Merge remote-tracking branch 'upstream/master' into feature/fix_wom

Author: asdf8601

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,27 +1,3 @@
-Checklist for the pandas documentation sprint (ignore this if you are doing
-an unrelated PR):
-
-- [ ] PR title is "DOC: update the <your-function-or-method> docstring"
-- [ ] The validation script passes: `scripts/validate_docstrings.py <your-function-or-method>`
-- [ ] The PEP8 style check passes: `git diff upstream/master -u -- "*.py" | flake8 --diff`
-- [ ] The html version looks good: `python doc/make.py --single <your-function-or-method>`
-- [ ] It has been proofread on language by another sprint participant
-
-Please include the output of the validation script below between the "```" ticks:
-
-```
-# paste output of "scripts/validate_docstrings.py <your-function-or-method>" here
-# between the "```" (remove this comment, but keep the "```")
-
-```
-
-If the validation script still gives errors, but you think there is a good reason
-to deviate in this case (and there are certainly such cases), please state this
-explicitly.
-
-
-Checklist for other PRs (remove this part if you are doing a PR for the pandas documentation sprint):
-
 - [ ] closes #xxxx
 - [ ] tests added / passed
 - [ ] passes `git diff upstream/master -u -- "*.py" | flake8 --diff`

.travis.yml

@@ -56,7 +56,7 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="2.7_SLOW" SLOW=true
+        - JOB="3.6_SLOW" SLOW=true
     # In allow_failures
     - dist: trusty
       env:
@@ -72,7 +72,7 @@ matrix:
     allow_failures:
       - dist: trusty
         env:
-          - JOB="2.7_SLOW" SLOW=true
+          - JOB="3.6_SLOW" SLOW=true
       - dist: trusty
         env:
           - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"

asv_bench/benchmarks/frame_ctor.py

@@ -16,11 +16,11 @@ class FromDicts(object):
 
     def setup(self):
         N, K = 5000, 50
-        index = tm.makeStringIndex(N)
-        columns = tm.makeStringIndex(K)
-        frame = DataFrame(np.random.randn(N, K), index=index, columns=columns)
+        self.index = tm.makeStringIndex(N)
+        self.columns = tm.makeStringIndex(K)
+        frame = DataFrame(np.random.randn(N, K), index=self.index,
+                          columns=self.columns)
         self.data = frame.to_dict()
-        self.some_dict = list(self.data.values())[0]
         self.dict_list = frame.to_dict(orient='records')
         self.data2 = {i: {j: float(j) for j in range(100)}
                       for i in range(2000)}
@@ -31,8 +31,14 @@ def time_list_of_dict(self):
     def time_nested_dict(self):
         DataFrame(self.data)
 
-    def time_dict(self):
-        Series(self.some_dict)
+    def time_nested_dict_index(self):
+        DataFrame(self.data, index=self.index)
+
+    def time_nested_dict_columns(self):
+        DataFrame(self.data, columns=self.columns)
+
+    def time_nested_dict_index_columns(self):
+        DataFrame(self.data, index=self.index, columns=self.columns)
 
     def time_nested_dict_int64(self):
         # nested dict, integer indexes, regression described in #621

ci/environment-dev.yaml

@@ -11,5 +11,5 @@ dependencies:
   - python-dateutil>=2.5.0
   - python=3
   - pytz
-  - setuptools>=3.3
+  - setuptools>=24.2.0
   - sphinx

ci/lint.sh

@@ -165,6 +165,14 @@ if [ "$LINT" ]; then
         RET=1
     fi
     echo "Check for deprecated messages without sphinx directive DONE"
+
+    echo "Check for old-style classes"
+    grep -R --include="*.py" -E "class\s\S*[^)]:" pandas scripts
+
+    if [ $? = "0" ]; then
+        RET=1
+    fi
+    echo "Check for old-style classes DONE"
 
 else
     echo "NOT Linting"

ci/requirements-3.6_DOC.run

@@ -5,7 +5,7 @@ sphinx
 nbconvert
 nbformat
 notebook
-matplotlib=2.1*
+matplotlib
 seaborn
 scipy
 lxml

ci/requirements-2.7_SLOW.build renamed to ci/requirements-3.6_SLOW.build

@@ -1,5 +1,5 @@
-python=2.7*
+python=3.6*
 python-dateutil
 pytz
-numpy=1.10*
+numpy
 cython

ci/requirements-2.7_SLOW.pip renamed to ci/requirements-3.6_SLOW.pip

@@ -1,7 +1,7 @@
 python-dateutil
 pytz
-numpy=1.10*
-matplotlib=1.4.3
+numpy
+matplotlib
 scipy
 patsy
 xlwt

ci/requirements-2.7_SLOW.run renamed to ci/requirements-3.6_SLOW.run

@@ -7,5 +7,5 @@ moto
 pytest>=3.1
 python-dateutil>=2.5.0
 pytz
-setuptools>=3.3
-sphinx
+setuptools>=24.2.0
+sphinx

ci/requirements_dev.txt

@@ -99,6 +99,7 @@ HDFStore: PyTables (HDF5)
    HDFStore.get
    HDFStore.select
    HDFStore.info
+   HDFStore.keys
 
