CLN: Fix typos (mainly in docs and comments) (#27007)

Author: minho42

Diff for: asv_bench/benchmarks/offset.py

@@ -9,7 +9,7 @@
     pass
 
 hcal = pd.tseries.holiday.USFederalHolidayCalendar()
-# These offests currently raise a NotImplimentedError with .apply_index()
+# These offsets currently raise a NotImplimentedError with .apply_index()
 non_apply = [pd.offsets.Day(),
              pd.offsets.BYearEnd(),
              pd.offsets.BYearBegin(),

Diff for: doc/source/getting_started/comparison/comparison_with_sas.rst

@@ -660,7 +660,7 @@ example, to subtract the mean for each observation by smoker group.
    run;
 
 
-pandas ``groubpy`` provides a ``transform`` mechanism that allows
+pandas ``groupby`` provides a ``transform`` mechanism that allows
 these type of operations to be succinctly expressed in one
 operation.
 

Diff for: doc/source/getting_started/comparison/comparison_with_stata.rst

@@ -634,7 +634,7 @@ For example, to subtract the mean for each observation by smoker group.
    generate adj_total_bill = total_bill - group_bill
 
 
-pandas ``groubpy`` provides a ``transform`` mechanism that allows
+pandas ``groupby`` provides a ``transform`` mechanism that allows
 these type of operations to be succinctly expressed in one
 operation.
 

Diff for: doc/source/user_guide/io.rst

@@ -488,7 +488,7 @@ specification:
 
 .. versionadded:: 0.21.0
 
-Specifying ``dtype='cateogry'`` will result in an unordered ``Categorical``
+Specifying ``dtype='category'`` will result in an unordered ``Categorical``
 whose ``categories`` are the unique values observed in the data. For more
 control on the categories and order, create a
 :class:`~pandas.api.types.CategoricalDtype` ahead of time, and pass that for
@@ -1679,7 +1679,7 @@ S3 URLs are handled as well but require installing the `S3Fs
 
    df = pd.read_csv('s3://pandas-test/tips.csv')
 
-If your S3 bucket requires cedentials you will need to set them as environment
+If your S3 bucket requires credentials you will need to set them as environment
 variables or in the ``~/.aws/credentials`` config file, refer to the `S3Fs
 documentation on credentials
 <https://s3fs.readthedocs.io/en/latest/#credentials>`_.
@@ -2078,7 +2078,7 @@ Dates written in nanoseconds need to be read back in nanoseconds:
 
    json = dfj2.to_json(date_unit='ns')
 
-   # Try to parse timestamps as millseconds -> Won't Work
+   # Try to parse timestamps as milliseconds -> Won't Work
    dfju = pd.read_json(json, date_unit='ms')
    dfju
 

Diff for: doc/source/user_guide/timeseries.rst

@@ -1133,7 +1133,7 @@ Valid business hours are distinguished by whether it started from valid ``Busine
     pd.Timestamp('2014-08-01 17:00') + bh
     pd.Timestamp('2014-08-01 23:00') + bh
 
-    # Although 2014-08-02 is Satuaday,
+    # Although 2014-08-02 is Saturday,
     # it is valid because it starts from 08-01 (Friday).
     pd.Timestamp('2014-08-02 04:00') + bh
 

Diff for: doc/source/whatsnew/v0.10.1.rst

@@ -170,7 +170,7 @@ combined result, by using ``where`` on a selector table.
                             df_mt, selector='df1_mt')
    store
 
-   # indiviual tables were created
+   # individual tables were created
    store.select('df1_mt')
    store.select('df2_mt')
 

