[ci] Introduce `typos` pre-commit hook (#6564)

Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

docker/README.md

@@ -55,7 +55,7 @@ After this runs, a LightGBM model can be found at `LightGBM-CLI-model.txt`.
 
 For more details on how to configure and use the LightGBM CLI, see https://lightgbm.readthedocs.io/en/latest/Quick-Start.html.
 
-## Running the Python-package Сontainer
+## Running the Python-package Container
 
 Build an image with the LightGBM Python-package installed.
 
@@ -114,7 +114,7 @@ docker run \
     python
 ```
 
-## Running the R-package Сontainer
+## Running the R-package Container
 
 Build an image with the LightGBM R-package installed.
 

docs/Parameters.rst

@@ -35,7 +35,7 @@ For example, in Python:
 
 .. code-block:: python
 
-   # use learning rate of 0.07, becase 'learning_rate'
+   # use learning rate of 0.07, because 'learning_rate'
    # is the primary parameter name
    lgb.train(
       params={

docs/_static/js/script.js

@@ -17,7 +17,7 @@ $(() => {
         $(
             '<style>.closed, .opened {cursor: pointer;} .closed:before, .opened:before {font-family: FontAwesome; display: inline-block; padding-right: 6px;} .closed:before {content: "\\f078";} .opened:before {content: "\\f077";}</style>',
         ).appendTo("body");
-        const collapsable = [
+        const collapsible = [
             "#build-threadless-version-not-recommended",
             "#build-mpi-version",
             "#build-gpu-version",
@@ -25,7 +25,7 @@ $(() => {
             "#build-java-wrapper",
             "#build-c-unit-tests",
         ];
-        $.each(collapsable, (_, val) => {
+        $.each(collapsible, (_, val) => {
             const header = `${val} > :header:first`;
             const content = `${val} :not(:header:first)`;
             $(header).addClass("closed");

examples/lambdarank/train.conf

@@ -64,7 +64,7 @@ num_leaves = 31
 # alias: tree
 tree_learner = serial
 
-# number of threads for multi-threading. One thread will use one CPU, defalut is setted to #cpu.
+# number of threads for multi-threading. One thread will use one CPU, default is set to #cpu.
 # num_threads = 8
 
 # feature sub-sample, will random select 80% feature to train on each iteration

examples/regression/train.conf

@@ -20,7 +20,7 @@ objective = regression
 # binary_error
 metric = l2
 
-# frequence for metric output
+# frequency for metric output
 metric_freq = 1
 
 # true if need output metric for training data, alias: tranining_metric, train_metric
@@ -36,12 +36,12 @@ max_bin = 255
 # forcedbins_filename = forced_bins.json
 
 # training data
-# if exsting weight file, should name to "regression.train.weight"
+# if existing weight file, should name to "regression.train.weight"
 # alias: train_data, train
 data = regression.train
 
 # validation data, support multi validation data, separated by ','
-# if exsting weight file, should name to "regression.test.weight"
+# if existing weight file, should name to "regression.test.weight"
 # alias: valid, test, test_data,
 valid_data = regression.test
 
@@ -62,7 +62,7 @@ num_leaves = 31
 # alias: tree
 tree_learner = serial
 
-# number of threads for multi-threading. One thread will use one CPU, default is setted to #cpu.
+# number of threads for multi-threading. One thread will use one CPU, default is set to #cpu.
