[DOC] Fix typos (#1290)

Found via `codespell -L
nam,ans,bage,te,mapp,zar,caf,fro,som,tha,tje,yot,bu,fo,ressources,onl,regon,licens,variabl`

Author: kianmeng

examples/notebooks/Pivoting Data from Wide to Long.ipynb

@@ -3564,7 +3564,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The data above requires extracting `a`, `ab` and `ac` from `1` and `2`. This is another example of a paired column. We could solve this using [pd.wide_to_long](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.wide_to_long.html); infact there is a very good solution from [Stack Overflow](https://stackoverflow.com/a/45124775/7175713)"
+    "The data above requires extracting `a`, `ab` and `ac` from `1` and `2`. This is another example of a paired column. We could solve this using [pd.wide_to_long](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.wide_to_long.html); in fact there is a very good solution from [Stack Overflow](https://stackoverflow.com/a/45124775/7175713)"
    ]
   },
   {

examples/notebooks/anime.ipynb

@@ -55,7 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Supress user warnings when we try overwriting our custom pandas flavor functions\n",
+    "# Suppress user warnings when we try overwriting our custom pandas flavor functions\n",
     "import warnings\n",
     "warnings.filterwarnings('ignore')"
    ]
@@ -1316,7 +1316,7 @@
     "    :param df: A pandas DataFrame.\n",
     "    :param column_name: A `str` indicating which column the split action is to be made.\n",
     "    :param start: optional An `int` for the start index of the slice\n",
-    "    :param stop: optinal  An `int` for the end index of the slice\n",
+    "    :param stop: optional  An `int` for the end index of the slice\n",
     "    :param pat: String or regular expression to split on. If not specified, split on whitespace.\n",
     "\n",
     "    \"\"\"\n",

examples/notebooks/board_games.ipynb

@@ -938,7 +938,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### What is the relationship between games' player numbers, reccomended minimum age, and the game's estimated length?"
+    "### What is the relationship between games' player numbers, recommended minimum age, and the game's estimated length?"
    ]
   },
   {

examples/notebooks/dirty_data.ipynb

@@ -708,7 +708,7 @@
   {
    "cell_type": "markdown",
    "source": [
-    "Note how now we have really nice column names! You might be wondering why I'm not modifying the two certifiation columns -- that is the next thing we'll tackle."
+    "Note how now we have really nice column names! You might be wondering why I'm not modifying the two certification columns -- that is the next thing we'll tackle."
    ],
    "metadata": {}
   },

examples/notebooks/medium_franchise.ipynb

@@ -15,7 +15,7 @@
     "\n",
     "* String operations with regular expressions (with `pandas-favor`)\n",
     "* Data type changes (with `pyjanitor`)\n",
-    "* Split strings in cells into seperate rows (with `pandas-flavor`)\n",
+    "* Split strings in cells into separate rows (with `pandas-flavor`)\n",
     "* Split strings in cells into separate columns (with `pyjanitor` + `pandas-flavor`)\n",
     "* Filter dataframe values based on substring pattern (with `pyjanitor`)\n",
     "* Column value remapping with fuzzy substring matching (with `pyjanitor` + `pandas-flavor`)\n",
@@ -66,7 +66,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Supress user warnings when we try overwriting our custom pandas flavor functions\n",
+    "# Suppress user warnings when we try overwriting our custom pandas flavor functions\n",
     "import warnings\n",
     "warnings.filterwarnings('ignore')"
    ]
@@ -220,7 +220,7 @@
     "# [pandas-flavor]\n",
     "@pf.register_dataframe_method\n",
     "def str_remove(df, column_name: str, pattern: str = ''):\n",
-    "    \"\"\"Remove string patten from a column\n",
+    "    \"\"\"Remove string pattern from a column\n",
     "\n",
     "    Wrapper around df.str.replace()\n",
     "\n",
@@ -595,7 +595,7 @@
     "    column_name: str\n",
     "        Name of the column to be operated on\n",
     "    into: List[str], default to None\n",
-    "        New column names for the splitted columns\n",
+    "        New column names for the split columns\n",
     "    sep: str, default to ''\n",
     "        Separator at which to split the column\n",
     "\n",

janitor/functions/complete.py

@@ -326,7 +326,7 @@ def _computations_complete(
                 # instead of assign (which is also a for loop),
                 # to cater for scenarios where the column_name is not a string
                 # assign only works with keys that are strings
-                # Also, the output wil be floats (for numeric types),
+                # Also, the output will be floats (for numeric types),
                 # even if all the columns could be integers
                 # user can always convert to int if required
                 for column_name, value in fill_value.items():

janitor/functions/conditional_join.py

@@ -798,7 +798,7 @@ def _multiple_conditional_join_le_lt(
         # and then build the remaining indices,
         # using _generate_indices function
         # the aim of this for loop is to see if there is
-        # the possiblity of a range join, and if there is,
+        # the possibility of a range join, and if there is,
         # then use the optimised path
         le_lt = None
         ge_gt = None

janitor/functions/factorize_columns.py

@@ -17,7 +17,7 @@ def factorize_columns(
 
     This method will create a new column with the string `_enc` appended
     after the original column's name.
-    This can be overriden with the suffix parameter.
+    This can be overridden with the suffix parameter.
 
