Port over to AutoML common

.github/workflows/dist.yml

@@ -5,25 +5,34 @@ on: [push, pull_request]
 jobs:
   dist:
     runs-on: ubuntu-latest
+
     steps:
-    - uses: actions/checkout@v2
+    - name: Check out the repo
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+
     - name: Setup Python
       uses: actions/setup-python@v2
       with:
         python-version: 3.8
+
     - name: Build dist
       run: |
         python setup.py sdist
+
     - name: Twine check
       run: |
         pip install twine
         last_dist=$(ls -t dist/auto-sklearn-*.tar.gz | head -n 1)
         twine_output=`twine check "$last_dist"`
         if [[ "$twine_output" != "Checking $last_dist: PASSED" ]]; then echo $twine_output && exit 1;fi
+
     - name: Install dist
       run: |
         last_dist=$(ls -t dist/auto-sklearn-*.tar.gz | head -n 1)
         pip install $last_dist
+
     - name: PEP 561 Compliance
       run: |
         pip install mypy

.github/workflows/docker-publish.yml

@@ -12,13 +12,18 @@ jobs:
   push_to_registry:
     name: Push Docker image to GitHub Packages
     runs-on: ubuntu-latest
+
     steps:
       - name: Check out the repo
         uses: actions/checkout@v2
+        with:
+          submodules: recursive
+
       - name: Extract branch name
         shell: bash
         run: echo "##[set-output name=branch;]$(echo ${GITHUB_REF#refs/heads/})"
         id: extract_branch
+
       - name: Push to GitHub Packages
         uses: docker/build-push-action@v1
         with:
@@ -28,26 +33,32 @@ jobs:
           repository: automl/auto-sklearn/auto-sklearn
           tag_with_ref: true
           tags: ${{ steps.extract_branch.outputs.branch }}
+
       - name: Push to Docker Hub
         uses: docker/build-push-action@v1
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
           repository: mfeurer/auto-sklearn
           tags: ${{ steps.extract_branch.outputs.branch }}
+
       - name: Docker Login
         run: docker login docker.pkg.github.com -u $GITHUB_ACTOR -p $GITHUB_TOKEN
         env:
             GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+
       - name: Pull Docker image
         run: docker pull docker.pkg.github.com/$GITHUB_REPOSITORY/auto-sklearn:$BRANCH
         env:
             BRANCH: ${{ steps.extract_branch.outputs.branch }}
+
       - name: Run image
         run: docker run -i -d --name unittester -v $GITHUB_WORKSPACE:/workspace -w /workspace docker.pkg.github.com/$GITHUB_REPOSITORY/auto-sklearn:$BRANCH
         env:
             BRANCH: ${{ steps.extract_branch.outputs.branch }}
+
       - name: Auto-Sklearn loaded
         run: docker exec  -i unittester python3 -c 'import autosklearn; print(f"Auto-sklearn imported from {autosklearn.__file__}")'
+
       - name: Run unit testing
         run: docker exec  -i unittester python3 -m pytest -v test

.github/workflows/docs.yml

@@ -6,33 +6,42 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2
+      with:
+        submodules: recursive
+
     - name: Setup Python
       uses: actions/setup-python@v2
       with:
         python-version: 3.8
+
     - name: Install dependencies
       run: |
-        pip install -e .[docs,examples,examples_unix]
+        pip install -e .[docs,examples]
+
     - name: Make docs
       run: |
         cd doc
         make html
+
     - name: Check links
       run: |
         cd doc
         make linkcheck
+
     - name: Pull latest gh-pages
       if: (contains(github.ref, 'develop') || contains(github.ref, 'master')) && github.event_name == 'push'
       run: |
         cd ..
         git clone https://github.com/automl/auto-sklearn.git --branch gh-pages --single-branch gh-pages
+
     - name: Copy new doc into gh-pages
       if: (contains(github.ref, 'develop') || contains(github.ref, 'master')) && github.event_name == 'push'
       run: |
         branch_name=${GITHUB_REF##*/}
         cd ../gh-pages
         rm -rf $branch_name
         cp -r ../auto-sklearn/doc/build/html $branch_name
+
     - name: Push to gh-pages
       if: (contains(github.ref, 'develop') || contains(github.ref, 'master')) && github.event_name == 'push'
       run: |