 # num_threads = 8
 
 # feature sub-sample, will random select 80% feature to train on each iteration
@@ -72,7 +72,7 @@ feature_fraction = 0.9
 # Support bagging (data sub-sample), will perform bagging every 5 iterations
 bagging_freq = 5
 
-# Bagging farction, will random select 80% data on bagging
+# Bagging fraction, will random select 80% data on bagging
 # alias: sub_row
 bagging_fraction = 0.8
 

include/LightGBM/cuda/cuda_algorithms.hpp

@@ -115,7 +115,7 @@ __device__ __forceinline__ T ShuffleReduceSumWarp(T value, const data_size_t len
   return value;
 }
 
-// reduce values from an 1-dimensional block (block size must be no greather than 1024)
+// reduce values from an 1-dimensional block (block size must be no greater than 1024)
 template <typename T>
 __device__ __forceinline__ T ShuffleReduceSum(T value, T* shared_mem_buffer, const size_t len) {
   const uint32_t warpLane = threadIdx.x % warpSize;
@@ -145,7 +145,7 @@ __device__ __forceinline__ T ShuffleReduceMaxWarp(T value, const data_size_t len
   return value;
 }
 
-// reduce values from an 1-dimensional block (block size must be no greather than 1024)
+// reduce values from an 1-dimensional block (block size must be no greater than 1024)
 template <typename T>
 __device__ __forceinline__ T ShuffleReduceMax(T value, T* shared_mem_buffer, const size_t len) {
   const uint32_t warpLane = threadIdx.x % warpSize;
@@ -196,7 +196,7 @@ __device__ __forceinline__ T ShuffleReduceMinWarp(T value, const data_size_t len
   return value;
 }
 
-// reduce values from an 1-dimensional block (block size must be no greather than 1024)
+// reduce values from an 1-dimensional block (block size must be no greater than 1024)
 template <typename T>
 __device__ __forceinline__ T ShuffleReduceMin(T value, T* shared_mem_buffer, const size_t len) {
   const uint32_t warpLane = threadIdx.x % warpSize;

include/LightGBM/dataset.h

@@ -376,7 +376,7 @@ class Metadata {
   std::vector<data_size_t> query_boundaries_;
   /*! \brief Query weights */
   std::vector<label_t> query_weights_;
-  /*! \brief Number of querys */
+  /*! \brief Number of queries */
   data_size_t num_queries_;
   /*! \brief Number of Initial score, used to check correct weight file */
   int64_t num_init_score_;

include/LightGBM/utils/common.h

@@ -925,11 +925,11 @@ class AlignmentAllocator {
 
   inline ~AlignmentAllocator() throw() {}
 
-  inline pointer adress(reference r) {
+  inline pointer address(reference r) {
     return &r;
   }
 
-  inline const_pointer adress(const_reference r) const {
+  inline const_pointer address(const_reference r) const {
     return &r;
   }
 

include/LightGBM/utils/random.h

@@ -22,9 +22,9 @@ class Random {
   */
   Random() {
     std::random_device rd;
-    auto genrator = std::mt19937(rd());
+    auto generator = std::mt19937(rd());
     std::uniform_int_distribution<int> distribution(0, x);
-    x = distribution(genrator);
+    x = distribution(generator);
   }
   /*!
   * \brief Constructor, with specific seed

python-package/lightgbm/basic.py

@@ -3525,7 +3525,7 @@ class Dataset:
             _log_warning(err_msg)
         self.feature_name = self.get_feature_name()
         _log_warning(
-            "Reseting categorical features.\n"
+            "Resetting categorical features.\n"
             "You can set new categorical features via ``set_categorical_feature`` method"
         )
         self.categorical_feature = "auto"

python-package/lightgbm/dask.py

@@ -967,7 +967,7 @@ def _predict(
                     out[i].append(part)
 
             # by default, dask.array.concatenate() concatenates sparse arrays into a COO matrix
-            # the code below is used instead to ensure that the sparse type is preserved during concatentation
+            # the code below is used instead to ensure that the sparse type is preserved during concatenation
             if isinstance(pred_meta, ss.csr_matrix):
                 concat_fn = partial(ss.vstack, format="csr")
             elif isinstance(pred_meta, ss.csc_matrix):

src/boosting/bagging.hpp

