Fix Invalid Component 'NoPreprocessing' in 'data_preprocessor' Argument (Fixes #1745)

.github/workflows/citation_cff.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out a copy of the repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v3.1.0
 
       - name: Check whether the citation metadata from CITATION.cff is valid
         uses: citation-file-format/[email protected]

.github/workflows/dist.yml

@@ -22,7 +22,7 @@ jobs:
 
     steps:
     - name: Check out the repo
-      uses: actions/checkout@v3
+      uses: actions/checkout@v3.1.0
       with:
         submodules: recursive
 

.github/workflows/docker-publish.yml

@@ -22,7 +22,7 @@ jobs:
 
     steps:
       - name: Check out the repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v3.1.0
         with:
           submodules: recursive
 

.github/workflows/docs.yml

@@ -23,7 +23,7 @@ jobs:
     steps:
 
     - name: Checkout
-      uses: actions/checkout@v3
+      uses: actions/checkout@v3.1.0
       with:
         submodules: recursive
 

.github/workflows/generate-baselines.yml

@@ -64,7 +64,7 @@ jobs:
           python-version: ${{ steps.python-version.outputs.value }}
 
       - name: Checkout Automlbenchmark
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3.1.0
         with:
           repository: ${{ env.AUTOMLBENCHMARK_REPO }}
           ref: ${{ env.AUTOMLBENCHMARK_REF }}

.github/workflows/pre-commit-update.yml

@@ -11,7 +11,7 @@ jobs:
   auto-update:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3.1.0
 
       - uses: actions/setup-python@v2
 

.github/workflows/pre-commit.yaml

@@ -20,7 +20,7 @@ jobs:
   run-all-files:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v3.1.0
       with:
         submodules: recursive
 

.github/workflows/pytest.yml

@@ -74,7 +74,7 @@ jobs:
     steps:
 
     - name: Checkout
-      uses: actions/checkout@v3
+      uses: actions/checkout@v3.1.0
       with:
         submodules: recursive
 

.github/workflows/regressions.yml

@@ -82,7 +82,7 @@ jobs:
         #   branch: the branch name
 
       - name: Checkout Automlbenchmark
-        uses: actions/checkout@v3
+        uses: actions/checkout@v3.1.0
         with:
           repository: ${{ env.AUTOMLBENCHMARK_REPO }}
           ref: ${{ env.AUTOMLBENCHMARK_REF }}

.github/workflows/stale.yaml

@@ -9,7 +9,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v5
+      - uses: actions/stale@v6
         with:
           days-before-stale: 60
           days-before-close: 7

.pre-commit-config.yaml

@@ -4,7 +4,7 @@
 repos:
 
   - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+    rev: 5.11.5
     hooks:
       - id: isort
         name: isort imports autosklearn
@@ -15,7 +15,7 @@ repos:
         files: test/.*
 
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.3.0
     hooks:
       - id: black
         name: black formatter autosklearn
@@ -31,15 +31,15 @@ repos:
 
   # This is disabled as most modules fail this
   - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.1.1
+    rev: 6.3.0
     hooks:
       - id: pydocstyle
         files: DISABLED # autosklearn/.*
         always_run: false
         additional_dependencies: ["toml"] # Needed to parse pyproject.toml
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    rev: v1.2.0
     hooks:
       - id: mypy
         name: mypy auto-sklearn

CONTRIBUTING.md

@@ -252,10 +252,11 @@ Lastly, if the feature really is a game changer or you're very proud of it, cons
     make doc
     ```
     *   If you're unfamiliar with sphinx, it's a documentation generator which can read comments and docstrings from within the code and generate html documentation.
-    *   If you've added documentation, we also has a command `linkcheck` for making sure all the links correctly go to some destination.
+    *   If you've added documentation, we also have a command `links` for making 
+        sure all the links correctly go to some destination.
         This helps tests for dead links or accidental typos.
     ```bash
-    make linkcheck
+    make links
     ```
     *   We also use sphinx-gallery which can take python files (such as those in the `examples` folder) and run them, creating html which shows the code and the output it generates.
     ```bash
@@ -396,7 +397,7 @@ Lastly, if the feature really is a game changer or you're very proud of it, cons
     # If you changed documentation:
     # This will generate all documentation and check links
     make doc
-    make linkcheck
+    make links
     make examples  # mainly needed if you modified some examples
 
     # ... fix any issues

autosklearn/__version__.py

@@ -1,4 +1,4 @@
 """Version information."""
 
