Merge remote-tracking branch 'upstream/master' into bisect

Author: simonjayhawkins

.github/workflows/autoupdate-pre-commit-config.yml

@@ -2,7 +2,7 @@ name: "Update pre-commit config"
 
 on:
   schedule:
-    - cron: "0 7 * * 1" # At 07:00 on each Monday.
+    - cron: "0 7 1 * *" # At 07:00 on 1st of every month.
   workflow_dispatch:
 
 jobs:

asv_bench/benchmarks/dtypes.py

@@ -50,15 +50,26 @@ def time_pandas_dtype_invalid(self, dtype):
 
 class SelectDtypes:
 
-    params = [
-        tm.ALL_INT_NUMPY_DTYPES
-        + tm.ALL_INT_EA_DTYPES
-        + tm.FLOAT_NUMPY_DTYPES
-        + tm.COMPLEX_DTYPES
-        + tm.DATETIME64_DTYPES
-        + tm.TIMEDELTA64_DTYPES
-        + tm.BOOL_DTYPES
-    ]
+    try:
+        params = [
+            tm.ALL_INT_NUMPY_DTYPES
+            + tm.ALL_INT_EA_DTYPES
+            + tm.FLOAT_NUMPY_DTYPES
+            + tm.COMPLEX_DTYPES
+            + tm.DATETIME64_DTYPES
+            + tm.TIMEDELTA64_DTYPES
+            + tm.BOOL_DTYPES
+        ]
+    except AttributeError:
+        params = [
+            tm.ALL_INT_DTYPES
+            + tm.ALL_EA_INT_DTYPES
+            + tm.FLOAT_DTYPES
+            + tm.COMPLEX_DTYPES
+            + tm.DATETIME64_DTYPES
+            + tm.TIMEDELTA64_DTYPES
+            + tm.BOOL_DTYPES
+        ]
     param_names = ["dtype"]
 
     def setup(self, dtype):

asv_bench/benchmarks/indexing.py

@@ -399,12 +399,14 @@ class ChainIndexing:
 
     def setup(self, mode):
         self.N = 1000000
+        self.df = DataFrame({"A": np.arange(self.N), "B": "foo"})
 
     def time_chained_indexing(self, mode):
+        df = self.df
+        N = self.N
         with warnings.catch_warnings(record=True):
             with option_context("mode.chained_assignment", mode):
-                df = DataFrame({"A": np.arange(self.N), "B": "foo"})
-                df2 = df[df.A > self.N // 2]
+                df2 = df[df.A > N // 2]
                 df2["C"] = 1.0
 
 

doc/source/conf.py

@@ -461,7 +461,6 @@
 # eg pandas.Series.str and pandas.Series.dt (see GH9322)
 
 import sphinx  # isort:skip
-from sphinx.util import rpartition  # isort:skip
 from sphinx.ext.autodoc import (  # isort:skip
     AttributeDocumenter,
     Documenter,
@@ -521,8 +520,8 @@ def resolve_name(self, modname, parents, path, base):
             # HACK: this is added in comparison to ClassLevelDocumenter
             # mod_cls still exists of class.accessor, so an extra
             # rpartition is needed
-            modname, accessor = rpartition(mod_cls, ".")
-            modname, cls = rpartition(modname, ".")
+            modname, _, accessor = mod_cls.rpartition(".")
+            modname, _, cls = modname.rpartition(".")
             parents = [cls, accessor]
             # if the module name is still missing, get it like above
             if not modname:

doc/source/getting_started/comparison/includes/nth_word.rst

@@ -5,5 +5,5 @@ word by index. Note there are more powerful approaches should you need them.
 
    firstlast = pd.DataFrame({"String": ["John Smith", "Jane Cook"]})
    firstlast["First_Name"] = firstlast["String"].str.split(" ", expand=True)[0]
-   firstlast["Last_Name"] = firstlast["String"].str.rsplit(" ", expand=True)[0]
+   firstlast["Last_Name"] = firstlast["String"].str.rsplit(" ", expand=True)[1]
    firstlast

doc/source/user_guide/advanced.rst

@@ -851,12 +851,12 @@ values **not** in the categories, similarly to how you can reindex **any** panda
 Int64Index and RangeIndex
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. note::
-
+.. deprecated:: 1.4.0
     In pandas 2.0, :class:`NumericIndex` will become the default index type for numeric types
     instead of ``Int64Index``, ``Float64Index`` and ``UInt64Index`` and those index types
-    will be removed. See :ref:`here <advanced.numericindex>` for more.
-    ``RangeIndex`` however, will not be removed, as it represents an optimized version of an integer index.
+    are therefore deprecated and will be removed in a futire version.
+    See :ref:`here <advanced.numericindex>` for more.
+    ``RangeIndex`` will not be removed, as it represents an optimized version of an integer index.
 
