Merge branch 'master' into arrow-support

.ci/lint_r_code.R

@@ -33,29 +33,37 @@ LINTERS_TO_USE <- list(
     , "any_duplicated"       = lintr::any_duplicated_linter()
     , "any_is_na"            = lintr::any_is_na_linter()
     , "assignment"           = lintr::assignment_linter()
+    , "boolean_arithmetic"   = lintr::boolean_arithmetic_linter()
     , "braces"               = lintr::brace_linter()
     , "class_equals"         = lintr::class_equals_linter()
     , "commas"               = lintr::commas_linter()
     , "duplicate_argument"   = lintr::duplicate_argument_linter()
+    , "empty_assignment"     = lintr::empty_assignment_linter()
     , "equals_na"            = lintr::equals_na_linter()
+    , "for_loop_index"       = lintr::for_loop_index_linter()
     , "function_left"        = lintr::function_left_parentheses_linter()
     , "implicit_integers"    = lintr::implicit_integer_linter()
     , "infix_spaces"         = lintr::infix_spaces_linter()
     , "inner_combine"        = lintr::inner_combine_linter()
+    , "is_numeric"           = lintr::is_numeric_linter()
     , "fixed_regex"          = lintr::fixed_regex_linter()
+    , "function_return"      = lintr::function_return_linter()
+    , "lengths"              = lintr::lengths_linter()
     , "literal_coercion"     = lintr::literal_coercion_linter()
     , "long_lines"           = lintr::line_length_linter(length = 120L)
+    , "matrix"               = lintr::matrix_apply_linter()
     , "missing_argument"     = lintr::missing_argument_linter()
-    , "no_tabs"              = lintr::no_tab_linter()
     , "non_portable_path"    = lintr::nonportable_path_linter()
     , "numeric_leading_zero" = lintr::numeric_leading_zero_linter()
     , "outer_negation"       = lintr::outer_negation_linter()
     , "package_hooks"        = lintr::package_hooks_linter()
     , "paste"                = lintr::paste_linter()
+    , "quotes"               = lintr::quotes_linter()
+    , "redundant_equals"     = lintr::redundant_equals_linter()
     , "regex_subset"         = lintr::regex_subset_linter()
+    , "routine_registration" = lintr::routine_registration_linter()
     , "semicolon"            = lintr::semicolon_linter()
     , "seq"                  = lintr::seq_linter()
-    , "single_quotes"        = lintr::single_quotes_linter()
     , "spaces_inside"        = lintr::spaces_inside_linter()
     , "spaces_left_parens"   = lintr::spaces_left_parentheses_linter()
     , "sprintf"              = lintr::sprintf_linter()
@@ -96,9 +104,11 @@ LINTERS_TO_USE <- list(
             , "??" = interactive_text
         )
     )
-    , "unneeded_concatenation" = lintr::unneeded_concatenation_linter()
-    , "unreachable_code"       = lintr::unreachable_code_linter()
-    , "vector_logic"           = lintr::vector_logic_linter()
+    , "unnecessary_concatenation" = lintr::unnecessary_concatenation_linter()
+    , "unnecessary_lambda"        = lintr::unnecessary_lambda_linter()
+    , "unreachable_code"          = lintr::unreachable_code_linter()
+    , "vector_logic"              = lintr::vector_logic_linter()
+    , "whitespace"                = lintr::whitespace_linter()
 )
 
 noquote(paste0(length(FILES_TO_LINT), " R files need linting"))

.ci/test.sh

@@ -73,7 +73,7 @@ if [[ $TASK == "lint" ]]; then
         cpplint \
         isort \
         mypy \
-        'r-lintr>=3.0' \
+        'r-lintr>=3.1' \
         ruff
     source activate $CONDA_ENV
     echo "Linting Python code"

