pandas-plots 0.8.2__tar.gz → 0.8.3__tar.gz

{pandas-plots-0.8.2/src/pandas_plots.egg-info → pandas-plots-0.8.3}/PKG-INFO

@@ -1,19 +1,14 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.8.2
+Version: 0.8.3
 Summary: A collection of helper for table handling and vizualization
-Author-email: smeisegeier <dsexterDSDo@googlemail.com>
-License: Copyright 2024 smeisegeier
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-        
-Project-URL: homepage, https://github.com/smeisegeier/pandas-plots
-Project-URL: repository, https://github.com/smeisegeier/pandas-plots
-Keywords: tables,pivot,plotly,venn,plot,vizualization
+Home-page: https://github.com/smeisegeier/pandas-plots
+Author: smeisegeier
+Author-email: dexterDSDo@googlemail.com
+License: MIT License
+Project-URL: Documentation, https://github.com/smeisegeier/pandas-plots
+Project-URL: Source Code, https://github.com/smeisegeier/pandas-plots
+Project-URL: Bug Tracker, https://github.com/smeisegeier/pandas-plots/issues
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
@@ -47,7 +42,7 @@ pip install pandas-plots -U
 include in python
 
 ```python
-from pandas_plots import tbl, plt, ven
+from pandas_plots import tbl, pls, ven
 ```
 
 ## example
@@ -57,7 +52,7 @@ from pandas_plots import tbl, plt, ven
 import seaborn as sb
 df = sb.load_dataset('taxis')
 
-plt.plot_box(df['fare'], height=400, violin=True)
+pls.plot_box(df['fare'], height=400, violin=True)
 ```
 
 ![plot_box](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-13-00-40-27.png?raw=true)
@@ -73,7 +68,7 @@ It is subdivided into:
   - `pivot_df()` gets a pivot table of a 3 column dataframe
   - 🆕 `show_num_df()` displays a table as styled version with additional information
 
-- `plt` for plotly visualizations
+- `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plots_bars()` a standardized bar plot
@@ -90,6 +85,8 @@ It is subdivided into:
 - `txt` includes some text based utilities
   - `wrap` formats strings or lists to a given width to fit nicely on the screen
 
+> note: theming can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+
 ## more examples
 
 ```python
@@ -110,24 +107,22 @@ tbl.pivot_df(df[['color', 'payment', 'fare']])
 # show venn diagram for 3 sets
 from pandas_plots import ven
 
-set_a = set(df.pickup_zone)
-set_b = set(df.dropoff_zone)
-set_c = set(df['pickup_borough'])
+set_a = {'ford','ferrari','mercedes', 'bmw'}
+set_b = {'opel','bmw','bentley','audi'}
+set_c = {'ferrari','bmw','chrysler','renault','peugeot','fiat'}
 _df, _details = ven.show_venn3(
-    "taxis",
-    set_a,
-    "pick",
-    set_b,
-    "drop",
+    title="taxis",
+    a_set=set_a,
+    a_label="cars1",
+    b_set=set_b,
+    b_label="cars2",
     c_set=set_c,
-    c_label="borough",
+    c_label="cars3",
     verbose=0,
     size=8,
 )
 ```
 
-![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-17-11-43-46.png?raw=true)
+![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-19-20-49-52.png?raw=true)
 
 ## dependencies
-
-<!-- todo add themeing hint -->

{pandas-plots-0.8.2 → pandas-plots-0.8.3}/README.md

@@ -13,7 +13,7 @@ pip install pandas-plots -U
 include in python
 
 ```python
-from pandas_plots import tbl, plt, ven
+from pandas_plots import tbl, pls, ven
 ```
 
 ## example
@@ -23,7 +23,7 @@ from pandas_plots import tbl, plt, ven
 import seaborn as sb
 df = sb.load_dataset('taxis')
 
-plt.plot_box(df['fare'], height=400, violin=True)
+pls.plot_box(df['fare'], height=400, violin=True)
 ```
 
