Fix isinstance usage issues (#1488)

thinkall · web-flow · commit f6a5163e6ae5 · 2026-01-19T15:19:05.000+08:00
* Fix isinstance usage issues

* Pin python version to 3.12 for pre-commit

* Update mdformat to 0.7.22
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 < 3.13**. 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/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
@@ -2,7 +2,7 @@
 
 ### Prerequisites for this example
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl] matplotlib openml"
diff --git a/website/docs/Examples/AutoML-for-XGBoost.md b/website/docs/Examples/AutoML-for-XGBoost.md
@@ -2,7 +2,7 @@
 
 ### Prerequisites for this example
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl] matplotlib openml"
diff --git a/website/docs/Examples/Default-Flamlized.md b/website/docs/Examples/Default-Flamlized.md
@@ -6,7 +6,7 @@ Flamlized estimators automatically use data-dependent default hyperparameter con
 
 ### Prerequisites
 
-This example requires the \[autozero\] option.
+This example requires the [autozero] option.
 
 ```bash
 pip install flaml[autozero] lightgbm openml
diff --git a/website/docs/Examples/Integrate - AzureML.md b/website/docs/Examples/Integrate - AzureML.md
@@ -2,7 +2,7 @@ FLAML can be used together with AzureML. On top of that, using mlflow and ray is
 
 ### Prerequisites
 
-Install the \[automl,azureml\] option.
+Install the [automl,azureml] option.
 
 ```bash
 pip install "flaml[automl,azureml]"
diff --git a/website/docs/Examples/Integrate - Scikit-learn Pipeline.md b/website/docs/Examples/Integrate - Scikit-learn Pipeline.md
@@ -2,7 +2,7 @@ As FLAML's AutoML module can be used a transformer in the Sklearn's pipeline we
 
 ### Prerequisites
 
-Install the \[automl\] option.
+Install the [automl] option.
 
 ```bash
 pip install "flaml[automl] openml"
diff --git a/website/docs/FAQ.md b/website/docs/FAQ.md
@@ -8,7 +8,7 @@
 
 ### About `low_cost_partial_config` in `tune`.
 
-- Definition and purpose: The `low_cost_partial_config` is a dictionary of subset of the hyperparameter coordinates whose value corresponds to a configuration with known low-cost (i.e., low computation cost for training the corresponding model).  The concept of low/high-cost is meaningful in the case where a subset of the hyperparameters to tune directly affects the computation cost for training the model. For example, `n_estimators` and `max_leaves` are known to affect the training cost of tree-based learners. We call this subset of hyperparameters, *cost-related hyperparameters*. In such scenarios, if you are aware of low-cost configurations for the cost-related hyperparameters, you are recommended to set them as the `low_cost_partial_config`. Using the tree-based method example again, since we know that small `n_estimators` and  `max_leaves` generally correspond to simpler models and thus lower cost, we set `{'n_estimators': 4, 'max_leaves': 4}` as the `low_cost_partial_config` by default (note that `4` is the lower bound of search space for these two hyperparameters), e.g., in [LGBM](https://github.com/microsoft/FLAML/blob/main/flaml/model.py#L215).  Configuring `low_cost_partial_config` helps the search algorithms make more cost-efficient choices.
+- Definition and purpose: The `low_cost_partial_config` is a dictionary of subset of the hyperparameter coordinates whose value corresponds to a configuration with known low-cost (i.e., low computation cost for training the corresponding model). The concept of low/high-cost is meaningful in the case where a subset of the hyperparameters to tune directly affects the computation cost for training the model. For example, `n_estimators` and `max_leaves` are known to affect the training cost of tree-based learners. We call this subset of hyperparameters, *cost-related hyperparameters*. In such scenarios, if you are aware of low-cost configurations for the cost-related hyperparameters, you are recommended to set them as the `low_cost_partial_config`. Using the tree-based method example again, since we know that small `n_estimators` and `max_leaves` generally correspond to simpler models and thus lower cost, we set `{'n_estimators': 4, 'max_leaves': 4}` as the `low_cost_partial_config` by default (note that `4` is the lower bound of search space for these two hyperparameters), e.g., in [LGBM](https://github.com/microsoft/FLAML/blob/main/flaml/model.py#L215). Configuring `low_cost_partial_config` helps the search algorithms make more cost-efficient choices.
   In AutoML, the `low_cost_init_value` in `search_space()` function for each estimator serves the same role.
 
 - Usage in practice: It is recommended to configure it if there are cost-related hyperparameters in your tuning task and you happen to know the low-cost values for them, but it is not required (It is fine to leave it the default value, i.e., `None`).
diff --git a/website/docs/Installation.md b/website/docs/Installation.md
@@ -57,7 +57,7 @@ pip install "flaml[hf]"
 #### Notebook
 
 To run the [notebook examples](https://github.com/microsoft/FLAML/tree/main/notebook),
-install flaml with the \[notebook\] option:
+install flaml with the [notebook] option:
 
