Revert "Merge remote-tracking branch 'upstream/master'"

This reverts commit 561096c, reversing
changes made to b492293.

Author: GYHHAHA

Dockerfile

@@ -1,4 +1,4 @@
-FROM quay.io/condaforge/miniforge3
+FROM continuumio/miniconda3
 
 # if you forked pandas, you can pass in your own GitHub username to use your fork
 # i.e. gh_username=myname
@@ -15,6 +15,10 @@ RUN apt-get update \
     # Verify git, process tools, lsb-release (common in install instructions for CLIs) installed
     && apt-get -y install git iproute2 procps iproute2 lsb-release \
     #
+    # Install C compilers (gcc not enough, so just went with build-essential which admittedly might be overkill),
+    # needed to build pandas C extensions
+    && apt-get -y install build-essential \
+    #
     # cleanup
     && apt-get autoremove -y \
     && apt-get clean -y \
@@ -35,14 +39,9 @@ RUN mkdir "$pandas_home" \
 # we just update the base/root one from the 'environment.yml' file instead of creating a new one.
 #
 # Set up environment
-RUN conda install -y mamba
-RUN mamba env update -n base -f "$pandas_home/environment.yml"
+RUN conda env update -n base -f "$pandas_home/environment.yml"
 
 # Build C extensions and pandas
-SHELL ["/bin/bash", "-c"]
-RUN . /opt/conda/etc/profile.d/conda.sh \
-    && conda activate base \
-    && cd "$pandas_home" \
-    && export \
+RUN cd "$pandas_home" \
     && python setup.py build_ext -j 4 \
     && python -m pip install -e .

README.md

@@ -63,24 +63,24 @@ Here are just a few of the things that pandas does well:
     date shifting and lagging
 
 
-   [missing-data]: https://pandas.pydata.org/pandas-docs/stable/user_guide/missing_data.html
-   [insertion-deletion]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html#column-selection-addition-deletion
-   [alignment]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html?highlight=alignment#intro-to-data-structures
-   [groupby]: https://pandas.pydata.org/pandas-docs/stable/user_guide/groupby.html#group-by-split-apply-combine
-   [conversion]: https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html#dataframe
-   [slicing]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#slicing-ranges
-   [fancy-indexing]: https://pandas.pydata.org/pandas-docs/stable/user_guide/advanced.html#advanced
-   [subsetting]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#boolean-indexing
-   [merging]: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html#database-style-dataframe-or-named-series-joining-merging
-   [joining]: https://pandas.pydata.org/pandas-docs/stable/user_guide/merging.html#joining-on-index
-   [reshape]: https://pandas.pydata.org/pandas-docs/stable/user_guide/reshaping.html
-   [pivot-table]: https://pandas.pydata.org/pandas-docs/stable/user_guide/reshaping.html
-   [mi]: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#hierarchical-indexing-multiindex
-   [flat-files]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#csv-text-files
-   [excel]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#excel-files
-   [db]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#sql-queries
-   [hdfstore]: https://pandas.pydata.org/pandas-docs/stable/user_guide/io.html#hdf5-pytables
-   [timeseries]: https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#time-series-date-functionality
+   [missing-data]: https://pandas.pydata.org/pandas-docs/stable/missing_data.html#working-with-missing-data
+   [insertion-deletion]: https://pandas.pydata.org/pandas-docs/stable/dsintro.html#column-selection-addition-deletion
+   [alignment]: https://pandas.pydata.org/pandas-docs/stable/dsintro.html?highlight=alignment#intro-to-data-structures
+   [groupby]: https://pandas.pydata.org/pandas-docs/stable/groupby.html#group-by-split-apply-combine
+   [conversion]: https://pandas.pydata.org/pandas-docs/stable/dsintro.html#dataframe
+   [slicing]: https://pandas.pydata.org/pandas-docs/stable/indexing.html#slicing-ranges
+   [fancy-indexing]: https://pandas.pydata.org/pandas-docs/stable/indexing.html#advanced-indexing-with-ix
+   [subsetting]: https://pandas.pydata.org/pandas-docs/stable/indexing.html#boolean-indexing
+   [merging]: https://pandas.pydata.org/pandas-docs/stable/merging.html#database-style-dataframe-joining-merging
+   [joining]: https://pandas.pydata.org/pandas-docs/stable/merging.html#joining-on-index
+   [reshape]: https://pandas.pydata.org/pandas-docs/stable/reshaping.html#reshaping-and-pivot-tables
+   [pivot-table]: https://pandas.pydata.org/pandas-docs/stable/reshaping.html#pivot-tables-and-cross-tabulations
+   [mi]: https://pandas.pydata.org/pandas-docs/stable/indexing.html#hierarchical-indexing-multiindex
+   [flat-files]: https://pandas.pydata.org/pandas-docs/stable/io.html#csv-text-files
+   [excel]: https://pandas.pydata.org/pandas-docs/stable/io.html#excel-files
+   [db]: https://pandas.pydata.org/pandas-docs/stable/io.html#sql-queries
+   [hdfstore]: https://pandas.pydata.org/pandas-docs/stable/io.html#hdf5-pytables
+   [timeseries]: https://pandas.pydata.org/pandas-docs/stable/timeseries.html#time-series-date-functionality
 
