Merge pull request #706 from openml/develop

Release version 0.9

Author: mfeurer

.gitignore

@@ -57,6 +57,7 @@ nosetests.xml
 coverage.xml
 *,cover
 .hypothesis/
+prof/
 
 # Translations
 *.mo
@@ -74,3 +75,11 @@ target/
 # IDE
 .idea
 *.swp
+
+# MYPY
+.mypy_cache
+dmypy.json
+dmypy.sock
+
+# Tests
+.pytest_cache

.travis.yml

@@ -15,15 +15,14 @@ env:
   - TEST_DIR=/tmp/test_dir/
   - MODULE=openml
   matrix:
-  - DISTRIB="conda" PYTHON_VERSION="2.7" SKLEARN_VERSION="0.20.0"
   - DISTRIB="conda" PYTHON_VERSION="3.5" SKLEARN_VERSION="0.20.0"
   - DISTRIB="conda" PYTHON_VERSION="3.6" SKLEARN_VERSION="0.20.0"
   - DISTRIB="conda" PYTHON_VERSION="3.7" SKLEARN_VERSION="0.20.0" RUN_FLAKE8="true" SKIP_TESTS="true"
   - DISTRIB="conda" PYTHON_VERSION="3.7" SKLEARN_VERSION="0.20.0" COVERAGE="true" DOCPUSH="true"
   # Checks for older scikit-learn versions (which also don't nicely work with
   # Python3.7)
   - DISTRIB="conda" PYTHON_VERSION="3.6" SKLEARN_VERSION="0.19.2"
-  - DISTRIB="conda" PYTHON_VERSION="3.6" SKLEARN_VERSION="0.18.2"
+  - DISTRIB="conda" PYTHON_VERSION="3.6" SKLEARN_VERSION="0.18.2" SCIPY_VERSION=1.2.0
 
 # Travis issue
 # https://github.com/travis-ci/travis-ci/issues/8920

CONTRIBUTING.md

@@ -19,7 +19,7 @@ local disk:
    $ cd openml-python
    ```
 
-3. Swith to the ``develop`` branch:
+3. Switch to the ``develop`` branch:
 
    ```bash
    $ git checkout develop
@@ -31,7 +31,8 @@ local disk:
    $ git checkout -b feature/my-feature
    ```
 
-   Always use a ``feature`` branch. It's good practice to never work on the ``master`` or ``develop`` branch! To make the nature of your pull request easily visible, please perpend the name of the branch with the type of changes you want to merge, such as ``feature`` if it contains a new feature, ``fix`` for a bugfix, ``doc`` for documentation and ``maint`` for other maintenance on the package.
+   Always use a ``feature`` branch. It's good practice to never work on the ``master`` or ``develop`` branch! 
+   To make the nature of your pull request easily visible, please prepend the name of the branch with the type of changes you want to merge, such as ``feature`` if it contains a new feature, ``fix`` for a bugfix, ``doc`` for documentation and ``maint`` for other maintenance on the package.
 
 4. Develop the feature on your feature branch. Add changed files using ``git add`` and then ``git commit`` files:
 
@@ -59,18 +60,25 @@ We recommended that your contribution complies with the
 following rules before you submit a pull request:
 
 -  Follow the
-   [pep8 style guilde](https://www.python.org/dev/peps/pep-0008/).
+   [pep8 style guide](https://www.python.org/dev/peps/pep-0008/).
+   With the following exceptions or additions:
+    - The max line length is 100 characters instead of 80.
+    - When creating a multi-line expression with binary operators, break before the operator.
+    - Add type hints to all function signatures.
+    (note: not all functions have type hints yet, this is work in progress.)
+    - Use the [`str.format`](https://docs.python.org/3/library/stdtypes.html#str.format) over [`printf`](https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting) style formatting.
+     E.g. use `"{} {}".format('hello', 'world')` not `"%s %s" % ('hello', 'world')`.
+     (note: old code may still use `printf`-formatting, this is work in progress.)
 
 -  If your pull request addresses an issue, please use the pull request title
    to describe the issue and mention the issue number in the pull request description. This will make sure a link back to the original issue is
    created.
 
 -  An incomplete contribution -- where you expect to do more work before
-   receiving a full review -- should be prefixed `[WIP]` (to indicate a work
-   in progress) and changed to `[MRG]` when it matures. WIPs may be useful
+   receiving a full review -- should be submitted as a `draft`. These may be useful
    to: indicate you are working on something to avoid duplicated work,
    request broad review of functionality or API, or seek collaborators.
-   WIPs often benefit from the inclusion of a
+   Drafts often benefit from the inclusion of a
    [task list](https://github.com/blog/1375-task-lists-in-gfm-issues-pulls-comments)
    in the PR description.
 
