Merge branch 'main' into copilot/fix-blendsearch-udf-warning

thinkall · web-flow · commit dd55eaf961da · 2026-01-19T22:37:24.000+08:00
diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
@@ -40,7 +40,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest]
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
@@ -74,6 +74,11 @@ jobs:
         run: |
           pip install pyspark==4.0.1
           pip list | grep "pyspark"
+      - name: On Ubuntu python 3.13, install pyspark 4.1.0
+        if: matrix.python-version == '3.13' && matrix.os == 'ubuntu-latest'
+        run: |
+          pip install pyspark==4.1.0
+          pip list | grep "pyspark"
       # # TODO: support ray
       # - name: If linux and python<3.11, install ray 2
       #   if: matrix.os == 'ubuntu-latest' && matrix.python-version < '3.11'
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -36,7 +36,7 @@ repos:
     - id: black
 
   - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.17
+    rev: 0.7.22
     hooks:
       - id: mdformat
         additional_dependencies:
diff --git a/NOTICE.md b/NOTICE.md
@@ -4,8 +4,8 @@ This repository incorporates material as listed below or described in the code.
 
 ## Component. Ray.
 
-Code in tune/\[analysis.py, sample.py, trial.py, result.py\],
-searcher/\[suggestion.py, variant_generator.py\], and scheduler/trial_scheduler.py is adapted from
+Code in tune/[analysis.py, sample.py, trial.py, result.py],
+searcher/[suggestion.py, variant_generator.py], and scheduler/trial_scheduler.py is adapted from
 https://github.com/ray-project/ray/blob/master/python/ray/tune/
 
 ## Open Source License/Copyright Notice.
diff --git a/README.md b/README.md
@@ -34,7 +34,7 @@ FLAML has a .NET implementation in [ML.NET](http://dot.net/ml), an open-source,
 
