Fix typos (#30481)

Author: bwignall

doc/source/user_guide/advanced.rst

@@ -573,7 +573,7 @@ When working with an ``Index`` object directly, rather than via a ``DataFrame``,
    .. code-block:: none
 
       >>> mi.levels[0].name = 'name via level'
-      >>> mi.names[0]  # only works for older panads
+      >>> mi.names[0]  # only works for older pandas
       'name via level'
 
    As of pandas 1.0, this will *silently* fail to update the names

doc/source/user_guide/missing_data.rst

@@ -791,7 +791,7 @@ the nullable :doc:`integer <integer_na>`, boolean and
 :ref:`dedicated string <text.types>` data types as the missing value indicator.
 
 The goal of ``pd.NA`` is provide a "missing" indicator that can be used
-consistently accross data types (instead of ``np.nan``, ``None`` or ``pd.NaT``
+consistently across data types (instead of ``np.nan``, ``None`` or ``pd.NaT``
 depending on the data type).
 
 For example, when having missing values in a Series with the nullable integer

doc/source/user_guide/text.rst

@@ -101,10 +101,10 @@ l. For ``StringDtype``, :ref:`string accessor methods<api.series.str>`
 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
+3. In comparison 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
+   will propagate in comparison operations, rather than always comparing
    unequal like :attr:`numpy.nan`.
 
 Everything else that follows in the rest of this document applies equally to

doc/source/whatsnew/v1.0.0.rst

@@ -111,7 +111,7 @@ A new ``pd.NA`` value (singleton) is introduced to represent scalar missing
 values. Up to now, ``np.nan`` is used for this for float data, ``np.nan`` or
 ``None`` for object-dtype data and ``pd.NaT`` for datetime-like data. The
 goal of ``pd.NA`` is provide a "missing" indicator that can be used
-consistently accross data types. For now, the nullable integer and boolean
+consistently across data types. For now, the nullable integer and boolean
 data types and the new string data type make use of ``pd.NA`` (:issue:`28095`).
 
 .. warning::
@@ -826,7 +826,7 @@ Plotting
 - Bug where :meth:`DataFrame.boxplot` would not accept a `color` parameter like `DataFrame.plot.box` (:issue:`26214`)
 - 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`).
+- :meth:`DataFrame.plot` now allow a ``backend`` keyword argument to allow changing between backends in one session (:issue:`28619`).
 - Bug in color validation incorrectly raising for non-color styles (:issue:`29122`).
 
 Groupby/resample/rolling

pandas/core/arrays/datetimelike.py

@@ -915,7 +915,7 @@ def _is_unique(self):
     __rdivmod__ = make_invalid_op("__rdivmod__")
 
     def _add_datetimelike_scalar(self, other):
-        # Overriden by TimedeltaArray
+        # Overridden by TimedeltaArray
         raise TypeError(f"cannot add {type(self).__name__} and {type(other).__name__}")
 
     _add_datetime_arraylike = _add_datetimelike_scalar
@@ -928,7 +928,7 @@ def _sub_datetimelike_scalar(self, other):
     _sub_datetime_arraylike = _sub_datetimelike_scalar
 
     def _sub_period(self, other):
-        # Overriden by PeriodArray
+        # Overridden by PeriodArray
         raise TypeError(f"cannot subtract Period from a {type(self).__name__}")
 
     def _add_offset(self, offset):
@@ -1085,7 +1085,7 @@ def _addsub_int_array(self, other, op):
         -------
         result : same class as self
         """
-        # _addsub_int_array is overriden by PeriodArray
+        # _addsub_int_array is overridden by PeriodArray
         assert not is_period_dtype(self)
         assert op in [operator.add, operator.sub]
 

pandas/core/groupby/groupby.py

@@ -4,7 +4,7 @@ class providing the base-class of operations.
 
 The SeriesGroupBy and DataFrameGroupBy sub-class
 (defined in pandas.core.groupby.generic)
-expose these user-facing objects to provide specific functionailty.
+expose these user-facing objects to provide specific functionality.
 """
 
 from contextlib import contextmanager

pandas/core/indexes/interval.py

@@ -978,7 +978,7 @@ def get_indexer(
             right_indexer = self.right.get_indexer(target_as_index.right)
             indexer = np.where(left_indexer == right_indexer, left_indexer, -1)
         elif is_categorical(target_as_index):
-            # get an indexer for unique categories then propogate to codes via take_1d
+            # get an indexer for unique categories then propagate to codes via take_1d
             categories_indexer = self.get_indexer(target_as_index.categories)
             indexer = take_1d(categories_indexer, target_as_index.codes, fill_value=-1)
         elif not is_object_dtype(target_as_index):

