Merge remote-tracking branch 'upstream/master' into 26814-optional-fu

Author: TomAugspurger

azure-pipelines.yml

@@ -24,7 +24,6 @@ jobs:
       # XXX next command should avoid redefining the path in every step, but
       # made the process crash as it couldn't find deactivate
       #echo '##vso[task.prependpath]$HOME/miniconda3/bin'
-      echo '##vso[task.setvariable variable=CONDA_ENV]pandas-dev'
       echo '##vso[task.setvariable variable=ENV_FILE]environment.yml'
       echo '##vso[task.setvariable variable=AZURE]true'
     displayName: 'Setting environment variables'
@@ -116,3 +115,65 @@ jobs:
       fi
     displayName: 'Running benchmarks'
     condition: true
+
+- job: 'Docs'
+  pool:
+    vmImage: ubuntu-16.04
+  timeoutInMinutes: 90
+  steps:
+  - script: |
+      echo '##vso[task.setvariable variable=ENV_FILE]ci/deps/travis-36-doc.yaml'
+    displayName: 'Setting environment variables'
+
+  - script: |
+      export PATH=$HOME/miniconda3/bin:$PATH
+      sudo apt-get install -y libc6-dev-i386
+      ci/setup_env.sh
+    displayName: 'Setup environment and build pandas'
+
+  - script: |
+      export PATH=$HOME/miniconda3/bin:$PATH
+      source activate pandas-dev
+      doc/make.py
+    displayName: 'Build documentation'
+
+  - script: |
+      cd doc/build/html
+      git init
+      touch .nojekyll
+      echo "dev.pandas.io" > CNAME
+      git add --all .
+      git config user.email "[email protected]"
+      git config user.name "pandas-docs-bot"
+      git commit -m "pandas documentation in master"
+    displayName: 'Create git repo for docs build'
+    condition : |
+      and(not(eq(variables['Build.Reason'], 'PullRequest')),
+          eq(variables['Build.SourceBranch'], 'refs/heads/master'))
+
+  # For `InstallSSHKey@0` to work, next steps are required:
+  # 1. Generate a pair of private/public keys (i.e. `ssh-keygen -t rsa -b 4096 -C "[email protected]"`)
+  # 2. Go to "Library > Secure files" in the Azure Pipelines dashboard: https://dev.azure.com/pandas-dev/pandas/_library?itemType=SecureFiles
+  # 3. Click on "+ Secure file"
+  # 4. Upload the private key (the name of the file must match with the specified in "sshKeySecureFile" input below, "pandas_docs_key")
+  # 5. Click on file name after it is created, tick the box "Authorize for use in all pipelines" and save
+  # 6. The public key specified in "sshPublicKey" is the pair of the uploaded private key, and needs to be set as a deploy key of the repo where the docs will be pushed (with write access): https://github.com/pandas-dev/pandas-dev.github.io/settings/keys
+  - task: InstallSSHKey@0
+    inputs:
+      hostName: 'github.com,192.30.252.128 ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAq2A7hRGmdnm9tUDbO9IDSwBK6TbQa+PXYPCPy6rbTrTtw7PHkccKrpp0yVhp5HdEIcKr6pLlVDBfOLX9QUsyCOV0wzfjIJNlGEYsdlLJizHhbn2mUjvSAHQqZETYP81eFzLQNnPHt4EVVUh7VfDESU84KezmD5QlWpXLmvU31/yMf+Se8xhHTvKSCZIFImWwoG6mbUoWf9nzpIoaSjB+weqqUUmpaaasXVal72J+UX2B+2RPW3RcT0eOzQgqlJL3RKrTJvdsjE3JEAvGq3lGHSZXy28G3skua2SmVi/w4yCE6gbODqnTWlg7+wC604ydGXA8VJiS5ap43JXiUFFAaQ=='
+      sshPublicKey: 'ssh-rsa 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 [email protected]'
+      sshKeySecureFile: 'pandas_docs_key'
+    displayName: 'Install GitHub ssh deployment key'
+    condition : |
+      and(not(eq(variables['Build.Reason'], 'PullRequest')),
+          eq(variables['Build.SourceBranch'], 'refs/heads/master'))
+
+  - script: |
+      cd doc/build/html
+      git remote add origin [email protected]:pandas-dev/pandas-dev.github.io.git
+      git push -f origin master
+      exit 0  # FIXME this will leave the build green even if the step fails. To be removed when we are confident with this.
+    displayName: 'Publish docs to GitHub pages'
+    condition : |
+      and(not(eq(variables['Build.Reason'], 'PullRequest')),
+          eq(variables['Build.SourceBranch'], 'refs/heads/master'))

doc/source/reference/indexing.rst

@@ -190,6 +190,9 @@ Numeric Index
 .. autosummary::
    :toctree: api/
 
+   RangeIndex.start
+   RangeIndex.stop
+   RangeIndex.step
    RangeIndex.from_range
 
 .. _api.categoricalindex:

doc/source/reference/series.rst

@@ -473,6 +473,7 @@ strings and apply several methods to it. These can be accessed like
        Series.cat
        Series.dt
        Series.sparse
+       DataFrame.sparse
        Index.str
 
 .. _api.series.cat:

doc/source/user_guide/sparse.rst

@@ -77,6 +77,8 @@ A sparse array can be converted to a regular (dense) ndarray with :meth:`numpy.a
    np.asarray(sparr)
 
