Merge remote-tracking branch 'upstream/master' into unique-index

Author: TomAugspurger

.pre-commit-config.yaml

@@ -15,3 +15,4 @@ repos:
     hooks:
     -   id: isort
         language: python_venv
+        exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$

README.md

@@ -225,7 +225,7 @@ Most development discussion is taking place on github in this repo. Further, the
 
 All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome.
 
-A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
+A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/docs/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
 
 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.
 

azure-pipelines.yml

@@ -104,7 +104,7 @@ jobs:
     displayName: 'Running benchmarks'
     condition: true
 
-- job: 'Docs'
+- job: 'Web_and_Docs'
   pool:
     vmImage: ubuntu-16.04
   timeoutInMinutes: 90
@@ -119,6 +119,11 @@ jobs:
       ci/setup_env.sh
     displayName: 'Setup environment and build pandas'
 
+  - script: |
+      source activate pandas-dev
+      python web/pandas_web.py web/pandas
+    displayName: 'Build website'
+
   - script: |
       source activate pandas-dev
       # Next we should simply have `doc/make.py --warnings-are-errors`, everything else is required because the ipython directive doesn't fail the build on errors (https://github.com/ipython/ipython/issues/11547)
@@ -128,15 +133,21 @@ jobs:
     displayName: 'Build documentation'
 
   - script: |
-      cd doc/build/html
+      mkdir -p to_deploy/docs
+      cp -r web/build/* to_deploy/
+      cp -r doc/build/html/* to_deploy/docs/
+    displayName: 'Merge website and docs'
+
+  - script: |
+      cd to_deploy
       git init
       touch .nojekyll
       echo "dev.pandas.io" > CNAME
       printf "User-agent: *\nDisallow: /" > robots.txt
       git add --all .
       git config user.email "pandas-dev@python.org"
-      git config user.name "pandas-docs-bot"
-      git commit -m "pandas documentation in master"
+      git config user.name "pandas-bot"
+      git commit -m "pandas web and documentation in master"
     displayName: 'Create git repo for docs build'
     condition : |
       and(not(eq(variables['Build.Reason'], 'PullRequest')),
@@ -160,10 +171,10 @@ jobs:
           eq(variables['Build.SourceBranch'], 'refs/heads/master'))
 
   - script: |
-      cd doc/build/html
+      cd to_deploy
       git remote add origin git@github.com:pandas-dev/pandas-dev.github.io.git
       git push -f origin master
-    displayName: 'Publish docs to GitHub pages'
+    displayName: 'Publish web and docs to GitHub pages'
     condition : |
       and(not(eq(variables['Build.Reason'], 'PullRequest')),
           eq(variables['Build.SourceBranch'], 'refs/heads/master'))

ci/azure/posix.yml

@@ -60,15 +60,21 @@ jobs:
         echo "Creating Environment"
         ci/setup_env.sh
       displayName: 'Setup environment and build pandas'
+
     - script: |
         source activate pandas-dev
         ci/run_tests.sh
       displayName: 'Test'
+
     - script: source activate pandas-dev && pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
+      displayName: 'Build versions'
+
     - task: PublishTestResults@2
       inputs:
         testResultsFiles: 'test-data-*.xml'
         testRunTitle: ${{ format('{0}-$(CONDA_PY)', parameters.name) }}
+      displayName: 'Publish test results'
+
     - powershell: |
         $junitXml = "test-data-single.xml"
         $(Get-Content $junitXml | Out-String) -match 'failures="(.*?)"'
@@ -94,6 +100,7 @@ jobs:
           Write-Error "$($matches[1]) tests failed"
         }
       displayName: 'Check for test failures'
+
     - script: |
         source activate pandas-dev
         python ci/print_skipped.py

ci/print_skipped.py

@@ -1,52 +1,40 @@
 #!/usr/bin/env python
-
-import math
 import os
-import sys
 import xml.etree.ElementTree as et
 
 
-def parse_results(filename):
+def main(filename):
+    if not os.path.isfile(filename):
+        return
+
     tree = et.parse(filename)
     root = tree.getroot()
-    skipped = []
-
     current_class = ""
-    i = 1
-    assert i - 1 == len(skipped)
     for el in root.findall("testcase"):
         cn = el.attrib["classname"]
         for sk in el.findall("skipped"):
             old_class = current_class
             current_class = cn
-            name = "{classname}.{name}".format(
-                classname=current_class, name=el.attrib["name"]
-            )
-            msg = sk.attrib["message"]
-            out = ""
             if old_class != current_class:
-                ndigits = int(math.log(i, 10) + 1)
-
-                # 4 for : + space + # + space
-                out += "-" * (len(name + msg) + 4 + ndigits) + "\n"
-            out += "#{i} {name}: {msg}".format(i=i, name=name, msg=msg)
-            skipped.append(out)
-            i += 1
-            assert i - 1 == len(skipped)
-    assert i - 1 == len(skipped)
-    # assert len(skipped) == int(root.attrib['skip'])
-    return "\n".join(skipped)
-
-
-def main():
-    test_files = ["test-data-single.xml", "test-data-multiple.xml", "test-data.xml"]
-
-    print("SKIPPED TESTS:")
-    for fn in test_files:
-        if os.path.isfile(fn):
-            print(parse_results(fn))
-    return 0
+                yield None
+            yield {
+                "class_name": current_class,
+                "test_name": el.attrib["name"],
+                "message": sk.attrib["message"],
+            }
 
