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

Author: deflatSOCO

Makefile

@@ -23,3 +23,4 @@ doc:
 	cd doc; \
 	python make.py clean; \
 	python make.py html
+	python make.py spellcheck

README.md

@@ -233,7 +233,7 @@ All contributions, bug reports, bug fixes, documentation improvements, enhanceme
 
 A detailed overview on how to contribute can be found in the **[contributing guide.](https://pandas.pydata.org/pandas-docs/stable/contributing.html)**
 
-If you are simply looking to start working with the pandas codebase, navigate to the [GitHub “issues” tab](https://github.com/pandas-dev/pandas/issues) and start looking through interesting issues. There are a number of issues listed under [Docs](https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open) and [Difficulty Novice](https://github.com/pandas-dev/pandas/issues?q=is%3Aopen+is%3Aissue+label%3A%22Difficulty+Novice%22) where you could start out.
+If you are simply looking to start working with the pandas codebase, navigate to the [GitHub “issues” tab](https://github.com/pandas-dev/pandas/issues) and start looking through interesting issues. There are a number of issues listed under [Docs](https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open) and [good first issue](https://github.com/pandas-dev/pandas/issues?labels=good+first+issue&sort=updated&state=open) where you could start out.
 
 You can also triage issues which may include reproducing bug reports, or asking for vital information such as version numbers or reproduction instructions. If you would like to start triaging issues, one easy way to get started is to [subscribe to pandas on CodeTriage](https://www.codetriage.com/pandas-dev/pandas).
 

asv_bench/benchmarks/categoricals.py

@@ -51,6 +51,7 @@ def setup(self):
 
         self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
         self.values_all_nan = [np.nan] * len(self.values)
+        self.values_all_int8 = np.ones(N, 'int8')
 
     def time_regular(self):
         pd.Categorical(self.values, self.categories)
@@ -70,6 +71,9 @@ def time_with_nan(self):
     def time_all_nan(self):
         pd.Categorical(self.values_all_nan)
 
+    def time_from_codes_all_int8(self):
+        pd.Categorical.from_codes(self.values_all_int8, self.categories)
+
 
 class ValueCounts(object):
 
@@ -169,3 +173,23 @@ def setup(self, dtype):
 
     def time_isin_categorical(self, dtype):
         self.series.isin(self.sample)
+
+
+class IsMonotonic(object):
+
+    def setup(self):
+        N = 1000
+        self.c = pd.CategoricalIndex(list('a' * N + 'b' * N + 'c' * N))
+        self.s = pd.Series(self.c)
+
+    def time_categorical_index_is_monotonic_increasing(self):
+        self.c.is_monotonic_increasing
+
+    def time_categorical_index_is_monotonic_decreasing(self):
+        self.c.is_monotonic_decreasing
+
+    def time_categorical_series_is_monotonic_increasing(self):
+        self.s.is_monotonic_increasing
+
+    def time_categorical_series_is_monotonic_decreasing(self):
+        self.s.is_monotonic_decreasing

asv_bench/benchmarks/frame_methods.py

@@ -512,3 +512,21 @@ def time_nlargest(self, keep):
 
     def time_nsmallest(self, keep):
         self.df.nsmallest(100, 'A', keep=keep)
+
+
+class Describe(object):
+
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame({
+            'a': np.random.randint(0, 100, int(1e6)),
+            'b': np.random.randint(0, 100, int(1e6)),
+            'c': np.random.randint(0, 100, int(1e6))
+        })
+
+    def time_series_describe(self):
+        self.df['a'].describe()
+
+    def time_dataframe_describe(self):
+        self.df.describe()

asv_bench/benchmarks/pandas_vb_common.py

@@ -2,10 +2,7 @@
 from importlib import import_module
 
 import numpy as np
-try:
-    from pandas import Panel
-except ImportError:
-    from pandas import WidePanel as Panel  # noqa
+from pandas import Panel
 
