Merge pull request #1181 from automl/master

Synchronize dev and master again

.github/ISSUE_TEMPLATE/question.md

@@ -0,0 +1,29 @@
+---
+name: Question
+about: Ask a question!
+title: "[Question] My Question?"
+labels: ''
+assignees: ''
+
+---
+
+# Short Question Description
+A clear single sentence question we can try to help with?
+
+With some extra context to follow it up. This way the question is clear for both you and us without it being lost in the paragraph. 
+Some useful information to help us with your question:
+* How did this question come about? 
+* Would a small code snippet help?
+* What have you already looked at?
+
+Before you ask, please have a look at the
+* [Documentation](https://automl.github.io/auto-sklearn/master/manual.html)
+    * If it's related but not clear, please include it in your question with a link, we'll try to make it better!
+* [Examples](https://automl.github.io/auto-sklearn/master/examples/index.html) 
+    * Likewise, an example can answer many questions! However we can't cover all question with examples but if you think your question would benefit from an example, let us know!
+* [Issues](https://github.com/automl/auto-sklearn/issues?q=label%3Aquestion+)
+    * We try to label all questions with the label `Question`, maybe someone has already asked. If the question is about a feature, try searching more of the issues. If you find something related but doesn't directly answer your question, please link to it with #(issue number)!
+
+# System Details (if relevant)
+* Which version of `auto-sklearn` are you using?
+* Are you running this on Linux / Mac / ... ?

.github/workflows/stale.yaml

@@ -9,7 +9,7 @@ jobs:
     steps:
       - uses: actions/stale@v3
         with:
-          days-before-stale: 60
+          days-before-stale: 30
           days-before-close: 7
           stale-issue-message: >
             This issue has been automatically marked as stale because it has not had
@@ -18,5 +18,7 @@ jobs:
           close-issue-message: >
             This issue has been automatically closed due to inactivity.
           stale-issue-label: 'stale'
-          only-issue-labels: 'Answered,Feedback-Required,invalid,wontfix'
+          # Only issues with ANY of these labels are checked.
+          # Separate multiple labels with commas (eg. "incomplete,waiting-feedback").
+          any-of-labels: 'Answered,Feedback-Required,invalid,wontfix'
           exempt-all-milestones: true

LICENSE.txt

@@ -1,24 +1,29 @@
-Copyright (c) 2014, Matthias Feurer
+BSD 3-Clause License
+
+Copyright (c) 2014-2021, AutoML Freiburg
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:
-    * Redistributions of source code must retain the above copyright
-      notice, this list of conditions and the following disclaimer.
-    * Redistributions in binary form must reproduce the above copyright
-      notice, this list of conditions and the following disclaimer in the
-      documentation and/or other materials provided with the distribution.
-    * Neither the name of the <organization> nor the
-      names of its contributors may be used to endorse or promote products
-      derived from this software without specific prior written permission.
 
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
-ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
-DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
-(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
-ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

MANIFEST.in

@@ -4,5 +4,6 @@ recursive-include autosklearn/metalearning/files *.txt
 include autosklearn/util/logging.yaml
 include requirements.txt
 include autosklearn/requirements.txt
-recursive-include autosklearn/experimental/askl2_portfolios *.json
+recursive-include autosklearn/experimental/ *.json
 include autosklearn/experimental/askl2_training_data.json
+include LICENSE.txt

autosklearn/__version__.py

@@ -1,4 +1,4 @@
 """Version information."""
 
 # The following line *must* be the last in the module, exactly as formatted:
-__version__ = "0.12.6"
+__version__ = "0.12.7"

autosklearn/automl.py

@@ -885,9 +885,10 @@ def subsample_if_too_large(
         task: int,
     ):
         if memory_limit and isinstance(X, np.ndarray):
+
             if X.dtype == np.float32:
                 multiplier = 4
-            elif X.dtype in (np.float64, np.float):
+            elif X.dtype in (np.float64, float):
                 multiplier = 8
             elif (
                 # In spite of the names, np.float96 and np.float128
@@ -903,6 +904,21 @@ def subsample_if_too_large(
                 multiplier = 8
                 logger.warning('Unknown dtype for X: %s, assuming it takes 8 bit/number',
                                str(X.dtype))
+
+            megabytes = X.shape[0] * X.shape[1] * multiplier / 1024 / 1024
+            if memory_limit <= megabytes * 10 and X.dtype != np.float32:
+                cast_to = {
+                    8: np.float32,
+                    16: np.float64,
+                }.get(multiplier, np.float32)
+                logger.warning(
+                    'Dataset too large for memory limit %dMB, reducing the precision from %s to %s',
+                    memory_limit,
+                    X.dtype,
+                    cast_to,
+                )
+                X = X.astype(cast_to)
+
             megabytes = X.shape[0] * X.shape[1] * multiplier / 1024 / 1024
             if memory_limit <= megabytes * 10:
                 new_num_samples = int(

autosklearn/experimental/askl2.py

@@ -15,53 +15,60 @@
 import autosklearn
 from autosklearn.classification import AutoSklearnClassifier
 import autosklearn.experimental.selector
-from autosklearn.metrics import Scorer
+from autosklearn.metrics import Scorer, balanced_accuracy, roc_auc, log_loss, accuracy
 
