Resolved merge conflicts in pandas/io/pickle.py and doc/source/whatsnew/v1.0.0.rst.

Author: TomoyukiSuzuki-Aidea

.travis.yml

@@ -30,31 +30,34 @@ matrix:
       - python: 3.5
 
     include:
-    - dist: trusty
-      env:
+    - env:
         - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network)"
 
-    - dist: trusty
-      env:
+    - env:
         - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network)"
 
-    - dist: trusty
-      env:
-        - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8"
+    - env:
+        - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
+      services:
+        - mysql
+        - postgresql
 
-    - dist: trusty
-      env:
-        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36-cov.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
+    - env:
+        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36-cov.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true SQL="1"
+      services:
+        - mysql
+        - postgresql
 
     # In allow_failures
-    - dist: trusty
-      env:
-        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
+    - env:
+        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow" SQL="1"
+      services:
+        - mysql
+        - postgresql
 
     allow_failures:
-      - dist: trusty
-        env:
-          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
+      - env:
+          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow" SQL="1"
 
 before_install:
   - echo "before_install"

README.md

@@ -124,7 +124,7 @@ Here are just a few of the things that pandas does well:
     and saving/loading data from the ultrafast [**HDF5 format**][hdfstore]
   - [**Time series**][timeseries]-specific functionality: date range
     generation and frequency conversion, moving window statistics,
-    moving window linear regressions, date shifting and lagging, etc.
+    date shifting and lagging.
 
 
    [missing-data]: https://pandas.pydata.org/pandas-docs/stable/missing_data.html#working-with-missing-data

ci/azure/windows.yml

@@ -31,7 +31,8 @@ jobs:
     - bash: |
         source activate pandas-dev
         conda list
-        ci\\incremental\\build.cmd
+        python setup.py build_ext -q -i
+        python -m pip install --no-build-isolation -e .
       displayName: 'Build'
     - bash: |
         source activate pandas-dev

ci/code_checks.sh

@@ -52,7 +52,7 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     black --version
 
     MSG='Checking black formatting' ; echo $MSG
-	black . --check
+    black . --check
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     # `setup.cfg` contains the list of error codes that are being ignored in flake8
@@ -104,7 +104,7 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     isort --version-number
 
     # Imports - Check formatting using isort see setup.cfg for settings
-    MSG='Check import format using isort ' ; echo $MSG
+    MSG='Check import format using isort' ; echo $MSG
     ISORT_CMD="isort --recursive --check-only pandas asv_bench"
     if [[ "$GITHUB_ACTIONS" == "true" ]]; then
         eval $ISORT_CMD | awk '{print "##[error]" $0}'; RET=$(($RET + ${PIPESTATUS[0]}))
@@ -203,6 +203,10 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     invgrep -R --include=*.{py,pyx} '\.__class__' pandas
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Check for use of xrange instead of range' ; echo $MSG
+    invgrep -R --include=*.{py,pyx} 'xrange' pandas
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Check that no file in the repo contains trailing whitespaces' ; echo $MSG
     INVGREP_APPEND=" <- trailing whitespaces found"
     invgrep -RI --exclude=\*.{svg,c,cpp,html,js} --exclude-dir=env "\s$" *

ci/incremental/build.cmd

@@ -38,6 +38,6 @@ sh -c "$PYTEST_CMD"
 
 if [[ "$COVERAGE" && $? == 0 && "$TRAVIS_BRANCH" == "master" ]]; then
     echo "uploading coverage"
-    echo "bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME"
-          bash <(curl -s https://codecov.io/bash) -Z -c -F $TYPE -f $COVERAGE_FNAME
+    echo "bash <(curl -s https://codecov.io/bash) -Z -c -f $COVERAGE_FNAME"
+          bash <(curl -s https://codecov.io/bash) -Z -c -f $COVERAGE_FNAME
 fi

ci/run_tests.sh

@@ -140,7 +140,8 @@ echo "conda list"
 conda list
 
 # Install DB for Linux
-if [ "${TRAVIS_OS_NAME}" == "linux" ]; then
+
+if [[ -n ${SQL:0} ]]; then
   echo "installing dbs"
   mysql -e 'create database pandas_nosetest;'
   psql -c 'create database pandas_nosetest;' -U postgres