 ## Installation
 
-The latest version of FLAML requires **Python >= 3.10 and \< 3.13**. While other Python versions may work for core components, full model support is not guaranteed. FLAML can be installed via `pip`:
+The latest version of FLAML requires **Python >= 3.10 and < 3.14**. While other Python versions may work for core components, full model support is not guaranteed. FLAML can be installed via `pip`:
 
 ```bash
 pip install flaml
diff --git a/SECURITY.md b/SECURITY.md
@@ -12,7 +12,7 @@ If you believe you have found a security vulnerability in any Microsoft-owned re
 
 Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://msrc.microsoft.com/create-report).
 
-If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://www.microsoft.com/en-us/msrc/pgp-key-msrc).
+If you prefer to submit without logging in, send email to [secure@microsoft.com](mailto:secure@microsoft.com). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://www.microsoft.com/en-us/msrc/pgp-key-msrc).
 
 You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
 
diff --git a/flaml/automl/ml.py b/flaml/automl/ml.py
@@ -311,14 +311,14 @@ def get_y_pred(estimator, X, eval_metric, task: Task):
     else:
         y_pred = estimator.predict(X)
 
-    if isinstance(y_pred, Series) or isinstance(y_pred, DataFrame):
+    if isinstance(y_pred, (Series, DataFrame)):
         y_pred = y_pred.values
 
     return y_pred
 
 
 def to_numpy(x):
-    if isinstance(x, Series or isinstance(x, DataFrame)):
+    if isinstance(x, (Series, DataFrame)):
         x = x.values
     else:
         x = np.ndarray(x)
@@ -586,7 +586,7 @@ def _eval_estimator(
 
         # TODO: why are integer labels being cast to str in the first place?
 
-        if isinstance(val_pred_y, Series) or isinstance(val_pred_y, DataFrame) or isinstance(val_pred_y, np.ndarray):
+        if isinstance(val_pred_y, (Series, DataFrame, np.ndarray)):
             test = val_pred_y if isinstance(val_pred_y, np.ndarray) else val_pred_y.values
             if not np.issubdtype(test.dtype, np.number):
                 # some NLP models return a list
diff --git a/flaml/automl/nlp/utils.py b/flaml/automl/nlp/utils.py
@@ -25,9 +25,7 @@ def load_default_huggingface_metric_for_task(task):
 
 
 def is_a_list_of_str(this_obj):
-    return (isinstance(this_obj, list) or isinstance(this_obj, np.ndarray)) and all(
-        isinstance(x, str) for x in this_obj
-    )
+    return isinstance(this_obj, (list, np.ndarray)) and all(isinstance(x, str) for x in this_obj)
 
 
 def _clean_value(value: Any) -> str:
diff --git a/flaml/automl/state.py b/flaml/automl/state.py
@@ -37,10 +37,9 @@ def valid_starting_point_one_dim(self, value_one_dim, domain_one_dim):
         if isinstance(domain_one_dim, sample.Domain):
             renamed_type = list(inspect.signature(domain_one_dim.is_valid).parameters.values())[0].annotation
             type_match = (
-                renamed_type == Any
+                renamed_type is Any
                 or isinstance(value_one_dim, renamed_type)
-                or isinstance(value_one_dim, int)
-                and renamed_type is float
+                or (renamed_type is float and isinstance(value_one_dim, int))
             )
             if not (type_match and domain_one_dim.is_valid(value_one_dim)):
                 return False
diff --git a/flaml/automl/task/time_series_task.py b/flaml/automl/task/time_series_task.py
@@ -386,9 +386,8 @@ def _preprocess(self, X, transformer=None):
         return X
 
     def preprocess(self, X, transformer=None):
-        if isinstance(X, pd.DataFrame) or isinstance(X, np.ndarray) or isinstance(X, pd.Series):
-            X = X.copy()
-            X = normalize_ts_data(X, self.target_names, self.time_col)
+        if isinstance(X, (pd.DataFrame, np.ndarray, pd.Series)):
+            X = normalize_ts_data(X.copy(), self.target_names, self.time_col)
             return self._preprocess(X, transformer)
         elif isinstance(X, int):
             return X
diff --git a/flaml/automl/time_series/ts_data.py b/flaml/automl/time_series/ts_data.py
@@ -546,14 +546,12 @@ def normalize_ts_data(X_train_all, target_names, time_col, y_train_all=None):
 
 
 def validate_data_basic(X_train_all, y_train_all):
-    assert isinstance(X_train_all, np.ndarray) or issparse(X_train_all) or isinstance(X_train_all, pd.DataFrame), (
-        "X_train_all must be a numpy array, a pandas dataframe, " "or Scipy sparse matrix."
-    )
+    assert isinstance(X_train_all, (np.ndarray, DataFrame)) or issparse(
+        X_train_all
+    ), "X_train_all must be a numpy array, a pandas dataframe, or Scipy sparse matrix."
 
-    assert (
-        isinstance(y_train_all, np.ndarray)
-        or isinstance(y_train_all, pd.Series)
-        or isinstance(y_train_all, pd.DataFrame)
+    assert isinstance(
+        y_train_all, (np.ndarray, pd.Series, pd.DataFrame)
     ), "y_train_all must be a numpy array or a pandas series or DataFrame."
 