 :class:`Int64Index` is a fundamental basic index in pandas. This is an immutable array
 implementing an ordered, sliceable set.
@@ -869,12 +869,12 @@ implementing an ordered, sliceable set.
 Float64Index
 ~~~~~~~~~~~~
 
-.. note::
-
-    In pandas 2.0, :class:`NumericIndex` will become the default index type for numeric types
+.. deprecated:: 1.4.0
+    :class:`NumericIndex` will become the default index type for numeric types in the future
     instead of ``Int64Index``, ``Float64Index`` and ``UInt64Index`` and those index types
-    will be removed. See :ref:`here <advanced.numericindex>` for more.
-    ``RangeIndex`` however, will not be removed, as it represents an optimized version of an integer index.
+    are therefore deprecated and will be removed in a future version of Pandas.
+    See :ref:`here <advanced.numericindex>` for more.
+    ``RangeIndex`` will not be removed as it represents an optimized version of an integer index.
 
 By default a :class:`Float64Index` will be automatically created when passing floating, or mixed-integer-floating values in index creation.
 This enables a pure label-based slicing paradigm that makes ``[],ix,loc`` for scalar indexing and slicing work exactly the
@@ -981,9 +981,9 @@ NumericIndex
 .. note::
 
     In pandas 2.0, :class:`NumericIndex` will become the default index type for numeric types
-    instead of ``Int64Index``, ``Float64Index`` and ``UInt64Index`` and those index types
-    will be removed.
-    ``RangeIndex`` however, will not be removed, as it represents an optimized version of an integer index.
+    instead of :class:`Int64Index`, :class:`Float64Index` and :class:`UInt64Index` and those index types
+    are therefore deprecated and will be removed in a future version.
+    :class:`RangeIndex` will not be removed as it represents an optimized version of an integer index.
 
 :class:`NumericIndex` is an index type that can hold data of any numpy int/uint/float dtype. For example:
 
@@ -998,7 +998,7 @@ NumericIndex
 ``UInt64Index`` except that it can hold any numpy int, uint or float dtype.
 
 Until Pandas 2.0, you will have to call ``NumericIndex`` explicitly in order to use it, like in the example above.
-In Pandas 2.0, ``NumericIndex`` will become the default pandas numeric index type and will automatically be used where appropriate.
+In the future, ``NumericIndex`` will become the default pandas numeric index type and will automatically be used where appropriate.
 
 Please notice that ``NumericIndex`` *can not* hold Pandas numeric dtypes (:class:`Int64Dtype`, :class:`Int32Dtype` etc.).
 

doc/source/user_guide/io.rst

@@ -2502,14 +2502,16 @@ Read a URL with no options:
 
 .. ipython:: python
 
-   url = (
-       "https://raw.githubusercontent.com/pandas-dev/pandas/master/"
-       "pandas/tests/io/data/html/spam.html"
-   )
+   url = "https://www.fdic.gov/resources/resolutions/bank-failures/failed-bank-list"
    dfs = pd.read_html(url)
    dfs
 
-Read in the content of the "banklist.html" file and pass it to ``read_html``
+.. note::
+
+   The data from the above URL changes every Monday so the resulting data above
+   and the data below may be slightly different.
+
+Read in the content of the file from the above URL and pass it to ``read_html``
 as a string:
 
 .. ipython:: python

doc/source/user_guide/options.rst

@@ -138,7 +138,7 @@ More information can be found in the `IPython documentation
   import pandas as pd
 
   pd.set_option("display.max_rows", 999)
-  pd.set_option("precision", 5)
+  pd.set_option("display.precision", 5)
 
 .. _options.frequently_used:
 
@@ -253,9 +253,9 @@ This is only a suggestion.
 .. ipython:: python
 
    df = pd.DataFrame(np.random.randn(5, 5))
-   pd.set_option("precision", 7)
+   pd.set_option("display.precision", 7)
    df
-   pd.set_option("precision", 4)
+   pd.set_option("display.precision", 4)
    df
 
 ``display.chop_threshold`` sets at what level pandas rounds to zero when
@@ -487,8 +487,27 @@ styler.sparse.index                     True         "Sparsify" MultiIndex displ
                                                      elements in outer levels within groups).
 styler.sparse.columns                   True         "Sparsify" MultiIndex display for columns
                                                      in Styler output.
+styler.render.repr                      html         Standard output format for Styler rendered in Jupyter Notebook.
+                                                     Should be one of "html" or "latex".
 styler.render.max_elements              262144       Maximum number of datapoints that Styler will render
                                                      trimming either rows, columns or both to fit.
+styler.render.encoding                  utf-8        Default encoding for output HTML or LaTeX files.
+styler.format.formatter                 None         Object to specify formatting functions to ``Styler.format``.
