshold Number of threshold
   * \param data_indices Used data indices. After called this function. The less than or equal data indices will store on this object.

include/LightGBM/c_api.h

@@ -832,7 +832,7 @@ LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMat(BoosterHandle handle,
                                                 double* out_result);
 
 /*!
- * \brief Make prediction for an new dataset. This method re-uses the internal predictor structure
+ * \brief Make prediction for a new dataset. This method re-uses the internal predictor structure
  *        from previous calls and is optimized for single row invocation.
  * \note
  * You should pre-allocate memory for ``out_result``:

include/LightGBM/config.h

@@ -371,7 +371,7 @@ struct Config {
 
   // check = >=0.0
   // desc = used for the categorical features
-  // desc = L2 regularization in categorcial split
+  // desc = L2 regularization in categorical split
   double cat_l2 = 10.0;
 
   // check = >=0.0

include/LightGBM/dataset.h

@@ -27,25 +27,25 @@ namespace LightGBM {
 class DatasetLoader;
 /*!
 * \brief This class is used to store some meta(non-feature) data for training data,
-*        e.g. labels, weights, initial scores, qurey level informations.
+*        e.g. labels, weights, initial scores, query level informations.
 *
 *        Some details:
-*        1. Label, used for traning.
+*        1. Label, used for training.
 *        2. Weights, weighs of records, optional
 *        3. Query Boundaries, necessary for lambdarank.
-*           The documents of i-th query is in [ query_boundarise[i], query_boundarise[i+1] )
-*        4. Query Weights, auto calculate by weights and query_boundarise(if both of them are existed)
-*           the weight for i-th query is sum(query_boundarise[i] , .., query_boundarise[i+1]) / (query_boundarise[i + 1] -  query_boundarise[i+1])
-*        5. Initial score. optional. if exsitng, the model will boost from this score, otherwise will start from 0.
+*           The documents of i-th query is in [ query_boundaries[i], query_boundaries[i+1] )
+*        4. Query Weights, auto calculate by weights and query_boundaries(if both of them are existed)
+*           the weight for i-th query is sum(query_boundaries[i] , .., query_boundaries[i+1]) / (query_boundaries[i + 1] -  query_boundaries[i+1])
+*        5. Initial score. optional. if existing, the model will boost from this score, otherwise will start from 0.
 */
 class Metadata {
  public:
   /*!
-  * \brief Null costructor
+  * \brief Null constructor
   */
   Metadata();
   /*!
-  * \brief Initialization will load qurey level informations, since it is need for sampling data
+  * \brief Initialization will load query level informations, since it is need for sampling data
   * \param data_filename Filename of data
   * \param init_score_filename Filename of initial score
   */
@@ -75,7 +75,7 @@ class Metadata {
 
   /*!
   * \brief Partition label by used indices
-  * \param used_indices Indice of local used
+  * \param used_indices Indices of local used
   */
   void PartitionLabel(const std::vector<data_size_t>& used_indices);
 
@@ -268,7 +268,7 @@ class Parser {
   virtual int NumFeatures() const = 0;
 
   /*!
-  * \brief Create a object of parser, will auto choose the format depend on file
+  * \brief Create an object of parser, will auto choose the format depend on file
   * \param filename One Filename of data
   * \param num_features Pass num_features of this data file if you know, <=0 means don't know
   * \param label_idx index of label column
@@ -278,7 +278,7 @@ class Parser {
 };
 
 /*! \brief The main class of data set,
-*          which are used to traning or validation
+*          which are used to training or validation
 */
 class Dataset {
  public:

include/LightGBM/lightgbm_R.h

@@ -13,9 +13,9 @@
 /*!
 * \brief get string message of the last error
 *  all functions in this file will return 0 on success
-*  and -1 when an error occured
-* \return err_msg error inforomation
-* \return error inforomation
+*  and -1 when an error occurred
+* \return err_msg error information
+* \return error information
 */
 LIGHTGBM_C_EXPORT LGBM_SE LGBM_GetLastError_R(LGBM_SE buf_len, LGBM_SE actual_len, LGBM_SE err_msg);
 
@@ -117,7 +117,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_DatasetGetFeatureNames_R(LGBM_SE handle,
   LGBM_SE call_state);
 
 /*!
-* \brief save dateset to binary file
+* \brief save dataset to binary file
 * \param handle an instance of dataset
 * \param filename file name
 * \return 0 when succeed, -1 when failure happens
@@ -176,7 +176,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_DatasetGetField_R(LGBM_SE handle,
 
 /*!
 * \brief Update parameters for a Dataset
-* \param handle a instance of data matrix
+* \param handle an instance of data matrix
 * \param parameters parameters
 * \return 0 when succeed, -1 when failure happens
 */
@@ -207,10 +207,10 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_DatasetGetNumFeature_R(LGBM_SE handle,
 // --- start Booster interfaces
 
