Merge remote-tracking branch 'upstream/master' into unique_inverse_cython

Author: h-vetinari

.gitignore

@@ -109,6 +109,5 @@ doc/build/html/index.html
 # Windows specific leftover:
 doc/tmp.sv
 doc/source/styled.xlsx
-doc/source/templates/
 env/
 doc/source/savefig/

.travis.yml

@@ -23,7 +23,7 @@ env:
 
 git:
     # for cloning
-    depth: 1000
+    depth: 1500
 
 matrix:
     fast_finish: true

ci/build_docs.sh

@@ -5,7 +5,7 @@ if [ "${TRAVIS_OS_NAME}" != "linux" ]; then
    exit 0
 fi
 
-cd "$TRAVIS_BUILD_DIR"
+cd "$TRAVIS_BUILD_DIR"/doc
 echo "inside $0"
 
 if [ "$DOC" ]; then
@@ -14,10 +14,6 @@ if [ "$DOC" ]; then
 
     source activate pandas
 
-    mv "$TRAVIS_BUILD_DIR"/doc /tmp
-    mv "$TRAVIS_BUILD_DIR/LICENSE" /tmp  # included in the docs.
-    cd /tmp/doc
-
     echo ###############################
     echo # Log file for the doc build  #
     echo ###############################
@@ -29,7 +25,7 @@ if [ "$DOC" ]; then
     echo # Create and send docs #
     echo ########################
 
-    cd /tmp/doc/build/html
+    cd build/html
     git config --global user.email "[email protected]"
     git config --global user.name "pandas-docs-bot"
 

ci/deps/travis-36-doc.yaml

@@ -8,10 +8,11 @@ dependencies:
   - bottleneck
   - cython>=0.28.2
   - fastparquet
+  - gitpython
   - html5lib
   - hypothesis>=3.58.0
   - ipykernel
-  - ipython==6.5.0
+  - ipython
   - ipywidgets
   - lxml
   - matplotlib

ci/deps/travis-36.yaml

@@ -9,7 +9,7 @@ dependencies:
   - fastparquet
   - flake8>=3.5
   - flake8-comprehensions
-  - flake8-rst
+  - flake8-rst=0.4.2
   - gcsfs
   - geopandas
   - html5lib

doc/make.py

@@ -126,7 +126,12 @@ def _process_single_doc(self, single_doc):
             self.single_doc = 'api'
         elif os.path.exists(os.path.join(SOURCE_PATH, single_doc)):
             self.single_doc_type = 'rst'
-            self.single_doc = os.path.splitext(os.path.basename(single_doc))[0]
+
+            if 'whatsnew' in single_doc:
+                basename = single_doc
+            else:
+                basename = os.path.basename(single_doc)
+            self.single_doc = os.path.splitext(basename)[0]
         elif os.path.exists(
                 os.path.join(SOURCE_PATH, '{}.rst'.format(single_doc))):
             self.single_doc_type = 'rst'

doc/source/advanced.rst

@@ -702,7 +702,7 @@ Index Types
 
 We have discussed ``MultiIndex`` in the previous sections pretty extensively.
 Documentation about ``DatetimeIndex`` and ``PeriodIndex`` are shown :ref:`here <timeseries.overview>`,
-and documentation about ``TimedeltaIndex`` is found :ref:`here <timedeltas.timedeltaindex>`.
+and documentation about ``TimedeltaIndex`` is found :ref:`here <timedeltas.index>`.
 
 In the following sub-sections we will highlight some other index types.
 

doc/source/api.rst

@@ -1724,6 +1724,7 @@ MultiIndex Components
    MultiIndex.set_levels
    MultiIndex.set_labels
    MultiIndex.to_hierarchical
+   MultiIndex.to_flat_index
    MultiIndex.to_frame
    MultiIndex.is_lexsorted
    MultiIndex.sortlevel

doc/source/conf.py

@@ -40,7 +40,6 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 # sys.path.append(os.path.abspath('.'))
 sys.path.insert(0, os.path.abspath('../sphinxext'))
-
 sys.path.extend([
 
     # numpy standard doc extensions
@@ -75,6 +74,7 @@
               'sphinx.ext.ifconfig',
               'sphinx.ext.linkcode',
               'nbsphinx',
+              'contributors',  # custom pandas extension
               ]
 
 try:
@@ -120,7 +120,9 @@
 templates_path = ['../_templates']
 
 # The suffix of source filenames.
-source_suffix = '.rst'
+source_suffix = [
+    '.rst',
+]
 
 # The encoding of source files.
 source_encoding = 'utf-8'
@@ -298,8 +300,26 @@
     for page in moved_api_pages
 }
 
+
+common_imports = """\
+.. currentmodule:: pandas
+
+.. ipython:: python
+   :suppress:
+
+   import numpy as np
+   from pandas import *
+   import pandas as pd
+   randn = np.random.randn
+   np.set_printoptions(precision=4, suppress=True)
+   options.display.max_rows = 15
+   from pandas.compat import StringIO
+"""
+
+
 html_context = {
-    'redirects': {old: new for old, new in moved_api_pages}
+    'redirects': {old: new for old, new in moved_api_pages},
+    'common_imports': common_imports,
 }
 
 # If false, no module index is generated.
@@ -388,6 +408,7 @@
                         category=FutureWarning)
 
 
+ipython_warning_is_error = False
 ipython_exec_lines = [
     'import numpy as np',
     'import pandas as pd',
@@ -653,7 +674,23 @@ def process_class_docstrings(app, what, name, obj, options, lines):
 ]
 