.ci/test_windows.ps1

@@ -126,7 +126,7 @@ if (($env:TASK -eq "regular") -or (($env:APPVEYOR -eq "true") -and ($env:TASK -e
   cd $env:BUILD_SOURCESDIRECTORY/examples/python-guide
   @("import matplotlib", "matplotlib.use('Agg')") + (Get-Content "plot_example.py") | Set-Content "plot_example.py"
   (Get-Content "plot_example.py").replace('graph.render(view=True)', 'graph.render(view=False)') | Set-Content "plot_example.py"  # prevent interactive window mode
-  conda install -q -y -n $env:CONDA_ENV h5py ipywidgets notebook
+  conda install -q -y -n $env:CONDA_ENV "h5py>3.0" ipywidgets notebook
   foreach ($file in @(Get-ChildItem *.py)) {
     @("import sys, warnings", "warnings.showwarning = lambda message, category, filename, lineno, file=None, line=None: sys.stdout.write(warnings.formatwarning(message, category, filename, lineno, line))") + (Get-Content $file) | Set-Content $file
     python $file ; Check-Output $?

.github/CODEOWNERS

@@ -7,56 +7,4 @@
 # offer a reasonable automatic best-guess
 
 # catch-all rule (this only gets matched if no rules below match)
-*    @guolinke @StrikerRUS @jameslamb @shiyu1994
-
-# other catch-alls that will get matched if specific rules below are not matched
-*.R    @jameslamb @jmoralez
-*.py    @StrikerRUS @jmoralez @jameslamb @shiyu1994
-*.cpp    @guolinke @shiyu1994
-*.h    @guolinke @shiyu1994
-
-# main C++ code
-include/    @guolinke @shiyu1994
-src/    @guolinke @shiyu1994
-CMakeLists.txt    @guolinke @jameslamb @StrikerRUS @shiyu1994
-tests/c_api_test/    @guolinke @shiyu1994
-tests/cpp_tests/    @guolinke @shiyu1994
-tests/data/    @guolinke @shiyu1994
-windows/    @guolinke @StrikerRUS @shiyu1994
-
-# R code
-build_r.R    @jameslamb @StrikerRUS @jmoralez
-build-cran-package.sh    @jameslamb @StrikerRUS @jmoralez
-R-package/    @jameslamb @jmoralez
-
-# Python code
-python-package/    @StrikerRUS @shiyu1994 @jameslamb @jmoralez
-
-# Dask integration
-python-package/lightgbm/dask.py    @jameslamb @jmoralez
-tests/python_package_test/test_dask.py    @jameslamb @jmoralez
-
-# helpers
-helpers/    @StrikerRUS @guolinke
-
-# CI administrative stuff
-.ci/    @StrikerRUS @jameslamb
-docs/    @StrikerRUS @jameslamb
-examples/     @StrikerRUS @jameslamb @guolinke @jmoralez
-*.yml    @StrikerRUS @jameslamb
-.vsts-ci.yml    @StrikerRUS @jameslamb
-
-# docker setup
-docker/    @StrikerRUS @jameslamb
-docker/dockerfile-cli    @guolinke @shiyu1994 @StrikerRUS @jameslamb
-docker/gpu/    @StrikerRUS @jameslamb
-docker/dockerfile-python    @StrikerRUS @shiyu1994 @jameslamb @jmoralez
-docker/dockerfile-r    @jameslamb @jmoralez
-
-# GPU code
-docs/GPU-*.rst    @shiyu1994 @guolinke
-src/treelearner/gpu_tree_learner.cpp    @guolinke @shiyu1994
-src/treelearner/tree_learner.cpp    @guolinke @shiyu1994
-
-# JAVA code
-swig/    @guolinke @shiyu1994
+*    @guolinke @jameslamb @shiyu1994 @jmoralez

R-package/R/lgb.Dataset.R

@@ -494,11 +494,10 @@ Dataset <- R6::R6Class(
         if (info_len > 0L) {
 
           # Get back fields
-          ret <- NULL
-          ret <- if (field_name == "group") {
-            integer(info_len)
+          if (field_name == "group") {
+            ret <- integer(info_len)
           } else {
-            numeric(info_len)
+            ret <- numeric(info_len)
           }
 
