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

Author: TomAugspurger

asv_bench/benchmarks/arithmetic.py

@@ -50,6 +50,36 @@ def time_frame_op_with_scalar(self, dtype, scalar, op):
         op(self.df, scalar)
 
 
+class MixedFrameWithSeriesAxis0:
+    params = [
+        [
+            "eq",
+            "ne",
+            "lt",
+            "le",
+            "ge",
+            "gt",
+            "add",
+            "sub",
+            "div",
+            "floordiv",
+            "mul",
+            "pow",
+        ]
+    ]
+    param_names = ["opname"]
+
+    def setup(self, opname):
+        arr = np.arange(10 ** 6).reshape(100, -1)
+        df = DataFrame(arr)
+        df["C"] = 1.0
+        self.df = df
+        self.ser = df[0]
+
+    def time_frame_op_with_series_axis0(self, opname):
+        getattr(self.df, opname)(self.ser, axis=0)
+
+
 class Ops:
 
     params = [[True, False], ["default", 1]]

ci/code_checks.sh

@@ -267,11 +267,6 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
         -k"-nonzero -reindex -searchsorted -to_dict"
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Doctests generic.py' ; echo $MSG
-    pytest -q --doctest-modules pandas/core/generic.py \
-        -k"-_set_axis_name -_xs -describe -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -to_json -transpose -values -xs -to_clipboard"
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
     MSG='Doctests groupby.py' ; echo $MSG
     pytest -q --doctest-modules pandas/core/groupby/groupby.py -k"-cumcount -describe -pipe"
     RET=$(($RET + $?)) ; echo $MSG "DONE"
@@ -311,6 +306,17 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/arrays/boolean.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests base.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/base.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    MSG='Doctests construction.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/construction.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    MSG='Doctests generic.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/generic.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
 fi
 
 ### DOCSTRINGS ###
@@ -320,6 +326,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03,SA05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Validate correct capitalization among titles in documentation' ; echo $MSG
+    $BASE_DIR/scripts/validate_rst_title_capitalization.py $BASE_DIR/doc/source/development/contributing.rst
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
 fi
 
 ### DEPENDENCIES ###

doc/redirects.csv

@@ -49,7 +49,25 @@ internals,development/internals
 # api moved function
 reference/api/pandas.io.json.json_normalize,pandas.json_normalize
 
-# api rename
+# rename due to refactors
+reference/api/pandas.core.window.Rolling,pandas.core.window.rolling.Rolling
+reference/api/pandas.core.window.Rolling.aggregate,pandas.core.window.rolling.Rolling.aggregate
+reference/api/pandas.core.window.Rolling.apply,pandas.core.window.rolling.Rolling.apply
+reference/api/pandas.core.window.Rolling.corr,pandas.core.window.rolling.Rolling.corr
+reference/api/pandas.core.window.Rolling.count,pandas.core.window.rolling.Rolling.count
+reference/api/pandas.core.window.Rolling.cov,pandas.core.window.rolling.Rolling.cov
+reference/api/pandas.core.window.Rolling.kurt,pandas.core.window.rolling.Rolling.kurt
+reference/api/pandas.core.window.Rolling.max,pandas.core.window.rolling.Rolling.max
+reference/api/pandas.core.window.Rolling.mean,pandas.core.window.rolling.Rolling.mean
+reference/api/pandas.core.window.Rolling.median,pandas.core.window.rolling.Rolling.median
+reference/api/pandas.core.window.Rolling.min,pandas.core.window.rolling.Rolling.min
+reference/api/pandas.core.window.Rolling.quantile,pandas.core.window.rolling.Rolling.quantile
+reference/api/pandas.core.window.Rolling.skew,pandas.core.window.rolling.Rolling.skew
+reference/api/pandas.core.window.Rolling.std,pandas.core.window.rolling.Rolling.std
+reference/api/pandas.core.window.Rolling.sum,pandas.core.window.rolling.Rolling.sum
+reference/api/pandas.core.window.Rolling.var,pandas.core.window.rolling.Rolling.var
+
+# api url change (generated -> reference/api rename)
 api,reference/index
 generated/pandas.api.extensions.ExtensionArray.argsort,../reference/api/pandas.api.extensions.ExtensionArray.argsort
 generated/pandas.api.extensions.ExtensionArray.astype,../reference/api/pandas.api.extensions.ExtensionArray.astype

doc/source/_static/question_mark_noback.svg

@@ -146,7 +146,7 @@ requires a C compiler and Python environment. If you're making documentation
 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
+Using a Docker container
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
 Instead of manually setting up a development environment, you can use Docker to
@@ -754,7 +754,7 @@ You can then verify the changes look ok, then git :ref:`commit <contributing.com
 