@@ -105,18 +113,18 @@ tools:
   $ pytest --cov=. path/to/tests_for_package
   ```
 
--  No pyflakes warnings, check with:
+-  No style warnings, check with:
 
   ```bash
-  $ pip install pyflakes
-  $ pyflakes path/to/module.py
+  $ pip install flake8
+  $ flake8 --ignore E402,W503 --show-source --max-line-length 100
   ```
 
--  No PEP8 warnings, check with:
+-  No mypy (typing) issues, check with:
 
   ```bash
-  $ pip install pep8
-  $ pep8 path/to/module.py
+  $ pip install mypy
+  $ mypy openml --ignore-missing-imports --follow-imports skip
   ```
 
 Filing bugs
@@ -151,8 +159,8 @@ following rules before submitting:
 New contributor tips
 --------------------
 
-A great way to start contributing to scikit-learn is to pick an item
-from the list of [Easy issues](https://github.com/openml/openml-python/issues?q=label%3Aeasy)
+A great way to start contributing to openml-python is to pick an item
+from the list of [Good First Issues](https://github.com/openml/openml-python/labels/Good%20first%20issue)
 in the issue tracker. Resolving these issues allow you to start
 contributing to the project without much prior knowledge. Your
 assistance in this area will be greatly appreciated by the more
@@ -175,6 +183,14 @@ information.
 
 For building the documentation, you will need
 [sphinx](http://sphinx.pocoo.org/),
-[matplotlib](http://matplotlib.org/), and
-[pillow](http://pillow.readthedocs.io/en/latest/).
-[sphinx-bootstrap-theme](https://ryan-roemer.github.io/sphinx-bootstrap-theme/)
+[sphinx-bootstrap-theme](https://ryan-roemer.github.io/sphinx-bootstrap-theme/),
+[sphinx-gallery](https://sphinx-gallery.github.io/)
+and
+[numpydoc](https://numpydoc.readthedocs.io/en/latest/).
+```bash
+$ pip install sphinx sphinx-bootstrap-theme sphinx-gallery numpydoc
+```
+When dependencies are installed, run
+```bash
+$ sphinx-build -b html doc YOUR_PREFERRED_OUTPUT_DIRECTORY
+```

PULL_REQUEST_TEMPLATE.md

@@ -5,8 +5,12 @@ the contribution guidelines: https://github.com/openml/openml-python/blob/master
 Please make sure that:
 
 * this pull requests is against the `develop` branch
-* you updated all docs
+* you updated all docs, this includes the changelog!
+* for any new function or class added, please add it to doc/api.rst
+    * the list of classes and functions should be alphabetical 
+* for any new functionality, consider adding a relevant example
 -->
+
 #### Reference Issue
 <!-- Example: Fixes #1234 -->
 

appveyor.yml

@@ -29,22 +29,18 @@ install:
   - rmdir C:\\cygwin /s /q
 
   # Update previous packages and install the build and runtime dependencies of the project.
-  # XXX: setuptools>23 is currently broken on Win+py3 with numpy
-  # (https://github.com/pypa/setuptools/issues/728)
-  - conda update --all --yes setuptools=23
-  - conda install --yes nb_conda nb_conda_kernels
+  - conda update conda --yes
+  - conda update --all --yes
 
   # Install the build and runtime dependencies of the project.
   - "cd C:\\projects\\openml-python"
-  - conda install --quiet --yes scikit-learn=0.18.2
-  - conda install --quiet --yes mock numpy scipy pytest requests nbformat python-dateutil nbconvert pandas matplotlib seaborn
-  - pip install liac-arff xmltodict oslo.concurrency
-  - "pip install .[test]"
-  
+  - "pip install .[examples,test]"
+  - conda install --quiet --yes scikit-learn=0.20.0
+
 
 # Not a .NET project, we build scikit-learn in the install step instead
 build: false
 
 test_script:
   - "cd C:\\projects\\openml-python"
-  - "%CMD_IN_ENV% pytest"
+  - "%CMD_IN_ENV% pytest -n 4 --timeout=600 --timeout-method=thread -sv --ignore='test_OpenMLDemo.py'"

ci_scripts/flake8_diff.sh

@@ -1,140 +1,7 @@
 #!/bin/bash
 
-# Inspired from https://github.com/scikit-learn/scikit-learn/blob/master/build_tools/travis/flake8_diff.sh
-
-# This script is used in Travis to check that PRs do not add obvious
-# flake8 violations. It relies on two things:
