Merge branch 'master' of github.com:microsoft/LightGBM into googletes…

…t-version

.ci/test.sh

@@ -124,7 +124,7 @@ fi
 # ref: https://github.com/microsoft/LightGBM/issues/6030
 CONSTRAINED_DEPENDENCIES="'dask-core>=2023.5.0' 'distributed>=2023.5.0' 'pandas>=2.0'"
 if [[ $PYTHON_VERSION == "3.7" ]]; then
-    CONSTRAINED_DEPENDENCIES="'dask-core' 'distributed 'pandas<2.0'"
+    CONSTRAINED_DEPENDENCIES="'dask-core' 'distributed' 'pandas<2.0'"
 fi
 
 # including python=version[build=*cpython] to ensure that conda doesn't fall back to pypy

.ci/test_r_package_windows.ps1

@@ -203,6 +203,19 @@ if ($env:COMPILER -ne "MSVC") {
   }
 }
 
+# Checking that the correct R version was used
+if ($env:TOOLCHAIN -ne "MSVC") {
+  $checks = Select-String -Path "${LOG_FILE_NAME}" -Pattern "using R version $env:R_WINDOWS_VERSION"
+  $checks_cnt = $checks.Matches.length
+} else {
+  $checks = Select-String -Path "${INSTALL_LOG_FILE_NAME}" -Pattern "R version passed into FindLibR.* $env:R_WINDOWS_VERSION"
+  $checks_cnt = $checks.Matches.length
+}
+if ($checks_cnt -eq 0) {
+  Write-Output "Wrong R version was found (expected '$env:R_WINDOWS_VERSION'). Check the build logs."
+  Check-Output $False
+}
+
 # Checking that we actually got the expected compiler. The R package has some logic
 # to fail back to MinGW if MSVC fails, but for CI builds we need to check that the correct
 # compiler was used.

python-package/lightgbm/basic.py

@@ -24,6 +24,13 @@
 if TYPE_CHECKING:
     from typing import Literal
 
+    # typing.TypeGuard was only introduced in Python 3.10
+    try:
+        from typing import TypeGuard
+    except ImportError:
+        from typing_extensions import TypeGuard
+
+
 __all__ = [
     'Booster',
     'Dataset',
@@ -279,6 +286,20 @@ def _is_1d_list(data: Any) -> bool:
     return isinstance(data, list) and (not data or _is_numeric(data[0]))
 