.github/workflows/pre-commit.yaml

@@ -7,14 +7,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2
+      with:
+        submodules: recursive
+
     - name: Setup Python 3.7
       uses: actions/setup-python@v2
       with:
         python-version: 3.7
+
     - name: Install pre-commit
       run: |
         pip install pre-commit
         pre-commit install
+
     - name: Run pre-commit
       run: |
         pre-commit run --all-files

.github/workflows/pytest.yml

@@ -27,6 +27,9 @@ jobs:
     steps:
 
     - uses: actions/checkout@v2
+      with:
+        submodules: recursive
+
     - name: Setup Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
       # A note on checkout: When checking out the repository that

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "autosklearn/automl_common"]
+	path = autosklearn/automl_common
+	url = https://github.com/automl/automl_common

CONTRIBUTING.md

@@ -30,17 +30,24 @@ Following that we'll tell you about how you can test your changes locally and th
     It's important to work off the latest changes on the **development** branch.
     ```bash
     # With https
-    git clone https://github.com/your-username/auto-sklearn
+    # Note the --recurse-submodules args, we use a submodule autosklearn/automl_common
+    # so it needs to be downloaded too
+    git clone --recurse-submodules https://github.com/your-username/auto-sklearn
 
     # ... or with ssh
-    git clone [email protected]:your-username/auto-sklearn.git
+    git clone --recurse-submodules [email protected]:your-username/auto-sklearn.git
 
     # Navigate into the cloned repo
     cd auto-sklearn
 
     # Create a new branch based off the development one
     git checkout -b my_new_branch development
 
+    # If you missed the --recurse-submodules arg during clone or need to install the
+    # submodule manually, then execute the following line:
+    #
+    # git submodule udate --init --recursive
+
     # ... Alternatively, if you would prefer a more manual method
     # Show all the available branches with a * beside your current one
     git branch
@@ -50,6 +57,11 @@ Following that we'll tell you about how you can test your changes locally and th
 
     # Create a new branch based on the currently active branch
     git checkout -b my_new_branch
+
+    # If you missed the --recurse-submodules arg during clone or need to install the
+    # submodule manually, then execute the following line:
+    #
+    # git submodule udate --init --recursive
     ```
 
     The reason to create a new branch is two fold:
@@ -335,6 +347,9 @@ Lastly, if the feature really is a game changer or you're very proud of it, cons
     cd auto-sklearn
     git checkout -b my_new_branch development
 
+    # Initialize autosklearn/automl_common submodule
+    git submodule update --init --recursive
+
     # Create a virtual environment and activate it so there are no package
     # conflicts
     python -m venv my-virtual-env

MANIFEST.in

@@ -1,9 +1,17 @@
-recursive-include autosklearn/metalearning/files *.arff
-recursive-include autosklearn/metalearning/files *.csv
-recursive-include autosklearn/metalearning/files *.txt
-include autosklearn/util/logging.yaml
+include LICENSE.txt
 include requirements.txt
+include autosklearn/util/logging.yaml
 include autosklearn/requirements.txt
-recursive-include autosklearn/experimental/ *.json
-include autosklearn/experimental/askl2_training_data.json
-include LICENSE.txt
+
+# Meta-data
+recursive-include autosklearn/metalearning/files *.arff *.csv *.txt
+recursive-include autosklearn/experimental *.json
+
+# Remove tests from automl_common
+prune autosklearn/automl_common/test
+exclude autosklearn/automl_common/setup.py
+
+# Include automl_common LICENSE and README
+include autosklearn/automl_common/LICENSE
+include autosklearn/automl_common/README.md
+

autosklearn/automl.py

@@ -37,6 +37,8 @@
 from sklearn.metrics._classification import type_of_target
 from sklearn.dummy import DummyClassifier, DummyRegressor
 
+from autosklearn.automl_common.common.utils.backend import Backend, create
+
 from autosklearn.metrics import Scorer, default_metric_for_task
 from autosklearn.data.xy_data_manager import XYDataManager
 from autosklearn.data.validation import (
@@ -49,7 +51,6 @@
 from autosklearn.evaluation.abstract_evaluator import _fit_and_suppress_warnings
 from autosklearn.evaluation.train_evaluator import TrainEvaluator, _fit_with_budget
 from autosklearn.metrics import calculate_metric
-from autosklearn.util.backend import Backend, create
 from autosklearn.util.stopwatch import StopWatch
 from autosklearn.util.logging_ import (
     setup_logger,
@@ -280,6 +281,8 @@ def __init__(self,
     def _create_backend(self) -> Backend:
         return create(
             temporary_directory=self._temporary_directory,
+            output_directory=None,
+            prefix="auto-sklearn",
             delete_tmp_folder_after_terminate=self._delete_tmp_folder_after_terminate,
         )
 

autosklearn/ensemble_builder.py

@@ -24,11 +24,12 @@
 from smac.runhistory.runhistory import RunInfo, RunValue
 from smac.tae.base import StatusType
 
