add logging warning

Author: Samoed

autointent/_pipeline/_pipeline.py

@@ -144,6 +144,14 @@ def _fit(self, context: Context, sampler: SamplerType) -> None:
         """
         self.context = context
         self._logger.info("starting pipeline optimization...")
+
+        if context.logging_config.clear_ram:
+            self._logger.warning(
+                "Memory storage is not compatible with resuming optimization. "
+                "Modules from previous runs won't be available. "
+                "Set dump_modules=True in LoggingConfig to enable proper resuming."
+            )
+
         self.context.callback_handler.start_run(
             run_name=self.context.logging_config.get_run_name(),
             dirpath=self.context.logging_config.dirpath,

autointent/nodes/_node_optimizer.py

@@ -113,6 +113,12 @@ def fit(self, context: Context, sampler: SamplerType = "brute", n_jobs: int = 1)
             )
             self._counter = max(self._counter, finished_trials)
 
+            # if n_trials == 0:
+            #     config = self.suggest(Trial(), search_space)
+            #
+            #     module = self.node_info.modules_available[module_name]
+            #     module.load()
+
             optuna.logging.set_verbosity(optuna.logging.WARNING)
             obj = partial(self.objective, module_name=module_name, search_space=search_space, context=context)
 

tests/pipeline/test_pipeline_interruption.py

@@ -96,7 +96,6 @@ def tracking_objective2(trial, *args, **kwargs):
         second_run_trials.add(trial.number)
         return original_objective2(trial, *args, **kwargs)
 
-    # pipeline_optimizer.nodes[NodeType.scoring].objective = tracking_objective2
     pipeline_optimizer.set_config(logging_config)
     pipeline_optimizer.set_config(DataConfig(scheme="ho", separation_ratio=None))
     with patch.object(pipeline_optimizer.nodes[NodeType.scoring], "objective", side_effect=tracking_objective2):
@@ -121,3 +120,30 @@ def tracking_objective2(trial, *args, **kwargs):
                 f"Database {db_file.name} did not have more trials after second run "
                 f"({trials_after_first_run[db_file.name]} vs {trials_after_second_run})"
             )
+
+
+def test_resuming_with_memory_storage_warning(dataset_no_oos, tmp_path, caplog):
+    """Test that a warning is issued when trying to resume with memory storage."""
+    project_dir = tmp_path
+    search_space = get_search_space("optuna")
+
+    # Setup first pipeline with memory storage
+    logging_config = LoggingConfig(
+        project_dir=project_dir,
+        run_name="test_memory_storage_warning",
+        dump_modules=False,  # Keep modules in RAM
+        clear_ram=False,
+    )
+
+    pipeline_optimizer = Pipeline.from_search_space(search_space)
+    pipeline_optimizer.set_config(logging_config)
+    pipeline_optimizer.set_config(DataConfig(
+        scheme="ho",
+        separation_ratio=None,
+        n_folds=2,
+        validation_size=0.2
+    ))
+    pipeline_optimizer.fit(dataset_no_oos, refit_after=False, sampler="random")
+
+    assert any("Memory storage is not compatible with resuming optimization" in record.message for record in caplog.records)
+