Merge pull request #4 from pydata/master

Merge new changes in pydata master

Author: phausamann

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,5 @@
- - [ ] Closes #xxxx (remove if there is no corresponding issue, which should only be the case for minor changes)
- - [ ] Tests added (for all bug fixes or enhancements)
- - [ ] Fully documented, including `whats-new.rst` for all changes and `api.rst` for new API (remove if this change should not be visible to users, e.g., if it is an internal clean-up, or if this is part of a larger project that will be documented later)
+<!-- Feel free to remove check-list items aren't relevant to your change -->
+
+ - [ ] Closes #xxxx
+ - [ ] Tests added
+ - [ ] Fully documented, including `whats-new.rst` for all changes and `api.rst` for new API

.github/stale.yml

@@ -0,0 +1,59 @@
+# Configuration for probot-stale - https://github.com/probot/stale
+
+# Number of days of inactivity before an Issue or Pull Request becomes stale
+daysUntilStale: 700  # start with a large number and reduce shortly
+
+# Number of days of inactivity before an Issue or Pull Request with the stale label is closed.
+# Set to false to disable. If disabled, issues still need to be closed manually, but will remain marked as stale.
+daysUntilClose: 30
+
+# Issues or Pull Requests with these labels will never be considered stale. Set to `[]` to disable
+exemptLabels:
+  - pinned
+  - security
+  - "[Status] Maybe Later"
+
+# Set to true to ignore issues in a project (defaults to false)
+exemptProjects: false
+
+# Set to true to ignore issues in a milestone (defaults to false)
+exemptMilestones: false
+
+# Set to true to ignore issues with an assignee (defaults to false)
+exemptAssignees: true
+
+# Label to use when marking as stale
+staleLabel: stale
+
+# Comment to post when marking as stale. Set to `false` to disable
+markComment: |
+  In order to maintain a list of currently relevant issues, we mark issues as stale after a period of inactivity
+
+  If this issue remains relevant, please comment here or remove the `stale` label; otherwise it will be marked as closed automatically
+
+# Comment to post when removing the stale label.
+# unmarkComment: >
+#   Your comment here.
+
+# Comment to post when closing a stale Issue or Pull Request.
+# closeComment: >
+#   Your comment here.
+
+# Limit the number of actions per hour, from 1-30. Default is 30
+limitPerRun: 1  # start with a small number
+
+
+# Limit to only `issues` or `pulls`
+# only: issues
+
+# Optionally, specify configuration settings that are specific to just 'issues' or 'pulls':
+# pulls:
+#   daysUntilStale: 30
+#   markComment: >
+#     This pull request has been automatically marked as stale because it has not had
+#     recent activity. It will be closed if no further activity occurs. Thank you
+#     for your contributions.
+
+# issues:
+#   exemptLabels:
+#     - confirmed

.pep8speaks.yml

@@ -1,12 +1,16 @@
 # File : .pep8speaks.yml
 
+# This should be kept in sync with the duplicate config in the [pycodestyle]
+# block of setup.cfg.
+
 scanner:
-    diff_only: True  # If True, errors caused by only the patch are shown
+    diff_only: False  # If True, errors caused by only the patch are shown
 
 pycodestyle:
     max-line-length: 79
     ignore:  # Errors and warnings to ignore
-        - E402,  # module level import not at top of file
-        - E731,  # do not assign a lambda expression, use a def
-        - W503   # line break before binary operator
-        - W504   # line break after binary operator
+        - E402  # module level import not at top of file
+        - E731  # do not assign a lambda expression, use a def
+        - E741  # ambiguous variable name
+        - W503  # line break before binary operator
+        - W504  # line break after binary operator

.travis.yml

@@ -10,58 +10,41 @@ branches:
 matrix:
   fast_finish: true
   include:
-  - env: CONDA_ENV=py27-min
-  - env: CONDA_ENV=py27-cdat+iris+pynio
+  - env: CONDA_ENV=py35-min
   - env: CONDA_ENV=py35
   - env: CONDA_ENV=py36
   - env: CONDA_ENV=py37
   - env:
     - CONDA_ENV=py36
     - EXTRA_FLAGS="--run-flaky --run-network-tests"
-  - env: CONDA_ENV=py36-netcdf4-dev
-    addons:
-      apt_packages:
-        - libhdf5-serial-dev
-        - netcdf-bin
-        - libnetcdf-dev
   - env: CONDA_ENV=py36-dask-dev
   - env: CONDA_ENV=py36-pandas-dev
-  - env: CONDA_ENV=py36-bottleneck-dev
-  - env: CONDA_ENV=py36-condaforge-rc
-  - env: CONDA_ENV=py36-pynio-dev
-  - env: CONDA_ENV=py36-rasterio-0.36
+  - env: CONDA_ENV=py36-rasterio
   - env: CONDA_ENV=py36-zarr-dev
   - env: CONDA_ENV=docs
+  - env: CONDA_ENV=lint
   - env: CONDA_ENV=py36-hypothesis
 