 
+.. _sparse.dtype:
+
 SparseDtype
 -----------
 

doc/source/whatsnew/v0.20.0.rst

@@ -1564,7 +1564,7 @@ Removal of prior version deprecations/changes
 
 - The ``pandas.rpy`` module is removed. Similar functionality can be accessed
   through the `rpy2 <https://rpy2.readthedocs.io/>`__ project.
-  See the :ref:`R interfacing docs <https://pandas.pydata.org/pandas-docs/version/0.20/r_interface.html>`__ for more details.
+  See the `R interfacing docs <https://pandas.pydata.org/pandas-docs/version/0.20/r_interface.html>`__ for more details.
 - The ``pandas.io.ga`` module with a ``google-analytics`` interface is removed (:issue:`11308`).
   Similar functionality can be found in the `Google2Pandas <https://github.com/panalysis/Google2Pandas>`__ package.
 - ``pd.to_datetime`` and ``pd.to_timedelta`` have dropped the ``coerce`` parameter in favor of ``errors`` (:issue:`13602`)

pandas/compat/_optional.py

@@ -1,7 +1,6 @@
 import distutils.version
 import importlib
 import types
-from typing import Optional
 import warnings
 
 # Update install.rst when updating versions!
@@ -53,7 +52,7 @@ def import_optional_dependency(
     extra: str = "",
     raise_on_missing: bool = True,
     on_version: str = "raise",
-) -> Optional[types.ModuleType]:
+):
     """
     Import an optional dependency.
 

pandas/core/frame.py

@@ -6284,8 +6284,8 @@ def _gotitem(self,
     index (default) or the column axis. This behavior is different from
     `numpy` aggregation functions (`mean`, `median`, `prod`, `sum`, `std`,
     `var`), where the default is to compute the aggregation of the flattened
-    array, e.g., ``numpy.mean(arr_2d)`` as opposed to ``numpy.mean(arr_2d,
-    axis=0)``.
+    array, e.g., ``numpy.mean(arr_2d)`` as opposed to
+    ``numpy.mean(arr_2d, axis=0)``.
 
     `agg` is an alias for `aggregate`. Use the alias.
 

pandas/core/strings.py

@@ -2360,13 +2360,13 @@ def cat(self, others=None, sep=None, na_rep=None, join=None):
 
     See Also
     --------
-     Series.str.split : Split strings around given separator/delimiter.
-     Series.str.rsplit : Splits string around given separator/delimiter,
-     starting from the right.
-     Series.str.join : Join lists contained as elements in the Series/Index
-     with passed delimiter.
-     str.split : Standard library version for split.
-     str.rsplit : Standard library version for rsplit.
+    Series.str.split : Split strings around given separator/delimiter.
+    Series.str.rsplit : Splits string around given separator/delimiter,
+        starting from the right.
+    Series.str.join : Join lists contained as elements in the Series/Index
+        with passed delimiter.
+    str.split : Standard library version for split.
+    str.rsplit : Standard library version for rsplit.
 
     Notes
     -----
@@ -2383,7 +2383,12 @@ def cat(self, others=None, sep=None, na_rep=None, join=None):
     Examples
     --------
     >>> s = pd.Series(["this is a regular sentence",
-    "https://docs.python.org/3/tutorial/index.html", np.nan])
+    ...                "https://docs.python.org/3/tutorial/index.html",
+    ...                np.nan])
+    0                       this is a regular sentence
+    1    https://docs.python.org/3/tutorial/index.html
+    2                                              NaN
+    dtype: object
 
     In the default setting, the string is split by whitespace.
 
@@ -2434,7 +2439,6 @@ def cat(self, others=None, sep=None, na_rep=None, join=None):
     0                                           this    is     a  regular
     1  https://docs.python.org/3/tutorial/index.html  None  None     None
     2                                            NaN   NaN   NaN      NaN \
-
                  4
     0     sentence
     1         None

pandas/core/tools/datetimes.py

@@ -456,7 +456,7 @@ def to_datetime(arg, errors='raise', dayfirst=False, yearfirst=False,
         - If False returns ndarray of values.
 
         .. deprecated:: 0.25.0
-            Use :meth:`.to_numpy` or :meth:`Timestamp.to_datetime64`
+            Use :meth:`Series.to_numpy` or :meth:`Timestamp.to_datetime64`
             instead to get an ndarray of values or numpy.datetime64,
             respectively.
 

pandas/core/tools/timedeltas.py

@@ -44,7 +44,7 @@ def to_timedelta(arg, unit='ns', box=True, errors='raise'):
           values of dtype timedelta64[ns].
 
         .. deprecated:: 0.25.0
-            Use :meth:`.to_numpy` or :meth:`Timedelta.to_timedelta64`
+            Use :meth:`Series.to_numpy` or :meth:`Timedelta.to_timedelta64`
             instead to get an ndarray of values or numpy.timedelta64,
             respectively.
 

pandas/io/gcs.py

@@ -15,5 +15,5 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
 
     fs = gcsfs.GCSFileSystem()
     filepath_or_buffer = fs.open(
-        filepath_or_buffer, mode)  # type: gcsfs.GCSFile
+        filepath_or_buffer, mode)
     return filepath_or_buffer, None, compression, True

pandas/io/s3.py

@@ -34,5 +34,5 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
         # for that bucket.
         fs = s3fs.S3FileSystem(anon=True)
         filepath_or_buffer = fs.open(
-            _strip_schema(filepath_or_buffer), mode)  # type: s3fs.S3File
+            _strip_schema(filepath_or_buffer), mode)
     return filepath_or_buffer, None, compression, True