Merge branch 'master' into move-info

Author: MarcoGorelli

ci/code_checks.sh

@@ -259,8 +259,7 @@ fi
 if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
     MSG='Doctests frame.py' ; echo $MSG
-    pytest -q --doctest-modules pandas/core/frame.py \
-        -k" -itertuples -join -reindex -reindex_axis -round"
+    pytest -q --doctest-modules pandas/core/frame.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Doctests series.py' ; echo $MSG
@@ -294,8 +293,7 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     MSG='Doctests interval classes' ; echo $MSG
     pytest -q --doctest-modules \
         pandas/core/indexes/interval.py \
-        pandas/core/arrays/interval.py \
-        -k"-from_arrays -from_breaks -from_intervals -from_tuples -set_closed -to_tuples -interval_range"
+        pandas/core/arrays/interval.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Doctests arrays'; echo $MSG

pandas/__init__.py

@@ -25,6 +25,7 @@
     _np_version_under1p16,
     _np_version_under1p17,
     _np_version_under1p18,
+    _is_numpy_dev,
 )
 
 try:

pandas/_config/config.py

@@ -82,7 +82,8 @@
 
 
 class OptionError(AttributeError, KeyError):
-    """Exception for pandas.options, backwards compatible with KeyError
+    """
+    Exception for pandas.options, backwards compatible with KeyError
     checks
     """
 
@@ -395,7 +396,6 @@ class option_context:
 
     Examples
     --------
-
     >>> with option_context('display.max_rows', 10, 'display.max_columns', 5):
     ...     ...
     """
@@ -546,7 +546,8 @@ def deprecate_option(
 
 
 def _select_options(pat: str) -> List[str]:
-    """returns a list of keys matching `pat`
+    """
+    returns a list of keys matching `pat`
 
     if pat=="all", returns all registered options
     """
@@ -709,15 +710,16 @@ def pp(name: str, ks: Iterable[str]) -> List[str]:
 
 @contextmanager
 def config_prefix(prefix):
-    """contextmanager for multiple invocations of API with a common prefix
+    """
+    contextmanager for multiple invocations of API with a common prefix
 
     supported API functions: (register / get / set )__option
 
     Warning: This is not thread - safe, and won't work properly if you import
     the API functions into your module using the "from x import y" construct.
 
-    Example:
-
+    Example
+    -------
     import pandas._config.config as cf
     with cf.config_prefix("display.font"):
         cf.register_option("color", "red")

pandas/_libs/lib.pyx

@@ -571,6 +571,8 @@ def array_equivalent_object(left: object[:], right: object[:]) -> bool:
             if PyArray_Check(x) and PyArray_Check(y):
                 if not array_equivalent_object(x, y):
                     return False
+            elif (x is C_NA) ^ (y is C_NA):
+                return False
             elif not (PyObject_RichCompareBool(x, y, Py_EQ) or
                       (x is None or is_nan(x)) and (y is None or is_nan(y))):
                 return False

pandas/_testing.py

@@ -743,7 +743,8 @@ def repr_class(x):
 
 
 def assert_attr_equal(attr, left, right, obj="Attributes"):
-    """checks attributes are equal. Both objects must have attribute.
+    """
+    checks attributes are equal. Both objects must have attribute.
 
     Parameters
     ----------
@@ -820,7 +821,8 @@ def assert_is_sorted(seq):
 def assert_categorical_equal(
     left, right, check_dtype=True, check_category_order=True, obj="Categorical"
 ):
-    """Test that Categoricals are equivalent.
+    """
+    Test that Categoricals are equivalent.
 
     Parameters
     ----------
@@ -860,7 +862,8 @@ def assert_categorical_equal(
 
 
 def assert_interval_array_equal(left, right, exact="equiv", obj="IntervalArray"):
-    """Test that two IntervalArrays are equivalent.
+    """
+    Test that two IntervalArrays are equivalent.
 
     Parameters
     ----------
@@ -1009,12 +1012,13 @@ def _raise(left, right, err_msg):
 def assert_extension_array_equal(
     left, right, check_dtype=True, check_less_precise=False, check_exact=False
 ):
-    """Check that left and right ExtensionArrays are equal.
+    """
+    Check that left and right ExtensionArrays are equal.
 
     Parameters
     ----------
     left, right : ExtensionArray
-        The two arrays to compare
+        The two arrays to compare.
     check_dtype : bool, default True
         Whether to check if the ExtensionArray dtypes are identical.
     check_less_precise : bool or int, default False
@@ -1489,7 +1493,8 @@ def assert_sp_array_equal(
     check_fill_value=True,
     consolidate_block_indices=False,
 ):
-    """Check that the left and right SparseArray are equal.
+    """
+    Check that the left and right SparseArray are equal.
 