 ![plot_box](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-13-00-40-27.png?raw=true)
@@ -39,7 +39,7 @@ It is subdivided into:
   - `pivot_df()` gets a pivot table of a 3 column dataframe
   - 🆕 `show_num_df()` displays a table as styled version with additional information
 
-- `plt` for plotly visualizations
+- `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plots_bars()` a standardized bar plot
@@ -56,6 +56,8 @@ It is subdivided into:
 - `txt` includes some text based utilities
   - `wrap` formats strings or lists to a given width to fit nicely on the screen
 
+> note: theming can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+
 ## more examples
 
 ```python
@@ -76,24 +78,22 @@ tbl.pivot_df(df[['color', 'payment', 'fare']])
 # show venn diagram for 3 sets
 from pandas_plots import ven
 
-set_a = set(df.pickup_zone)
-set_b = set(df.dropoff_zone)
-set_c = set(df['pickup_borough'])
+set_a = {'ford','ferrari','mercedes', 'bmw'}
+set_b = {'opel','bmw','bentley','audi'}
+set_c = {'ferrari','bmw','chrysler','renault','peugeot','fiat'}
 _df, _details = ven.show_venn3(
-    "taxis",
-    set_a,
-    "pick",
-    set_b,
-    "drop",
+    title="taxis",
+    a_set=set_a,
+    a_label="cars1",
+    b_set=set_b,
+    b_label="cars2",
     c_set=set_c,
-    c_label="borough",
+    c_label="cars3",
     verbose=0,
     size=8,
 )
 ```
 
-![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-17-11-43-46.png?raw=true)
+![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-19-20-49-52.png?raw=true)
 
 ## dependencies
-
-<!-- todo add themeing hint -->

pandas-plots-0.8.3/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires      = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+# [project]
+# name = "pandas-plots"
+# version = "0.8.2"
+# requires-python = ">=3.10"
+# description = "A collection of helper for table handling and vizualization"
+# readme = "README.md"
+# authors = [{ name = "smeisegeier", email = "dexterDSDo@googlemail.com" }]
+# license = { text = "MIT licence" }
+# # license = { file = "LICENSE" }
+# classifiers = [
+#     "License :: OSI Approved :: MIT License",
+#     "Programming Language :: Python :: 3",
+#     "Programming Language :: Python :: 3.10",
+#     'Development Status :: 4 - Beta',
+#     'Intended Audience :: Science/Research',
+#     'Operating System :: OS Independent',
+#     'Topic :: Scientific/Engineering'    
+# ]
+# keywords = ["tables", "pivot", "plotly", "venn", "plot", "vizualization"]
+# dependencies = [
+#     "pandas >= 2.0.0",
+#     "plotly >= 5.18.0",
+#     "matplotlib >= 3.8.2",
+#     "matplotlib-venn >= 0.11.10",
+#     "seaborn >= 0.13.2",
+#     "sqlalchemy < 2.0.0",
+#     "Jinja2 >= 3.1.3",
+# ]
+
+# # [project.optional-dependencies]
+# # dev = ["black", "bumpver", "isort", "pip-tools", "pytest"]
+
+# [project.urls]
+# homepage = "https://github.com/smeisegeier/pandas-plots"
+# repository = "https://github.com/smeisegeier/pandas-plots"
+
+# # [project.scripts]
+# # realpython = "reader.__main__:main"