Diff for: doc/source/whatsnew/v0.14.0.rst

@@ -816,7 +816,7 @@ Enhancements
 - Implemented ``Panel.pct_change`` (:issue:`6904`)
 - Added ``how`` option to rolling-moment functions to dictate how to handle resampling; :func:`rolling_max` defaults to max,
   :func:`rolling_min` defaults to min, and all others default to mean (:issue:`6297`)
-- ``CustomBuisnessMonthBegin`` and ``CustomBusinessMonthEnd`` are now available (:issue:`6866`)
+- ``CustomBusinessMonthBegin`` and ``CustomBusinessMonthEnd`` are now available (:issue:`6866`)
 - :meth:`Series.quantile` and :meth:`DataFrame.quantile` now accept an array of
   quantiles.
 - :meth:`~DataFrame.describe` now accepts an array of percentiles to include in the summary statistics (:issue:`4196`)

Diff for: doc/source/whatsnew/v0.14.1.rst

@@ -247,7 +247,7 @@ Bug Fixes
 - Bug in ``DatetimeIndex`` comparison doesn't handle ``NaT`` properly (:issue:`7529`)
 - Bug in passing input with ``tzinfo`` to some offsets ``apply``, ``rollforward`` or ``rollback`` resets ``tzinfo`` or raises ``ValueError`` (:issue:`7465`)
 - Bug in ``DatetimeIndex.to_period``, ``PeriodIndex.asobject``, ``PeriodIndex.to_timestamp`` doesn't preserve ``name`` (:issue:`7485`)
-- Bug in ``DatetimeIndex.to_period`` and ``PeriodIndex.to_timestanp`` handle ``NaT`` incorrectly (:issue:`7228`)
+- Bug in ``DatetimeIndex.to_period`` and ``PeriodIndex.to_timestamp`` handle ``NaT`` incorrectly (:issue:`7228`)
 - Bug in ``offsets.apply``, ``rollforward`` and ``rollback`` may return normal ``datetime`` (:issue:`7502`)
 - Bug in ``resample`` raises ``ValueError`` when target contains ``NaT`` (:issue:`7227`)
 - Bug in ``Timestamp.tz_localize`` resets ``nanosecond`` info (:issue:`7534`)

Diff for: doc/source/whatsnew/v0.19.0.rst

@@ -1513,7 +1513,7 @@ Bug Fixes
 - Bug in ``Series`` comparison may output incorrect result if rhs contains ``NaT`` (:issue:`9005`)
 - Bug in ``Series`` and ``Index`` comparison may output incorrect result if it contains ``NaT`` with ``object`` dtype (:issue:`13592`)
 - Bug in ``Period`` addition raises ``TypeError`` if ``Period`` is on right hand side (:issue:`13069`)
-- Bug in ``Peirod`` and ``Series`` or ``Index`` comparison raises ``TypeError`` (:issue:`13200`)
+- Bug in ``Period`` and ``Series`` or ``Index`` comparison raises ``TypeError`` (:issue:`13200`)
 - Bug in ``pd.set_eng_float_format()`` that would prevent NaN and Inf from formatting (:issue:`11981`)
 - Bug in ``.unstack`` with ``Categorical`` dtype resets ``.ordered`` to ``True`` (:issue:`13249`)
 - Clean some compile time warnings in datetime parsing (:issue:`13607`)

Diff for: doc/source/whatsnew/v0.21.0.rst

@@ -263,7 +263,7 @@ Now, to find prices per store/product, we can simply do:
 See the :ref:`documentation <groupby.pipe>` for more.
 
 
-.. _whatsnew_0210.enhancements.reanme_categories:
+.. _whatsnew_0210.enhancements.rename_categories:
 
 ``Categorical.rename_categories`` accepts a dict-like
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -418,7 +418,7 @@ New Behavior, without regard to the bottleneck installation:
 
    s.sum()
 
-Note that this also changes the sum of an empty ``Series``. Previously this always returned 0 regardless of a ``bottlenck`` installation:
+Note that this also changes the sum of an empty ``Series``. Previously this always returned 0 regardless of a ``bottleneck`` installation:
 