+styler.format.na_rep                    None         String representation for missing data.
+styler.format.precision                 6            Precision to display floating point and complex numbers.
+styler.format.decimal                   .            String representation for decimal point separator for floating
+                                                     point and complex numbers.
+styler.format.thousands                 None         String representation for thousands separator for
+                                                     integers, and floating point and complex numbers.
+styler.format.escape                    None         Whether to escape "html" or "latex" special
+                                                     characters in the display representation.
+styler.html.mathjax                     True         If set to False will render specific CSS classes to
+                                                     table attributes that will prevent Mathjax from rendering
+                                                     in Jupyter Notebook.
+styler.latex.multicol_align             r            Alignment of headers in a merged column due to sparsification. Can be in {"r", "c", "l"}.
+styler.latex.multirow_align             c            Alignment of index labels in a merged row due to sparsification. Can be in {"c", "t", "b"}.
+styler.latex.environment                None         If given will replace the default ``\\begin{table}`` environment. If "longtable" is specified
+                                                     this will render with a specific "longtable" template with longtable features.
 ======================================= ============ ==================================
 
 

doc/source/whatsnew/v0.20.0.rst

@@ -248,11 +248,12 @@ or purely non-negative, integers. Previously, handling these integers would
 result in improper rounding or data-type casting, leading to incorrect results.
 Notably, a new numerical index, ``UInt64Index``, has been created (:issue:`14937`)
 
-.. ipython:: python
+.. code-block:: ipython
 
-   idx = pd.UInt64Index([1, 2, 3])
-   df = pd.DataFrame({'A': ['a', 'b', 'c']}, index=idx)
-   df.index
+   In [1]: idx = pd.UInt64Index([1, 2, 3])
+   In [2]: df = pd.DataFrame({'A': ['a', 'b', 'c']}, index=idx)
+   In [3]: df.index
+   Out[3]: UInt64Index([1, 2, 3], dtype='uint64')
 
 - Bug in converting object elements of array-like objects to unsigned 64-bit integers (:issue:`4471`, :issue:`14982`)
 - Bug in ``Series.unique()`` in which unsigned 64-bit integers were causing overflow (:issue:`14721`)

doc/source/whatsnew/v0.23.0.rst

@@ -861,21 +861,21 @@ Previous behavior:
 
 Current behavior:
 
-.. ipython:: python
+.. code-block:: ipython
 
-    index = pd.Int64Index([-1, 0, 1])
+    In [12]: index = pd.Int64Index([-1, 0, 1])
     # division by zero gives -infinity where negative,
     # +infinity where positive, and NaN for 0 / 0
-    index / 0
+    In [13]: index / 0
 
     # The result of division by zero should not depend on
     # whether the zero is int or float
-    index / 0.0
+    In [14]: index / 0.0
 
-    index = pd.UInt64Index([0, 1])
-    index / np.array([0, 0], dtype=np.uint64)
+    In [15]: index = pd.UInt64Index([0, 1])
+    In [16]: index / np.array([0, 0], dtype=np.uint64)
 
-    pd.RangeIndex(1, 5) / 0
+    In [17]: pd.RangeIndex(1, 5) / 0
 
 .. _whatsnew_0230.api_breaking.extract:
 

doc/source/whatsnew/v0.25.0.rst

@@ -473,10 +473,12 @@ considered commutative, such that ``A.union(B) == B.union(A)`` (:issue:`23525`).
 
 *New behavior*:
 
-.. ipython:: python
+.. code-block:: python
 
-    pd.period_range('19910905', periods=2).union(pd.Int64Index([1, 2, 3]))
-    pd.Index([], dtype=object).union(pd.Index([1, 2, 3]))
+    In [3]: pd.period_range('19910905', periods=2).union(pd.Int64Index([1, 2, 3]))
+    Out[3]: Index([1991-09-05, 1991-09-06, 1, 2, 3], dtype='object')
+    In [4]: pd.Index([], dtype=object).union(pd.Index([1, 2, 3]))
+    Out[4]: Index([1, 2, 3], dtype='object')
 
 Note that integer- and floating-dtype indexes are considered "compatible". The integer
 values are coerced to floating point, which may result in loss of precision. See

doc/source/whatsnew/v1.3.3.rst

@@ -18,6 +18,7 @@ Fixed regressions
 - Performance regression in :meth:`core.window.ewm.ExponentialMovingWindow.mean` (:issue:`42333`)
 - Fixed regression in :meth:`.GroupBy.agg` incorrectly raising in some cases (:issue:`42390`)
 - Fixed regression in :meth:`RangeIndex.where` and :meth:`RangeIndex.putmask` raising ``AssertionError`` when result did not represent a :class:`RangeIndex` (:issue:`43240`)
+- Fixed regression in :meth:`read_parquet` where the ``fastparquet`` engine would not work properly with fastparquet 0.7.0 (:issue:`43075`)
 
 .. ---------------------------------------------------------------------------