ci/setup_env.sh

@@ -777,7 +777,7 @@ generated/pandas.io.formats.style.Styler.to_excel,../reference/api/pandas.io.for
 generated/pandas.io.formats.style.Styler.use,../reference/api/pandas.io.formats.style.Styler.use
 generated/pandas.io.formats.style.Styler.where,../reference/api/pandas.io.formats.style.Styler.where
 generated/pandas.io.json.build_table_schema,../reference/api/pandas.io.json.build_table_schema
-generated/pandas.io.json.json_normalize,../reference/api/pandas.io.json.json_normalize
+generated/pandas.io.json.json_normalize,../reference/api/pandas.json_normalize
 generated/pandas.io.stata.StataReader.data_label,../reference/api/pandas.io.stata.StataReader.data_label
 generated/pandas.io.stata.StataReader.value_labels,../reference/api/pandas.io.stata.StataReader.value_labels
 generated/pandas.io.stata.StataReader.variable_labels,../reference/api/pandas.io.stata.StataReader.variable_labels

doc/redirects.csv

@@ -204,7 +204,11 @@
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
-# html_theme_options = {}
+html_theme_options = {
+    "external_links": [],
+    "github_url": "https://github.com/pandas-dev/pandas",
+    "twitter_url": "https://twitter.com/pandas_dev",
+}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = ["themes"]
@@ -228,7 +232,7 @@
 # The name of an image file (within the static path) to use as favicon of the
 # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-html_favicon = os.path.join(html_static_path[0], "favicon.ico")
+html_favicon = "../../web/pandas/static/img/favicon.ico"
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.

doc/source/_static/favicon.ico

@@ -57,8 +57,7 @@ Here are just a few of the things that pandas does well:
     Excel files, databases, and saving / loading data from the ultrafast **HDF5
     format**
   - **Time series**-specific functionality: date range generation and frequency
-    conversion, moving window statistics, moving window linear regressions,
-    date shifting and lagging, etc.
+    conversion, moving window statistics, date shifting and lagging.
 
 Many of these principles are here to address the shortcomings frequently
 experienced using other languages / scientific research environments. For data

doc/source/conf.py

@@ -50,13 +50,13 @@ JSON
    :toctree: api/
 
    read_json
+   json_normalize
 
 .. currentmodule:: pandas.io.json
 
 .. autosummary::
    :toctree: api/
 
-   json_normalize
    build_table_schema
 
 .. currentmodule:: pandas

doc/source/getting_started/overview.rst

@@ -2136,27 +2136,26 @@ into a flat table.
 
 .. ipython:: python
 
-   from pandas.io.json import json_normalize
    data = [{'id': 1, 'name': {'first': 'Coleen', 'last': 'Volk'}},
            {'name': {'given': 'Mose', 'family': 'Regner'}},
            {'id': 2, 'name': 'Faye Raker'}]
-   json_normalize(data)
+   pd.json_normalize(data)
 
 .. ipython:: python
 
    data = [{'state': 'Florida',
             'shortname': 'FL',
             'info': {'governor': 'Rick Scott'},
-            'counties': [{'name': 'Dade', 'population': 12345},
-                         {'name': 'Broward', 'population': 40000},
-                         {'name': 'Palm Beach', 'population': 60000}]},
+            'county': [{'name': 'Dade', 'population': 12345},
+                       {'name': 'Broward', 'population': 40000},
+                       {'name': 'Palm Beach', 'population': 60000}]},
            {'state': 'Ohio',
             'shortname': 'OH',
             'info': {'governor': 'John Kasich'},
-            'counties': [{'name': 'Summit', 'population': 1234},
-                         {'name': 'Cuyahoga', 'population': 1337}]}]
+            'county': [{'name': 'Summit', 'population': 1234},
+                       {'name': 'Cuyahoga', 'population': 1337}]}]
 
-   json_normalize(data, 'counties', ['state', 'shortname', ['info', 'governor']])
+   pd.json_normalize(data, 'county', ['state', 'shortname', ['info', 'governor']])
 
 The max_level parameter provides more control over which level to end normalization.
 With max_level=1 the following snippet normalizes until 1st nesting level of the provided dict.
@@ -2169,7 +2168,7 @@ With max_level=1 the following snippet normalizes until 1st nesting level of the
                                       'Name': 'Name001'}},
              'Image': {'a': 'b'}
              }]
-    json_normalize(data, max_level=1)
+    pd.json_normalize(data, max_level=1)
 
 .. _io.jsonl:
 
@@ -4764,10 +4763,10 @@ Parquet supports partitioning of data based on the values of one or more columns
 .. ipython:: python
 
     df = pd.DataFrame({'a': [0, 0, 1, 1], 'b': [0, 1, 0, 1]})
-    df.to_parquet(fname='test', engine='pyarrow',
+    df.to_parquet(path='test', engine='pyarrow',
                   partition_cols=['a'], compression=None)
 
-The `fname` specifies the parent directory to which data will be saved.
+The `path` specifies the parent directory to which data will be saved.
 The `partition_cols` are the column names by which the dataset will be partitioned.
 Columns are partitioned in the order they are given. The partition splits are
 determined by the unique values in the partition columns.
@@ -4829,7 +4828,6 @@ See also some :ref:`cookbook examples <cookbook.sql>` for some advanced strategi
 The key functions are:
 
 .. autosummary::
-    :toctree: ../reference/api/
 
     read_sql_table
     read_sql_query

doc/source/reference/io.rst

@@ -74,6 +74,7 @@ These are places where the behavior of ``StringDtype`` objects differ from
 l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
    that return **numeric** output will always return a nullable integer dtype,
    rather than either int or float dtype, depending on the presence of NA values.
+   Methods returning **boolean** output will return a nullable boolean dtype.
 