     Parameters
     ----------
@@ -1724,7 +1729,8 @@ def _make_timeseries(start="2000-01-01", end="2000-12-31", freq="1D", seed=None)
 
 
 def all_index_generator(k=10):
-    """Generator which can be iterated over to get instances of all the various
+    """
+    Generator which can be iterated over to get instances of all the various
     index classes.
 
     Parameters
@@ -1763,7 +1769,8 @@ def index_subclass_makers_generator():
 
 
 def all_timeseries_index_generator(k=10):
-    """Generator which can be iterated over to get instances of all the classes
+    """
+    Generator which can be iterated over to get instances of all the classes
     which represent time-series.
 
     Parameters
@@ -1854,7 +1861,8 @@ def makePeriodFrame(nper=None):
 def makeCustomIndex(
     nentries, nlevels, prefix="#", names=False, ndupe_l=None, idx_type=None
 ):
-    """Create an index/multindex with given dimensions, levels, names, etc'
+    """
+    Create an index/multindex with given dimensions, levels, names, etc'
 
     nentries - number of entries in index
     nlevels - number of levels (> 1 produces multindex)
@@ -1970,35 +1978,39 @@ def makeCustomDataframe(
     r_idx_type=None,
 ):
     """
-   nrows,  ncols - number of data rows/cols
-   c_idx_names, idx_names  - False/True/list of strings,  yields No names ,
-        default names or uses the provided names for the levels of the
-        corresponding index. You can provide a single string when
-        c_idx_nlevels ==1.
-   c_idx_nlevels - number of levels in columns index. > 1 will yield MultiIndex
-   r_idx_nlevels - number of levels in rows index. > 1 will yield MultiIndex
-   data_gen_f - a function f(row,col) which return the data value
-        at that position, the default generator used yields values of the form
-        "RxCy" based on position.
-   c_ndupe_l, r_ndupe_l - list of integers, determines the number
-        of duplicates for each label at a given level of the corresponding
-        index. The default `None` value produces a multiplicity of 1 across
-        all levels, i.e. a unique index. Will accept a partial list of length
-        N < idx_nlevels, for just the first N levels. If ndupe doesn't divide
-        nrows/ncol, the last label might have lower multiplicity.
-   dtype - passed to the DataFrame constructor as is, in case you wish to
-        have more control in conjunction with a custom `data_gen_f`
-   r_idx_type, c_idx_type -  "i"/"f"/"s"/"u"/"dt"/"td".
-       If idx_type is not None, `idx_nlevels` must be 1.
-       "i"/"f" creates an integer/float index,
-       "s"/"u" creates a string/unicode index
-       "dt" create a datetime index.
-       "td" create a timedelta index.
+    Create a DataFrame using supplied parameters.
 
-        if unspecified, string labels will be generated.
-
-    Examples:
+    Parameters
+    ----------
+    nrows,  ncols - number of data rows/cols
+    c_idx_names, idx_names  - False/True/list of strings,  yields No names ,
+            default names or uses the provided names for the levels of the
+            corresponding index. You can provide a single string when
+            c_idx_nlevels ==1.
+    c_idx_nlevels - number of levels in columns index. > 1 will yield MultiIndex
+    r_idx_nlevels - number of levels in rows index. > 1 will yield MultiIndex
+    data_gen_f - a function f(row,col) which return the data value
+            at that position, the default generator used yields values of the form
+            "RxCy" based on position.
+    c_ndupe_l, r_ndupe_l - list of integers, determines the number
+            of duplicates for each label at a given level of the corresponding
+            index. The default `None` value produces a multiplicity of 1 across
+            all levels, i.e. a unique index. Will accept a partial list of length
+            N < idx_nlevels, for just the first N levels. If ndupe doesn't divide
+            nrows/ncol, the last label might have lower multiplicity.
+    dtype - passed to the DataFrame constructor as is, in case you wish to
+            have more control in conjunction with a custom `data_gen_f`
+    r_idx_type, c_idx_type -  "i"/"f"/"s"/"u"/"dt"/"td".
+        If idx_type is not None, `idx_nlevels` must be 1.
+        "i"/"f" creates an integer/float index,
+        "s"/"u" creates a string/unicode index
+        "dt" create a datetime index.
+        "td" create a timedelta index.
+
+            if unspecified, string labels will be generated.
 
+    Examples
+    --------
     # 5 row, 3 columns, default names on both, single index on both axis
     >> makeCustomDataframe(5,3)
 
@@ -2140,7 +2152,8 @@ def makeMissingDataframe(density=0.9, random_state=None):
 
 
 def optional_args(decorator):
-    """allows a decorator to take optional positional and keyword arguments.
+    """
+    allows a decorator to take optional positional and keyword arguments.
     Assumes that taking a single, callable, positional argument means that
     it is decorating a function, i.e. something like this::
 
@@ -2212,7 +2225,8 @@ def _get_default_network_errors():
 
 
 def can_connect(url, error_classes=None):
-    """Try to connect to the given url. True if succeeds, False if IOError
+    """
+    Try to connect to the given url. True if succeeds, False if IOError
     raised
 
     Parameters
@@ -2514,7 +2528,6 @@ class RNGContext:
 
     Examples
     --------
-
     with RNGContext(42):
         np.random.randn()
     """
@@ -2581,7 +2594,8 @@ def use_numexpr(use, min_elements=None):
 
 
 def test_parallel(num_threads=2, kwargs_list=None):
-    """Decorator to run the same function multiple times in parallel.
+    """
+    Decorator to run the same function multiple times in parallel.
 
