Merge from master

Author: Dr-Irv

.gitignore

@@ -61,6 +61,7 @@ dist
 .coverage
 coverage.xml
 coverage_html_report
+*.pytest_cache
 
 # OS generated files #
 ######################
@@ -90,7 +91,6 @@ scikits
 
 # Unit / Performance Testing #
 ##############################
-.pytest_cache/
 asv_bench/env/
 asv_bench/html/
 asv_bench/results/
@@ -109,3 +109,4 @@ doc/tmp.sv
 doc/source/styled.xlsx
 doc/source/templates/
 env/
+doc/source/savefig/

.travis.yml

@@ -34,55 +34,59 @@ matrix:
     - os: osx
       language: generic
       env:
-        - JOB="3.5_OSX" TEST_ARGS="--skip-slow --skip-network"
+        - JOB="3.5, OSX" ENV_FILE="ci/travis-35-osx.yaml" TEST_ARGS="--skip-slow --skip-network"
+
     - dist: trusty
       env:
-        - JOB="2.7_LOCALE" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true
+        - JOB="3.7" ENV_FILE="ci/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
+
+    - dist: trusty
+      env:
+        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true
       addons:
         apt:
           packages:
           - language-pack-zh-hans
     - dist: trusty
       env:
-        - JOB="2.7" TEST_ARGS="--skip-slow" LINT=true
+        - JOB="2.7, lint" ENV_FILE="ci/travis-27.yaml" TEST_ARGS="--skip-slow" LINT=true
       addons:
         apt:
           packages:
           - python-gtk2
-    # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" CONDA_FORGE=true COVERAGE=true
+        - JOB="3.6, coverage" ENV_FILE="ci/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="2.7_SLOW" SLOW=true
+        - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+        - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
       addons:
         apt:
           packages:
           - xsel
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6_DOC" DOC=true
+        - JOB="3.6, doc" ENV_FILE="ci/travis-36-doc.yaml" DOC=true
     allow_failures:
       - dist: trusty
         env:
-          - JOB="2.7_SLOW" SLOW=true
+          - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
       - dist: trusty
         env:
-          - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+          - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
         addons:
           apt:
             packages:
             - xsel
       - dist: trusty
         env:
-          - JOB="3.6_DOC" DOC=true
+          - JOB="3.6, doc" ENV_FILE="ci/travis-36-doc.yaml" DOC=true
 
 before_install:
   - echo "before_install"

MANIFEST.in

@@ -3,27 +3,39 @@ include LICENSE
 include RELEASE.md
 include README.md
 include setup.py
-include pyproject.toml
 
 graft doc
 prune doc/build
 
+graft LICENSES
+
 graft pandas
 
-global-exclude *.so
-global-exclude *.pyd
+global-exclude *.bz2
+global-exclude *.csv
+global-exclude *.dta
+global-exclude *.gz
+global-exclude *.h5
+global-exclude *.html
+global-exclude *.json
+global-exclude *.msgpack
+global-exclude *.pickle
+global-exclude *.png
 global-exclude *.pyc
+global-exclude *.pyd
+global-exclude *.sas7bdat
+global-exclude *.so
+global-exclude *.xls
+global-exclude *.xlsm
+global-exclude *.xlsx
+global-exclude *.xpt
+global-exclude *.xz
+global-exclude *.zip
 global-exclude *~
-global-exclude \#*
-global-exclude .git*
 global-exclude .DS_Store
-global-exclude *.png
+global-exclude .git*
+global-exclude \#*
 
-# include examples/data/*
-# recursive-include examples *.py
-# recursive-include doc/source *
-# recursive-include doc/sphinxext *
-# recursive-include LICENSES *
 include versioneer.py
 include pandas/_version.py
 include pandas/io/formats/templates/*.tpl

Makefile

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

README.md

@@ -9,18 +9,33 @@
 <table>
 <tr>
   <td>Latest Release</td>
-  <td><img src="https://img.shields.io/pypi/v/pandas.svg" alt="latest release" /></td>
+  <td>
+    <a href="https://pypi.org/project/pandas/">
+    <img src="https://img.shields.io/pypi/v/pandas.svg" alt="latest release" />
+    </a>
+  </td>
 </tr>
   <td></td>
-  <td><img src="https://anaconda.org/conda-forge/pandas/badges/version.svg" alt="latest release" /></td>
+  <td>
+    <a href="https://anaconda.org/anaconda/pandas/">
+    <img src="https://anaconda.org/conda-forge/pandas/badges/version.svg" alt="latest release" />
+    </a>
+</td>
 </tr>
 <tr>
   <td>Package Status</td>
-  <td><img src="https://img.shields.io/pypi/status/pandas.svg" alt="status" /></td>
+  <td>
+		<a href="https://pypi.org/project/pandas/">
+		<img src="https://img.shields.io/pypi/status/pandas.svg" alt="status" /></td>
+		</a>
 </tr>
 <tr>
   <td>License</td>
-  <td><img src="https://img.shields.io/pypi/l/pandas.svg" alt="license" /></td>
+  <td>
+    <a href="https://github.com/pandas-dev/pandas/blob/master/LICENSE">
+    <img src="https://img.shields.io/pypi/l/pandas.svg" alt="license" />
+    </a>
+</td>
 </tr>
 <tr>
   <td>Build Status</td>
@@ -48,35 +63,31 @@
 </tr>
 <tr>
   <td>Coverage</td>
-  <td><img src="https://codecov.io/github/pandas-dev/pandas/coverage.svg?branch=master" alt="coverage" /></td>
-</tr>
-<tr>
-  <td>Conda</td>
-  <td>
-    <a href="https://pandas.pydata.org">
-    <img src="http://pubbadges.s3-website-us-east-1.amazonaws.com/pkgs-downloads-pandas.png" alt="conda default downloads" />
+  <td>
+    <a href="https://codecov.io/gh/pandas-dev/pandas">
+    <img src="https://codecov.io/github/pandas-dev/pandas/coverage.svg?branch=master" alt="coverage" />
     </a>
   </td>
 </tr>
 <tr>
-  <td>Conda-forge</td>
+  <td>Downloads</td>
   <td>
     <a href="https://pandas.pydata.org">
     <img src="https://anaconda.org/conda-forge/pandas/badges/downloads.svg" alt="conda-forge downloads" />
     </a>
   </td>
 </tr>
 <tr>
-  <td>PyPI</td>
-  <td>
-    <a href="https://pypi.python.org/pypi/pandas/">
-    <img src="https://img.shields.io/pypi/dm/pandas.svg" alt="pypi downloads" />
-    </a>
-  </td>
+	<td>Gitter</td>
+	<td>
+		<a href="https://gitter.im/pydata/pandas">
+		<img src="https://badges.gitter.im/Join%20Chat.svg"
+	</a>
+	</td>
 </tr>
 </table>
 