    .. ipython:: python
 
@@ -89,12 +90,22 @@ l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
       s.astype(object).str.count("a")
       s.astype(object).dropna().str.count("a")
 
-   When NA values are present, the output dtype is float64.
+   When NA values are present, the output dtype is float64. Similarly for
+   methods returning boolean values.
+
+   .. ipython:: python
+
+      s.str.isdigit()
+      s.str.match("a")
 
 2. Some string methods, like :meth:`Series.str.decode` are not available
    on ``StringArray`` because ``StringArray`` only holds strings, not
    bytes.
-
+3. In comparision operations, :class:`arrays.StringArray` and ``Series`` backed
+   by a ``StringArray`` will return an object with :class:`BooleanDtype`,
+   rather than a ``bool`` dtype object. Missing values in a ``StringArray``
+   will propagate in comparision operations, rather than always comparing
+   unequal like :attr:`numpy.nan`.
 
 Everything else that follows in the rest of this document applies equally to
 ``string`` and ``object`` dtype.

doc/source/user_guide/io.rst

@@ -170,7 +170,7 @@ which level to end normalization (:issue:`23843`):
 
 The repr now looks like this:
 
-.. ipython:: python
+.. code-block:: ipython
 
     from pandas.io.json import json_normalize
     data = [{

doc/source/user_guide/text.rst

@@ -205,6 +205,9 @@ Other enhancements
   (:meth:`~DataFrame.to_parquet` / :func:`read_parquet`) using the `'pyarrow'` engine
   now preserve those data types with pyarrow >= 1.0.0 (:issue:`20612`).
 - The ``partition_cols`` argument in :meth:`DataFrame.to_parquet` now accepts a string (:issue:`27117`)
+- :func:`to_parquet` now appropriately handles the ``schema`` argument for user defined schemas in the pyarrow engine. (:issue: `30270`)
+- DataFrame constructor preserve `ExtensionArray` dtype with `ExtensionArray` (:issue:`11363`)
+
 
 Build Changes
 ^^^^^^^^^^^^^
@@ -252,10 +255,10 @@ To update, use ``MultiIndex.set_names``, which returns a new ``MultiIndex``.
    mi2 = mi.set_names("new name", level=0)
    mi2.names
 
-New repr for :class:`pandas.core.arrays.IntervalArray`
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+New repr for :class:`~pandas.arrays.IntervalArray`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-- :class:`pandas.core.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
+- :class:`pandas.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
 