 .. code-block:: ipython
 

Diff for: doc/source/whatsnew/v0.23.0.rst

@@ -276,7 +276,7 @@ To show only observed values:
 
    df.groupby(['A', 'B', 'C'], observed=True).count()
 
-For pivotting operations, this behavior is *already* controlled by the ``dropna`` keyword:
+For pivoting operations, this behavior is *already* controlled by the ``dropna`` keyword:
 
 .. ipython:: python
 

Diff for: doc/source/whatsnew/v0.23.1.rst

@@ -26,7 +26,7 @@ Fixed Regressions
 **Comparing Series with datetime.date**
 
 We've reverted a 0.23.0 change to comparing a :class:`Series` holding datetimes and a ``datetime.date`` object (:issue:`21152`).
-In pandas 0.22 and earlier, comparing a Series holding datetimes and ``datetime.date`` objects would coerce the ``datetime.date`` to a datetime before comapring.
+In pandas 0.22 and earlier, comparing a Series holding datetimes and ``datetime.date`` objects would coerce the ``datetime.date`` to a datetime before comparing.
 This was inconsistent with Python, NumPy, and :class:`DatetimeIndex`, which never consider a datetime and ``datetime.date`` equal.
 
 In 0.23.0, we unified operations between DatetimeIndex and Series, and in the process changed comparisons between a Series of datetimes and ``datetime.date`` without warning.

Diff for: doc/source/whatsnew/v0.24.0.rst

@@ -1061,7 +1061,7 @@ The affected cases are:
 
 .. code-block:: ipython
 
-   # Comparison operations and arithmetic opeartions both raise ValueError.
+   # Comparison operations and arithmetic operations both raise ValueError.
    In [6]: df == (1, 2, 3)
    ...
    ValueError: Unable to coerce to Series, length must be 2: given 3
@@ -1324,7 +1324,7 @@ Deprecations
 - :meth:`Series.clip_lower`, :meth:`Series.clip_upper`, :meth:`DataFrame.clip_lower` and :meth:`DataFrame.clip_upper` are deprecated and will be removed in a future version. Use ``Series.clip(lower=threshold)``, ``Series.clip(upper=threshold)`` and the equivalent ``DataFrame`` methods (:issue:`24203`)
 - :meth:`Series.nonzero` is deprecated and will be removed in a future version (:issue:`18262`)
 - Passing an integer to :meth:`Series.fillna` and :meth:`DataFrame.fillna` with ``timedelta64[ns]`` dtypes is deprecated, will raise ``TypeError`` in a future version.  Use ``obj.fillna(pd.Timedelta(...))`` instead (:issue:`24694`)
-- ``Series.cat.categorical``, ``Series.cat.name`` and ``Sersies.cat.index`` have been deprecated. Use the attributes on ``Series.cat`` or ``Series`` directly. (:issue:`24751`).
+- ``Series.cat.categorical``, ``Series.cat.name`` and ``Series.cat.index`` have been deprecated. Use the attributes on ``Series.cat`` or ``Series`` directly. (:issue:`24751`).
 - Passing a dtype without a precision like ``np.dtype('datetime64')`` or ``timedelta64`` to :class:`Index`, :class:`DatetimeIndex` and :class:`TimedeltaIndex` is now deprecated. Use the nanosecond-precision dtype instead (:issue:`24753`).
 
