Fix issue with "list index out of range" when max_iter=1 (#1419)

Author: Stickic-cyber

flaml/automl/automl.py

@@ -2529,6 +2529,21 @@ def _search(self):
             self._selected = state = self._search_states[estimator]
             state.best_config_sample_size = self._state.data_size[0]
             state.best_config = state.init_config[0] if state.init_config else {}
+            self._track_iter = 0
+            self._config_history[self._track_iter] = (estimator, state.best_config, self._state.time_from_start)
+            self._best_iteration = self._track_iter
+            state.val_loss = getattr(state, "val_loss", float("inf"))
+            state.best_loss = getattr(state, "best_loss", float("inf"))
+            state.config = getattr(state, "config", state.best_config.copy())
+            state.metric_for_logging = getattr(state, "metric_for_logging", None)
+            state.sample_size = getattr(state, "sample_size", self._state.data_size[0])
+            state.learner_class = getattr(state, "learner_class", self._state.learner_classes.get(estimator))
+            if hasattr(self, "mlflow_integration") and self.mlflow_integration:
+                self.mlflow_integration.record_state(
+                    automl=self,
+                    search_state=state,
+                    estimator=estimator,
+                )
         elif self._use_ray is False and self._use_spark is False:
             self._search_sequential()
         else:

test/automl/test_max_iter_1.py

@@ -0,0 +1,51 @@
+import mlflow
+import numpy as np
+import pandas as pd
+
+from flaml import AutoML
+
+
+def test_max_iter_1():
+    date_rng = pd.date_range(start="2024-01-01", periods=100, freq="H")
+    X = pd.DataFrame({"ds": date_rng})
+    y_train_24h = np.random.rand(len(X)) * 100
+
+    # AutoML
+    settings = {
+        "max_iter": 1,
+        "estimator_list": ["xgboost", "lgbm"],
+        "starting_points": {"xgboost": {}, "lgbm": {}},
+        "task": "ts_forecast",
+        "log_file_name": "test_max_iter_1.log",
+        "seed": 41,
+        "mlflow_exp_name": "TestExp-max_iter-1",
+        "use_spark": False,
+        "n_concurrent_trials": 1,
+        "verbose": 1,
+        "featurization": "off",
+        "metric": "rmse",
+        "mlflow_logging": True,
+    }
+
+    automl = AutoML(**settings)
+
+    with mlflow.start_run(run_name="AutoMLModel-XGBoost-and-LGBM-max_iter_1"):
+        automl.fit(
+            X_train=X,
+            y_train=y_train_24h,
+            period=24,
+            X_val=X,
+            y_val=y_train_24h,
+            split_ratio=0,
+            force_cancel=False,
+        )
+
+    assert automl.model is not None, "AutoML failed to return a model"
+    assert automl.best_run_id is not None, "Best run ID should not be None with mlflow logging"
+
+    print("Best model:", automl.model)
+    print("Best run ID:", automl.best_run_id)
+
+
+if __name__ == "__main__":
+    test_max_iter_1()