 *pandas 0.25.x*
 
@@ -486,6 +489,7 @@ Documentation Improvements
 Deprecations
 ~~~~~~~~~~~~
 
+- :meth:`Series.item` and :meth:`Index.item` have been _undeprecated_ (:issue:`29250`)
 - ``Index.set_value`` has been deprecated. For a given index ``idx``, array ``arr``,
   value in ``idx`` of ``idx_val`` and a new value of ``val``, ``idx.set_value(arr, idx_val, val)``
   is equivalent to ``arr[idx.get_loc(idx_val)] = val``, which should be used instead (:issue:`28621`).
@@ -495,7 +499,11 @@ Deprecations
 - The parameter ``numeric_only`` of :meth:`Categorical.min` and :meth:`Categorical.max` is deprecated and replaced with ``skipna`` (:issue:`25303`)
 - The parameter ``label`` in :func:`lreshape` has been deprecated and will be removed in a future version (:issue:`29742`)
 - ``pandas.core.index`` has been deprecated and will be removed in a future version, the public classes are available in the top-level namespace (:issue:`19711`)
--
+- :func:`pandas.json_normalize` is now exposed in the top-level namespace.
+  Usage of ``json_normalize`` as ``pandas.io.json.json_normalize`` is now deprecated and
+  it is recommended to use ``json_normalize`` as :func:`pandas.json_normalize` instead (:issue:`27586`).
+- :meth:`DataFrame.to_stata`, :meth:`DataFrame.to_feather`, and :meth:`DataFrame.to_parquet` argument "fname" is deprecated, use "path" instead (:issue:`23574`)
+
 
 .. _whatsnew_1000.prior_deprecations:
 
@@ -571,7 +579,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - :meth:`Series.where` with ``Categorical`` dtype (or :meth:`DataFrame.where` with ``Categorical`` column) no longer allows setting new categories (:issue:`24114`)
 - :class:`DatetimeIndex`, :class:`TimedeltaIndex`, and :class:`PeriodIndex` constructors no longer allow ``start``, ``end``, and ``periods`` keywords, use :func:`date_range`, :func:`timedelta_range`, and :func:`period_range` instead (:issue:`23919`)
 - :class:`DatetimeIndex` and :class:`TimedeltaIndex` constructors no longer have a ``verify_integrity`` keyword argument (:issue:`23919`)
-- :func:`core.internals.blocks.make_block` no longer accepts the "fastpath" keyword(:issue:`19265`)
+- ``pandas.core.internals.blocks.make_block`` no longer accepts the "fastpath" keyword(:issue:`19265`)
 - :meth:`Block.make_block_same_class` no longer accepts the "dtype" keyword(:issue:`19434`)
 - Removed the previously deprecated :meth:`ExtensionArray._formatting_values`. Use :attr:`ExtensionArray._formatter` instead. (:issue:`23601`)
 - Removed the previously deprecated :meth:`MultiIndex.to_hierarchical` (:issue:`21613`)
@@ -648,7 +656,7 @@ Performance improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 - Performance improvement in indexing with a non-unique :class:`IntervalIndex` (:issue:`27489`)
-- Performance improvement in `MultiIndex.is_monotonic` (:issue:`27495`)
+- Performance improvement in :attr:`MultiIndex.is_monotonic` (:issue:`27495`)
 - Performance improvement in :func:`cut` when ``bins`` is an :class:`IntervalIndex` (:issue:`27668`)
 - Performance improvement when initializing a :class:`DataFrame` using a ``range`` (:issue:`30171`)
 - Performance improvement in :meth:`DataFrame.corr` when ``method`` is ``"spearman"`` (:issue:`28139`)
@@ -703,6 +711,8 @@ Datetimelike
 - Bug in :attr:`Timestamp.resolution` being a property instead of a class attribute (:issue:`29910`)
 - Bug in :func:`pandas.to_datetime` when called with ``None`` raising ``TypeError`` instead of returning ``NaT`` (:issue:`30011`)
 - Bug in :func:`pandas.to_datetime` failing for `deques` when using ``cache=True`` (the default) (:issue:`29403`)
+- Bug in :meth:`Series.item` with ``datetime64`` or ``timedelta64`` dtype, :meth:`DatetimeIndex.item`, and :meth:`TimedeltaIndex.item` returning an integer instead of a :class:`Timestamp` or :class:`Timedelta` (:issue:`30175`)
+- Bug in :class:`DatetimeIndex` addition when adding a non-optimized :class:`DateOffset` incorrectly dropping timezone information (:issue:`30336`)
 
 Timedelta
 ^^^^^^^^^
@@ -749,7 +759,7 @@ Interval
 ^^^^^^^^
 
 - Bug in :meth:`IntervalIndex.get_indexer` where a :class:`Categorical` or :class:`CategoricalIndex` ``target`` would incorrectly raise a ``TypeError`` (:issue:`30063`)
--
+- Bug in ``pandas.core.dtypes.cast.infer_dtype_from_scalar`` where passing ``pandas_dtype=True`` did not infer :class:`IntervalDtype` (:issue:`30337`)
 
 Indexing
 ^^^^^^^^
@@ -813,7 +823,7 @@ Plotting
 - Bug in the ``xticks`` argument being ignored for :meth:`DataFrame.plot.bar` (:issue:`14119`)
 - :func:`set_option` now validates that the plot backend provided to ``'plotting.backend'`` implements the backend when the option is set, rather than when a plot is created (:issue:`28163`)
 - :meth:`DataFrame.plot` now allow a ``backend`` keyword arugment to allow changing between backends in one session (:issue:`28619`).
-- Bug in color validation incorrectly raising for non-color styles (:issue:`29122`).
+- Bug in color validation incorrectly raising for non-color styles (:issue:`30163`).
 
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
@@ -833,6 +843,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrame.groupby` where ``any``, ``all``, ``nunique`` and transform functions would incorrectly handle duplicate column labels (:issue:`21668`)
 - Bug in :meth:`DataFrameGroupBy.agg` with timezone-aware datetime64 column incorrectly casting results to the original dtype (:issue:`29641`)
 - Bug in :meth:`DataFrame.groupby` when using axis=1 and having a single level columns index (:issue:`30208`)
+- Bug in :meth:`DataFrame.groupby` when using nunique on axis=1 (:issue:`30253`)
 
 Reshaping
 ^^^^^^^^^