 .. _contributing.pre-commit:
 
-Pre-Commit
+Pre-commit
 ~~~~~~~~~~
 
 You can run many of these styling checks manually as we have described above. However,
@@ -822,12 +822,12 @@ See :ref:`contributing.warnings` for more.
 
 .. _contributing.type_hints:
 
-Type Hints
+Type hints
 ----------
 
 *pandas* strongly encourages the use of :pep:`484` style type hints. New development should contain type hints and pull requests to annotate existing code are accepted as well!
 
-Style Guidelines
+Style guidelines
 ~~~~~~~~~~~~~~~~
 
 Types imports should follow the ``from typing import ...`` convention. So rather than
@@ -903,7 +903,7 @@ The limitation here is that while a human can reasonably understand that ``is_nu
 
 With custom types and inference this is not always possible so exceptions are made, but every effort should be exhausted to avoid ``cast`` before going down such paths.
 
-Pandas-specific Types
+pandas-specific types
 ~~~~~~~~~~~~~~~~~~~~~
 
 Commonly used types specific to *pandas* will appear in `pandas._typing <https://github.com/pandas-dev/pandas/blob/master/pandas/_typing.py>`_ and you should use these where applicable. This module is private for now but ultimately this should be exposed to third party libraries who want to implement type checking against pandas.
@@ -919,7 +919,7 @@ For example, quite a few functions in *pandas* accept a ``dtype`` argument. This
 
 This module will ultimately house types for repeatedly used concepts like "path-like", "array-like", "numeric", etc... and can also hold aliases for commonly appearing parameters like `axis`. Development of this module is active so be sure to refer to the source for the most up to date list of available types.
 
-Validating Type Hints
+Validating type hints
 ~~~~~~~~~~~~~~~~~~~~~
 
 *pandas* uses `mypy <http://mypy-lang.org>`_ to statically analyze the code base and type hints. After making any change you can ensure your type hints are correct by running
@@ -1539,7 +1539,7 @@ The branch will still exist on GitHub, so to delete it there do::
 .. _Gitter: https://gitter.im/pydata/pandas
 
 
-Tips for a successful Pull Request
+Tips for a successful pull request
 ==================================
 
 If you have made it to the `Review your code`_ phase, one of the core contributors may

doc/source/development/contributing.rst

@@ -24,6 +24,7 @@ Fixed regressions
 - Fixed regression in :class:`DataFrame` arithmetic operations with mis-matched columns (:issue:`31623`)
 - Fixed regression in :meth:`GroupBy.agg` calling a user-provided function an extra time on an empty input (:issue:`31760`)
 - Joining on :class:`DatetimeIndex` or :class:`TimedeltaIndex` will preserve ``freq`` in simple cases (:issue:`32166`)
+- Fixed bug in the repr of an object-dtype ``Index`` with bools and missing values (:issue:`32146`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -85,6 +86,10 @@ Bug fixes
 - Fix bug in :meth:`Series.convert_dtypes` for series with mix of integers and strings (:issue:`32117`)
 - Fixed bug in :meth:`DataFrame.convert_dtypes`, where ``BooleanDtype`` columns were converted to ``Int64`` (:issue:`32287`)
 
+**Strings**
+
+- Using ``pd.NA`` with :meth:`Series.str.repeat` now correctly outputs a null value instead of raising error for vector inputs (:issue:`31632`)
+
 .. ---------------------------------------------------------------------------
 