 
 if __name__ == "__main__":
-    sys.exit(main())
+    print("SKIPPED TESTS:")
+    i = 1
+    for file_type in ("-single", "-multiple", ""):
+        for test_data in main("test-data{}.xml".format(file_type)):
+            if test_data is None:
+                print("-" * 80)
+            else:
+                print(
+                    "#{i} {class_name}.{test_name}: {message}".format(
+                        **dict(test_data, i=i)
+                    )
+                )
+                i += 1

ci/run_tests.sh

@@ -1,13 +1,6 @@
-#!/bin/bash
+#!/bin/bash -e
 
-set -e
-
-if [ "$DOC" ]; then
-    echo "We are not running pytest as this is a doc-build"
-    exit 0
-fi
-
-# Workaround for pytest-xdist flaky collection order
+# Workaround for pytest-xdist (it collects different tests in the workers if PYTHONHASHSEED is not set)
 # https://github.com/pytest-dev/pytest/issues/920
 # https://github.com/pytest-dev/pytest/issues/1075
 export PYTHONHASHSEED=$(python -c 'import random; print(random.randint(1, 4294967295))')
@@ -16,7 +9,7 @@ if [ -n "$LOCALE_OVERRIDE" ]; then
     export LC_ALL="$LOCALE_OVERRIDE"
     export LANG="$LOCALE_OVERRIDE"
     PANDAS_LOCALE=`python -c 'import pandas; pandas.get_option("display.encoding")'`
-    if [[ "$LOCALE_OVERIDE" != "$PANDAS_LOCALE" ]]; then
+    if [[ "$LOCALE_OVERRIDE" != "$PANDAS_LOCALE" ]]; then
         echo "pandas could not detect the locale. System locale: $LOCALE_OVERRIDE, pandas detected: $PANDAS_LOCALE"
         # TODO Not really aborting the tests until https://github.com/pandas-dev/pandas/issues/23923 is fixed
         # exit 1

doc/redirects.csv

@@ -503,7 +503,6 @@ generated/pandas.DataFrame.to_parquet,../reference/api/pandas.DataFrame.to_parqu
 generated/pandas.DataFrame.to_period,../reference/api/pandas.DataFrame.to_period
 generated/pandas.DataFrame.to_pickle,../reference/api/pandas.DataFrame.to_pickle
 generated/pandas.DataFrame.to_records,../reference/api/pandas.DataFrame.to_records
-generated/pandas.DataFrame.to_sparse,../reference/api/pandas.DataFrame.to_sparse
 generated/pandas.DataFrame.to_sql,../reference/api/pandas.DataFrame.to_sql
 generated/pandas.DataFrame.to_stata,../reference/api/pandas.DataFrame.to_stata
 generated/pandas.DataFrame.to_string,../reference/api/pandas.DataFrame.to_string
@@ -1432,7 +1431,6 @@ generated/pandas.Series.to_msgpack,../reference/api/pandas.Series.to_msgpack
 generated/pandas.Series.to_numpy,../reference/api/pandas.Series.to_numpy
 generated/pandas.Series.to_period,../reference/api/pandas.Series.to_period
 generated/pandas.Series.to_pickle,../reference/api/pandas.Series.to_pickle
-generated/pandas.Series.to_sparse,../reference/api/pandas.Series.to_sparse
 generated/pandas.Series.to_sql,../reference/api/pandas.Series.to_sql
 generated/pandas.Series.to_string,../reference/api/pandas.Series.to_string
 generated/pandas.Series.to_timestamp,../reference/api/pandas.Series.to_timestamp

doc/source/reference/frame.rst

@@ -357,15 +357,7 @@ Serialization / IO / conversion
    DataFrame.to_msgpack
    DataFrame.to_gbq
    DataFrame.to_records
-   DataFrame.to_sparse
    DataFrame.to_dense
    DataFrame.to_string
    DataFrame.to_clipboard
    DataFrame.style
-
-Sparse
-~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   SparseDataFrame.to_coo

doc/source/reference/series.rst

@@ -577,18 +577,7 @@ Serialization / IO / conversion
    Series.to_sql
    Series.to_msgpack
    Series.to_json
-   Series.to_sparse
    Series.to_dense
    Series.to_string
    Series.to_clipboard
    Series.to_latex
-
-
-Sparse
-------
-
-.. autosummary::
-   :toctree: api/
-
-   SparseSeries.to_coo
-   SparseSeries.from_coo

doc/source/user_guide/io.rst

@@ -4641,6 +4641,14 @@ Several caveats.
 