pandas-plots-0.8.3/setup.cfg

@@ -0,0 +1,39 @@
+[metadata]
+name = pandas-plots
+version = 0.8.3
+author = smeisegeier
+author_email = dexterDSDo@googlemail.com
+description = A collection of helper for table handling and vizualization
+long_description = file: README.md
+long_description_content_type = text/markdown
+license = MIT License
+license_files = LICENSE
+url = https://github.com/smeisegeier/pandas-plots
+project_urls = 
+	Documentation   = https://github.com/smeisegeier/pandas-plots
+	Source Code     = https://github.com/smeisegeier/pandas-plots
+	Bug Tracker     = https://github.com/smeisegeier/pandas-plots/issues
+classifiers = 
+	License :: OSI Approved :: MIT License
+	Programming Language :: Python :: 3
+	Programming Language :: Python :: 3.10
+	Development Status :: 4 - Beta
+	Intended Audience :: Science/Research
+	Operating System :: OS Independent
+	Topic :: Scientific/Engineering
+
+[options]
+python_requires = >=3.10
+install_requires = 
+	pandas >= 2.0.0
+	plotly >= 5.18.0
+	matplotlib >= 3.8.2
+	matplotlib-venn >= 0.11.10
+	seaborn >= 0.13.2
+	sqlalchemy < 2.0.0
+	Jinja2 >= 3.1.3
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

pandas-plots-0.8.2/src/pandas_plots/plt.py → pandas-plots-0.8.3/src/pandas_plots/pls.py

@@ -27,7 +27,7 @@ def plot_quadrants(
                 columns axis
                 values (can be derived as cnt=1)
             df columns must contain 2 values
-        title (str, optional): The title for the heatmap. Defaults to None.
+        title (str, optional): The title for the heatmap to override the default. 
         caption (str, optional): The caption for the heatmap. Defaults to None.
 
     Returns:
@@ -61,7 +61,7 @@ def plot_quadrants(
     n = heat_wide.sum().sum()
     heat_label = heat_wide.map(lambda x: f'{x:_}\n({x/n*100:.1f}%)')
     
-    
+    # * seaborn. use less fancy stuff :)
     caption= f'#{caption.lower()}, ' if caption else 'heatmap, '
 
     # * plot
@@ -96,7 +96,8 @@ def plot_stacked_bars(
     top_n_color: int = 0,
     dropna: bool = False,
     swap: bool = False,
-    normalize: Literal['values','bars',False] = False,
+    normalize: bool = False,
+    relative: bool = False,
     orientation: Literal["h", "v"] = "v",
     height: int=500,
     width: int=2000,
@@ -119,7 +120,8 @@ def plot_stacked_bars(
     - top_n_index: int = 0 - The number of top colors to include in the plot. WARNING: this forces distribution to 100% on a subset
     - dropna: bool = False - Whether to include NULL values in the plot.
     - swap: bool = False - Whether to swap the x-axis and y-axis.
-    - normalize: Literal['values','bars',False] = False - The normalization method for the bars.
+    - normalize: bool = False - Whether to normalize the values.
+    - relative: bool = False - Whether to show relative values as bars instead of absolute.
     - orientation: Literal["h", "v"] = "v" - The orientation of the plot.
     - height: int = 500 - The height of the plot.
     - width: An optional integer indicating the width of the chart. Default is 2000.
@@ -246,7 +248,7 @@ def plot_stacked_bars(
     )
     
     # * ignore if bar mode is on 
-    if normalize != 'bars':
+    if not relative:
         if orientation == "v":
             _fig.update_yaxes(range=[0, bar_max])
         else:
@@ -269,12 +271,12 @@ def plot_stacked_bars(
     _fig.update_xaxes(
         showgrid=True, 
         gridwidth=1,
-        dtick=.05 if orientation == "h" and normalize == 'values' else 5 if orientation == "h" and normalize == 'bars' else None,
+        dtick=.05 if orientation == "h" and normalize else 5 if orientation == "h" and relative else None,
         )
     _fig.update_yaxes(
         showgrid=True, 
         gridwidth=1,
-        dtick=.05 if orientation == "v" and normalize == 'values' else 5 if orientation == "v" and normalize == 'bars' else None,
+        dtick=.05 if orientation == "v" and normalize else 5 if orientation == "v" and relative else None,
         )
 