   allow_failures:
   - env:
     - CONDA_ENV=py36
     - EXTRA_FLAGS="--run-flaky --run-network-tests"
-  - env: CONDA_ENV=py36-netcdf4-dev
-    addons:
-      apt_packages:
-        - libhdf5-serial-dev
-        - netcdf-bin
-        - libnetcdf-dev
   - env: CONDA_ENV=py36-pandas-dev
-  - env: CONDA_ENV=py36-bottleneck-dev
-  - env: CONDA_ENV=py36-condaforge-rc
-  - env: CONDA_ENV=py36-pynio-dev
   - env: CONDA_ENV=py36-zarr-dev
 
 before_install:
-  - wget http://repo.continuum.io/miniconda/Miniconda3-3.16.0-Linux-x86_64.sh -O miniconda.sh;
+  - wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh;
   - bash miniconda.sh -b -p $HOME/miniconda
   - export PATH="$HOME/miniconda/bin:$PATH"
   - hash -r
   - conda config --set always_yes yes --set changeps1 no --set show_channel_urls true
-  - conda update -q conda
   - conda info -a
 
 install:
   - if [[ "$CONDA_ENV" == "docs" ]]; then
       conda env create -n test_env --file doc/environment.yml;
+    elif [[ "$CONDA_ENV" == "lint" ]]; then
+      conda env create -n test_env --file ci/requirements-py37.yml;
     else
       conda env create -n test_env --file ci/requirements-$CONDA_ENV.yml;
     fi
@@ -75,8 +58,10 @@ script:
   - python --version
   - python -OO -c "import xarray"
   - if [[ "$CONDA_ENV" == "docs" ]]; then
-      conda install -c conda-forge sphinx sphinx_rtd_theme sphinx-gallery numpydoc;
-      sphinx-build -n -j auto -b html -d _build/doctrees doc _build/html;
+      cd doc;
+      sphinx-build -n -j auto -b html -d _build/doctrees . _build/html;
+    elif [[ "$CONDA_ENV" == "lint" ]]; then
+      pycodestyle xarray ;
     elif [[ "$CONDA_ENV" == "py36-hypothesis" ]]; then
       pytest properties ;
     else

README.rst

@@ -9,35 +9,47 @@ xarray: N-D labeled arrays and datasets
    :target: https://coveralls.io/r/pydata/xarray
 .. image:: https://readthedocs.org/projects/xray/badge/?version=latest
    :target: http://xarray.pydata.org/
-.. image:: https://img.shields.io/pypi/v/xarray.svg
-   :target: https://pypi.python.org/pypi/xarray/
-.. image:: https://zenodo.org/badge/13221727.svg
-  :target: https://zenodo.org/badge/latestdoi/13221727
 .. image:: http://img.shields.io/badge/benchmarked%20by-asv-green.svg?style=flat
   :target: http://pandas.pydata.org/speed/xarray/
-.. image:: https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A
-  :target: http://numfocus.org
+.. image:: https://img.shields.io/pypi/v/xarray.svg
+   :target: https://pypi.python.org/pypi/xarray/
+
+**xarray** (formerly **xray**) is an open source project and Python package
+that makes working with labelled multi-dimensional arrays simple,
+efficient, and fun!
 
-**xarray** (formerly **xray**) is an open source project and Python package that aims to bring the
-labeled data power of pandas_ to the physical sciences, by providing
-N-dimensional variants of the core pandas data structures.
+Xarray introduces labels in the form of dimensions, coordinates and
+attributes on top of raw NumPy_-like arrays, which allows for a more
+intuitive, more concise, and less error-prone developer experience.
+The package includes a large and growing library of domain-agnostic functions
+for advanced analytics and visualization with these data structures.
 
-Our goal is to provide a pandas-like and pandas-compatible toolkit for
-analytics on multi-dimensional arrays, rather than the tabular data for which
-pandas excels. Our approach adopts the `Common Data Model`_ for self-
-describing scientific data in widespread use in the Earth sciences:
-``xarray.Dataset`` is an in-memory representation of a netCDF file.
+Xarray was inspired by and borrows heavily from pandas_, the popular data
+analysis package focused on labelled tabular data.
+It is particularly tailored to working with netCDF_ files, which were the
+source of xarray's data model, and integrates tightly with dask_ for parallel
+computing.
 
+.. _NumPy: http://www.numpy.org
 .. _pandas: http://pandas.pydata.org
-.. _Common Data Model: http://www.unidata.ucar.edu/software/thredds/current/netcdf-java/CDM
+.. _dask: http://dask.org
 .. _netCDF: http://www.unidata.ucar.edu/software/netcdf
-.. _OPeNDAP: http://www.opendap.org/
 
 Why xarray?
 -----------
 
-Adding dimensions names and coordinate indexes to numpy's ndarray_ makes many
-powerful array operations possible:
+Multi-dimensional (a.k.a. N-dimensional, ND) arrays (sometimes called
+"tensors") are an essential part of computational science.
+They are encountered in a wide range of fields, including physics, astronomy,
+geoscience, bioinformatics, engineering, finance, and deep learning.
+In Python, NumPy_ provides the fundamental data structure and API for
+working with raw ND arrays.
+However, real-world datasets are usually more than just raw numbers;
+they have labels which encode information about how the array values map
+to locations in space, time, etc.
+
+Xarray doesn't just keep track of labels on arrays -- it uses them to provide a
+powerful and concise interface. For example:
 
 -  Apply operations over dimensions by name: ``x.sum('time')``.
 -  Select values by label instead of integer location:
@@ -51,42 +63,10 @@ powerful array operations possible:
 -  Keep track of arbitrary metadata in the form of a Python dictionary:
    ``x.attrs``.
 