 # Compatibility import for lib
 for imp in ['pandas._libs.lib', 'pandas.lib']:

ci/appveyor-27.yaml

@@ -11,9 +11,9 @@ dependencies:
   - lxml
   - matplotlib
   - numexpr
-  - numpy=1.10*
+  - numpy=1.12*
   - openpyxl
-  - pytables==3.2.2
+  - pytables
   - python=2.7.*
   - pytz
   - s3fs

ci/appveyor-36.yaml

@@ -9,7 +9,7 @@ dependencies:
   - feather-format
   - matplotlib
   - numexpr
-  - numpy=1.13*
+  - numpy=1.14*
   - openpyxl
   - pyarrow
   - pytables

ci/travis-36.yaml

@@ -18,12 +18,10 @@ dependencies:
   - numexpr
   - numpy
   - openpyxl
-  - pandas-datareader
   - psycopg2
   - pyarrow
   - pymysql
   - pytables
-  - python-dateutil
   - python-snappy
   - python=3.6*
   - pytz
@@ -45,3 +43,5 @@ dependencies:
   - pip:
     - brotlipy
     - coverage
+    - pandas-datareader
+    - python-dateutil

doc/README.rst

@@ -42,7 +42,7 @@ Some other important things to know about the docs:
 - The docstrings follow the **Numpy Docstring Standard** which is used widely
   in the Scientific Python community. This standard specifies the format of
   the different sections of the docstring. See `this document
-  <https://github.com/numpy/numpy/blob/master/doc/HOWTO_DOCUMENT.rst.txt>`_
+  <https://numpydoc.readthedocs.io/en/latest/>`_
   for a detailed explanation, or look at some of the existing functions to
   extend it in a similar manner.
 

doc/make.py

@@ -224,8 +224,9 @@ def _sphinx_build(self, kind):
         --------
         >>> DocBuilder(num_jobs=4)._sphinx_build('html')
         """
-        if kind not in ('html', 'latex'):
-            raise ValueError('kind must be html or latex, not {}'.format(kind))
+        if kind not in ('html', 'latex', 'spelling'):
+            raise ValueError('kind must be html, latex or '
+                             'spelling, not {}'.format(kind))
 
         self._run_os('sphinx-build',
                      '-j{}'.format(self.num_jobs),
@@ -304,6 +305,18 @@ def zip_html(self):
                      '-q',
                      *fnames)
 
+    def spellcheck(self):
+        """Spell check the documentation."""
+        self._sphinx_build('spelling')
+        output_location = os.path.join('build', 'spelling', 'output.txt')
+        with open(output_location) as output:
+            lines = output.readlines()
+            if lines:
+                raise SyntaxError(
+                    'Found misspelled words.'
+                    ' Check pandas/doc/build/spelling/output.txt'
+                    ' for more details.')
+
 
 def main():
     cmds = [method for method in dir(DocBuilder) if not method.startswith('_')]

doc/source/_static/reshaping_melt.png

@@ -342,7 +342,7 @@ As usual, **both sides** of the slicers are included as this is label indexing.
                        columns=micolumns).sort_index().sort_index(axis=1)
    dfmi
 
-Basic multi-index slicing using slices, lists, and labels.
+Basic MultiIndex slicing using slices, lists, and labels.
 
 .. ipython:: python
 
@@ -924,6 +924,55 @@ bins, with ``NaN`` representing a missing value similar to other dtypes.
 
    pd.cut([0, 3, 5, 1], bins=c.categories)
 