 Feather
 ~~~~~~~
@@ -1687,6 +1688,7 @@ MultiIndex Components
    MultiIndex.swaplevel
    MultiIndex.reorder_levels
    MultiIndex.remove_unused_levels
+   MultiIndex.unique
 
 MultiIndex Selecting
 ~~~~~~~~~~~~~~~~~~~~
@@ -2206,6 +2208,7 @@ Computations / Descriptive Stats
    GroupBy.ohlc
    GroupBy.prod
    GroupBy.rank
+   GroupBy.pct_change
    GroupBy.size
    GroupBy.sem
    GroupBy.std

doc/source/api.rst

@@ -16,6 +16,7 @@
 import re
 import inspect
 import importlib
+from sphinx.ext.autosummary import _import_by_name
 import warnings
 
 
@@ -47,6 +48,10 @@
 
 ])
 
+# numpydoc is available in the sphinxext directory, and can't be imported
+# until sphinxext is available in the Python path
+from numpydoc.docscrape import NumpyDocString
+
 # -- General configuration -----------------------------------------------
 
 # Add any Sphinx extension module names here, as strings. They can be
@@ -350,6 +355,7 @@
 intersphinx_mapping = {
     'statsmodels': ('http://www.statsmodels.org/devel/', None),
     'matplotlib': ('http://matplotlib.org/', None),
+    'pandas-gbq': ('https://pandas-gbq.readthedocs.io/en/latest/', None),
     'python': ('https://docs.python.org/3/', None),
     'numpy': ('https://docs.scipy.org/doc/numpy/', None),
     'scipy': ('https://docs.scipy.org/doc/scipy/reference/', None),
@@ -505,9 +511,27 @@ def _replace_pandas_items(self, display_name, sig, summary, real_name):
             summary = 'Series plotting accessor and method'
         return (display_name, sig, summary, real_name)
 
+    @staticmethod
+    def _is_deprecated(real_name):
+        try:
+            obj, parent, modname = _import_by_name(real_name)
+        except ImportError:
+            return False
+        doc = NumpyDocString(obj.__doc__ or '')
+        summary = ''.join(doc['Summary'] + doc['Extended Summary'])
+        return '.. deprecated::' in summary
+
+    def _add_deprecation_prefixes(self, items):
+        for item in items:
+            display_name, sig, summary, real_name = item
+            if self._is_deprecated(real_name):
+                summary = '(DEPRECATED) %s' % summary
+            yield display_name, sig, summary, real_name
+
     def get_items(self, names):
         items = Autosummary.get_items(self, names)
         items = [self._replace_pandas_items(*item) for item in items]
+        items = list(self._add_deprecation_prefixes(items))
         return items
 
 

doc/source/conf.py

@@ -15,6 +15,31 @@ Instructions for installing from source,
 `PyPI <http://pypi.python.org/pypi/pandas>`__, `ActivePython <https://www.activestate.com/activepython/downloads>`__, various Linux distributions, or a
 `development version <http://github.com/pandas-dev/pandas>`__ are also provided.
 
+.. _install.dropping_27:
+
+Plan for dropping Python 2.7
+----------------------------
+
+The Python core team plans to stop supporting Python 2.7 on January 1st, 2020.
+In line with `NumPy's plans`_, all pandas releases through December 31, 2018
+will support Python 2.
+
+The final release before **December 31, 2018** will be the last release to
+support Python 2. The released package will continue to be available on
+PyPI and through conda.
+
+Starting **January 1, 2019**, all releases will be Python 3 only.
+
+If there are people interested in continued support for Python 2.7 past December
+31, 2018 (either backporting bugfixes or funding) please reach out to the
+maintainers on the issue tracker.
+
+For more information, see the `Python 3 statement`_ and the `Porting to Python 3 guide`_.
+
+.. _NumPy's plans: https://github.com/numpy/numpy/blob/master/doc/neps/nep-0014-dropping-python2.7-proposal.rst#plan-for-dropping-python-27-support
+.. _Python 3 statement: http://python3statement.org/
+.. _Porting to Python 3 guide: https://docs.python.org/3/howto/pyporting.html
+
 Python version support
 ----------------------
 
@@ -137,8 +162,8 @@ pandas can be installed via pip from
 Installing with ActivePython
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Installation instructions for 
-`ActivePython <https://www.activestate.com/activepython>`__ can be found 
+Installation instructions for
+`ActivePython <https://www.activestate.com/activepython>`__ can be found
 `here <https://www.activestate.com/activepython/downloads>`__. Versions
 2.7 and 3.5 include pandas.
 
@@ -198,7 +223,7 @@ installed), make sure you have `pytest
 Dependencies
 ------------
 
-* `setuptools <https://setuptools.readthedocs.io/en/latest/>`__: 3.3.0 or higher
+* `setuptools <https://setuptools.readthedocs.io/en/latest/>`__: 24.2.0 or higher
 * `NumPy <http://www.numpy.org>`__: 1.9.0 or higher
 * `python-dateutil <//https://dateutil.readthedocs.io/en/stable/>`__: 2.5.0 or higher
 * `pytz <http://pytz.sourceforge.net/>`__