-from autosklearn.util.backend import Backend
+from autosklearn.automl_common.common.utils.backend import Backend
+from autosklearn.automl_common.common.ensemble_building.abstract_ensemble import AbstractEnsemble
+
 from autosklearn.constants import BINARY_CLASSIFICATION
 from autosklearn.metrics import calculate_score, calculate_loss, Scorer
 from autosklearn.ensembles.ensemble_selection import EnsembleSelection
-from autosklearn.ensembles.abstract_ensemble import AbstractEnsemble
 from autosklearn.util.logging_ import get_named_client_logger
 from autosklearn.util.parallel import preload_modules
 

autosklearn/ensembles/singlebest_ensemble.py

@@ -5,10 +5,10 @@
 
 from smac.runhistory.runhistory import RunHistory
 
+from autosklearn.automl_common.common.utils.backend import Backend
 from autosklearn.ensembles.abstract_ensemble import AbstractEnsemble
 from autosklearn.metrics import Scorer
 from autosklearn.pipeline.base import BasePipeline
-from autosklearn.util.backend import Backend
 
 
 class SingleBest(AbstractEnsemble):

autosklearn/evaluation/__init__.py

@@ -19,14 +19,15 @@
 
 from sklearn.model_selection._split import _RepeatedSplits, BaseShuffleSplit,\
     BaseCrossValidator
-from autosklearn.metrics import Scorer
 
+from autosklearn.automl_common.common.utils.backend import Backend
+
+from autosklearn.metrics import Scorer
 import autosklearn.evaluation.train_evaluator
 import autosklearn.evaluation.test_evaluator
 import autosklearn.evaluation.util
 import autosklearn.pipeline.components
 from autosklearn.evaluation.train_evaluator import TYPE_ADDITIONAL_INFO
-from autosklearn.util.backend import Backend
 from autosklearn.util.logging_ import PickableLoggerAdapter, get_named_client_logger
 from autosklearn.util.parallel import preload_modules
 

autosklearn/evaluation/abstract_evaluator.py

@@ -14,6 +14,8 @@
 
 from threadpoolctl import threadpool_limits
 
+from autosklearn.automl_common.common.utils.backend import Backend
+
 import autosklearn.pipeline.classification
 import autosklearn.pipeline.regression
 from autosklearn.pipeline.components.base import ThirdPartyComponents, _addons
@@ -28,7 +30,6 @@
     convert_multioutput_multiclass_to_multilabel
 )
 from autosklearn.metrics import calculate_loss, Scorer
-from autosklearn.util.backend import Backend
 from autosklearn.util.logging_ import PicklableClientLogger, get_named_client_logger
 
 from ConfigSpace import Configuration

autosklearn/evaluation/test_evaluator.py

@@ -8,13 +8,14 @@
 
 from smac.tae import StatusType
 
+from autosklearn.automl_common.common.utils.backend import Backend
+
 from autosklearn.evaluation.abstract_evaluator import (
     AbstractEvaluator,
     _fit_and_suppress_warnings,
 )
 from autosklearn.pipeline.components.base import ThirdPartyComponents
 from autosklearn.metrics import calculate_loss, Scorer
-from autosklearn.util.backend import Backend
 
 
 __all__ = [

autosklearn/evaluation/train_evaluator.py

@@ -17,6 +17,8 @@
     StratifiedKFold, train_test_split, BaseCrossValidator, PredefinedSplit
 from sklearn.model_selection._split import _RepeatedSplits, BaseShuffleSplit
 
+from autosklearn.automl_common.common.utils.backend import Backend
+
 from autosklearn.evaluation.abstract_evaluator import (
     AbstractEvaluator,
     TYPE_ADDITIONAL_INFO,
@@ -37,7 +39,6 @@
 from autosklearn.pipeline.base import PIPELINE_DATA_DTYPE
 from autosklearn.pipeline.components.base import IterativeComponent, ThirdPartyComponents
 from autosklearn.metrics import Scorer
-from autosklearn.util.backend import Backend
 from autosklearn.util.logging_ import PicklableClientLogger