+metrics = (balanced_accuracy, roc_auc, log_loss)
+selector_files = {}
 this_directory = pathlib.Path(__file__).resolve().parent
-training_data_file = this_directory / 'askl2_training_data.json'
-with open(training_data_file) as fh:
-    training_data = json.load(fh)
-    fh.seek(0)
-    m = hashlib.md5()
-    m.update(fh.read().encode('utf8'))
-training_data_hash = m.hexdigest()[:10]
-selector_filename = "askl2_selector_%s_%s_%s.pkl" % (
-    autosklearn.__version__,
-    sklearn.__version__,
-    training_data_hash
-)
-selector_directory = os.environ.get('XDG_CACHE_HOME')
-if selector_directory is None:
-    selector_directory = pathlib.Path.home()
-selector_directory = pathlib.Path(selector_directory).joinpath('auto-sklearn').expanduser()
-selector_file = selector_directory / selector_filename
-metafeatures = pd.DataFrame(training_data['metafeatures'])
-y_values = np.array(training_data['y_values'])
-strategies = training_data['strategies']
-minima_for_methods = training_data['minima_for_methods']
-maxima_for_methods = training_data['maxima_for_methods']
-if not selector_file.exists():
-    selector = autosklearn.experimental.selector.OneVSOneSelector(
-        configuration=training_data['configuration'],
-        default_strategy_idx=strategies.index('RF_SH-eta4-i_holdout_iterative_es_if'),
-        rng=1,
+for metric in metrics:
+    training_data_file = this_directory / metric.name / 'askl2_training_data.json'
+    with open(training_data_file) as fh:
+        training_data = json.load(fh)
+        fh.seek(0)
+        m = hashlib.md5()
+        m.update(fh.read().encode('utf8'))
+    training_data_hash = m.hexdigest()[:10]
+    selector_filename = "askl2_selector_%s_%s_%s_%s.pkl" % (
+        autosklearn.__version__,
+        sklearn.__version__,
+        metric.name,
+        training_data_hash
     )
-    selector.fit(
-        X=metafeatures,
-        y=y_values,
-        methods=strategies,
-        minima=minima_for_methods,
-        maxima=maxima_for_methods,
-    )
-    selector_file.parent.mkdir(exist_ok=True, parents=True)
-    try:
-        with open(selector_file, 'wb') as fh:
-            pickle.dump(selector, fh)
-    except Exception as e:
-        print("AutoSklearn2Classifier needs to create a selector file under "
-              "the user's home directory or XDG_CACHE_HOME. Nevertheless "
-              "the path {} is not writable.".format(selector_file))
-        raise e
+    selector_directory = os.environ.get('XDG_CACHE_HOME')
+    if selector_directory is None:
+        selector_directory = pathlib.Path.home()
+    selector_directory = pathlib.Path(selector_directory).joinpath('auto-sklearn').expanduser()
+    selector_files[metric.name] = selector_directory / selector_filename
+    metafeatures = pd.DataFrame(training_data['metafeatures'])
+    strategies = training_data['strategies']
+    y_values = pd.DataFrame(training_data['y_values'], columns=strategies, index=metafeatures.index)
+    minima_for_methods = training_data['minima_for_methods']
+    maxima_for_methods = training_data['maxima_for_methods']
+    default_strategies = training_data['tie_break_order']
+    if not selector_files[metric.name].exists():
+        selector = autosklearn.experimental.selector.OVORF(
+            configuration=training_data['configuration'],
+            random_state=np.random.RandomState(1),
+            n_estimators=500,
+            tie_break_order=default_strategies,
+        )
+        selector = autosklearn.experimental.selector.FallbackWrapper(selector, default_strategies)
+        selector.fit(
+            X=metafeatures,
+            y=y_values,
+            minima=minima_for_methods,
+            maxima=maxima_for_methods,
+        )
+        selector_files[metric.name].parent.mkdir(exist_ok=True, parents=True)
+
+        try:
+            with open(selector_files[metric.name], 'wb') as fh:
+                pickle.dump(selector, fh)
+        except Exception as e:
+            print("AutoSklearn2Classifier needs to create a selector file under "
+                  "the user's home directory or XDG_CACHE_HOME. Nevertheless "
+                  "the path {} is not writable.".format(selector_files[metric.name]))
+            raise e
 
 
 class SmacObjectCallback:
@@ -286,7 +293,7 @@ def __init__(
         Attributes
         ----------
 
-        cv_results\_ : dict of numpy (masked) ndarrays
+        cv_results_ : dict of numpy (masked) ndarrays
             A dict with keys as column headers and values as columns, that can be
             imported into a pandas ``DataFrame``.
 
@@ -334,10 +341,22 @@ def fit(self, X, y,
             feat_type=None,
             dataset_name=None):
 
+        if self.metric is None:
+            if len(y.shape) == 1 or y.shape[1] == 1:
+                self.metric = accuracy
+            else:
+                self.metric = log_loss
+
+        if self.metric in metrics:
+            metric_name = self.metric.name
+            selector_file = selector_files[metric_name]
+        else:
+            metric_name = 'balanced_accuracy'
+            selector_file = selector_files[metric_name]
         with open(selector_file, 'rb') as fh:
             selector = pickle.load(fh)
 
-        metafeatures = np.array([len(np.unique(y)), X.shape[1], X.shape[0]])
+        metafeatures = pd.DataFrame({dataset_name: [X.shape[1], X.shape[0]]}).transpose()
         selection = np.argmax(selector.predict(metafeatures))
         automl_policy = strategies[selection]
 
@@ -388,7 +407,9 @@ def fit(self, X, y,
         else:
             resampling_strategy_kwargs = None
 
-        portfolio_file = this_directory / 'askl2_portfolios' / ('%s.json' % automl_policy)
+        portfolio_file = (
+            this_directory / metric_name / 'askl2_portfolios' / ('%s.json' % automl_policy)
+        )
         with open(portfolio_file) as fh:
             portfolio_json = json.load(fh)
         portfolio = portfolio_json['portfolio']