     assert X_train_all.size != 0 and y_train_all.size != 0, "Input data must not be empty, use None if no data"
diff --git a/flaml/onlineml/README.md b/flaml/onlineml/README.md
@@ -1,6 +1,6 @@
 # ChaCha for Online AutoML
 
-FLAML includes *ChaCha* which is an automatic hyperparameter tuning solution for online machine learning. Online machine learning has the following properties: (1) data comes in sequential order; and (2) the performance of the machine learning model is evaluated online, i.e., at every iteration. *ChaCha* performs online AutoML respecting the aforementioned properties of online learning, and at the same time respecting the following constraints: (1) only a small constant number of 'live' models are allowed to perform online learning at the same time;  and (2) no model persistence or offline training is allowed, which means that once we decide to replace a 'live' model with a new one, the replaced model can no longer be retrieved.
+FLAML includes *ChaCha* which is an automatic hyperparameter tuning solution for online machine learning. Online machine learning has the following properties: (1) data comes in sequential order; and (2) the performance of the machine learning model is evaluated online, i.e., at every iteration. *ChaCha* performs online AutoML respecting the aforementioned properties of online learning, and at the same time respecting the following constraints: (1) only a small constant number of 'live' models are allowed to perform online learning at the same time; and (2) no model persistence or offline training is allowed, which means that once we decide to replace a 'live' model with a new one, the replaced model can no longer be retrieved.
 
 For more technical details about *ChaCha*, please check our paper.
 
diff --git a/flaml/tune/searcher/flow2.py b/flaml/tune/searcher/flow2.py
@@ -641,8 +641,10 @@ def config_signature(self, config, space: Dict = None) -> tuple:
             else:
                 # key must be in space
                 domain = space[key]
-                if self.hierarchical and not (
-                    domain is None or type(domain) in (str, int, float) or isinstance(domain, sample.Domain)
+                if (
+                    self.hierarchical
+                    and domain is not None
+                    and not isinstance(domain, (str, int, float, sample.Domain))
                 ):
                     # not domain or hashable
                     # get rid of list type for hierarchical search space.
diff --git a/flaml/tune/searcher/online_searcher.py b/flaml/tune/searcher/online_searcher.py
@@ -207,7 +207,7 @@ def _query_config_oracle(
                     hyperparameter_config_groups.append(partial_new_configs)
                     # does not have searcher_trial_ids
                     searcher_trial_ids_groups.append([])
-            elif isinstance(config_domain, Float) or isinstance(config_domain, Categorical):
+            elif isinstance(config_domain, (Float, Categorical)):
                 # otherwise we need to deal with them in group
                 nonpoly_config[k] = v
                 if k not in self._space_of_nonpoly_hp:
diff --git a/flaml/version.py b/flaml/version.py
@@ -1 +1 @@
-__version__ = "2.4.1"
+__version__ = "2.4.2"
diff --git a/setup.py b/setup.py
@@ -52,8 +52,8 @@
         ],
         "test": [
             "numpy>=1.17,<2.0.0; python_version<'3.13'",
-            "numpy>2.0.0; python_version>='3.13'",
-            "jupyter; python_version<'3.13'",
+            "numpy>=1.17; python_version>='3.13'",
+            "jupyter",
             "lightgbm>=2.3.1",
             "xgboost>=0.90,<2.0.0; python_version<'3.11'",
             "xgboost>=2.0.0; python_version>='3.11'",
@@ -68,10 +68,10 @@
             "pre-commit",
             "torch",
             "torchvision",
-            "catboost>=0.26; python_version<'3.13'",
+            "catboost>=0.26",
             "rgf-python",
             "optuna>=2.8.0,<=3.6.1",
-            "openml; python_version<'3.13'",
+            "openml",
             "statsmodels>=0.12.2",
             "psutil",
             "dataclasses",
@@ -82,7 +82,7 @@
             "rouge_score",
             "hcrystalball",
             "seqeval",
-            "pytorch-forecasting; python_version<'3.13'",
+            "pytorch-forecasting",
             "mlflow-skinny<=2.22.1",  # Refer to https://mvnrepository.com/artifact/org.mlflow/mlflow-spark
             "joblibspark>=0.5.0",
             "joblib<=1.3.2",
@@ -140,7 +140,7 @@
             "prophet>=1.1.5",
             "statsmodels>=0.12.2",
             "hcrystalball>=0.1.10",
-            "pytorch-forecasting>=0.10.4; python_version<'3.13'",
+            "pytorch-forecasting>=0.10.4",
             "pytorch-lightning>=1.9.0",
             "tensorboardX>=2.6",
         ],
diff --git a/test/automl/test_custom_hp.py b/test/automl/test_custom_hp.py
@@ -72,5 +72,39 @@ def test_custom_hp():
     print(automl.best_config_per_estimator)
 
 
+def test_lgbm_objective():
+    """Test that objective parameter can be set via custom_hp for LGBMEstimator"""