 ## Where to get it
 The source code is currently hosted on GitHub at:
@@ -154,7 +154,7 @@ For usage questions, the best place to go to is [StackOverflow](https://stackove
 Further, general questions and discussions can also take place on the [pydata mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata).
 
 ## Discussion and Development
-Most development discussions take place on GitHub in this repo. Further, the [pandas-dev mailing list](https://mail.python.org/mailman/listinfo/pandas-dev) can also be used for specialized discussions or design issues, and a [Gitter channel](https://gitter.im/pydata/pandas) is available for quick development related questions.
+Most development discussions take place on github in this repo. Further, the [pandas-dev mailing list](https://mail.python.org/mailman/listinfo/pandas-dev) can also be used for specialized discussions or design issues, and a [Gitter channel](https://gitter.im/pydata/pandas) is available for quick development related questions.
 
 ## Contributing to pandas [![Open Source Helpers](https://www.codetriage.com/pandas-dev/pandas/badges/users.svg)](https://www.codetriage.com/pandas-dev/pandas)
 

asv_bench/benchmarks/indexing.py

@@ -358,14 +358,6 @@ def time_assign_with_setitem(self):
         for i in range(100):
             self.df[i] = np.random.randn(self.N)
 
-    def time_assign_list_like_with_setitem(self):
-        np.random.seed(1234)
-        self.df[list(range(100))] = np.random.randn(self.N, 100)
-
-    def time_assign_list_of_columns_concat(self):
-        df = DataFrame(np.random.randn(self.N, 100))
-        concat([self.df, df], axis=1)
-
 
 class ChainIndexing:
 

asv_bench/benchmarks/rolling.py

@@ -225,20 +225,6 @@ def time_rolling_offset(self, method):
         getattr(self.groupby_roll_offset, method)()
 
 
-class GroupbyLargeGroups:
-    # https://github.com/pandas-dev/pandas/issues/38038
-    # specific example where the rolling operation on a larger dataframe
-    # is relatively cheap (few but large groups), but creation of
-    # MultiIndex of result can be expensive
-
-    def setup(self):
-        N = 100000
-        self.df = pd.DataFrame({"A": [1, 2] * int(N / 2), "B": np.random.randn(N)})
-
-    def time_rolling_multiindex_creation(self):
-        self.df.groupby("A").rolling(3).mean()
-
-
 class GroupbyEWM:
 
     params = ["cython", "numba"]

ci/deps/azure-38-numpydev.yaml

@@ -12,7 +12,7 @@ dependencies:
 
   # pandas dependencies
   - pytz
-  - pip=20.2
+  - pip
   - pip:
     - cython==0.29.21 # GH#34014
     - "git+git://github.com/dateutil/dateutil.git"

doc/source/development/contributing.rst

@@ -147,9 +147,8 @@ Creating a development environment
 
 To test out code changes, you'll need to build pandas from source, which
 requires a C/C++ compiler and Python environment. If you're making documentation
-changes, you can skip to :ref:`contributing.documentation` but if you skip
-creating the development environment you won't be able to build the documentation
-locally before pushing your changes.
+changes, you can skip to :ref:`contributing.documentation` but you won't be able
+to build the documentation locally before pushing your changes.
 
