Merge branch 'master' of https://github.com/pandas-dev/pandas

Author: Si Wei How

.travis.yml

@@ -86,6 +86,14 @@ install:
   - ci/submit_cython_cache.sh
   - echo "install done"
 
+before_script:
+  # display server (for clipboard functionality) needs to be started here,
+  # does not work if done in install:setup_env.sh (GH-26103)
+  - export DISPLAY=":99.0"
+  - echo "sh -e /etc/init.d/xvfb start"
+  - sh -e /etc/init.d/xvfb start
+  - sleep 3
+
 script:
   - echo "script start"
   - source activate pandas-dev

ci/azure/windows.yml

@@ -17,16 +17,15 @@ jobs:
         CONDA_PY: "37"
 
   steps:
-    - task: CondaEnvironment@1
-      inputs:
-        updateConda: no
-        packageSpecs: ''
-
-    - script: |
-        ci\\incremental\\setup_conda_environment.cmd
-      displayName: 'Before Install'
+    - powershell: Write-Host "##vso[task.prependpath]$env:CONDA\Scripts"
+      displayName: Add conda to PATH
+    - script: conda update -q -n base conda
+      displayName: Update conda
+    - script: conda env create -q --file ci\\deps\\azure-windows-$(CONDA_PY).yaml
+      displayName: Create anaconda environment
     - script: |
         call activate pandas-dev
+        call conda list
         ci\\incremental\\build.cmd
       displayName: 'Build'
     - script: |

ci/code_checks.sh

@@ -169,15 +169,6 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -r -E --include '*.py' '(unittest(\.| import )mock|mock\.Mock\(\)|mock\.patch)' pandas/tests/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    # Check that we use pytest.raises only as a context manager
-    #
-    # For any flake8-compliant code, the only way this regex gets
-    # matched is if there is no "with" statement preceding "pytest.raises"
-    MSG='Check for pytest.raises as context manager (a line starting with `pytest.raises` is invalid, needs a `with` to precede it)' ; echo $MSG
-    MSG='TODO: This check is currently skipped because so many files fail this. Please enable when all are corrected (xref gh-24332)' ; echo $MSG
-    # invgrep -R --include '*.py' -E '[[:space:]] pytest.raises' pandas/tests
-    # RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     MSG='Check for wrong space after code-block directive and before colon (".. code-block ::" instead of ".. code-block::")' ; echo $MSG
     invgrep -R --include="*.rst" ".. code-block ::" doc/source
     RET=$(($RET + $?)) ; echo $MSG "DONE"
@@ -239,6 +230,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/groupby/groupby.py -k"-cumcount -describe -pipe"
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests datetimes.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/tools/datetimes.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Doctests top-level reshaping functions' ; echo $MSG
     pytest -q --doctest-modules \
         pandas/core/reshape/concat.py \

ci/deps/azure-windows-37.yaml

@@ -1,9 +1,11 @@
 name: pandas-dev
 channels:
   - defaults
+  - conda-forge
 dependencies:
   - beautifulsoup4
   - bottleneck
+  - gcsfs
   - html5lib
   - jinja2
   - lxml

ci/incremental/setup_conda_environment.cmd

@@ -118,16 +118,10 @@ echo "conda list"
 conda list
 
 # Install DB for Linux
-export DISPLAY=":99."
 if [ ${TRAVIS_OS_NAME} == "linux" ]; then
   echo "installing dbs"
   mysql -e 'create database pandas_nosetest;'
   psql -c 'create database pandas_nosetest;' -U postgres
-
-  echo
-  echo "sh -e /etc/init.d/xvfb start"
-  sh -e /etc/init.d/xvfb start
-  sleep 3
 else
    echo "not using dbs on non-linux"
 fi

ci/setup_env.sh

@@ -285,6 +285,11 @@ provides a familiar ``DataFrame`` interface for out-of-core, parallel and distri
 
 Dask-ML enables parallel and distributed machine learning using Dask alongside existing machine learning libraries like Scikit-Learn, XGBoost, and TensorFlow.
 
+`Koalas <https://koalas.readthedocs.io/en/latest/>`__
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Koalas provides a familiar pandas DataFrame interface on top of Apache Spark. It enables users to leverage multi-cores on one machine or a cluster of machines to speed up or scale their DataFrame code.
+
 `Odo <http://odo.pydata.org>`__
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

doc/source/ecosystem.rst

@@ -865,7 +865,7 @@ which is equivalent to using weights
 
 The difference between the above two variants arises because we are
 dealing with series which have finite history. Consider a series of infinite
-history:
+history, with ``adjust=True``:
 
 .. math::
 
@@ -884,10 +884,11 @@ and a ratio of :math:`1 - \alpha` we have
     &= \alpha x_t + (1 - \alpha)[x_{t-1} + (1 - \alpha) x_{t-2} + ...]\alpha\\
     &= \alpha x_t + (1 - \alpha) y_{t-1}
 
-which shows the equivalence of the above two variants for infinite series.
-When ``adjust=True`` we have :math:`y_0 = x_0` and from the last
-representation above we have :math:`y_t = \alpha x_t + (1 - \alpha) y_{t-1}`,
-therefore there is an assumption that :math:`x_0` is not an ordinary value
+which is the same expression as ``adjust=False`` above and therefore
+shows the equivalence of the two variants for infinite series.
+When ``adjust=False``, we have :math:`y_0 = x_0` and
+:math:`y_t = \alpha x_t + (1 - \alpha) y_{t-1}`.
+Therefore, there is an assumption that :math:`x_0` is not an ordinary value
 but rather an exponentially weighted moment of the infinite series up to that
 point.
 

doc/source/user_guide/computation.rst

@@ -238,14 +238,9 @@ Enhancements
 
     - support ``read_hdf/to_hdf`` API similar to ``read_csv/to_csv``
 
-      .. ipython:: python
-          :suppress:
-
-          from pandas.compat import lrange
-
       .. ipython:: python
 
-          df = pd.DataFrame({'A': lrange(5), 'B': lrange(5)})
+          df = pd.DataFrame({'A': range(5), 'B': range(5)})
           df.to_hdf('store.h5', 'table', append=True)
           pd.read_hdf('store.h5', 'table', where=['index > 2'])
 

doc/source/whatsnew/v0.11.0.rst

@@ -83,13 +83,8 @@ API changes
     ``iloc`` API to be *purely* positional based.
 
     .. ipython:: python
-       :suppress:
 
-       from pandas.compat import lrange
-
-    .. ipython:: python
-
-       df = pd.DataFrame(lrange(5), list('ABCDE'), columns=['a'])
+       df = pd.DataFrame(range(5), index=list('ABCDE'), columns=['a'])
        mask = (df.a % 2 == 0)
        mask