CLN: Fix common spelling mistakes (#32895)

Author: SaturnFromTitan

asv_bench/benchmarks/rolling.py

@@ -11,7 +11,7 @@ class Methods:
         ["int", "float"],
         ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
     )
-    param_names = ["contructor", "window", "dtype", "method"]
+    param_names = ["constructor", "window", "dtype", "method"]
 
     def setup(self, constructor, window, dtype, method):
         N = 10 ** 5
@@ -72,7 +72,7 @@ class ExpandingMethods:
         ["int", "float"],
         ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
     )
-    param_names = ["contructor", "window", "dtype", "method"]
+    param_names = ["constructor", "window", "dtype", "method"]
 
     def setup(self, constructor, dtype, method):
         N = 10 ** 5
@@ -86,7 +86,7 @@ def time_expanding(self, constructor, dtype, method):
 class EWMMethods:
 
     params = (["DataFrame", "Series"], [10, 1000], ["int", "float"], ["mean", "std"])
-    param_names = ["contructor", "window", "dtype", "method"]
+    param_names = ["constructor", "window", "dtype", "method"]
 
     def setup(self, constructor, window, dtype, method):
         N = 10 ** 5
@@ -104,7 +104,7 @@ class VariableWindowMethods(Methods):
         ["int", "float"],
         ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum"],
     )
-    param_names = ["contructor", "window", "dtype", "method"]
+    param_names = ["constructor", "window", "dtype", "method"]
 
     def setup(self, constructor, window, dtype, method):
         N = 10 ** 5

ci/azure/posix.yml

@@ -24,7 +24,7 @@ jobs:
           ENV_FILE: ci/deps/azure-36-locale_slow.yaml
           CONDA_PY: "36"
           PATTERN: "slow"
-          # pandas does not use the language (zh_CN), but should support diferent encodings (utf8)
+          # pandas does not use the language (zh_CN), but should support different encodings (utf8)
           # we should test with encodings different than utf8, but doesn't seem like Ubuntu supports any
           LANG: "zh_CN.utf8"
           LC_ALL: "zh_CN.utf8"

doc/source/getting_started/intro_tutorials/02_read_write.rst

@@ -225,7 +225,7 @@ The method :meth:`~DataFrame.info` provides technical information about a
     <div class="d-flex flex-row bg-light gs-torefguide">
         <span class="badge badge-info">To user guide</span>
 
-For a complete overview of the input and output possibilites from and to pandas, see the user guide section about :ref:`reader and writer functions <io>`.
+For a complete overview of the input and output possibilities from and to pandas, see the user guide section about :ref:`reader and writer functions <io>`.
 
 .. raw:: html
 

doc/source/getting_started/intro_tutorials/03_subset_data.rst

@@ -101,7 +101,7 @@ And have a look at the ``shape`` of the output:
 
     titanic["Age"].shape
 
-:attr:`DataFrame.shape` is an attribute (remember :ref:`tutorial on reading and writing <10min_tut_02_read_write>`, do not use parantheses for attributes) of a
+:attr:`DataFrame.shape` is an attribute (remember :ref:`tutorial on reading and writing <10min_tut_02_read_write>`, do not use parentheses for attributes) of a
 pandas ``Series`` and ``DataFrame`` containing the number of rows and
 columns: *(nrows, ncolumns)*. A pandas Series is 1-dimensional and only
 the number of rows is returned.

doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst

@@ -165,7 +165,7 @@ index. For example:
 .. note::
     The existence of multiple row/column indices at the same time
     has not been mentioned within these tutorials. *Hierarchical indexing*
-    or *MultiIndex* is an advanced and powerfull pandas feature to analyze
+    or *MultiIndex* is an advanced and powerful pandas feature to analyze
     higher dimensional data.
 
     Multi-indexing is out of scope for this pandas introduction. For the

doc/source/getting_started/intro_tutorials/10_text_data.rst

@@ -188,7 +188,7 @@ Which passenger of the titanic has the longest name?
 
     titanic["Name"].str.len()
 
-To get the longest name we first have to get the lenghts of each of the
+To get the longest name we first have to get the lengths of each of the
 names in the ``Name`` column. By using pandas string methods, the
 :meth:`Series.str.len` function is applied to each of the names individually
 (element-wise).

doc/source/user_guide/dsintro.rst

@@ -406,7 +406,7 @@ From a list of dataclasses
 
 Data Classes as introduced in `PEP557 <https://www.python.org/dev/peps/pep-0557>`__,
 can be passed into the DataFrame constructor.
-Passing a list of dataclasses is equivilent to passing a list of dictionaries.
+Passing a list of dataclasses is equivalent to passing a list of dictionaries.
 
 Please be aware, that that all values in the list should be dataclasses, mixing
 types in the list would result in a TypeError.

doc/source/user_guide/indexing.rst

@@ -374,7 +374,7 @@ For getting values with a boolean array:
    df1.loc['a'] > 0
    df1.loc[:, df1.loc['a'] > 0]
 
-NA values in a boolean array propogate as ``False``:
+NA values in a boolean array propagate as ``False``:
 
 .. versionchanged:: 1.0.2
 

doc/source/user_guide/io.rst

@@ -5005,7 +5005,7 @@ Possible values are:
   This usually provides better performance for analytic databases
   like *Presto* and *Redshift*, but has worse performance for
   traditional SQL backend if the table contains many columns.
-  For more information check the SQLAlchemy `documention
+  For more information check the SQLAlchemy `documentation
   <https://docs.sqlalchemy.org/en/latest/core/dml.html#sqlalchemy.sql.expression.Insert.values.params.*args>`__.
 - callable with signature ``(pd_table, conn, keys, data_iter)``:
   This can be used to implement a more performant insertion method based on

doc/source/user_guide/scale.rst

@@ -259,7 +259,7 @@ Inspecting the ``ddf`` object, we see a few things
 * There are familiar methods like ``.groupby``, ``.sum``, etc.
 * There are new attributes like ``.npartitions`` and ``.divisions``
 
-The partitions and divisions are how Dask parallizes computation. A **Dask**
+The partitions and divisions are how Dask parallelizes computation. A **Dask**
 DataFrame is made up of many **Pandas** DataFrames. A single method call on a
 Dask DataFrame ends up making many pandas method calls, and Dask knows how to
 coordinate everything to get the result.