 ```bash
 pip install "flaml[notebook]"
diff --git a/website/docs/Use-Cases/Task-Oriented-AutoML.md b/website/docs/Use-Cases/Task-Oriented-AutoML.md
@@ -144,7 +144,7 @@ The estimator list can contain one or more estimator names, each corresponding t
 - Built-in estimator.
   - 'lgbm': LGBMEstimator for task "classification", "regression", "rank", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators, num_leaves, min_child_samples, learning_rate, log_max_bin (logarithm of (max_bin + 1) with base 2), colsample_bytree, reg_alpha, reg_lambda.
   - 'xgboost': XGBoostSkLearnEstimator for task "classification", "regression", "rank", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators, max_leaves, min_child_weight, learning_rate, subsample, colsample_bylevel, colsample_bytree, reg_alpha, reg_lambda.
-  - 'xgb_limitdepth': XGBoostLimitDepthEstimator for task "classification", "regression", "rank", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators,  max_depth, min_child_weight, learning_rate, subsample, colsample_bylevel, colsample_bytree, reg_alpha, reg_lambda.
+  - 'xgb_limitdepth': XGBoostLimitDepthEstimator for task "classification", "regression", "rank", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators, max_depth, min_child_weight, learning_rate, subsample, colsample_bylevel, colsample_bytree, reg_alpha, reg_lambda.
   - 'rf': RandomForestEstimator for task "classification", "regression", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators, max_features, max_leaves, criterion (for classification only). Starting from v1.1.0,
     it uses a fixed random_state by default.
   - 'extra_tree': ExtraTreesEstimator for task "classification", "regression", "ts_forecast" and "ts_forecast_classification". Hyperparameters: n_estimators, max_features, max_leaves, criterion (for classification only). Starting from v1.1.0,
@@ -462,7 +462,7 @@ For both classification and regression tasks more advanced split configurations
 
 More in general, `split_type` can also be set as a custom splitter object, when `eval_method="cv"`. It needs to be an instance of a derived class of scikit-learn
 [KFold](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.KFold.html#sklearn.model_selection.KFold)
-and have `split` and `get_n_splits` methods with the same signatures.  To disable shuffling, the splitter instance must contain the attribute `shuffle=False`.
+and have `split` and `get_n_splits` methods with the same signatures. To disable shuffling, the splitter instance must contain the attribute `shuffle=False`.
 
 ### Parallel tuning
 
@@ -740,7 +740,7 @@ If you want to get a sense of how much time is needed to find the best model, yo
 
 > INFO - Estimated sufficient time budget=145194s. Estimated necessary time budget=2118s.
 
-> INFO -  at 2.6s,  estimator lgbm's best error=0.4459,     best estimator lgbm's best error=0.4459
+> INFO - at 2.6s, estimator lgbm's best error=0.4459, best estimator lgbm's best error=0.4459
 
 You will see that the time to finish the first and cheapest trial is 2.6 seconds. The estimated necessary time budget is 2118 seconds, and the estimated sufficient time budget is 145194 seconds. Note that this is only an estimated range to help you decide your budget.
 
diff --git a/website/docs/Use-Cases/Tune-User-Defined-Function.md b/website/docs/Use-Cases/Tune-User-Defined-Function.md