+    import numpy as np
+
+    # Create a simple regression dataset
+    np.random.seed(42)
+    X_train = np.random.rand(100, 5)
+    y_train = np.random.rand(100) * 100  # Scale to avoid division issues with MAPE
+
+    automl = AutoML()
+    settings = {
+        "time_budget": 3,
+        "metric": "mape",
+        "task": "regression",
+        "estimator_list": ["lgbm"],
+        "verbose": 0,
+        "custom_hp": {"lgbm": {"objective": {"domain": "mape"}}},  # Fixed value, not tuned
+    }
+
+    automl.fit(X_train, y_train, **settings)
+
+    # Verify that objective was set correctly
+    assert "objective" in automl.best_config, "objective should be in best_config"
+    assert automl.best_config["objective"] == "mape", "objective should be 'mape'"
+
+    # Verify the model has the correct objective
+    if hasattr(automl.model, "estimator") and hasattr(automl.model.estimator, "get_params"):
+        model_params = automl.model.estimator.get_params()
+        assert model_params.get("objective") == "mape", "Model should use 'mape' objective"
+
+    print("Test passed: objective parameter works correctly with LGBMEstimator")
+
+
 if __name__ == "__main__":
     test_custom_hp()
+    test_lgbm_objective()
diff --git a/test/automl/test_extra_models.py b/test/automl/test_extra_models.py
@@ -188,7 +188,11 @@ def _test_sparse_matrix_classification(estimator):
         "n_jobs": 1,
         "model_history": True,
     }
-    X_train = scipy.sparse.random(1554, 21, dtype=int)
+    # NOTE: Avoid `dtype=int` here. On some NumPy/SciPy combinations (notably
+    # Windows + Python 3.13), `scipy.sparse.random(..., dtype=int)` may trigger
+    # integer sampling paths which raise "low is out of bounds for int32".
+    # A float sparse matrix is sufficient to validate sparse-input support.
+    X_train = scipy.sparse.random(1554, 21, dtype=np.float32)
     y_train = np.random.randint(3, size=1554)
     automl_experiment.fit(X_train=X_train, y_train=y_train, **automl_settings)
 
diff --git a/test/automl/test_multiclass.py b/test/automl/test_multiclass.py
@@ -368,7 +368,11 @@ def test_sparse_matrix_classification(self):
             "n_jobs": 1,
             "model_history": True,
         }
-        X_train = scipy.sparse.random(1554, 21, dtype=int)
+        # NOTE: Avoid `dtype=int` here. On some NumPy/SciPy combinations (notably
+        # Windows + Python 3.13), `scipy.sparse.random(..., dtype=int)` may trigger
+        # integer sampling paths which raise "low is out of bounds for int32".
+        # A float sparse matrix is sufficient to validate sparse-input support.
+        X_train = scipy.sparse.random(1554, 21, dtype=np.float32)
         y_train = np.random.randint(3, size=1554)
         automl_experiment.fit(X_train=X_train, y_train=y_train, **automl_settings)
         print(automl_experiment.classes_)
diff --git a/test/spark/test_multiclass.py b/test/spark/test_multiclass.py
@@ -262,7 +262,11 @@ def test_sparse_matrix_classification(self):
             "n_concurrent_trials": 2,
             "use_spark": True,
         }
-        X_train = scipy.sparse.random(1554, 21, dtype=int)
+        # NOTE: Avoid `dtype=int` here. On some NumPy/SciPy combinations (notably
+        # Windows + Python 3.13), `scipy.sparse.random(..., dtype=int)` may trigger
+        # integer sampling paths which raise "low is out of bounds for int32".
+        # A float sparse matrix is sufficient to validate sparse-input support.
+        X_train = scipy.sparse.random(1554, 21, dtype=np.float32)
         y_train = np.random.randint(3, size=1554)
         automl_experiment.fit(X_train=X_train, y_train=y_train, **automl_settings)
         print(automl_experiment.classes_)
diff --git a/tutorials/flaml-tutorial-automl-24.md b/tutorials/flaml-tutorial-automl-24.md
@@ -4,7 +4,7 @@
 
 **Date and Time**: 09.09.2024, 15:30-17:00
 
-Location:  Sorbonne University, 4 place Jussieu, 75005 Paris
+Location: Sorbonne University, 4 place Jussieu, 75005 Paris
 
 Duration: 1.5 hours
 
diff --git a/tutorials/flaml-tutorial-pydata-23.md b/tutorials/flaml-tutorial-pydata-23.md
@@ -4,7 +4,7 @@
 
 **Date and Time**: 04-26, 09:00–10:30 PT.
 
-Location:  Microsoft Conference Center, Seattle, WA.
+Location: Microsoft Conference Center, Seattle, WA.
 
 Duration: 1.5 hours
 
diff --git a/website/docs/Best-Practices.md b/website/docs/Best-Practices.md
@@ -79,7 +79,6 @@ from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from flaml import AutoML
 
-
 X, y = load_iris(return_X_y=True, as_frame=True)
 X_train, X_test, y_train, y_test = train_test_split(
     X, y, test_size=0.2, random_state=42
@@ -110,7 +109,6 @@ from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from flaml import AutoML
 
-
 X, y = load_iris(return_X_y=True, as_frame=True)
 X_train, X_test, y_train, y_test = train_test_split(
     X, y, test_size=0.2, random_state=42
diff --git a/website/docs/Contribute.md b/website/docs/Contribute.md
@@ -49,7 +49,7 @@ print(flaml.__version__)
 ```
 