     Parameters
     ----------
@@ -2590,6 +2604,7 @@ def test_parallel(num_threads=2, kwargs_list=None):
     kwargs_list : list of dicts, optional
         The list of kwargs to update original
         function kwargs on different threads.
+
     Notes
     -----
     This decorator does not pass the return value of the decorated function.
@@ -2669,7 +2684,6 @@ def set_timezone(tz: str):
 
     Examples
     --------
-
     >>> from datetime import datetime
     >>> from dateutil.tz import tzlocal
     >>> tzlocal().tzname(datetime.now())

pandas/compat/chainmap.py

@@ -5,7 +5,8 @@
 
 
 class DeepChainMap(ChainMap[_KT, _VT]):
-    """Variant of ChainMap that allows direct updates to inner scopes.
+    """
+    Variant of ChainMap that allows direct updates to inner scopes.
 
     Only works when all passed mapping are mutable.
     """

pandas/conftest.py

@@ -17,6 +17,7 @@
 from pandas import DataFrame
 import pandas._testing as tm
 from pandas.core import ops
+from pandas.core.indexes.api import Index, MultiIndex
 
 hypothesis.settings.register_profile(
     "ci",
@@ -982,3 +983,69 @@ def __len__(self):
             return self._data.__len__()
 
     return TestNonDictMapping
+
+
+indices_dict = {
+    "unicode": tm.makeUnicodeIndex(100),
+    "string": tm.makeStringIndex(100),
+    "datetime": tm.makeDateIndex(100),
+    "datetime-tz": tm.makeDateIndex(100, tz="US/Pacific"),
+    "period": tm.makePeriodIndex(100),
+    "timedelta": tm.makeTimedeltaIndex(100),
+    "int": tm.makeIntIndex(100),
+    "uint": tm.makeUIntIndex(100),
+    "range": tm.makeRangeIndex(100),
+    "float": tm.makeFloatIndex(100),
+    "bool": tm.makeBoolIndex(2),
+    "categorical": tm.makeCategoricalIndex(100),
+    "interval": tm.makeIntervalIndex(100),
+    "empty": Index([]),
+    "tuples": MultiIndex.from_tuples(zip(["foo", "bar", "baz"], [1, 2, 3])),
+    "repeats": Index([0, 0, 1, 1, 2, 2]),
+}
+
+
+@pytest.fixture(params=indices_dict.keys())
+def indices(request):
+    # copy to avoid mutation, e.g. setting .name
+    return indices_dict[request.param].copy()
+
+
+def _create_series(index):
+    """ Helper for the _series dict """
+    size = len(index)
+    data = np.random.randn(size)
+    return pd.Series(data, index=index, name="a")
+
+
+_series = {
+    f"series-with-{index_id}-index": _create_series(index)
+    for index_id, index in indices_dict.items()
+}
+
+
+_narrow_dtypes = [
+    np.float16,
+    np.float32,
+    np.int8,
+    np.int16,
+    np.int32,
+    np.uint8,
+    np.uint16,
+    np.uint32,
+]
+_narrow_series = {
+    f"{dtype.__name__}-series": tm.makeFloatSeries(name="a").astype(dtype)
+    for dtype in _narrow_dtypes
+}
+
+_index_or_series_objs = {**indices_dict, **_series, **_narrow_series}
+
+
+@pytest.fixture(params=_index_or_series_objs.keys())
+def index_or_series_obj(request):
+    """
+    Fixture for tests on indexes, series and series with a narrow dtype
+    copy to avoid mutation, e.g. setting .name
+    """
+    return _index_or_series_objs[request.param].copy(deep=True)

pandas/core/accessor.py

@@ -233,7 +233,6 @@ def __init__(self, pandas_object):  # noqa: E999
 
     Examples
     --------
-
     In your library code::
 
         import pandas as pd

pandas/core/aggregation.py

@@ -98,7 +98,8 @@ def normalize_keyword_aggregation(kwargs: dict) -> Tuple[dict, List[str], List[i
 def _make_unique_kwarg_list(
     seq: Sequence[Tuple[Any, Any]]
 ) -> Sequence[Tuple[Any, Any]]:
-    """Uniquify aggfunc name of the pairs in the order list
+    """
+    Uniquify aggfunc name of the pairs in the order list
 
     Examples:
     --------