@@ -73,17 +73,17 @@ class BaggingSampleStrategy : public SampleStrategy {
           for (data_size_t i = start_index + 1; i < end_index; ++i) {
             sampled_query_boundaries_[i] += sampled_query_boundaries_[i - 1];
           }
-          sampled_query_boundaires_thread_buffer_[thread_index] = sampled_query_boundaries_[end_index - 1];
+          sampled_query_boundaries_thread_buffer_[thread_index] = sampled_query_boundaries_[end_index - 1];
          });
 
         for (int thread_index = 1; thread_index < num_blocks; ++thread_index) {
-          sampled_query_boundaires_thread_buffer_[thread_index] += sampled_query_boundaires_thread_buffer_[thread_index - 1];
+          sampled_query_boundaries_thread_buffer_[thread_index] += sampled_query_boundaries_thread_buffer_[thread_index - 1];
         }
 
         Threading::For<data_size_t>(0, num_sampled_queries_ + 1, 128, [this](int thread_index, data_size_t start_index, data_size_t end_index) {
           if (thread_index > 0) {
             for (data_size_t i = start_index; i < end_index; ++i) {
-              sampled_query_boundaries_[i] += sampled_query_boundaires_thread_buffer_[thread_index - 1];
+              sampled_query_boundaries_[i] += sampled_query_boundaries_thread_buffer_[thread_index - 1];
             }
           }
         });
@@ -171,7 +171,7 @@ class BaggingSampleStrategy : public SampleStrategy {
       } else {
         bagging_runner_.ReSize(num_queries_);
         sampled_query_boundaries_.resize(num_queries_ + 1, 0);
-        sampled_query_boundaires_thread_buffer_.resize(num_threads_, 0);
+        sampled_query_boundaries_thread_buffer_.resize(num_threads_, 0);
         bag_query_indices_.resize(num_data_);
       }
       bagging_rands_.clear();
@@ -280,7 +280,7 @@ class BaggingSampleStrategy : public SampleStrategy {
   /*! \brief query boundaries of the in-bag queries */
   std::vector<data_size_t> sampled_query_boundaries_;
   /*! \brief buffer for calculating sampled_query_boundaries_ */
-  std::vector<data_size_t> sampled_query_boundaires_thread_buffer_;
+  std::vector<data_size_t> sampled_query_boundaries_thread_buffer_;
   /*! \brief in-bag query indices */
   std::vector<data_size_t, Common::AlignmentAllocator<data_size_t, kAlignedSize>> bag_query_indices_;
   /*! \brief number of queries in the training dataset */

src/boosting/gbdt_model_text.cpp

@@ -545,17 +545,17 @@ bool GBDT::LoadModelFromString(const char* buffer, size_t len) {
     }
   } else {
     std::vector<size_t> tree_sizes = CommonC::StringToArray<size_t>(key_vals["tree_sizes"].c_str(), ' ');
-    std::vector<size_t> tree_boundries(tree_sizes.size() + 1, 0);
+    std::vector<size_t> tree_boundaries(tree_sizes.size() + 1, 0);
     int num_trees = static_cast<int>(tree_sizes.size());
     for (int i = 0; i < num_trees; ++i) {
-      tree_boundries[i + 1] = tree_boundries[i] + tree_sizes[i];
+      tree_boundaries[i + 1] = tree_boundaries[i] + tree_sizes[i];
       models_.emplace_back(nullptr);
     }
     OMP_INIT_EX();
     #pragma omp parallel for num_threads(OMP_NUM_THREADS()) schedule(static)
     for (int i = 0; i < num_trees; ++i) {
       OMP_LOOP_EX_BEGIN();
-      auto cur_p = p + tree_boundries[i];
+      auto cur_p = p + tree_boundaries[i];
       auto line_len = Common::GetLine(cur_p);
       std::string cur_line(cur_p, line_len);
       if (Common::StartsWith(cur_line, "Tree=")) {

src/io/metadata.cpp

@@ -225,7 +225,7 @@ void Metadata::CheckOrPartition(data_size_t num_all_data, const std::vector<data
       num_positions_ = 0;
     }
 
-    // check query boundries
+    // check query boundaries
     if (!query_boundaries_.empty() && query_boundaries_[num_queries_] != num_data_) {
       query_boundaries_.clear();
       num_queries_ = 0;
@@ -282,7 +282,7 @@ void Metadata::CheckOrPartition(data_size_t num_all_data, const std::vector<data
       }
     }
     if (query_load_from_file_) {
-      // check query boundries
+      // check query boundaries
       if (!query_boundaries_.empty() && query_boundaries_[num_queries_] != num_all_data) {