+
+Generating Ranges of Intervals
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If we need intervals on a regular frequency, we can use the :func:`interval_range` function
+to create an ``IntervalIndex`` using various combinations of ``start``, ``end``, and ``periods``.
+The default frequency for ``interval_range`` is a 1 for numeric intervals, and calendar day for
+datetime-like intervals:
+
+.. ipython:: python
+
+   pd.interval_range(start=0, end=5)
+
+   pd.interval_range(start=pd.Timestamp('2017-01-01'), periods=4)
+
+   pd.interval_range(end=pd.Timedelta('3 days'), periods=3)
+
+The ``freq`` parameter can used to specify non-default frequencies, and can utilize a variety
+of :ref:`frequency aliases <timeseries.offset_aliases>` with datetime-like intervals:
+
+.. ipython:: python
+
+   pd.interval_range(start=0, periods=5, freq=1.5)
+
+   pd.interval_range(start=pd.Timestamp('2017-01-01'), periods=4, freq='W')
+
+   pd.interval_range(start=pd.Timedelta('0 days'), periods=3, freq='9H')
+
+Additionally, the ``closed`` parameter can be used to specify which side(s) the intervals
+are closed on.  Intervals are closed on the right side by default.
+
+.. ipython:: python
+
+   pd.interval_range(start=0, end=4, closed='both')
+
+   pd.interval_range(start=0, end=4, closed='neither')
+
+.. versionadded:: 0.23.0
+
+Specifying ``start``, ``end``, and ``periods`` will generate a range of evenly spaced
+intervals from ``start`` to ``end`` inclusively, with ``periods`` number of elements
+in the resulting ``IntervalIndex``:
+
+.. ipython:: python
+
+   pd.interval_range(start=0, end=6, periods=4)
+
+   pd.interval_range(pd.Timestamp('2018-01-01'), pd.Timestamp('2018-02-28'), periods=3)
+
 Miscellaneous indexing FAQ
 --------------------------
 
@@ -990,7 +1039,7 @@ On the other hand, if the index is not monotonic, then both slice bounds must be
     KeyError: 'Cannot get right slice bound for non-unique label: 3'
 
 :meth:`Index.is_monotonic_increasing` and :meth:`Index.is_monotonic_decreasing` only check that
-an index is weakly monotonic. To check for strict montonicity, you can combine one of those with
+an index is weakly monotonic. To check for strict monotonicity, you can combine one of those with
 :meth:`Index.is_unique`
 
 .. ipython:: python

doc/source/_static/reshaping_pivot.png

@@ -1459,7 +1459,6 @@ Modifying and Computations
    Index.is_floating
    Index.is_integer
    Index.is_interval
-   Index.is_lexsorted_for_tuple
    Index.is_mixed
    Index.is_numeric
    Index.is_object
@@ -1471,11 +1470,19 @@ Modifying and Computations
    Index.where
    Index.take
    Index.putmask
-   Index.set_names
    Index.unique
    Index.nunique
    Index.value_counts
 