 
+def _is_list_of_numpy_arrays(data: Any) -> "TypeGuard[List[np.ndarray]]":
+    return (
+        isinstance(data, list)
+        and all(isinstance(x, np.ndarray) for x in data)
+    )
+
+
+def _is_list_of_sequences(data: Any) -> "TypeGuard[List[Sequence]]":
+    return (
+        isinstance(data, list)
+        and all(isinstance(x, Sequence) for x in data)
+    )
+
+
 def _is_1d_collection(data: Any) -> bool:
     """Check whether data is a 1-D collection."""
     return (
@@ -458,7 +479,7 @@ def _get_all_param_aliases() -> Dict[str, List[str]]:
         buffer_len = 1 << 20
         tmp_out_len = ctypes.c_int64(0)
         string_buffer = ctypes.create_string_buffer(buffer_len)
-        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+        ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
         _safe_call(_LIB.LGBM_DumpParamAliases(
             ctypes.c_int64(buffer_len),
             ctypes.byref(tmp_out_len),
@@ -467,7 +488,7 @@ def _get_all_param_aliases() -> Dict[str, List[str]]:
         # if buffer length is not long enough, re-allocate a buffer
         if actual_len > buffer_len:
             string_buffer = ctypes.create_string_buffer(actual_len)
-            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+            ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
             _safe_call(_LIB.LGBM_DumpParamAliases(
                 ctypes.c_int64(actual_len),
                 ctypes.byref(tmp_out_len),
@@ -1593,7 +1614,7 @@ def __init__(
         self.used_indices: Optional[List[int]] = None
         self._need_slice = True
         self._predictor: Optional[_InnerPredictor] = None
-        self.pandas_categorical = None
+        self.pandas_categorical: Optional[List[List]] = None
         self._params_back_up = None
         self.version = 0
         self._start_row = 0  # Used when pushing rows one by one.
@@ -1918,9 +1939,9 @@ def _lazy_init(
         elif isinstance(data, np.ndarray):
             self.__init_from_np2d(data, params_str, ref_dataset)
         elif isinstance(data, list) and len(data) > 0:
-            if all(isinstance(x, np.ndarray) for x in data):
+            if _is_list_of_numpy_arrays(data):
                 self.__init_from_list_np2d(data, params_str, ref_dataset)
-            elif all(isinstance(x, Sequence) for x in data):
+            elif _is_list_of_sequences(data):
                 self.__init_from_seqs(data, ref_dataset)
             else:
                 raise TypeError('Data list can only be of ndarray or Sequence')
@@ -2870,7 +2891,7 @@ def get_data(self) -> Optional[_LGBM_TrainDataType]:
                     self.data = self.data[self.used_indices, :]
                 elif isinstance(self.data, Sequence):
                     self.data = self.data[self.used_indices]
-                elif isinstance(self.data, list) and len(self.data) > 0 and all(isinstance(x, Sequence) for x in self.data):
+                elif _is_list_of_sequences(self.data) and len(self.data) > 0:
                     self.data = np.array(list(self._yield_row_from_seqlist(self.data, self.used_indices)))
                 else:
                     _log_warning(f"Cannot subset {type(self.data).__name__} type of raw data.\n"
@@ -3294,7 +3315,7 @@ def _get_loaded_param(self) -> Dict[str, Any]:
         buffer_len = 1 << 20
         tmp_out_len = ctypes.c_int64(0)
         string_buffer = ctypes.create_string_buffer(buffer_len)
-        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+        ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
         _safe_call(_LIB.LGBM_BoosterGetLoadedParam(
             self._handle,
             ctypes.c_int64(buffer_len),
@@ -3304,7 +3325,7 @@ def _get_loaded_param(self) -> Dict[str, Any]:
         # if buffer length is not long enough, re-allocate a buffer
         if actual_len > buffer_len:
             string_buffer = ctypes.create_string_buffer(actual_len)
-            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+            ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
             _safe_call(_LIB.LGBM_BoosterGetLoadedParam(
                 self._handle,
                 ctypes.c_int64(actual_len),
@@ -4057,7 +4078,7 @@ def model_to_string(
         buffer_len = 1 << 20
         tmp_out_len = ctypes.c_int64(0)
         string_buffer = ctypes.create_string_buffer(buffer_len)
-        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+        ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
         _safe_call(_LIB.LGBM_BoosterSaveModelToString(
             self._handle,
             ctypes.c_int(start_iteration),
@@ -4070,7 +4091,7 @@ def model_to_string(
         # if buffer length is not long enough, re-allocate a buffer
         if actual_len > buffer_len:
             string_buffer = ctypes.create_string_buffer(actual_len)
-            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+            ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
             _safe_call(_LIB.LGBM_BoosterSaveModelToString(
                 self._handle,
                 ctypes.c_int(start_iteration),
@@ -4125,7 +4146,7 @@ def dump_model(
         buffer_len = 1 << 20
         tmp_out_len = ctypes.c_int64(0)
         string_buffer = ctypes.create_string_buffer(buffer_len)
-        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+        ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
         _safe_call(_LIB.LGBM_BoosterDumpModel(
             self._handle,
             ctypes.c_int(start_iteration),
@@ -4138,7 +4159,7 @@ def dump_model(
         # if buffer length is not long enough, reallocate a buffer
         if actual_len > buffer_len:
             string_buffer = ctypes.create_string_buffer(actual_len)
-            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
+            ptr_string_buffer = ctypes.c_char_p(ctypes.addressof(string_buffer))
             _safe_call(_LIB.LGBM_BoosterDumpModel(
                 self._handle,
                 ctypes.c_int(start_iteration),

python-package/lightgbm/callback.py

@@ -164,7 +164,7 @@ def __call__(self, env: CallbackEnv) -> None:
             else:
                 data_name, eval_name = item[1].split()
                 res_mean = item[2]
-                res_stdv = item[4]
+                res_stdv = item[4]  # type: ignore[misc]
                 self.eval_result[data_name][f'{eval_name}-mean'].append(res_mean)
                 self.eval_result[data_name][f'{eval_name}-stdv'].append(res_stdv)