 - Please ensure all **code snippets and error messages are formatted in
-  appropriate code blocks**.  See [Creating and highlighting code blocks](https://help.github.com/articles/creating-and-highlighting-code-blocks)
+  appropriate code blocks**. See [Creating and highlighting code blocks](https://help.github.com/articles/creating-and-highlighting-code-blocks)
   for more details.
 
 ## Becoming a Reviewer
@@ -88,7 +88,7 @@ Run `pre-commit install` to install pre-commit into your git hooks. Before you c
 
 ### Coverage
 
-Any code you commit should not decrease coverage. To run all unit tests, install the \[test\] option under FLAML/:
+Any code you commit should not decrease coverage. To run all unit tests, install the [test] option under FLAML/:
 
 ```bash
 pip install -e."[test]"
diff --git a/website/docs/Examples/AutoML-Classification.md b/website/docs/Examples/AutoML-Classification.md
@@ -2,7 +2,7 @@
 
 ### Prerequisites
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl]"
diff --git a/website/docs/Examples/AutoML-NLP.md b/website/docs/Examples/AutoML-NLP.md
@@ -2,7 +2,7 @@
 
 ### Requirements
 
-This example requires GPU. Install the \[automl,hf\] option:
+This example requires GPU. Install the [automl,hf] option:
 
 ```python
 pip install "flaml[automl,hf]"
diff --git a/website/docs/Examples/AutoML-Rank.md b/website/docs/Examples/AutoML-Rank.md
@@ -2,7 +2,7 @@
 
 ### Prerequisites
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl]"
diff --git a/website/docs/Examples/AutoML-Regression.md b/website/docs/Examples/AutoML-Regression.md
@@ -2,7 +2,7 @@
 
 ### Prerequisites
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl]"
diff --git a/website/docs/Examples/AutoML-Time series forecast.md b/website/docs/Examples/AutoML-Time series forecast.md
@@ -2,7 +2,7 @@
 
 ### Prerequisites
 
-Install the \[automl,ts_forecast\] option.
+Install the [automl,ts_forecast] option.
 
 ```bash
 pip install "flaml[automl,ts_forecast]"
diff --git a/website/docs/Examples/AutoML-for-LightGBM.md b/website/docs/Examples/AutoML-for-LightGBM.md
diff --git a/website/docs/Examples/AutoML-for-XGBoost.md b/website/docs/Examples/AutoML-for-XGBoost.md
diff --git a/website/docs/Examples/Default-Flamlized.md b/website/docs/Examples/Default-Flamlized.md
diff --git a/website/docs/Examples/Integrate - AzureML.md b/website/docs/Examples/Integrate - AzureML.md
diff --git a/website/docs/Examples/Integrate - Scikit-learn Pipeline.md b/website/docs/Examples/Integrate - Scikit-learn Pipeline.md
diff --git a/website/docs/FAQ.md b/website/docs/FAQ.md
diff --git a/website/docs/Installation.md b/website/docs/Installation.md
diff --git a/website/docs/Use-Cases/Task-Oriented-AutoML.md b/website/docs/Use-Cases/Task-Oriented-AutoML.md
diff --git a/website/docs/Use-Cases/Tune-User-Defined-Function.md b/website/docs/Use-Cases/Tune-User-Defined-Function.md