 .. _whatsnew_102.contributors:

doc/source/whatsnew/v1.0.2.rst

@@ -67,6 +67,7 @@ Other enhancements
 - When writing directly to a sqlite connection :func:`to_sql` now supports the ``multi`` method (:issue:`29921`)
 - `OptionError` is now exposed in `pandas.errors` (:issue:`27553`)
 - :func:`timedelta_range` will now infer a frequency when passed ``start``, ``stop``, and ``periods`` (:issue:`32377`)
+- Positional slicing on a :class:`IntervalIndex` now supports slices with ``step > 1`` (:issue:`31658`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -91,6 +92,8 @@ Backwards incompatible API changes
   now raise a  ``TypeError`` if a not-accepted keyword argument is passed into it.
   Previously a ``UnsupportedFunctionCall`` was raised (``AssertionError`` if ``min_count`` passed into :meth:`~DataFrameGroupby.median``) (:issue:`31485`)
 - :meth:`DataFrame.at` and :meth:`Series.at` will raise a ``TypeError`` instead of a ``ValueError`` if an incompatible key is passed, and ``KeyError`` if a missing key is passed, matching the behavior of ``.loc[]`` (:issue:`31722`)
+- Passing an integer dtype other than ``int64`` to ``np.array(period_index, dtype=...)`` will now raise ``TypeError`` instead of incorrectly using ``int64`` (:issue:`32255`)
+-
 
 .. _whatsnew_110.api_breaking.indexing_raises_key_errors:
 
@@ -170,7 +173,7 @@ Deprecations
 ~~~~~~~~~~~~
 - Lookups on a :class:`Series` with a single-item list containing a slice (e.g. ``ser[[slice(0, 4)]]``) are deprecated, will raise in a future version.  Either convert the list to tuple, or pass the slice directly instead (:issue:`31333`)
 - :meth:`DataFrame.mean` and :meth:`DataFrame.median` with ``numeric_only=None`` will include datetime64 and datetime64tz columns in a future version (:issue:`29941`)
--
+- Setting values with ``.loc`` using a positional slice is deprecated and will raise in a future version.  Use ``.loc`` with labels or ``.iloc`` with positions instead (:issue:`31840`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -183,7 +186,7 @@ Performance improvements
 
 - Performance improvement in :class:`Timedelta` constructor (:issue:`30543`)
 - Performance improvement in :class:`Timestamp` constructor (:issue:`30543`)
--
+- Performance improvement in flex arithmetic ops between :class:`DataFrame` and :class:`Series` with ``axis=0`` (:issue:`31296`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -228,7 +231,7 @@ Timezones
 Numeric
 ^^^^^^^
 - Bug in :meth:`DataFrame.floordiv` with ``axis=0`` not treating division-by-zero like :meth:`Series.floordiv` (:issue:`31271`)
--
+- Bug in :meth:`to_numeric` with string argument ``"uint64"`` and ``errors="coerce"`` silently fails (:issue:`32394`)
 -
 
 Conversion
@@ -246,7 +249,6 @@ Strings
 
 Interval
 ^^^^^^^^
-
 -
 -
 

doc/source/whatsnew/v1.1.0.rst

@@ -2024,8 +2024,6 @@ def maybe_convert_numeric(ndarray[object] values, set na_values,
             except (TypeError, ValueError) as err:
                 if not seen.coerce_numeric:
                     raise type(err)(f"{err} at position {i}")
-                elif "uint64" in str(err):  # Exception from check functions.
-                    raise
 
                 seen.saw_null()
                 floats[i] = NaN
@@ -2298,7 +2296,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
                                 return uints
                             else:
                                 return ints
-                elif seen.is_bool:
+                elif seen.is_bool and not seen.nan_:
                     return bools.view(np.bool_)
 
     return objects

pandas/_libs/lib.pyx

@@ -100,7 +100,7 @@ def scalar_compare(object[:] values, object val, object op):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def vec_compare(object[:] left, object[:] right, object op):
+def vec_compare(ndarray[object] left, ndarray[object] right, object op):
     """
     Compare the elements of `left` with the elements of `right` pointwise,
     with the comparison operation described by `op`.

pandas/_libs/ops.pyx

@@ -1167,7 +1167,7 @@ class Timedelta(_Timedelta):
 
         Possible values:
 
-        * 'Y', 'M', 'W', 'D', 'T', 'S', 'L', 'U', or 'N'
+        * 'W', 'D', 'T', 'S', 'L', 'U', or 'N'
         * 'days' or 'day'
         * 'hours', 'hour', 'hr', or 'h'
         * 'minutes', 'minute', 'min', or 'm'