-pandas_ provides many of these features, but it does not make use of dimension
-names, and its core data structures are fixed dimensional arrays.
-
-Why isn't pandas enough?
-------------------------
-
-pandas_ excels at working with tabular data. That suffices for many statistical
-analyses, but physical scientists rely on N-dimensional arrays -- which is
-where xarray comes in.
-
-xarray aims to provide a data analysis toolkit as powerful as pandas_ but
-designed for working with homogeneous N-dimensional arrays
-instead of tabular data. When possible, we copy the pandas API and rely on
-pandas's highly optimized internals (in particular, for fast indexing).
-
-Why netCDF?
------------
-
-Because xarray implements the same data model as the netCDF_ file format,
-xarray datasets have a natural and portable serialization format. But it is also
-easy to robustly convert an xarray ``DataArray`` to and from a numpy ``ndarray``
-or a pandas ``DataFrame`` or ``Series``, providing compatibility with the full
-`PyData ecosystem <http://pydata.org/>`__.
-
-Our target audience is anyone who needs N-dimensional labeled arrays, but we
-are particularly focused on the data analysis needs of physical scientists --
-especially geoscientists who already know and love netCDF_.
-
-.. _ndarray: http://docs.scipy.org/doc/numpy/reference/arrays.ndarray.html
-.. _pandas: http://pandas.pydata.org
-.. _netCDF: http://www.unidata.ucar.edu/software/netcdf
-
 Documentation
 -------------
 
-The official documentation is hosted on ReadTheDocs at http://xarray.pydata.org/
+Learn more about xarray in its official documentation at http://xarray.pydata.org/
 
 Contributing
 ------------
@@ -134,7 +114,7 @@ __ http://climate.com/
 License
 -------
 
-Copyright 2014-2018, xarray Developers
+Copyright 2014-2019, xarray Developers
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

appveyor.yml

@@ -7,20 +7,14 @@ branches:
 environment:
 
   matrix:
-    - PYTHON: "C:\\Python27-conda32"
-      PYTHON_VERSION: "2.7"
-      PYTHON_ARCH: "32"
-      CONDA_ENV: "py27-windows"
-
-    - PYTHON: "C:\\Python27-conda64"
-      PYTHON_VERSION: "2.7"
-      PYTHON_ARCH: "64"
-      CONDA_ENV: "py27-windows"
-
     - PYTHON: "C:\\Python36-conda64"
       PYTHON_VERSION: "3.6"
       PYTHON_ARCH: "64"
       CONDA_ENV: "py36-windows"
+    - PYTHON: "C:\\Python37-conda64"
+      PYTHON_VERSION: "3.7"
+      PYTHON_ARCH: "64"
+      CONDA_ENV: "py37-windows"
 
 install:
   # Install miniconda Python

asv_bench/asv.conf.json

@@ -40,7 +40,7 @@
 
     // The Pythons you'd like to test against.  If not provided, defaults
     // to the current version of Python used to run `asv`.
-    "pythons": ["2.7", "3.6"],
+    "pythons": ["3.6"],
 
     // The matrix of dependencies to test.  Each key is the name of a
     // package (in PyPI) and the values are version numbers.  An empty

ci/install_python.ps1

@@ -2,16 +2,16 @@
 # Authors: Olivier Grisel, Jonathan Helmus and Kyle Kastner
 # License: CC0 1.0 Universal: http://creativecommons.org/publicdomain/zero/1.0/
 
-$MINICONDA_URL = "http://repo.continuum.io/miniconda/"
+$MINICONDA_URL = "https://repo.anaconda.com/miniconda/"
 $BASE_URL = "https://www.python.org/ftp/python/"
 
 
 function DownloadMiniconda ($python_version, $platform_suffix) {
     $webclient = New-Object System.Net.WebClient
-    if ($python_version -match "3.6") {
-        $filename = "Miniconda3-latest-Windows-" + $platform_suffix + ".exe"
-    } else {
+    if ($python_version -match "2.7") {
         $filename = "Miniconda2-latest-Windows-" + $platform_suffix + ".exe"
+    } else {
+        $filename = "Miniconda3-latest-Windows-" + $platform_suffix + ".exe"
     }
     $url = $MINICONDA_URL + $filename
 

ci/requirements-py27-cdat+iris+pynio.yml

@@ -1,11 +1,12 @@
 name: test_env
 dependencies:
-  - python=2.7
+  - python=3.5
   - pytest
   - flake8
   - mock
   - numpy=1.12
   - pandas=0.19
   - pip:
-    - coveralls
+    - pytest-env
     - pytest-cov
+    - coveralls