-#   - find common ancestor between branch and
-#     openml/openml-python remote
-#   - run flake8 --diff on the diff between the branch and the common
-#     ancestor
-#
-# Additional features:
-#   - the line numbers in Travis match the local branch on the PR
-#     author machine.
-#   - ./ci_scripts/flake8_diff.sh can be run locally for quick
-#     turn-around
-
-set -e
-# pipefail is necessary to propagate exit codes
-set -o pipefail
-
-PROJECT=openml/openml-python
-PROJECT_URL=https://github.com/$PROJECT.git
-
-# Find the remote with the project name (upstream in most cases)
-REMOTE=$(git remote -v | grep $PROJECT | cut -f1 | head -1 || echo '')
-
-# Add a temporary remote if needed. For example this is necessary when
-# Travis is configured to run in a fork. In this case 'origin' is the
-# fork and not the reference repo we want to diff against.
-if [[ -z "$REMOTE" ]]; then
-    TMP_REMOTE=tmp_reference_upstream
-    REMOTE=$TMP_REMOTE
-    git remote add $REMOTE $PROJECT_URL
-fi
-
-echo "Remotes:"
-echo '--------------------------------------------------------------------------------'
-git remote --verbose
-
-# Travis does the git clone with a limited depth (50 at the time of
-# writing). This may not be enough to find the common ancestor with
-# $REMOTE/develop so we unshallow the git checkout
-if [[ -a .git/shallow ]]; then
-    echo -e '\nTrying to unshallow the repo:'
-    echo '--------------------------------------------------------------------------------'
-    git fetch --unshallow
-fi
-
-if [[ "$TRAVIS" == "true" ]]; then
-    if [[ "$TRAVIS_PULL_REQUEST" == "false" ]]
-    then
-        # In main repo, using TRAVIS_COMMIT_RANGE to test the commits
-        # that were pushed into a branch
-        if [[ "$PROJECT" == "$TRAVIS_REPO_SLUG" ]]; then
-            if [[ -z "$TRAVIS_COMMIT_RANGE" ]]; then
-                echo "New branch, no commit range from Travis so passing this test by convention"
-                exit 0
-            fi
-            COMMIT_RANGE=$TRAVIS_COMMIT_RANGE
-        fi
-    else
-        # We want to fetch the code as it is in the PR branch and not
-        # the result of the merge into develop. This way line numbers
-        # reported by Travis will match with the local code.
-        LOCAL_BRANCH_REF=travis_pr_$TRAVIS_PULL_REQUEST
-        # In Travis the PR target is always origin
-        git fetch origin pull/$TRAVIS_PULL_REQUEST/head:refs/$LOCAL_BRANCH_REF
-    fi
-fi
-
-# If not using the commit range from Travis we need to find the common
-# ancestor between $LOCAL_BRANCH_REF and $REMOTE/develop
-if [[ -z "$COMMIT_RANGE" ]]; then
-    if [[ -z "$LOCAL_BRANCH_REF" ]]; then
-        LOCAL_BRANCH_REF=$(git rev-parse --abbrev-ref HEAD)
-    fi
-    echo -e "\nLast 2 commits in $LOCAL_BRANCH_REF:"
-    echo '--------------------------------------------------------------------------------'
-    git --no-pager log -2 $LOCAL_BRANCH_REF
-
-    REMOTE_DEV_REF="$REMOTE/develop"
-    # Make sure that $REMOTE_DEV_REF is a valid reference
-    echo -e "\nFetching $REMOTE_DEV_REF"
-    echo '--------------------------------------------------------------------------------'
-    git fetch $REMOTE develop:refs/remotes/$REMOTE_DEV_REF
-    LOCAL_BRANCH_SHORT_HASH=$(git rev-parse --short $LOCAL_BRANCH_REF)
-    REMOTE_DEV_SHORT_HASH=$(git rev-parse --short $REMOTE_DEV_REF)
-
-    COMMIT=$(git merge-base $LOCAL_BRANCH_REF $REMOTE_DEV_REF) || \
-        echo "No common ancestor found for $(git show $LOCAL_BRANCH_REF -q) and $(git show $REMOTE_DEV_REF -q)"
-
-    if [ -z "$COMMIT" ]; then
-        exit 1
-    fi
-
-    COMMIT_SHORT_HASH=$(git rev-parse --short $COMMIT)
-
-    echo -e "\nCommon ancestor between $LOCAL_BRANCH_REF ($LOCAL_BRANCH_SHORT_HASH)"\
-         "and $REMOTE_DEV_REF ($REMOTE_DEV_SHORT_HASH) is $COMMIT_SHORT_HASH:"