     # * sorting is in a weird spot, do a 1:1 matrix
@@ -317,7 +319,7 @@ def plot_bars(
     - dropna: A boolean indicating whether to drop NaN values from the chart. Default is False.
     - orientation: A string indicating the orientation of the chart. It can be either "h" for horizontal or "v" for vertical. Default is "v".
     - sort_values: A boolean indicating whether to sort the values in the chart. Default is False.
-    - nomalize: A boolean indicating whether to inluce pct values in the chart. Default is False.
+    - nomalize: A boolean indicating whether to show pct values in the chart. Default is False.
     - height: An optional integer indicating the height of the chart. Default is 500.
     - width: An optional integer indicating the width of the chart. Default is 2000.
     - title: An optional string indicating the title of the chart. If not provided, the title will be the name of the index column.
@@ -467,7 +469,7 @@ def plot_bars(
 
 def plot_box(
     ser: pd.Series, 
-    points: Literal['all', 'outliers', 'suspectedoutlieres', False] = False,
+    points: Literal['all', 'outliers', 'suspectedoutlieres', None] = None,
     precision: int=2,
     height: int=200,
     width: int=1200,
@@ -481,7 +483,7 @@ def plot_box(
 
     Args:
         ser: The pandas Series to plot.
-        points: The type of points to plot on the box plot ('all', 'outliers', 'suspectedoutliers', False).
+        points: The type of points to plot on the box plot ('all', 'outliers', 'suspectedoutliers', None).
         precision: The precision of the annotations.
         height: The height of the plot.
         width: The width of the plot.
@@ -550,7 +552,7 @@ def plot_box(
 def plot_boxes(
     df: pd.DataFrame,
     caption: str=None,
-    points: Literal["all", "outliers", "suspectedoutliers", False] = False,
+    points: Literal["all", "outliers", "suspectedoutliers", None] = None,
     precision: int = 2,
     height: int = 600,
     width: int = 800,
@@ -563,7 +565,7 @@ def plot_boxes(
     Args:
         df (pd.DataFrame): The input DataFrame with two columns, where the first column is string type and the second column is numeric.
         caption (str): The caption for the plot.
-        points (Literal["all", "outliers", "suspectedoutliers", True]): The points to be plotted.
+        points (Literal["all", "outliers", "suspectedoutliers", None]): The points to be plotted.
         precision (int): The precision for rounding the statistics.
         height (int): The height of the plot.
         width (int): The width of the plot.

{pandas-plots-0.8.2 → pandas-plots-0.8.3}/src/pandas_plots/tbl.py

@@ -66,12 +66,13 @@ def describe_df(
     if len(df) == 0:
         print(f"DataFrame is empty!")
         return
-    # todo maybe show col list only once
+
     print(f"🔵 {'*'*3} df: {caption} {'*'*3}")
     print(f"🟣 shape: ({df.shape[0]:_}, {df.shape[1]}) columns: {df.columns.tolist()} ")
     print(f"🟣 duplicates: {df.duplicated().sum():_}")
     print(f"🟣 missings: {dict(df.isna().sum())}")
     print("--- column uniques (all)")
+    print(f"🟠 index {txt.wrap(df.index.tolist()[:top_n_uniques])}")
     def get_uniques_header(col: str):
         # * sorting has issues when col is of mixed type (object)
         if df[col].dtype=='object':
@@ -166,64 +167,45 @@ def describe_df(
     fig.update_layout(template="plotly_dark" if os.getenv("THEME") == "dark" else "plotly")
     fig.show(renderer)
 