         query_boundaries_.clear();
         num_queries_ = 0;
@@ -584,7 +584,7 @@ void Metadata::SetPosition(const data_size_t* positions, data_size_t len) {
   if (positions_.empty()) {
     positions_.resize(num_data_);
   } else {
-    Log::Warning("Overwritting positions in dataset.");
+    Log::Warning("Overwriting positions in dataset.");
   }
   num_positions_ = num_data_;
 

src/network/linker_topo.cpp

@@ -35,10 +35,10 @@ BruckMap BruckMap::Construct(int rank, int num_machines) {
   }
   BruckMap bruckMap(k);
   for (int j = 0; j < k; ++j) {
-    // set incoming rank at k-th commuication
+    // set incoming rank at k-th communication
     const int in_rank = (rank + distance[j]) % num_machines;
     bruckMap.in_ranks[j] = in_rank;
-    // set outgoing rank at k-th commuication
+    // set outgoing rank at k-th communication
     const int out_rank = (rank - distance[j] + num_machines) % num_machines;
     bruckMap.out_ranks[j] = out_rank;
   }

src/objective/rank_objective.hpp

@@ -46,7 +46,7 @@ class RankingObjective : public ObjectiveFunction {
     position_ids_ = metadata.position_ids();
     // get number of different position ids
     num_position_ids_ = static_cast<data_size_t>(metadata.num_position_ids());
-    // get boundries
+    // get boundaries
     query_boundaries_ = metadata.query_boundaries();
     if (query_boundaries_ == nullptr) {
       Log::Fatal("Ranking tasks require query information");

src/treelearner/cuda/cuda_best_split_finder.cpp

@@ -120,7 +120,7 @@ void CUDABestSplitFinder::Init() {
 void CUDABestSplitFinder::InitCUDAFeatureMetaInfo() {
   AllocateCUDAMemory<int8_t>(&cuda_is_feature_used_bytree_, static_cast<size_t>(num_features_), __FILE__, __LINE__);
 
-  // intialize split find task information (a split find task is one pass through the histogram of a feature)
+  // initialize split find task information (a split find task is one pass through the histogram of a feature)
   num_tasks_ = 0;
   for (int inner_feature_index = 0; inner_feature_index < num_features_; ++inner_feature_index) {
     const uint32_t num_bin = feature_num_bins_[inner_feature_index];

src/treelearner/cuda/cuda_data_partition.cu

@@ -262,7 +262,7 @@ void CUDADataPartition::LaunchUpdateDataIndexToLeafIndexKernel_Inner4(
   }
 }
 
-#define GenDataToLeftBitVectorKernel_PARMS \
+#define GenDataToLeftBitVectorKernel_PARAMS \
   const BIN_TYPE* column_data, \
   const data_size_t num_data_in_leaf, \
   const data_size_t* data_indices_in_leaf, \
@@ -286,7 +286,7 @@ void CUDADataPartition::LaunchUpdateDataIndexToLeafIndexKernel_Inner4(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, bool MFB_IS_NA, bool MAX_TO_LEFT, bool USE_MIN_BIN, typename BIN_TYPE>
 __global__ void GenDataToLeftBitVectorKernel(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   uint16_t* block_to_left_offset,
   data_size_t* block_to_left_offset_buffer,
   data_size_t* block_to_right_offset_buffer) {
@@ -335,7 +335,7 @@ __global__ void GenDataToLeftBitVectorKernel(
 
 template <typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool missing_is_zero,
   const bool missing_is_na,
   const bool mfb_is_zero,
@@ -363,7 +363,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner0(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool missing_is_na,
   const bool mfb_is_zero,
   const bool mfb_is_na,
@@ -380,7 +380,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner0(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner1(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool mfb_is_zero,
   const bool mfb_is_na,
   const bool max_bin_to_left,
@@ -396,7 +396,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner1(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner2(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool mfb_is_na,
   const bool max_bin_to_left,
   const bool is_single_feature_in_column) {
@@ -413,7 +413,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner2(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, bool MFB_IS_NA, typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner3(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool max_bin_to_left,