+Compatibility with MultiIndex
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+.. autosummary::
+   :toctree: generated/
+
+   Index.set_names
+   Index.is_lexsorted_for_tuple
+   Index.droplevel
+
 Missing Values
 ~~~~~~~~~~~~~~
 .. autosummary::
@@ -1632,6 +1639,8 @@ IntervalIndex Components
    IntervalIndex.length
    IntervalIndex.values
    IntervalIndex.is_non_overlapping_monotonic
+   IntervalIndex.get_loc
+   IntervalIndex.get_indexer
 
 
 .. _api.multiindex:

doc/source/_static/reshaping_stack.png

@@ -168,7 +168,7 @@ either match on the *index* or *columns* via the **axis** keyword:
 
    df_orig = df
 
-Furthermore you can align a level of a multi-indexed DataFrame with a Series.
+Furthermore you can align a level of a MultiIndexed DataFrame with a Series.
 
 .. ipython:: python
 
@@ -593,7 +593,7 @@ categorical columns:
     frame = pd.DataFrame({'a': ['Yes', 'Yes', 'No', 'No'], 'b': range(4)})
     frame.describe()
 
-This behaviour can be controlled by providing a list of types as ``include``/``exclude``
+This behavior can be controlled by providing a list of types as ``include``/``exclude``
 arguments. The special value ``all`` can also be used:
 
 .. ipython:: python
@@ -1034,7 +1034,7 @@ Passing a single function to ``.transform()`` with a ``Series`` will yield a sin
 Transform with multiple functions
 +++++++++++++++++++++++++++++++++
 
-Passing multiple functions will yield a column multi-indexed DataFrame.
+Passing multiple functions will yield a column MultiIndexed DataFrame.
 The first level will be the original frame column names; the second level
 will be the names of the transforming functions.
 
@@ -1060,7 +1060,7 @@ Passing a dict of functions will allow selective transforming per column.
 
    tsdf.transform({'A': np.abs, 'B': lambda x: x+1})
 
-Passing a dict of lists will generate a multi-indexed DataFrame with these
+Passing a dict of lists will generate a MultiIndexed DataFrame with these
 selective transforms.
 
 .. ipython:: python
@@ -1889,12 +1889,12 @@ faster than sorting the entire Series and calling ``head(n)`` on the result.
    df.nsmallest(5, ['a', 'c'])
 
 
-.. _basics.multi-index_sorting:
+.. _basics.multiindex_sorting:
 
-Sorting by a multi-index column
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Sorting by a MultiIndex column
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-You must be explicit about sorting when the column is a multi-index, and fully specify
+You must be explicit about sorting when the column is a MultiIndex, and fully specify
 all levels to ``by``.
 
 .. ipython:: python

doc/source/_static/reshaping_unstack.png

@@ -358,10 +358,10 @@ Renaming categories is done by assigning new values to the
     s
     s.cat.categories = ["Group %s" % g for g in s.cat.categories]
     s
-    s.cat.rename_categories([1,2,3])
+    s = s.cat.rename_categories([1,2,3])
     s
     # You can also pass a dict-like object to map the renaming
-    s.cat.rename_categories({1: 'x', 2: 'y', 3: 'z'})
+    s = s.cat.rename_categories({1: 'x', 2: 'y', 3: 'z'})
     s
 
 .. note::

doc/source/_static/reshaping_unstack_0.png

@@ -73,10 +73,14 @@
               'sphinx.ext.ifconfig',
               'sphinx.ext.linkcode',
               'nbsphinx',
+              'sphinxcontrib.spelling'
               ]
 
 exclude_patterns = ['**.ipynb_checkpoints']
 
+spelling_word_list_filename = ['spelling_wordlist.txt', 'names_wordlist.txt']
+spelling_ignore_pypi_package_names = True
+
 with open("index.rst") as f:
     index_rst_lines = f.readlines()
 

doc/source/_static/reshaping_unstack_1.png

@@ -17,8 +17,8 @@ If you are brand new to pandas or open-source development, we recommend going
 through the `GitHub "issues" tab <https://github.com/pandas-dev/pandas/issues>`_
 to find issues that interest you. There are a number of issues listed under `Docs
 <https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open>`_
-and `Difficulty Novice
-<https://github.com/pandas-dev/pandas/issues?q=is%3Aopen+is%3Aissue+label%3A%22Difficulty+Novice%22>`_
+and `good first issue
+<https://github.com/pandas-dev/pandas/issues?labels=good+first+issue&sort=updated&state=open>`_
 where you could start out. Once you've found an interesting issue, you can
 return here to get your development environment setup.
 
@@ -436,6 +436,25 @@ the documentation are also built by Travis-CI. These docs are then hosted `here
 <http://pandas-docs.github.io/pandas-docs-travis>`__, see also
 the :ref:`Continuous Integration <contributing.ci>` section.
 
+Spell checking documentation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+When contributing to documentation to **pandas** it's good to check if your work
+contains any spelling errors. Sphinx provides an easy way to spell check documentation
+and docstrings.
+
+Running the spell check is easy. Just navigate to your local ``pandas/doc/`` directory and run::
+
+    python make.py spellcheck
+
+The spellcheck will take a few minutes to run (between 1 to 6 minutes). Sphinx will alert you
+with warnings and misspelt words - these misspelt words will be added to a file called
+``output.txt`` and you can find it on your local directory ``pandas/doc/build/spelling/``.
+
+The Sphinx spelling extension uses an EN-US dictionary to correct words, what means that in
+some cases you might need to add a word to this dictionary. You can do so by adding the word to
+the bag-of-words file named ``spelling_wordlist.txt`` located in the folder ``pandas/doc/``.
+
 .. _contributing.code:
 
 Contributing to the code base