Suppress categorical warning (fixes #3379)

python-package/lightgbm/basic.py

@@ -1510,6 +1510,8 @@ class Dataset:
             if categorical_indices:
                 for cat_alias in _ConfigAliases.get("categorical_feature"):
                     if cat_alias in params:
+                        # If the params[cat_alias] is equal to categorical_indices, do not report the warning.
+                        if not(isinstance(params[cat_alias], list) and set(params[cat_alias]) == categorical_indices):
                             _log_warning(f'{cat_alias} in param dict is overridden.')
                         params.pop(cat_alias, None)
                 params['categorical_column'] = sorted(categorical_indices)
@@ -1765,6 +1767,32 @@ class Dataset:
             ctypes.byref(self.handle)))
         return self
 
+    @staticmethod
+    def _compare_params_for_warning(params, other_params):
+        """Compare params.
+
+        It is only for the warning purpose. Thus some keys are ignored.
+
+        Returns
+        -------
+        compare_result: bool
+          If they are equal, return True; Otherwise, return False.
+        """
+        ignore_keys = _ConfigAliases.get("categorical_feature")
+        if params is None:
+            params = {}
+        if other_params is None:
+            other_params = {}
+        for k in other_params:
+            if k not in ignore_keys:
+                if k not in params or params[k] != other_params[k]:
+                    return False
+        for k in params:
+            if k not in ignore_keys:
+                if k not in other_params or params[k] != other_params[k]:
+                    return False
+        return True
+
     def construct(self):
         """Lazy init.
 
@@ -1776,7 +1804,9 @@ class Dataset:
         if self.handle is None:
             if self.reference is not None:
                 reference_params = self.reference.get_params()
-                if self.get_params() != reference_params:
+                params = self.get_params()
+                if params != reference_params:
+                    if self._compare_params_for_warning(params, reference_params) is False:
                         _log_warning('Overriding the parameters from Reference Dataset.')
                     self._update_params(reference_params)
                 if self.used_indices is None:
@@ -2062,9 +2092,9 @@ class Dataset:
                 self.categorical_feature = categorical_feature
                 return self._free_handle()
             elif categorical_feature == 'auto':
-                _log_warning('Using categorical_feature in Dataset.')
                 return self
             else:
+                if self.categorical_feature != 'auto':
                     _log_warning('categorical_feature in Dataset is overridden.\n'
                                  f'New categorical_feature is {sorted(list(categorical_feature))}')
                 self.categorical_feature = categorical_feature

tests/python_package_test/test_utilities.py

@@ -43,8 +43,6 @@ def test_register_logger(tmp_path):
     lgb.plot_metric(eval_records)
 
     expected_log = r"""
-WARNING | categorical_feature in Dataset is overridden.
-New categorical_feature is [1]
 INFO | [LightGBM] [Warning] There are no meaningful features, as all feature values are constant.
 INFO | [LightGBM] [Info] Number of positive: 2, number of negative: 2
 INFO | [LightGBM] [Info] Total Bins 0