1.0.7

Author: akanz1

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "klib"
-version = "1.0.6"
+version = "1.0.7"
 description = "Customized data preprocessing functions for frequent tasks."
 authors = ["Andreas Kanz <[email protected]>"]
 license = "MIT"

src/klib/__init__.py

@@ -1,6 +1,6 @@
 """
 Data Science Module for Python
-==================================
+===============================
 klib is an easy to use Python library of customized functions for cleaning and \
 analyzing data.
 """

src/klib/_version.py

@@ -1,2 +1,3 @@
-"""Current version of klib"""
-__version__ = "1.0.6"
+"""Current version of klib."""
+
+__version__ = "1.0.7"

src/klib/clean.py

@@ -1,5 +1,4 @@
-"""
-Functions for data cleaning.
+"""Functions for data cleaning.
 
 :author: Andreas Kanz
 """
@@ -279,7 +278,7 @@ def data_cleaning(
         changed to categorical, by default 0.03
     cat_exclude : Optional[list[str]], optional
         List of columns to exclude from categorical conversion, by default None
-    clean_column_names: bool, optional
+    clean_col_names: bool, optional
         Cleans the column names and provides hints on duplicate and long names, by \
         default True
     show : Optional[Literal["all", "changes"]], optional

src/klib/describe.py

@@ -1,5 +1,4 @@
-"""
-Functions for descriptive analytics.
+"""Functions for descriptive analytics.
 
 :author: Andreas Kanz
 
@@ -18,6 +17,7 @@
 from matplotlib import ticker
 from matplotlib.colors import LinearSegmentedColormap
 from matplotlib.colors import to_rgb
+from matplotlib.gridspec import GridSpec
 
 from klib.utils import _corr_selector
 from klib.utils import _missing_vals
@@ -38,7 +38,7 @@ def cat_plot(
     bottom: int = 3,
     bar_color_top: str = "#5ab4ac",
     bar_color_bottom: str = "#d8b365",
-):
+) -> GridSpec:
     """Two-dimensional visualization of the number and frequency of categorical \
         features.
 
@@ -263,7 +263,7 @@ def corr_plot(
     annot: bool = True,
     dev: bool = False,
     **kwargs,
-):
+) -> plt.Axes:
     """Two-dimensional visualization of the correlation between feature-columns \
         excluding NA values.
 
@@ -311,7 +311,7 @@ def corr_plot(
         Display figure settings in the plot by setting dev = True. If False, the \
         settings are not displayed, by default False
 
-    Keyword Arguments : optional
+    kwargs : optional
         Additional elements to control the visualization of the plot, e.g.:
 
             * mask: bool, default True
@@ -615,7 +615,7 @@ def missingval_plot(
     figsize: tuple = (20, 20),
     sort: bool = False,
     spine_color: str = "#EEEEEE",
-):
+) -> GridSpec:
     """Two-dimensional visualization of the missing values in a dataset.
 
     Parameters

src/klib/utils.py

@@ -141,7 +141,7 @@ def _diff_report(
     print(f"Reduced memory by at least: {round(mem_change,3)} MB (-{mem_perc}%)\n")
 
 
-def _print_cleaning_details(arg0, arg1, arg2, arg3):
+def _print_cleaning_details(arg0, arg1, arg2, arg3) -> None:
     print(arg0)
     print(f"dtypes:\n{arg1.dtypes.value_counts()}")
     print(f"\nNumber of rows: {str(arg1.shape[0]).rjust(8)}")
@@ -232,49 +232,49 @@ def _missing_vals(data: pd.DataFrame) -> MVResult:
     }
 
 
-def _validate_input_bool(value: bool, desc):
+def _validate_input_bool(value: bool, desc) -> None:
     if not isinstance(value, bool):
         raise TypeError(
             f"Input value for '{desc}' is {type(value)} but should be a boolean."
         )
 
 
-def _validate_input_int(value: int, desc):
+def _validate_input_int(value: int, desc) -> None:
     if not isinstance(value, int):
         raise TypeError(
             f"Input value for '{desc}' is {type(value)} but should be an integer."
         )
 
 
-def _validate_input_range(value, desc, lower, upper):
+def _validate_input_range(value, desc, lower, upper) -> None:
     if value < lower or value > upper:
         raise ValueError(
             f"'{desc}' = {value} but should be {lower} <= '{desc}' <= {upper}."
         )
 
 
-def _validate_input_smaller(value1, value2, desc):
+def _validate_input_smaller(value1, value2, desc) -> None:
     if value1 > value2:
         raise ValueError(
             f"The first input for '{desc}' should be smaller or equal to the second."
         )
 
 
-def _validate_input_sum_smaller(limit, desc, *args):
+def _validate_input_sum_smaller(limit, desc, *args) -> None:
     if sum(args) > limit:
         raise ValueError(
             f"The sum of input values for '{desc}' should be less or equal to {limit}."
         )
 
 
-def _validate_input_sum_larger(limit, desc, *args):
+def _validate_input_sum_larger(limit, desc, *args) -> None:
     if sum(args) < limit:
         raise ValueError(
             f"The sum of input values for '{desc}' should be larger/equal to {limit}."
         )
 
 
-def _validate_input_num_data(value: pd.DataFrame, desc):
+def _validate_input_num_data(value: pd.DataFrame, desc) -> None:
     if value.select_dtypes(include=["number"]).empty:
         raise TypeError(
             f"Input value for '{desc}' should contain at least one numerical column."