pandas/core/internals/blocks.py

@@ -1449,7 +1449,7 @@ def quantile(self, qs, interpolation="linear", axis=0):
         -------
         Block
         """
-        # We should always have ndim == 2 becase Series dispatches to DataFrame
+        # We should always have ndim == 2 because Series dispatches to DataFrame
         assert self.ndim == 2
 
         values = self.get_values()
@@ -2432,7 +2432,7 @@ def fillna(self, value, **kwargs):
             # Deprecation GH#24694, GH#19233
             raise TypeError(
                 "Passing integers to fillna for timedelta64[ns] dtype is no "
-                "longer supporetd.  To obtain the old behavior, pass "
+                "longer supported.  To obtain the old behavior, pass "
                 "`pd.Timedelta(seconds=n)` instead."
             )
         return super().fillna(value, **kwargs)
@@ -2971,7 +2971,7 @@ def make_block(values, placement, klass=None, ndim=None, dtype=None):
 
 
 def _extend_blocks(result, blocks=None):
-    """ return a new extended blocks, givin the result """
+    """ return a new extended blocks, given the result """
     from pandas.core.internals import BlockManager
 
     if blocks is None:

pandas/core/nanops.py

@@ -1337,7 +1337,7 @@ def f(x, y):
 
 def _nanpercentile_1d(values, mask, q, na_value, interpolation):
     """
-    Wraper for np.percentile that skips missing values, specialized to
+    Wrapper for np.percentile that skips missing values, specialized to
     1-dimensional case.
 
     Parameters
@@ -1368,7 +1368,7 @@ def _nanpercentile_1d(values, mask, q, na_value, interpolation):
 
 def nanpercentile(values, q, axis, na_value, mask, ndim, interpolation):
     """
-    Wraper for np.percentile that skips missing values.
+    Wrapper for np.percentile that skips missing values.
 
     Parameters
     ----------

pandas/core/series.py

@@ -727,7 +727,7 @@ def __array__(self, dtype=None):
                Timestamp('2000-01-02 00:00:00+0100', tz='CET', freq='D')],
               dtype=object)
 
-        Or the values may be localized to UTC and the tzinfo discared with
+        Or the values may be localized to UTC and the tzinfo discarded with
         ``dtype='datetime64[ns]'``
 
         >>> np.asarray(tzser, dtype="datetime64[ns]")  # doctest: +ELLIPSIS

pandas/io/pytables.py

@@ -3297,7 +3297,7 @@ def data_orientation(self):
     def queryables(self) -> Dict[str, Any]:
         """ return a dict of the kinds allowable columns for this object """
 
-        # mypy doesnt recognize DataFrame._AXIS_NAMES, so we re-write it here
+        # mypy doesn't recognize DataFrame._AXIS_NAMES, so we re-write it here
         axis_names = {0: "index", 1: "columns"}
 
         # compute the values_axes queryables
@@ -4993,7 +4993,7 @@ def _get_data_and_dtype_name(data: Union[np.ndarray, ABCExtensionArray]):
     if data.dtype.kind in ["m", "M"]:
         data = np.asarray(data.view("i8"))
         # TODO: we used to reshape for the dt64tz case, but no longer
-        #  doing that doesnt seem to break anything.  why?
+        #  doing that doesn't seem to break anything.  why?
 
     elif isinstance(data, PeriodIndex):
         data = data.asi8

pandas/tests/arithmetic/conftest.py

@@ -248,7 +248,7 @@ def box_df_fail(request):
 def box_transpose_fail(request):
     """
     Fixture similar to `box` but testing both transpose cases for DataFrame,
-    with the tranpose=True case xfailed.
+    with the transpose=True case xfailed.
     """
     # GH#23620
     return request.param

pandas/tests/arrays/test_integer.py

@@ -193,7 +193,7 @@ def _check_op_integer(self, result, expected, mask, s, op_name, other):
         # to compare properly, we convert the expected
         # to float, mask to nans and convert infs
         # if we have uints then we process as uints
-        # then conert to float
+        # then convert to float
         # and we ultimately want to create a IntArray
         # for comparisons
 

pandas/tests/indexes/datetimes/test_indexing.py

@@ -457,7 +457,7 @@ def test_insert(self):
     def test_delete(self):
         idx = date_range(start="2000-01-01", periods=5, freq="M", name="idx")
 
-        # prserve freq
+        # preserve freq
         expected_0 = date_range(start="2000-02-01", periods=4, freq="M", name="idx")
         expected_4 = date_range(start="2000-01-01", periods=4, freq="M", name="idx")
 