 .. _whatsnew_0240.deprecations.datetimelike_int_ops:
@@ -1604,7 +1604,7 @@ Datetimelike
 - Bug in :class:`DatetimeIndex` where calling ``np.array(dtindex, dtype=object)`` would incorrectly return an array of ``long`` objects (:issue:`23524`)
 - Bug in :class:`Index` where passing a timezone-aware :class:`DatetimeIndex` and `dtype=object` would incorrectly raise a ``ValueError`` (:issue:`23524`)
 - Bug in :class:`Index` where calling ``np.array(dtindex, dtype=object)`` on a timezone-naive :class:`DatetimeIndex` would return an array of ``datetime`` objects instead of :class:`Timestamp` objects, potentially losing nanosecond portions of the timestamps (:issue:`23524`)
-- Bug in :class:`Categorical.__setitem__` not allowing setting with another ``Categorical`` when both are undordered and have the same categories, but in a different order (:issue:`24142`)
+- Bug in :class:`Categorical.__setitem__` not allowing setting with another ``Categorical`` when both are unordered and have the same categories, but in a different order (:issue:`24142`)
 - Bug in :func:`date_range` where using dates with millisecond resolution or higher could return incorrect values or the wrong number of values in the index (:issue:`24110`)
 - Bug in :class:`DatetimeIndex` where constructing a :class:`DatetimeIndex` from a :class:`Categorical` or :class:`CategoricalIndex` would incorrectly drop timezone information (:issue:`18664`)
 - Bug in :class:`DatetimeIndex` and :class:`TimedeltaIndex` where indexing with ``Ellipsis`` would incorrectly lose the index's ``freq`` attribute (:issue:`21282`)
@@ -1670,7 +1670,7 @@ Timezones
 Offsets
 ^^^^^^^
 
-- Bug in :class:`FY5253` where date offsets could incorrectly raise an ``AssertionError`` in arithmetic operatons (:issue:`14774`)
+- Bug in :class:`FY5253` where date offsets could incorrectly raise an ``AssertionError`` in arithmetic operations (:issue:`14774`)
 - Bug in :class:`DateOffset` where keyword arguments ``week`` and ``milliseconds`` were accepted and ignored.  Passing these will now raise ``ValueError`` (:issue:`19398`)
 - Bug in adding :class:`DateOffset` with :class:`DataFrame` or :class:`PeriodIndex` incorrectly raising ``TypeError`` (:issue:`23215`)
 - Bug in comparing :class:`DateOffset` objects with non-DateOffset objects, particularly strings, raising ``ValueError`` instead of returning ``False`` for equality checks and ``True`` for not-equal checks (:issue:`23524`)
@@ -1838,7 +1838,7 @@ Groupby/Resample/Rolling
   ``SeriesGroupBy`` when the grouping variable only contains NaNs and numpy version < 1.13 (:issue:`21956`).
 - Multiple bugs in :func:`pandas.core.window.Rolling.min` with ``closed='left'`` and a
   datetime-like index leading to incorrect results and also segfault. (:issue:`21704`)
-- Bug in :meth:`pandas.core.resample.Resampler.apply` when passing postiional arguments to applied func (:issue:`14615`).
+- Bug in :meth:`pandas.core.resample.Resampler.apply` when passing positional arguments to applied func (:issue:`14615`).
 - Bug in :meth:`Series.resample` when passing ``numpy.timedelta64`` to ``loffset`` kwarg (:issue:`7687`).
 - Bug in :meth:`pandas.core.resample.Resampler.asfreq` when frequency of ``TimedeltaIndex`` is a subperiod of a new frequency (:issue:`13022`).
 - Bug in :meth:`pandas.core.groupby.SeriesGroupBy.mean` when values were integral but could not fit inside of int64, overflowing instead. (:issue:`22487`)