 
+def rstjinja(app, docname, source):
+    """
+    Render our pages as a jinja template for fancy templating goodness.
+    """
+    # http://ericholscher.com/blog/2016/jul/25/integrating-jinja-rst-sphinx/
+    # Make sure we're outputting HTML
+    if app.builder.format != 'html':
+        return
+    src = source[0]
+    rendered = app.builder.templates.render_string(
+        src, app.config.html_context
+    )
+    source[0] = rendered
+
+
 def setup(app):
+    app.connect("source-read", rstjinja)
     app.connect("autodoc-process-docstring", remove_flags_docstring)
     app.connect("autodoc-process-docstring", process_class_docstrings)
     app.add_autodocumenter(AccessorDocumenter)

doc/source/contributing.rst

@@ -591,21 +591,14 @@ run this slightly modified command::
 
    git diff master --name-only -- "*.py" | grep "pandas/" | xargs flake8
 
-Note that on Windows, these commands are unfortunately not possible because
-commands like ``grep`` and ``xargs`` are not available natively. To imitate the
-behavior with the commands above, you should run::
+Windows does not support the ``grep`` and ``xargs`` commands (unless installed
+for example via the `MinGW <http://www.mingw.org/>`__ toolchain), but one can
+imitate the behaviour as follows::
 
-    git diff master --name-only -- "*.py"
+    for /f %i in ('git diff upstream/master --name-only ^| findstr pandas/') do flake8 %i
 
-This will list all of the Python files that have been modified. The only ones
-that matter during linting are any whose directory filepath begins with "pandas."
-For each filepath, copy and paste it after the ``flake8`` command as shown below:
-
-    flake8 <python-filepath>
-
-Alternatively, you can install the ``grep`` and ``xargs`` commands via the
-`MinGW <http://www.mingw.org/>`__ toolchain, and it will allow you to run the
-commands above.
+This will also get all the files being changed by the PR (and within the
+``pandas/`` folder), and run ``flake8`` on them one after the other.
 
 .. _contributing.import-formatting:
 
@@ -1103,7 +1096,7 @@ Information on how to write a benchmark and how to use asv can be found in the
 Documenting your code
 ---------------------
 
-Changes should be reflected in the release notes located in ``doc/source/whatsnew/vx.y.z.txt``.
+Changes should be reflected in the release notes located in ``doc/source/whatsnew/vx.y.z.rst``.
 This file contains an ongoing change log for each release.  Add an entry to this file to
 document your fix, enhancement or (unavoidable) breaking change.  Make sure to include the
 GitHub issue number when adding your entry (using ``:issue:`1234``` where ``1234`` is the

doc/source/ecosystem.rst

@@ -140,7 +140,7 @@ which are utilized by Jupyter Notebook for displaying
 (Note: HTML tables may or may not be
 compatible with non-HTML Jupyter output formats.)
 
-See :ref:`Options and Settings <options>` and :ref:`options.available <available>`
+See :ref:`Options and Settings <options>` and :ref:`options.available`
 for pandas ``display.`` settings.
 
 `quantopian/qgrid <https://github.com/quantopian/qgrid>`__

doc/source/index.rst.template

@@ -118,7 +118,7 @@ See the package overview for more detail about what's in the library.
     {{ single_doc }}
     {% endif -%}
     {% if not single_doc -%}
-    whatsnew
+    What's New <whatsnew/v0.24.0>
     install
     contributing
     overview
@@ -159,5 +159,5 @@ See the package overview for more detail about what's in the library.
     developer
     internals
     extending
-    release
+    releases
     {% endif -%}

doc/source/install.rst

@@ -286,7 +286,9 @@ Optional Dependencies
   `xsel <http://www.vergenet.net/~conrad/software/xsel/>`__, or
   `xclip <https://github.com/astrand/xclip/>`__: necessary to use
   :func:`~pandas.read_clipboard`. Most package managers on Linux distributions will have ``xclip`` and/or ``xsel`` immediately available for installation.
-* `pandas-gbq <https://pandas-gbq.readthedocs.io/en/latest/install.html#dependencies>`__: for Google BigQuery I/O.
+* `pandas-gbq
+  <https://pandas-gbq.readthedocs.io/en/latest/install.html#dependencies>`__:
+  for Google BigQuery I/O. (pandas-gbq >= 0.8.0)
 
 
 * `Backports.lzma <https://pypi.org/project/backports.lzma/>`__: Only for Python 2, for writing to and/or reading from an xz compressed DataFrame in CSV; Python 3 support is built into the standard library.

doc/source/io.rst

@@ -1580,12 +1580,19 @@ You can pass in a URL to a CSV file:
    df = pd.read_csv('https://download.bls.gov/pub/time.series/cu/cu.item',
                     sep='\t')
 
-S3 URLs are handled as well:
+S3 URLs are handled as well but require installing the `S3Fs
+<https://pypi.org/project/s3fs/>`_ library:
 
 .. code-block:: python
 
    df = pd.read_csv('s3://pandas-test/tips.csv')
 
+If your S3 bucket requires cedentials you will need to set them as environment
+variables or in the ``~/.aws/credentials`` config file, refer to the `S3Fs
+documentation on credentials
+<https://s3fs.readthedocs.io/en/latest/#credentials>`_.
+
+
 
 Writing out Data
 ''''''''''''''''
@@ -2854,6 +2861,11 @@ It is often the case that users will insert columns to do temporary computations
 in Excel and you may not want to read in those columns. ``read_excel`` takes
 a ``usecols`` keyword to allow you to specify a subset of columns to parse.
 
+.. deprecated:: 0.24.0
+
+Passing in an integer for ``usecols`` has been deprecated. Please pass in a list
+of ints from 0 to ``usecols`` inclusive instead.
+
 If ``usecols`` is an integer, then it is assumed to indicate the last column
 to be parsed.