-    echo '--------------------------------------------------------------------------------'
-    git --no-pager show --no-patch $COMMIT_SHORT_HASH
-
-    COMMIT_RANGE="$COMMIT_SHORT_HASH..$LOCAL_BRANCH_SHORT_HASH"
-
-    if [[ -n "$TMP_REMOTE" ]]; then
-        git remote remove $TMP_REMOTE
-    fi
-
-else
-    echo "Got the commit range from Travis: $COMMIT_RANGE"
-fi
-
-echo -e '\nRunning flake8 on the diff in the range' "$COMMIT_RANGE" \
-     "($(git rev-list $COMMIT_RANGE | wc -l) commit(s)):"
-echo '--------------------------------------------------------------------------------'
-# We need the following command to exit with 0 hence the echo in case
-# there is no match
-MODIFIED_FILES="$(git diff --name-only $COMMIT_RANGE || echo "no_match")"
-
-check_files() {
-    files="$1"
-    shift
-    options="$*"
-    if [ -n "$files" ]; then
-        # Conservative approach: diff without context (--unified=0) so that code
-        # that was not changed does not create failures
-        git diff --unified=0 $COMMIT_RANGE -- $files | flake8 --ignore E402 --diff --show-source $options
-    fi
-}
-
-if [[ "$MODIFIED_FILES" == "no_match" ]]; then
-    echo "No file has been modified"
-else
-
-    check_files "$(echo "$MODIFIED_FILES" | grep -v ^examples)"
-    check_files "$(echo "$MODIFIED_FILES" | grep ^examples)" \
-        --config ./examples/.flake8
-fi
-echo -e "No problem detected by flake8\n"
+# Update /CONTRIBUTING.md if these commands change.
+# The reason for not advocating using this script directly is that it
+# might not work out of the box on Windows.
+flake8 --ignore E402,W503 --show-source --max-line-length 100 $options
+mypy openml --ignore-missing-imports --follow-imports skip

ci_scripts/install.sh

@@ -26,24 +26,29 @@ popd
 # provided versions
 conda create -n testenv --yes python=$PYTHON_VERSION pip
 source activate testenv
-pip install pytest pytest-xdist pytest-timeout numpy scipy cython scikit-learn==$SKLEARN_VERSION \
-    oslo.concurrency
+
+if [[ -v SCIPY_VERSION ]]; then
+    conda install --yes scipy=$SCIPY_VERSION
+fi
+
+python --version
+pip install -e '.[test]'
+python -c "import numpy; print('numpy %s' % numpy.__version__)"
+python -c "import scipy; print('scipy %s' % scipy.__version__)"
 
 if [[ "$EXAMPLES" == "true" ]]; then
-    pip install matplotlib jupyter notebook nbconvert nbformat jupyter_client \
-        ipython ipykernel pandas seaborn
+    pip install -e '.[examples]'
 fi
 if [[ "$DOCTEST" == "true" ]]; then
-    pip install pandas sphinx_bootstrap_theme
+    pip install sphinx_bootstrap_theme
 fi
 if [[ "$COVERAGE" == "true" ]]; then
     pip install codecov pytest-cov
 fi
 if [[ "$RUN_FLAKE8" == "true" ]]; then
-    pip install flake8
+    pip install flake8 mypy
 fi
 
-python --version
-python -c "import numpy; print('numpy %s' % numpy.__version__)"
-python -c "import scipy; print('scipy %s' % scipy.__version__)"
-pip install -e '.[test]'
+# Install scikit-learn last to make sure the openml package installation works
+# from a clean environment without scikit-learn.
+pip install scikit-learn==$SKLEARN_VERSION

ci_scripts/test.sh

@@ -22,7 +22,7 @@ run_tests() {
         PYTEST_ARGS=''
     fi
 
-    pytest -n 4 --timeout=600 --timeout-method=thread -sv --ignore='test_OpenMLDemo.py' $PYTEST_ARGS $test_dir
+    pytest -n 4 --duration=20 --timeout=600 --timeout-method=thread -sv --ignore='test_OpenMLDemo.py' $PYTEST_ARGS $test_dir
 }
 
 if [[ "$RUN_FLAKE8" == "true" ]]; then

doc/_static/codehighlightstyle.css

@@ -0,0 +1,7 @@
+.highlight .n { color: #000000 } /* code */
+.highlight .c1 { color: #1d8908 } /* comments */
+.highlight .mi { color: #0d9fe3; font-weight: bold } /* integers */
+.highlight .s1 { color: #d73c00 } /* string */
+.highlight .o { color: #292929 } /* operators */
+ /* Background color for code highlights. Color for bash highlights */
+pre { background-color: #fbfbfb; color: #000000 }