 # The following line *must* be the last in the module, exactly as formatted:
-__version__ = "0.15.0"
+__version__ = "0.16.0dev"

autosklearn/automl.py

@@ -120,6 +120,7 @@
     warnings_to,
 )
 from autosklearn.util.parallel import preload_modules
+from autosklearn.util.progress_bar import ProgressBar
 from autosklearn.util.smac_wrap import SMACCallback, SmacRunCallback
 from autosklearn.util.stopwatch import StopWatch
 
@@ -239,6 +240,7 @@ def __init__(
         get_trials_callback: SMACCallback | None = None,
         dataset_compression: bool | Mapping[str, Any] = True,
         allow_string_features: bool = True,
+        disable_progress_bar: bool = False,
     ):
         super().__init__()
 
@@ -295,6 +297,7 @@ def __init__(
         self.logging_config = logging_config
         self.precision = precision
         self.allow_string_features = allow_string_features
+        self.disable_progress_bar = disable_progress_bar
         self._initial_configurations_via_metalearning = (
             initial_configurations_via_metalearning
         )
@@ -626,6 +629,12 @@ def fit(
         # By default try to use the TCP logging port or get a new port
         self._logger_port = logging.handlers.DEFAULT_TCP_LOGGING_PORT
 
+        progress_bar = ProgressBar(
+            total=self._time_for_task,
+            disable=self.disable_progress_bar,
+            desc="Fitting to the training data",
+            colour="green",
+        )
         # Once we start the logging server, it starts in a new process
         # If an error occurs then we want to make sure that we exit cleanly
         # and shut it down, else it might hang
@@ -643,6 +652,7 @@ def fit(
                 # space
                 self._backend.save_start_time(self._seed)
 
+            progress_bar.start()
             self._stopwatch = StopWatch()
 
             # Make sure that input is valid
@@ -961,6 +971,7 @@ def fit(
             self._logger.exception(e)
             raise e
         finally:
+            progress_bar.join()
             self._fit_cleanup()
 
         self.fitted = True
@@ -1910,15 +1921,17 @@ def cv_results_(self):
             metric_dict[metric.name] = []
             metric_mask[metric.name] = []
 
+        model_ids = []
         mean_fit_time = []
         params = []
         status = []
         budgets = []
 
-        for run_key in self.runhistory_.data:
-            run_value = self.runhistory_.data[run_key]
+        for run_key, run_value in self.runhistory_.data.items():
             config_id = run_key.config_id
             config = self.runhistory_.ids_config[config_id]
+            if run_value.additional_info and "num_run" in run_value.additional_info:
+                model_ids.append(run_value.additional_info["num_run"])
 
             s = run_value.status
             if s == StatusType.SUCCESS:
@@ -1979,6 +1992,8 @@ def cv_results_(self):
                 metric_dict[metric.name].append(metric_value)
                 metric_mask[metric.name].append(mask_value)
 
+        results["model_ids"] = model_ids
+
         if len(self._metrics) == 1:
             results["mean_test_score"] = np.array(metric_dict[self._metrics[0].name])
             rank_order = -1 * self._metrics[0]._sign * results["mean_test_score"]
@@ -2154,14 +2169,11 @@ def show_models(self) -> dict[int, Any]:
             warnings.warn("No ensemble found. Returning empty dictionary.")
             return ensemble_dict
 
-        def has_key(rv, key):
-            return rv.additional_info and key in rv.additional_info
-
         table_dict = {}
-        for run_key, run_val in self.runhistory_.data.items():
-            if has_key(run_val, "num_run"):
-                model_id = run_val.additional_info["num_run"]
-                table_dict[model_id] = {"model_id": model_id, "cost": run_val.cost}
+        for run_key, run_value in self.runhistory_.data.items():
+            if run_value.additional_info and "num_run" in run_value.additional_info:
+                model_id = run_value.additional_info["num_run"]
+                table_dict[model_id] = {"model_id": model_id, "cost": run_value.cost}
 
         # Checking if the dictionary is empty
         if not table_dict:
@@ -2174,21 +2186,20 @@ def has_key(rv, key):
 
         table = pd.DataFrame.from_dict(table_dict, orient="index")
         table.sort_values(by="cost", inplace=True)
+        table["rank"] = np.arange(1, len(table.index) + 1)
 
         # Check which resampling strategy is chosen and selecting the appropriate models
         is_cv = self._resampling_strategy == "cv"
         models = self.cv_models_ if is_cv else self.models_
 