 See the `Full Documentation <https://github.com/wesm/feather>`__.
 
+.. ipython:: python
+   :suppress:
+
+   import warnings
+   # This can be removed once building with pyarrow >=0.15.0
+   warnings.filterwarnings("ignore", "The Sparse", FutureWarning)
+
+
 .. ipython:: python
 
    df = pd.DataFrame({'a': list('abc'),

doc/source/user_guide/sparse.rst

@@ -6,12 +6,6 @@
 Sparse data structures
 **********************
 
-.. note::
-
-   ``SparseSeries`` and ``SparseDataFrame`` have been deprecated. Their purpose
-   is served equally well by a :class:`Series` or :class:`DataFrame` with
-   sparse values. See :ref:`sparse.migration` for tips on migrating.
-
 Pandas provides data structures for efficiently storing sparse data.
 These are not necessarily sparse in the typical "mostly 0". Rather, you can view these
 objects as being "compressed" where any data matching a specific value (``NaN`` / missing value, though any value
@@ -168,6 +162,11 @@ the correct dense result.
 Migrating
 ---------
 
+.. note::
+
+   ``SparseSeries`` and ``SparseDataFrame`` were removed in pandas 1.0.0. This migration
+   guide is present to aid in migrating from previous versions.
+
 In older versions of pandas, the ``SparseSeries`` and ``SparseDataFrame`` classes (documented below)
 were the preferred way to work with sparse data. With the advent of extension arrays, these subclasses
 are no longer needed. Their purpose is better served by using a regular Series or DataFrame with
@@ -366,12 +365,3 @@ row and columns coordinates of the matrix. Note that this will consume a signifi
 
    ss_dense = pd.Series.sparse.from_coo(A, dense_index=True)
    ss_dense
-
-
-.. _sparse.subclasses:
-
-Sparse subclasses
------------------
-
-The :class:`SparseSeries` and :class:`SparseDataFrame` classes are deprecated. Visit their
-API pages for usage.

doc/source/whatsnew/v0.16.0.rst

@@ -91,8 +91,7 @@ Interaction with scipy.sparse
 
 Added :meth:`SparseSeries.to_coo` and :meth:`SparseSeries.from_coo` methods (:issue:`8048`) for converting to and from ``scipy.sparse.coo_matrix`` instances (see :ref:`here <sparse.scipysparse>`). For example, given a SparseSeries with MultiIndex we can convert to a `scipy.sparse.coo_matrix` by specifying the row and column labels as index levels:
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    s = pd.Series([3.0, np.nan, 1.0, 3.0, np.nan, np.nan])
    s.index = pd.MultiIndex.from_tuples([(1, 2, 'a', 0),
@@ -121,8 +120,7 @@ Added :meth:`SparseSeries.to_coo` and :meth:`SparseSeries.from_coo` methods (:is
 The from_coo method is a convenience method for creating a ``SparseSeries``
 from a ``scipy.sparse.coo_matrix``:
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    from scipy import sparse
    A = sparse.coo_matrix(([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])),

doc/source/whatsnew/v0.18.1.rst

@@ -393,8 +393,7 @@ used in the ``pandas`` implementation (:issue:`12644`, :issue:`12638`, :issue:`1
 
 An example of this signature augmentation is illustrated below:
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    sp = pd.SparseDataFrame([1, 2, 3])
    sp
@@ -409,8 +408,7 @@ Previous behaviour:
 
 New behaviour:
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    np.cumsum(sp, axis=0)
 

doc/source/whatsnew/v0.19.0.rst

@@ -1235,8 +1235,7 @@ Operators now preserve dtypes
 
 - Sparse data structure now can preserve ``dtype`` after arithmetic ops (:issue:`13848`)
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    s = pd.SparseSeries([0, 2, 0, 1], fill_value=0, dtype=np.int64)
    s.dtype
@@ -1245,8 +1244,7 @@ Operators now preserve dtypes
 
 - Sparse data structure now support ``astype`` to convert internal ``dtype`` (:issue:`13900`)
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    s = pd.SparseSeries([1., 0., 2., 0.], fill_value=0)
    s

doc/source/whatsnew/v0.20.0.rst

@@ -338,8 +338,7 @@ See the :ref:`documentation <sparse.scipysparse>` for more information. (:issue:
 
 All sparse formats are supported, but matrices that are not in :mod:`COOrdinate <scipy.sparse>` format will be converted, copying data as needed.
 
-.. ipython:: python
-   :okwarning:
+.. code-block:: python
 
    from scipy.sparse import csr_matrix
    arr = np.random.random(size=(1000, 5))
@@ -351,7 +350,7 @@ All sparse formats are supported, but matrices that are not in :mod:`COOrdinate
 
 To convert a ``SparseDataFrame`` back to sparse SciPy matrix in COO format, you can use:
 
-.. ipython:: python
+.. code-block:: python
 
    sdf.to_coo()