Diff for: doc/source/whatsnew/v0.25.0.rst

@@ -119,7 +119,7 @@ Other Enhancements
 - ``Series.str`` has gained :meth:`Series.str.casefold` method to removes all case distinctions present in a string (:issue:`25405`)
 - :meth:`DataFrame.set_index` now works for instances of ``abc.Iterator``, provided their output is of the same length as the calling frame (:issue:`22484`, :issue:`24984`)
 - :meth:`DatetimeIndex.union` now supports the ``sort`` argument. The behavior of the sort parameter matches that of :meth:`Index.union` (:issue:`24994`)
-- :meth:`RangeIndex.union` now supports the ``sort`` argument. If ``sort=False`` an unsorted ``Int64Index`` is always returned. ``sort=None`` is the default and returns a mononotically increasing ``RangeIndex`` if possible or a sorted ``Int64Index`` if not (:issue:`24471`)
+- :meth:`RangeIndex.union` now supports the ``sort`` argument. If ``sort=False`` an unsorted ``Int64Index`` is always returned. ``sort=None`` is the default and returns a monotonically increasing ``RangeIndex`` if possible or a sorted ``Int64Index`` if not (:issue:`24471`)
 - :meth:`TimedeltaIndex.intersection` now also supports the ``sort`` keyword (:issue:`24471`)
 - :meth:`DataFrame.rename` now supports the ``errors`` argument to raise errors when attempting to rename nonexistent keys (:issue:`13473`)
 - Added :ref:`api.frame.sparse` for working with a ``DataFrame`` whose values are sparse (:issue:`25681`)
@@ -694,7 +694,7 @@ I/O
 - Bug in :func:`read_json` for ``orient='table'`` and float index, as it infers index dtype by default, which is not applicable because index dtype is already defined in the JSON schema (:issue:`25433`)
 - Bug in :func:`read_json` for ``orient='table'`` and string of float column names, as it makes a column name type conversion to :class:`Timestamp`, which is not applicable because column names are already defined in the JSON schema (:issue:`25435`)
 - Bug in :func:`json_normalize` for ``errors='ignore'`` where missing values in the input data, were filled in resulting ``DataFrame`` with the string ``"nan"`` instead of ``numpy.nan`` (:issue:`25468`)
-- :meth:`DataFrame.to_html` now raises ``TypeError`` when using an invalid type for the ``classes`` parameter instead of ``AsseertionError`` (:issue:`25608`)
+- :meth:`DataFrame.to_html` now raises ``TypeError`` when using an invalid type for the ``classes`` parameter instead of ``AssertionError`` (:issue:`25608`)
 - Bug in :meth:`DataFrame.to_string` and :meth:`DataFrame.to_latex` that would lead to incorrect output when the ``header`` keyword is used (:issue:`16718`)
 - Bug in :func:`read_csv` not properly interpreting the UTF8 encoded filenames on Windows on Python 3.6+ (:issue:`15086`)
 - Improved performance in :meth:`pandas.read_stata` and :class:`pandas.io.stata.StataReader` when converting columns that have missing values (:issue:`25772`)

Diff for: doc/source/whatsnew/v0.8.0.rst

@@ -77,7 +77,7 @@ Time series changes and improvements
   interface while enabling working with nanosecond-resolution data. Also
   provides :ref:`easy time zone conversions <timeseries.timezone>`.
 - Enhanced support for :ref:`time zones <timeseries.timezone>`. Add
-  `tz_convert` and ``tz_lcoalize`` methods to TimeSeries and DataFrame. All
+  `tz_convert` and ``tz_localize`` methods to TimeSeries and DataFrame. All
   timestamps are stored as UTC; Timestamps from DatetimeIndex objects with time
   zone set will be localized to local time. Time zone conversions are therefore
   essentially free. User needs to know very little about pytz library now; only

Diff for: pandas/_libs/tslibs/fields.pyx

@@ -171,7 +171,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
         # YearBegin(), BYearBegin() use month = starting month of year.
         # QuarterBegin(), BQuarterBegin() use startingMonth = starting
-        # month of year. Other offests use month, startingMonth as ending
+        # month of year. Other offsets use month, startingMonth as ending
         # month of year.
 