-[![https://gitter.im/pydata/pandas](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/pydata/pandas?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
+
 
 ## What is it
 
@@ -147,7 +158,7 @@ The source code is currently hosted on GitHub at:
 https://github.com/pandas-dev/pandas
 
 Binary installers for the latest released version are available at the [Python
-package index](https://pypi.python.org/pypi/pandas) and on conda.
+package index](https://pypi.org/project/pandas) and on conda.
 
 ```sh
 # conda
@@ -160,7 +171,7 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](http://www.numpy.org): 1.9.0 or higher
+- [NumPy](https://www.numpy.org): 1.9.0 or higher
 - [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
 - [pytz](https://pythonhosted.org/pytz): 2011k or higher
 
@@ -222,7 +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).
 

appveyor.yml

@@ -73,19 +73,12 @@ install:
   - cmd: conda info -a
 
   # create our env
-  - cmd: conda create -n pandas python=%PYTHON_VERSION% cython pytest>=3.1.0 pytest-xdist
+  - cmd: conda env create -q -n pandas --file=ci\appveyor-%CONDA_PY%.yaml
   - cmd: activate pandas
-  - cmd: pip install moto
-  - SET REQ=ci\requirements-%PYTHON_VERSION%_WIN.run
-  - cmd: echo "installing requirements from %REQ%"
-  - cmd: conda install -n pandas --file=%REQ%
   - cmd: conda list -n pandas
-  - cmd: echo "installing requirements from %REQ% - done"
-
-  # add some pip only reqs to the env
-  - SET REQ=ci\requirements-%PYTHON_VERSION%_WIN.pip
-  - cmd: echo "installing requirements from %REQ%"
-  - cmd: pip install -Ur %REQ%
+  # uninstall pandas if it's present
+  - cmd: conda remove pandas -y --force & exit 0
+  - cmd: pip uninstall -y pandas & exit 0
 
   # build em using the local source checkout in the correct windows env
   - cmd: '%CMD_IN_ENV% python setup.py build_ext --inplace'

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):
 
@@ -148,3 +152,96 @@ def time_rank_int_cat(self):
 
     def time_rank_int_cat_ordered(self):
         self.s_int_cat_ordered.rank()
+
+
+class Isin(object):
+
+    goal_time = 0.2
+
+    params = ['object', 'int64']
+    param_names = ['dtype']
+
+    def setup(self, dtype):
+        np.random.seed(1234)
+        n = 5 * 10**5
+        sample_size = 100
+        arr = [i for i in np.random.randint(0, n // 10, size=n)]
+        if dtype == 'object':
+            arr = ['s%04d' % i for i in arr]
+        self.sample = np.random.choice(arr, sample_size)
+        self.series = pd.Series(arr).astype('category')
+
+    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
+
+
+class Contains(object):
+
+    goal_time = 0.2
+
+    def setup(self):
+        N = 10**5
+        self.ci = tm.makeCategoricalIndex(N)
+        self.c = self.ci.values
+        self.key = self.ci.categories[0]
+
+    def time_categorical_index_contains(self):
+        self.key in self.ci
+
+    def time_categorical_contains(self):
+        self.key in self.c
+
+
+class CategoricalSlicing(object):
+
+    goal_time = 0.2
+    params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
+    param_names = ['index']
+
+    def setup(self, index):
+        N = 10**6
+        values = list('a' * N + 'b' * N + 'c' * N)
+        indices = {
+            'monotonic_incr': pd.Categorical(values),
+            'monotonic_decr': pd.Categorical(reversed(values)),
+            'non_monotonic': pd.Categorical(list('abc' * N))}
+        self.data = indices[index]
+
+        self.scalar = 10000
+        self.list = list(range(10000))
+        self.cat_scalar = 'b'
+
+    def time_getitem_scalar(self, index):
+        self.data[self.scalar]
+
+    def time_getitem_slice(self, index):
+        self.data[:self.scalar]
+
+    def time_getitem_list_like(self, index):
+        self.data[[self.scalar]]
+
+    def time_getitem_list(self, index):
+        self.data[self.list]
+
+    def time_getitem_bool_array(self, index):
+        self.data[self.data == self.cat_scalar]