           .Call(

R-package/R/lgb.Predictor.R

@@ -98,8 +98,6 @@ Predictor <- R6::R6Class(
         start_iteration <- 0L
       }
 
-      num_row <- 0L
-
       # Check if data is a file name and not a matrix
       if (identical(class(data), "character") && length(data) == 1L) {
 

R-package/R/lgb.convert_with_rules.R

@@ -116,10 +116,6 @@ lgb.convert_with_rules <- function(data, rules = NULL) {
 
     column_classes <- .get_column_classes(df = data)
 
-    is_char <- which(column_classes == "character")
-    is_factor <- which(column_classes == "factor")
-    is_logical <- which(column_classes == "logical")
-
     is_data_table <- data.table::is.data.table(x = data)
     is_data_frame <- is.data.frame(data)
 

R-package/R/lgb.cv.R

@@ -225,8 +225,6 @@ lgb.cv <- function(params = list()
       stop(sQuote("folds"), " must be a list with 2 or more elements that are vectors of indices for each CV-fold")
     }
 
-    nfold <- length(folds)
-
   } else {
 
     if (nfold <= 1L) {

R-package/R/lgb.interprete.R

@@ -72,7 +72,9 @@ lgb.interprete <- function(model,
   leaf_index_dt <- data.table::as.data.table(x = pred_mat)
   leaf_index_mat_list <- lapply(
     X = leaf_index_dt
-    , FUN = function(x) matrix(x, ncol = num_class, byrow = TRUE)
+    , FUN = matrix
+    , ncol = num_class
+    , byrow = TRUE
   )
 
   # Get list of trees

R-package/R/lgb.train.R

@@ -154,6 +154,9 @@ lgb.train <- function(params = list(),
 
   # Construct datasets, if needed
   data$update_params(params = params)
+  if (!is.null(categorical_feature)) {
+    data$set_categorical_feature(categorical_feature)
+  }
   data$construct()
 
   # Check interaction constraints
@@ -179,11 +182,6 @@ lgb.train <- function(params = list(),
     data$set_colnames(colnames)
   }
 
-  # Write categorical features
-  if (!is.null(categorical_feature)) {
-    data$set_categorical_feature(categorical_feature)
-  }
-
   valid_contain_train <- FALSE
   train_data_name <- "train"
   reduced_valid_sets <- list()

R-package/tests/testthat/helper.R

@@ -1,5 +1,6 @@
 # ref for this file:
 #
+# * https://r-pkgs.org/testing-design.html#testthat-helper-files
 # * https://r-pkgs.org/testing-design.html#testthat-setup-files
 
 # LightGBM-internal fix to comply with CRAN policy of only using up to 2 threads in tests and example.
@@ -10,3 +11,21 @@
 #   the check farm is a shared resource and will typically be running many checks simultaneously.
 #
 .LGB_MAX_THREADS <- 2L
+
+# by default, how much should results in tests be allowed to differ from hard-coded expected numbers?
+.LGB_NUMERIC_TOLERANCE <- 1e-6
+
+# are the tests running on Windows?
+.LGB_ON_WINDOWS <- .Platform$OS.type == "windows"
+.LGB_ON_32_BIT_WINDOWS <- .LGB_ON_WINDOWS && .Machine$sizeof.pointer != 8L
+
+# are the tests running in a UTF-8 locale?
+.LGB_UTF8_LOCALE <- all(endsWith(
+  Sys.getlocale(category = "LC_CTYPE")
+  , "UTF-8"
+))
+
+# control how many loud LightGBM's logger is in tests
+.LGB_VERBOSITY <- as.integer(
+  Sys.getenv("LIGHTGBM_TEST_VERBOSITY", "-1")
+)