         if (freqstr[0:2] in ['MS', 'QS', 'AS']) or (

Diff for: pandas/compat/numpy/__init__.py

@@ -1,4 +1,4 @@
-""" support numpy compatiblitiy across versions """
+""" support numpy compatibility across versions """
 
 from distutils.version import LooseVersion
 import re

Diff for: pandas/conftest.py

@@ -122,7 +122,7 @@ def observed(request):
     """ pass in the observed keyword to groupby for [True, False]
     This indicates whether categoricals should return values for
     values which are not in the grouper [False / None], or only values which
-    appear in the grouper [True]. [None] is supported for future compatiblity
+    appear in the grouper [True]. [None] is supported for future compatibility
     if we decide to change the default (and would need to warn if this
     parameter is not passed)"""
     return request.param

Diff for: pandas/core/arrays/base.py

@@ -653,7 +653,7 @@ def factorize(
         -----
         :meth:`pandas.factorize` offers a `sort` keyword as well.
         """
-        # Impelmentor note: There are two ways to override the behavior of
+        # Implementer note: There are two ways to override the behavior of
         # pandas.factorize
         # 1. _values_for_factorize and _from_factorize.
         #    Specify the values passed to pandas' internal factorization

Diff for: pandas/core/arrays/datetimes.py

@@ -676,7 +676,7 @@ def _format_native_types(self, na_rep='NaT', date_format=None, **kwargs):
     def _has_same_tz(self, other):
         zzone = self._timezone
 
-        # vzone sholdn't be None if value is non-datetime like
+        # vzone shouldn't be None if value is non-datetime like
         if isinstance(other, np.datetime64):
             # convert to Timestamp as np.datetime64 doesn't have tz attr
             other = Timestamp(other)

Diff for: pandas/core/arrays/integer.py

@@ -28,7 +28,7 @@ class _IntegerDtype(ExtensionDtype):
     An ExtensionDtype to hold a single size & kind of integer dtype.
 
     These specific implementations are subclasses of the non-public
-    _IntegerDtype. For example we have Int8Dtype to represnt signed int 8s.
+    _IntegerDtype. For example we have Int8Dtype to represent signed int 8s.
 
     The attributes name & type are set when these subclasses are created.
     """

Diff for: pandas/core/arrays/period.py

@@ -854,7 +854,7 @@ def dt64arr_to_periodarr(data, freq, tz=None):
     -------
     ordinals : ndarray[int]
     freq : Tick
-        The frequencey extracted from the Series or DatetimeIndex if that's
+        The frequency extracted from the Series or DatetimeIndex if that's
         used.
 
     """

Diff for: pandas/core/arrays/sparse.py

@@ -562,7 +562,7 @@ class SparseArray(PandasObject, ExtensionArray, ExtensionOpsMixin):
         * 'block': Stores a `block` and `block_length` for each
           contiguous *span* of sparse values. This is best when
           sparse data tends to be clumped together, with large
-          regsions of ``fill-value`` values between sparse values.
+          regions of ``fill-value`` values between sparse values.
         * 'integer': uses an integer to store the location of
           each sparse value.
 
@@ -1316,7 +1316,7 @@ def _concat_same_type(cls, to_concat):
             sp_index = IntIndex(length, indices)
 
         else:
-            # when concatentating block indices, we don't claim that you'll
+            # when concatenating block indices, we don't claim that you'll
             # get an identical index as concating the values and then
             # creating a new index. We don't want to spend the time trying
             # to merge blocks across arrays in `to_concat`, so the resulting

Diff for: pandas/core/base.py

@@ -1137,7 +1137,7 @@ def __iter__(self):
         -------
         iterator
         """
-        # We are explicity making element iterators.
+        # We are explicitly making element iterators.
         if is_datetimelike(self._values):
             return map(com.maybe_box_datetimelike, self._values)
         elif is_extension_array_dtype(self._values):

Diff for: pandas/core/computation/pytables.py

@@ -410,7 +410,7 @@ def visit_Assign(self, node, **kwargs):
         return self.visit(cmpr)
 
     def visit_Subscript(self, node, **kwargs):
-        # only allow simple suscripts
+        # only allow simple subscripts
 
         value = self.visit(node.value)
         slobj = self.visit(node.slice)