-        rank = 1  # Initializing rank for the first model
         for (_, model_id, _), model in models.items():
             model_dict = {}  # Declaring model dictionary
 
             # Inserting model_id, rank, cost and ensemble weight
             model_dict["model_id"] = table.loc[model_id]["model_id"].astype(int)
-            model_dict["rank"] = rank
+            model_dict["rank"] = table.loc[model_id]["rank"].astype(int)
             model_dict["cost"] = table.loc[model_id]["cost"]
             model_dict["ensemble_weight"] = table.loc[model_id]["ensemble_weight"]
-            rank += 1  # Incrementing rank by 1 for the next model
 
             # The steps in the models pipeline are as follows:
             # 'data_preprocessor': DataPreprocessor,

autosklearn/estimators.py

@@ -76,6 +76,7 @@ def __init__(
         get_trials_callback: SMACCallback | None = None,
         dataset_compression: Union[bool, Mapping[str, Any]] = True,
         allow_string_features: bool = True,
+        disable_progress_bar: bool = False,
     ):
         """
         Parameters
@@ -275,12 +276,12 @@ def __init__(
 
         smac_scenario_args : dict, optional (None)
             Additional arguments inserted into the scenario of SMAC. See the
-            `SMAC documentation <https://automl.github.io/SMAC3/main/api/smac.scenario.scenario.html#module-smac.scenario.scenario>`_
+            `SMAC documentation <https://automl.github.io/SMAC3/main/api/smac.scenario.html#smac.scenario.Scenario>`_
             for a list of available arguments.
 
         get_smac_object_callback : callable
             Callback function to create an object of class
-            `smac.optimizer.smbo.SMBO <https://automl.github.io/SMAC3/main/api/smac.optimizer.smbo.html>`_.
+            `smac.facade.AbstractFacade <https://automl.github.io/SMAC3/main/api/smac.facade.html>`_.
             The function must accept the arguments ``scenario_dict``,
             ``instances``, ``num_params``, ``runhistory``, ``seed`` and ``ta``.
             This is an advanced feature. Use only if you are familiar with
@@ -381,6 +382,10 @@ def __init__(
             Whether autosklearn should process string features. By default the
             textpreprocessing is enabled.
 
+        disable_progress_bar: bool = False
+            Whether to disable the progress bar that is displayed in the console
+            while fitting to the training data.
+
         Attributes
         ----------
         cv_results_ : dict of numpy (masked) ndarrays
@@ -475,6 +480,7 @@ def __init__(
         self.get_trials_callback = get_trials_callback
         self.dataset_compression = dataset_compression
         self.allow_string_features = allow_string_features
+        self.disable_progress_bar = disable_progress_bar
 
         self.automl_ = None  # type: Optional[AutoML]
 
@@ -525,6 +531,7 @@ def build_automl(self):
             get_trials_callback=self.get_trials_callback,
             dataset_compression=self.dataset_compression,
             allow_string_features=self.allow_string_features,
+            disable_progress_bar=self.disable_progress_bar,
         )
 
         return automl

autosklearn/experimental/askl2.py

@@ -166,6 +166,7 @@ def __init__(
         load_models: bool = True,
         dataset_compression: Union[bool, Mapping[str, Any]] = True,
         allow_string_features: bool = True,
+        disable_progress_bar: bool = False,
     ):
 
         """
@@ -263,7 +264,7 @@ def __init__(
 
         smac_scenario_args : dict, optional (None)
             Additional arguments inserted into the scenario of SMAC. See the
-            `SMAC documentation <https://automl.github.io/SMAC3/main/api/smac.scenario.scenario.html#module-smac.scenario.scenario>`_
+            `SMAC documentation <https://automl.github.io/SMAC3/main/api/smac.scenario.html#smac.scenario.Scenario>`_
             for a list of available arguments.
 
         logging_config : dict, optional (None)
@@ -284,6 +285,10 @@ def __init__(
         load_models : bool, optional (True)
             Whether to load the models after fitting Auto-sklearn.
 
+        disable_progress_bar: bool = False
+            Whether to disable the progress bar that is displayed in the console
+            while fitting to the training data.
+
         Attributes
         ----------
 
@@ -337,6 +342,7 @@ def __init__(
             scoring_functions=scoring_functions,
             load_models=load_models,
             allow_string_features=allow_string_features,
+            disable_progress_bar=disable_progress_bar,
         )
 
     def train_selectors(self, selected_metric=None):