-# todo rebuild into using show_df, this also affects api
 def pivot_df(
     df: pd.DataFrame,
     dropna: bool = False,
-    normalize: bool = False,
-    normalize_mixed: bool = False,
     swap: bool = False,
     top_n_index: int = 0,
     top_n_columns: int = 0,
-    data_bar_axis: Literal["x", "y", "all", False] = "all",
+    data_bar_axis: Literal["x", "y", "xy", None] = "xy",
+    pct_axis: Literal["x", "xy", None] = "xy",
     precision: int = 0,
-    totals: Literal["x", "y", "all", False] = "all",
-# ) -> pd.DataFrame:
-) -> None:
+    show_totals: bool = True,
+) -> pd.DataFrame:
     """
-    Pivots a DataFrame and performs various operations based on the specified parameters.
-
-    Parameters:
-        df (pd.DataFrame): The DataFrame to be pivoted.
-        dropna (bool, optional): Whether to drop rows with missing values. Defaults to False.
-        normalize (bool, optional): Whether to normalize the values. Defaults to False.
-        normalize_mixed (bool, optional): Whether to show mixed values. Defaults to False. OVERRIDES "normalize"
-        swap (bool, optional): Whether to swap the index and column names. Defaults to False.
-        top_n_index (int, optional): The number of top indexes to consider. Defaults to 0.
-        top_n_columns (int, optional): The number of top columns to consider. Defaults to 0.
-        data_bar_axis (Literal["x", "y", "all", False], optional): The axis to apply data bars on. Defaults to "all".
-        precision (int, optional): The precision of the values. Defaults to 0.
-        totals (Literal["x", "y", "all", False], optional): Whether to show totals. Defaults to "all".
-
+    A function to pivot a DataFrame based on specified parameters and return the result as a new DataFrame.
+    
+    Args:
+        df (pd.DataFrame): The input DataFrame to be pivoted.
+        dropna (bool, optional): Whether to drop NaN values. Defaults to False.
+        swap (bool, optional): Whether to swap index and column. Defaults to False.
+        top_n_index (int, optional): The number of top index values to consider. Defaults to 0.
+        top_n_columns (int, optional): The number of top column values to consider. Defaults to 0.
+        data_bar_axis (Literal["x", "y", "xy", None], optional): The axis for displaying data bars. Defaults to "xy".
+        pct_axis (Literal["x", "xy", None], optional): The axis for displaying percentages. Defaults to None.
+        precision (int, optional): The precision for displaying values. Defaults to 0.
+        show_totals (bool, optional): Whether to show totals in the result. Defaults to False.
+        
     Returns:
-        None
-    Usage:
-    pivot_df(
-        df,
-        dropna=True,
-        normalize=True,
-        normalize_mixed=True
-        swap=True,
-        top_n_index=5,
-        top_n_columns=2,
-        data_bar_axis=None,
-        precision=2,
-    )
+        pd.DataFrame: The pivoted DataFrame.
     """
-
-    theme = os.getenv('THEME') or 'light'
-
-    color_highlight = 'lightblue' if theme == 'light' else 'darkgrey'
-    color_zeros = 'grey' if theme == 'light' else 'grey'
-    color_pct = 'grey' if theme == 'light' else 'yellow'
-    color_values = 'black' if theme == 'light' else 'white'
-    color_minus = 'red' if theme == 'light' else 'red'
+    # * ensure arguments match parameter definition
+    if (pct_axis and pct_axis not in ["x", "xy"]) or (data_bar_axis and  data_bar_axis not in ["x","y","xy"]):
+        print(f"❌ axis not supported")
+        return
 
     if len(df.columns) != 3:
-        print("df must have exactly 3 columns")
+        print("❌ df must have exactly 3 columns")
         return
+
     if not pd.api.types.is_numeric_dtype(df.iloc[:, 2]):
-        print("3rd column must be numeric")
+        print("❌ 3rd column must be numeric")
         return
 
     col_index = df.columns[0] if not swap else df.columns[1]
@@ -237,23 +219,6 @@ def pivot_df(
         df.dropna(inplace=True, subset=[col_index])
         df.dropna(inplace=True, subset=[col_column])
 
-    # * now calculate n, after dropna, before top n
-    n = df[col_value].sum()
-
-    if normalize:
-        df[col_value] = df[col_value] / n
-        _formatter = f"{{:_.{precision}%}}"
-    else:
-        # _type= 'int'
-        _formatter = f"{{:_.{precision}f}}"
-
-    if normalize_mixed:
-        _formatter = (
-            lambda x: f"{{:_.0f}} <span style='color: {color_pct}'>({{:.1%}})</span>".format(x, x / n)
-            if x > 0
-            else x
-        )
-
     # * top n indexes
     if top_n_index > 0:
         # * get top n -> series
@@ -266,7 +231,7 @@ def pivot_df(
         # * only process top n indexes. this does not change pct values
         df = df[df[col_index].isin(ser_top_n.index)]
 