     Internally, this method uses pandas `factorize` method.
     It takes in an optional suffix and keyword arguments also.

mkdocs/devguide.md

@@ -35,7 +35,7 @@ and mount the repository directory inside your Docker container.
 Follow best practices to submit a pull request by making a feature branch.
 Now, hack away, and submit in your pull request!
 
-You shouln't be able to access the cloned repo
+You shouldn't be able to access the cloned repo
 on your local hard drive.
 If you do want local access, then clone the repo locally first
 before selecting "Remote Containers: Open Folder In Container".
@@ -153,7 +153,7 @@ Now you can make your changes locally.
 
 ### Check your environment
 
-To ensure that your environemnt is properly set up, run the following command:
+To ensure that your environment is properly set up, run the following command:
 
 ```bash
 python -m pytest -m "not turtle"
@@ -165,7 +165,7 @@ development and you are ready to contribute 🥳.
 ### Check your code
 
 When you're done making changes, commit your staged files with a meaningful message.
-While we have automated checks that run before code is commited via pre-commit and GitHub Actions
+While we have automated checks that run before code is committed via pre-commit and GitHub Actions
 to run tests before code can be merged,
 you can still manually run the following commands to check that your changes are properly
 formatted and that all tests still pass.
@@ -188,7 +188,7 @@ To do so:
     the optional dependencies (e.g. `rdkit`) installed.
 
 !!! info
-    * pre-commit **does not run** your tests locally rather all tests are run in continous integration (CI).
+    * pre-commit **does not run** your tests locally rather all tests are run in continuous integration (CI).
     * All tests must pass in CI before the pull request is accepted,
     and the continuous integration system up on GitHub Actions
     will help run all of the tests before they are committed to the repository.

nbconvert_config.py

@@ -269,7 +269,7 @@
 #
 #  you can overwrite :meth:`preprocess_cell` to apply a transformation
 #  independently on each cell or :meth:`preprocess` if you prefer your own logic.
-#  See corresponding docstring for informations.
+#  See corresponding docstring for information.
 #
 #  Disabled by default and can be enabled via the config by
 #      'c.YourPreprocessorName.enabled = True'
@@ -430,7 +430,7 @@
 # DebugWriter(WriterBase) configuration
 # ------------------------------------------------------------------------------
 
-## Consumes output from nbconvert export...() methods and writes usefull
+## Consumes output from nbconvert export...() methods and writes useful
 #  debugging information to the stdout.  The information includes a list of
 #  resources that were extracted from the notebook(s) during export.
 

tests/functions/test_coalesce.py

@@ -56,7 +56,7 @@ def test_coalesce_without_target(df):
 
 @pytest.mark.functions
 def test_coalesce_without_delete():
-    """Test ouptut if nulls remain and `default_value` is provided."""
+    """Test output if nulls remain and `default_value` is provided."""
     df = pd.DataFrame(
         {"s1": [np.nan, np.nan, 6, 9, 9], "s2": [np.nan, 8, 7, 9, 9]}
     )

tests/functions/test_pivot_wider.py

@@ -217,7 +217,7 @@ def test_pivot_long_wide_long():
     assert_frame_equal(result, df_in)
 
 
-@pytest.mark.xfail(reason="doesnt match, since pivot implicitly sorts")
+@pytest.mark.xfail(reason="doesn't match, since pivot implicitly sorts")
 def test_pivot_wide_long_wide():
     """
     Test that transformation from pivot_longer to wider and

tests/functions/test_select_columns.py

@@ -382,7 +382,7 @@ def test_callable_length(numbers):
 
 @pytest.mark.functions
 def test_callable_dtype(dataframe):
-    """Test output when selecting columnns based on dtype"""
+    """Test output when selecting columns based on dtype"""
     expected = dataframe.select_dtypes("number")
     actual = dataframe.select_columns(is_numeric_dtype)
     assert_frame_equal(expected, actual)

tests/functions/test_sort_column_value_order.py

@@ -2,7 +2,7 @@
 Below, company_sales and company_sales_2 are both dfs.
 
 company_sales_2 is inverted, April is the first month
-    where in comapny_sales Jan is the first month
+    where in company_sales Jan is the first month
 
 The values found in each row are the same
     company_sales's Jan row contains the
@@ -14,7 +14,7 @@
 
 Test 3 asserts that company_sales_2 and
     company_sales with columns sorted
-    will become equivilent, meaning
+    will become equivalent, meaning
     the columns have been successfully ordered.
 """