 Using a Docker container
 ~~~~~~~~~~~~~~~~~~~~~~~~

doc/source/reference/series.rst

@@ -252,6 +252,7 @@ Combining / comparing / joining / merging
 
    Series.append
    Series.compare
+   Series.replace
    Series.update
 
 Time Series-related

doc/source/user_guide/io.rst

@@ -1577,21 +1577,19 @@ value will be an iterable object of type ``TextFileReader``:
 
 .. ipython:: python
 
-   with pd.read_csv("tmp.sv", sep="|", chunksize=4) as reader:
-       reader
-       for chunk in reader:
-           print(chunk)
+   reader = pd.read_csv("tmp.sv", sep="|", chunksize=4)
+   reader
 
-.. versionchanged:: 1.2
+   for chunk in reader:
+       print(chunk)
 
-  ``read_csv/json/sas`` return a context-manager when iterating through a file.
 
 Specifying ``iterator=True`` will also return the ``TextFileReader`` object:
 
 .. ipython:: python
 
-   with pd.read_csv("tmp.sv", sep="|", iterator=True) as reader:
-       reader.get_chunk(5)
+   reader = pd.read_csv("tmp.sv", sep="|", iterator=True)
+   reader.get_chunk(5)
 
 .. ipython:: python
    :suppress:
@@ -2240,10 +2238,10 @@ For line-delimited json files, pandas can also return an iterator which reads in
   df.to_json(orient="records", lines=True)
 
   # reader is an iterator that returns ``chunksize`` lines each iteration
-  with pd.read_json(StringIO(jsonl), lines=True, chunksize=1) as reader:
-      reader
-      for chunk in reader:
-          print(chunk)
+  reader = pd.read_json(StringIO(jsonl), lines=True, chunksize=1)
+  reader
+  for chunk in reader:
+      print(chunk)
 
 .. _io.table_schema:
 
@@ -5473,19 +5471,19 @@ object can be used as an iterator.
 
 .. ipython:: python
 
-  with pd.read_stata("stata.dta", chunksize=3) as reader:
-      for df in reader:
-          print(df.shape)
+  reader = pd.read_stata("stata.dta", chunksize=3)
+  for df in reader:
+      print(df.shape)
 
 For more fine-grained control, use ``iterator=True`` and specify
 ``chunksize`` with each call to
 :func:`~pandas.io.stata.StataReader.read`.
 
 .. ipython:: python
 
-  with pd.read_stata("stata.dta", iterator=True) as reader:
-      chunk1 = reader.read(5)
-      chunk2 = reader.read(5)
+  reader = pd.read_stata("stata.dta", iterator=True)
+  chunk1 = reader.read(5)
+  chunk2 = reader.read(5)
 
 Currently the ``index`` is retrieved as a column.
 
@@ -5597,9 +5595,9 @@ Obtain an iterator and read an XPORT file 100,000 lines at a time:
         pass
 
 
-    with pd.read_sas("sas_xport.xpt", chunk=100000) as rdr:
-        for chunk in rdr:
-            do_something(chunk)
+    rdr = pd.read_sas("sas_xport.xpt", chunk=100000)
+    for chunk in rdr:
+        do_something(chunk)
 
 The specification_ for the xport file format is available from the SAS
 web site.

doc/source/whatsnew/v1.1.5.rst

@@ -19,15 +19,10 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.loc` and :meth:`Series.loc` for ``__setitem__`` when one-dimensional tuple was given to select from :class:`MultiIndex` (:issue:`37711`)
 - Fixed regression in inplace operations on :class:`Series` with ``ExtensionDtype`` with NumPy dtyped operand (:issue:`37910`)
 - Fixed regression in metadata propagation for ``groupby`` iterator (:issue:`37343`)
-- Fixed regression in :class:`MultiIndex` constructed from a :class:`DatetimeIndex` not retaining frequency (:issue:`35563`)
-- Fixed regression in :meth:`DataFrame.unstack` with columns with integer dtype (:issue:`37115`)
 - Fixed regression in indexing on a :class:`Series` with ``CategoricalDtype`` after unpickling (:issue:`37631`)
 - Fixed regression in :meth:`DataFrame.groupby` aggregation with out-of-bounds datetime objects in an object-dtype column (:issue:`36003`)
 - Fixed regression in ``df.groupby(..).rolling(..)`` with the resulting :class:`MultiIndex` when grouping by a label that is in the index (:issue:`37641`)
 - Fixed regression in :meth:`DataFrame.fillna` not filling ``NaN`` after other operations such as :meth:`DataFrame.pivot` (:issue:`36495`).
-- Fixed performance regression in ``df.groupby(..).rolling(..)`` (:issue:`38038`)
-- Fixed regression in :meth:`MultiIndex.intersection` returning duplicates when at least one of the indexes had duplicates (:issue:`36915`)
-- Fixed regression in :meth:`.GroupBy.first` and :meth:`.GroupBy.last` where ``None`` was considered a non-NA value (:issue:`38286`)
 
 .. ---------------------------------------------------------------------------