-    # top n columns
+    # * top n columns
     if top_n_columns > 0:
         # * get top n -> series
         # * on pivot tables (all cells are values) you can also use sum for each column[df.sum(axis=1) > n]
@@ -287,83 +252,36 @@ def pivot_df(
     )
     df = df.fillna(0)  # .astype(_type)
 
-    if totals in(['x','all']):
-        df.loc["Total"] = df.sum(axis=0)
-    if totals in(['y','all']):
-        df.loc[:, "Total"] = df.sum(axis=1)
-
-    out = df.style.map(
-        lambda x: f"color: {color_zeros}"
-        if x == 0
-        else f"color: {color_minus}"
-        if x < 0
-        else f"color: {color_values}"
-    )
-
-    # * apply data bar coloring
-    if data_bar_axis:
-        out.bar(
-            color=f"{color_highlight}",
-            axis=1 if data_bar_axis == "y" else 0 if data_bar_axis == "x" else None,
-            # props="width: 5%;",
-        )
-
-    # * apply formatter selected above
-    out.format(_formatter)
-
-    # * apply fonts for cells
-    out.set_properties(**{'font-family': 'Courier'})
-
-    # * apply fonts for th (inkl. index)
-    _props=[
-                # ("font-size", "10pt"),
-                # ("font-weight", "bold"),
-                # ("font-family", "Courier"),
-                ("text-align", "right")
-                ]
-    out.set_table_styles(
-        [
-            dict(selector="th", props=_props),
-            # dict(selector="th:nth-child(1)", props=_props),
-        ]
-    )
-    # todo return out
-    display(out)
-    return
+    return show_num_df(df, show_totals=show_totals, data_bar_axis=data_bar_axis, pct_axis=pct_axis, swap=swap, precision=precision)
 
-# todo check if date col can be included
 def show_num_df(
     df,
-    axis: Literal["x", "all", None] = None,
     show_totals: bool = False,
-    show_bars: bool = False,
-    show_pct: bool = False,
+    data_bar_axis: Literal["x","y","xy", None] = None,
+    pct_axis: Literal["x", "xy", None] = None,
     swap: bool = False,
-    precision=0,
+    precision: int=0,
 ):
     """
-    Generate a styled display of a DataFrame, including options for axis, totals, bars, percentages, and precision.
-    Table must contain numeric data only (int / float).
+    A function to display a DataFrame with various options for styling and formatting, including the ability to show totals, apply data bar coloring, and control the display precision. 
 
     Parameters:
-    - df: DataFrame to display
-    - axis: Axis to show additional information on ("x", "all", None)
-    - show_totals: Whether to show totals
-    - show_bars: Whether to show data bars
-    - show_pct: Whether to show percentages
-    - swap: Whether to transpose the DataFrame
-    - precision: Number of decimal places for formatting
-
-    Returns:
-    - out: Styled display of the DataFrame
+    - df: the DataFrame to display
+    - show_totals: a boolean indicating whether to show totals
+    - data_bar_axis: a Literal indicating the axis for applying data bar coloring ["x","y","xy", None]
+    - pct_axis: a Literal indicating the directions for displaying percentages ["x","xy", None]. "x" means sum up pct per column
+    - swap: a boolean indicating whether to swap the axes
+    - precision: an integer indicating the display precision
+
+    The function returns a styled representation of the DataFrame.
     """
     # * ensure arguments match parameter definition
     if any([df[col].dtype.kind not in ['i','u','f'] for col in df.columns]) == True:
         print(f"❌ table must contain numeric data only")
         return
     