   const bool is_single_feature_in_column) {
   if (!max_bin_to_left) {
@@ -429,7 +429,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner3(
 
 template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, bool MFB_IS_NA, bool MAX_TO_LEFT, typename BIN_TYPE>
 void CUDADataPartition::LaunchGenDataToLeftBitVectorKernelInner4(
-  GenDataToLeftBitVectorKernel_PARMS,
+  GenDataToLeftBitVectorKernel_PARAMS,
   const bool is_single_feature_in_column) {
   if (!is_single_feature_in_column) {
     GenDataToLeftBitVectorKernel
@@ -548,7 +548,7 @@ void CUDADataPartition::LaunchGenDataToLeftBitVectorKernel(
 
 #undef UpdateDataIndexToLeafIndexKernel_PARAMS
 #undef UpdateDataIndexToLeafIndex_ARGS
-#undef GenDataToLeftBitVectorKernel_PARMS
+#undef GenDataToLeftBitVectorKernel_PARAMS
 #undef GenBitVector_ARGS
 
 template <typename BIN_TYPE, bool USE_MIN_BIN>

src/treelearner/cuda/cuda_data_partition.hpp

@@ -174,7 +174,7 @@ class CUDADataPartition {
     const int left_leaf_index,
     const int right_leaf_index);
 
-#define GenDataToLeftBitVectorKernel_PARMS \
+#define GenDataToLeftBitVectorKernel_PARAMS \
   const BIN_TYPE* column_data, \
   const data_size_t num_data_in_leaf, \
   const data_size_t* data_indices_in_leaf, \
@@ -187,7 +187,7 @@ class CUDADataPartition {
 
   template <typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool missing_is_zero,
     const bool missing_is_na,
     const bool mfb_is_zero,
@@ -197,7 +197,7 @@ class CUDADataPartition {
 
   template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner0(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool missing_is_na,
     const bool mfb_is_zero,
     const bool mfb_is_na,
@@ -206,7 +206,7 @@ class CUDADataPartition {
 
   template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner1(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool mfb_is_zero,
     const bool mfb_is_na,
     const bool max_bin_to_left,
@@ -214,23 +214,23 @@ class CUDADataPartition {
 
   template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner2(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool mfb_is_na,
     const bool max_bin_to_left,
     const bool is_single_feature_in_column);
 
   template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, bool MFB_IS_NA, typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner3(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool max_bin_to_left,
     const bool is_single_feature_in_column);
 
   template <bool MIN_IS_MAX, bool MISSING_IS_ZERO, bool MISSING_IS_NA, bool MFB_IS_ZERO, bool MFB_IS_NA, bool MAX_TO_LEFT, typename BIN_TYPE>
   void LaunchGenDataToLeftBitVectorKernelInner4(
-    GenDataToLeftBitVectorKernel_PARMS,
+    GenDataToLeftBitVectorKernel_PARAMS,
     const bool is_single_feature_in_column);
 
-#undef GenDataToLeftBitVectorKernel_PARMS
+#undef GenDataToLeftBitVectorKernel_PARAMS
 
 #define UpdateDataIndexToLeafIndexKernel_PARAMS \
   const BIN_TYPE* column_data, \
@@ -379,7 +379,7 @@ class CUDADataPartition {
   int* cuda_split_info_buffer_;
 
   // dataset information
-  /*! \brief number of data in training set, for intialization of cuda_leaf_num_data_ and cuda_leaf_data_end_ */
+  /*! \brief number of data in training set, for initialization of cuda_leaf_num_data_ and cuda_leaf_data_end_ */
   data_size_t* cuda_num_data_;
 
 

src/treelearner/cuda/cuda_histogram_constructor.cpp

@@ -150,7 +150,7 @@ void CUDAHistogramConstructor::CalcConstructHistogramKernelDim(
   int* block_dim_y,
   const data_size_t num_data_in_smaller_leaf) {
   *block_dim_x = cuda_row_data_->max_num_column_per_partition();
-  *block_dim_y = NUM_THRADS_PER_BLOCK / cuda_row_data_->max_num_column_per_partition();
+  *block_dim_y = NUM_THREADS_PER_BLOCK / cuda_row_data_->max_num_column_per_partition();
   *grid_dim_x = cuda_row_data_->num_feature_partitions();
   *grid_dim_y = std::max(min_grid_dim_y_,
     ((num_data_in_smaller_leaf + NUM_DATA_PER_THREAD - 1) / NUM_DATA_PER_THREAD + (*block_dim_y) - 1) / (*block_dim_y));