@@ -511,7 +511,7 @@ def test_delete(self):
     def test_delete_slice(self):
         idx = date_range(start="2000-01-01", periods=10, freq="D", name="idx")
 
-        # prserve freq
+        # preserve freq
         expected_0_2 = date_range(start="2000-01-04", periods=7, freq="D", name="idx")
         expected_7_9 = date_range(start="2000-01-01", periods=7, freq="D", name="idx")
 

pandas/tests/indexing/interval/test_interval.py

@@ -64,7 +64,7 @@ def test_non_matching(self):
         s = self.s
 
         # this is a departure from our current
-        # indexin scheme, but simpler
+        # indexing scheme, but simpler
         with pytest.raises(KeyError, match="^$"):
             s.loc[[-1, 3, 4, 5]]
 

pandas/tests/io/formats/test_format.py

@@ -446,7 +446,7 @@ def mkframe(n):
                     assert not has_truncated_repr(df6)
 
                 with option_context("display.max_rows", 9, "display.max_columns", 10):
-                    # out vertical bounds can not result in exanded repr
+                    # out vertical bounds can not result in expanded repr
                     assert not has_expanded_repr(df10)
                     assert has_vertically_truncated_repr(df10)
 

pandas/tests/io/pytables/test_store.py

@@ -1273,7 +1273,7 @@ def test_append_with_different_block_ordering(self, setup_path):
             with pytest.raises(ValueError):
                 store.append("df", df)
 
-            # store multile additional fields in different blocks
+            # store multiple additional fields in different blocks
             df["float_3"] = Series([1.0] * len(df), dtype="float64")
             with pytest.raises(ValueError):
                 store.append("df", df)

pandas/tests/plotting/test_frame.py

@@ -555,14 +555,14 @@ def test_subplots_timeseries_y_axis_not_supported(self):
             period:
                 since period isn't yet implemented in ``select_dtypes``
                 and because it will need a custom value converter +
-                tick formater (as was done for x-axis plots)
+                tick formatter (as was done for x-axis plots)
 
             categorical:
                  because it will need a custom value converter +
-                 tick formater (also doesn't work for x-axis, as of now)
+                 tick formatter (also doesn't work for x-axis, as of now)
 
             datetime_mixed_tz:
-                because of the way how pandas handels ``Series`` of
+                because of the way how pandas handles ``Series`` of
                 ``datetime`` objects with different timezone,
                 generally converting ``datetime`` objects in a tz-aware
                 form could help with this problem

pandas/tests/scalar/timedelta/test_timedelta.py

@@ -20,7 +20,7 @@ def test_arithmetic_overflow(self):
             Timestamp("1700-01-01") + timedelta(days=13 * 19999)
 
     def test_array_timedelta_floordiv(self):
-        # deprected GH#19761, enforced GH#29797
+        # deprecated GH#19761, enforced GH#29797
         ints = pd.date_range("2012-10-08", periods=4, freq="D").view("i8")
 
         with pytest.raises(TypeError, match="Invalid dtype"):

pandas/tests/series/test_api.py

@@ -310,7 +310,7 @@ def test_iteritems_strings(self, string_series):
         for idx, val in string_series.iteritems():
             assert val == string_series[idx]
 
-        # assert is lazy (genrators don't define reverse, lists do)
+        # assert is lazy (generators don't define reverse, lists do)
         assert not hasattr(string_series.iteritems(), "reverse")
 
     def test_items_datetimes(self, datetime_series):
@@ -321,7 +321,7 @@ def test_items_strings(self, string_series):
         for idx, val in string_series.items():
             assert val == string_series[idx]
 
-        # assert is lazy (genrators don't define reverse, lists do)
+        # assert is lazy (generators don't define reverse, lists do)
         assert not hasattr(string_series.items(), "reverse")
 
     def test_raise_on_info(self):

scripts/tests/test_validate_docstrings.py

@@ -719,7 +719,7 @@ def no_type(self):
 
     def no_description(self):
         """
-        Provides type but no descrption.
+        Provides type but no description.
 
         Returns
         -------

setup.py

@@ -510,7 +510,7 @@ def maybe_cythonize(extensions, *args, **kwargs):
         if hasattr(ext, "include_dirs") and numpy_incl not in ext.include_dirs:
             ext.include_dirs.append(numpy_incl)
 
-    # reuse any parallel arguments provided for compliation to cythonize
+    # reuse any parallel arguments provided for compilation to cythonize
     parser = argparse.ArgumentParser()
     parser.add_argument("-j", type=int)
     parser.add_argument("--parallel", type=int)