 /*!
-* \brief create an new boosting learner
+* \brief create a new boosting learner
 * \param train_data training data set
 * \param parameters format: 'key1=value1 key2=value2'
-* \prama out handle of created Booster
+* \param out handle of created Booster
 * \return 0 when succeed, -1 when failure happens
 */
 LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterCreate_R(LGBM_SE train_data,
@@ -229,7 +229,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterFree_R(LGBM_SE handle,
 /*!
 * \brief load an existing boosting from model file
 * \param filename filename of model
-* \prama out handle of created Booster
+* \param out handle of created Booster
 * \return 0 when succeed, -1 when failure happens
 */
 LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterCreateFromModelfile_R(LGBM_SE filename,
@@ -351,7 +351,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterGetEvalNames_R(LGBM_SE handle,
 * \brief get evaluation for training data and validation data
 * \param handle handle
 * \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
-* \param out_result float arrary contains result
+* \param out_result float array contains result
 * \return 0 when succeed, -1 when failure happens
 */
 LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterGetEval_R(LGBM_SE handle,
@@ -413,7 +413,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterPredictForFile_R(LGBM_SE handle,
 * \param is_rawscore
 * \param is_leafidx
 * \param num_iteration number of iteration for prediction, <= 0 means no limit
-* \param out_len lenght of prediction
+* \param out_len length of prediction
 * \return 0 when succeed, -1 when failure happens
 */
 LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterCalcNumPredict_R(LGBM_SE handle,
@@ -426,7 +426,7 @@ LIGHTGBM_C_EXPORT LGBM_SE LGBM_BoosterCalcNumPredict_R(LGBM_SE handle,
   LGBM_SE call_state);
 
 /*!
-* \brief make prediction for an new data set
+* \brief make prediction for a new data set
 *        Note:  should pre-allocate memory for out_result,
 *               for normal and raw score: its length is equal to num_class * num_data
 *               for leaf index, its length is equal to num_class * num_data * num_iteration

include/LightGBM/meta.h

@@ -17,10 +17,10 @@ namespace LightGBM {
 /*! \brief Type of data size, it is better to use signed type*/
 typedef int32_t data_size_t;
 
-// Enable following marco to use double for score_t
+// Enable following macro to use double for score_t
 // #define SCORE_T_USE_DOUBLE
 
-// Enable following marco to use double for label_t
+// Enable following macro to use double for label_t
 // #define LABEL_T_USE_DOUBLE
 
 /*! \brief Type of score, and gradients */

include/LightGBM/metric.h

@@ -38,7 +38,7 @@ class Metric {
 
   virtual double factor_to_bigger_better() const = 0;
   /*!
-  * \brief Calcaluting and printing metric result
+  * \brief Calculating and printing metric result
   * \param score Current prediction score
   */
   virtual std::vector<double> Eval(const double* score, const ObjectiveFunction* objective) const = 0;

include/LightGBM/network.h

@@ -23,7 +23,7 @@ class BruckMap {
  public:
   /*! \brief The communication times for one all gather operation */
   int k;
-  /*! \brief in_ranks[i] means the incomming rank on i-th communication */
+  /*! \brief in_ranks[i] means the incoming rank on i-th communication */
   std::vector<int> in_ranks;
   /*! \brief out_ranks[i] means the out rank on i-th communication */
   std::vector<int> out_ranks;
@@ -55,7 +55,7 @@ enum RecursiveHalvingNodeType {
 /*! \brief Network structure for recursive halving algorithm */
 class RecursiveHalvingMap {
  public:
-  /*! \brief Communication times for one recursize halving algorithm  */
+  /*! \brief Communication times for one recursive halving algorithm  */
   int k;
   /*! \brief Node type */
   RecursiveHalvingNodeType type;

include/LightGBM/tree.h

@@ -31,7 +31,7 @@ class Tree {
   explicit Tree(int max_leaves);
 
   /*!
-  * \brief Construtor, from a string
+  * \brief Constructor, from a string
   * \param str Model string
   * \param used_len used count of str
   */
@@ -103,7 +103,7 @@ class Tree {
                             double* score) const;
 
   /*!
-  * \brief Adding prediction value of this tree model to scorese
+  * \brief Adding prediction value of this tree model to scores
   * \param data The dataset
   * \param used_data_indices Indices of used data
   * \param num_data Number of total data
@@ -143,7 +143,7 @@ class Tree {
 
   /*!
   * \brief Shrinkage for the tree's output
-  *        shrinkage rate (a.k.a learning rate) is used to tune the traning process
+  *        shrinkage rate (a.k.a learning rate) is used to tune the training process
   * \param rate The factor of shrinkage
   */
   inline void Shrinkage(double rate) {
@@ -334,7 +334,7 @@ class Tree {
     double one_fraction;
 
     // note that pweight is included for convenience and is not tied with the other attributes,
-    // the pweight of the i'th path element is the permuation weight of paths with i-1 ones in them
+    // the pweight of the i'th path element is the permutation weight of paths with i-1 ones in them
     double pweight;
 
     PathElement() {}
@@ -354,12 +354,12 @@ class Tree {
   /*! \brief Undo a previous extension of the decision path for TreeSHAP*/
   static void UnwindPath(PathElement *unique_path, int unique_depth, int path_index);
 
-  /*! determine what the total permuation weight would be if we unwound a previous extension in the decision path*/
+  /*! determine what the total permutation weight would be if we unwound a previous extension in the decision path*/
   static double UnwoundPathSum(const PathElement *unique_path, int unique_depth, int path_index);
 
   /*! \brief Number of max leaves*/
   int max_leaves_;
-  /*! \brief Number of current levas*/
+  /*! \brief Number of current leaves*/
   int num_leaves_;
   // following values used for non-leaf node
   /*! \brief A non-leaf node's left child */
@@ -379,7 +379,7 @@ class Tree {
   std::vector<uint32_t> cat_threshold_inner_;
   std::vector<int> cat_boundaries_;
   std::vector<uint32_t> cat_threshold_;
-  /*! \brief Store the information for categorical feature handle and mising value handle. */
+  /*! \brief Store the information for categorical feature handle and missing value handle. */
   std::vector<int8_t> decision_type_;
   /*! \brief A non-leaf node's split gain */
   std::vector<float> split_gain_;