-    if axis not in ["x", "all"]:
-        print(f"❌ axis '{axis}' not supported")
+    if (pct_axis and pct_axis not in ["x", "xy"]) or (data_bar_axis and  data_bar_axis not in ["x","y","xy"]):
+        print(f"❌ axis not supported")
         return
 
     theme = os.getenv("THEME") or "light"
@@ -372,9 +290,8 @@ def show_num_df(
     df_ = df.copy() if not swap else df.T.copy()
     
     # * alter _df, add totals
-    if show_totals and axis:
+    if show_totals:
         df_.loc["Total"] = df_.sum(axis=0)
-    if show_totals and axis == "all":
         df_.loc[:, "Total"] = df_.sum(axis=1)
 
     # * derive style
@@ -387,14 +304,14 @@ def show_num_df(
     color_minus = "red" if theme == "light" else "red"
 
     # * apply data bar coloring
-    if show_bars and axis:
+    if data_bar_axis:
         out.bar(
             color=f"{color_highlight}",
-            axis= 0 if axis == "x" else None,
+            axis= 0 if data_bar_axis == "x" else 1 if data_bar_axis == "y" else None,
         )
 
     # * all cell formatting in one place
-    # hack call hierarchy is not very well organized. all options land here, even if no cellwise formatting is applied
+    # call hierarchy is not very well organized. all options land here, even if no cellwise formatting is applied
     def format_cell(cell, sum, show_pct):
         if cell == 0:
             return f'<span style="color: {color_zeros}">{cell:.0f}</span>'
@@ -406,15 +323,14 @@ def show_num_df(
         return f'{cell:_.{precision}f}'
 
     # * build pct formatting
-    
-    if axis =='x':
+    if pct_axis =='x':
         # * totals on either axis influence the sum
-        divider = 2 if show_totals and axis in(['x','all']) else 1
+        divider = 2 if show_totals else 1
         # * cell formatting to each column instead of altering values w/ df.apply
         # * uses dictionary comprehension, and a lambda function with two input variables
         col_sums = df_.sum() / divider
         formatter = {
-            col: lambda x, col=col: format_cell(x, col_sums[col], show_pct) for col in df_.columns
+            col: lambda x, col=col: format_cell(x, col_sums[col], pct_axis) for col in df_.columns
         }
 
     # ? y is not implemented, needs row wise formatting
@@ -424,11 +340,11 @@ def show_num_df(
     #         row: lambda x, row=row: format_cell(x, row_sums[row]) for row in _df.index
     #     }
 
-    elif axis=='all':
-        divider = 2 if show_totals and axis in(['x']) else 4 if show_totals and axis == 'all' else 1
+    elif pct_axis=='xy':
+        divider = 4 if show_totals else 1
         n = df_.sum().sum() / divider
         formatter = {
-            col: lambda x, col=col: format_cell(x, n, show_pct) for col in df_.columns
+            col: lambda x, col=col: format_cell(x, n, pct_axis) for col in df_.columns
         }
     else:
         # * 
@@ -437,6 +353,22 @@ def show_num_df(
         }
 
     out.format(formatter=formatter)
-    return out
 
-# display(test(df1_1_tum, axis="x", show_totals=True, show_bars=True, show_pct=False, swap=False, precision=0))
+    # * apply fonts for cells
+    out.set_properties(**{'font-family': 'Courier'})
+
+    # * apply fonts for th (inkl. index)
+    _props=[
+                # ("font-size", "10pt"),
+                # ("font-weight", "bold"),
+                # ("font-family", "Courier"),
+                ("text-align", "right")
+                ]
+    out.set_table_styles(
+        [
+            dict(selector="th", props=_props),
+            # dict(selector="th:nth-child(1)", props=_props),
+        ]
+    )
+
+    return out

{pandas-plots-0.8.2 → pandas-plots-0.8.3/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,19 +1,14 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.8.2
+Version: 0.8.3
 Summary: A collection of helper for table handling and vizualization
-Author-email: smeisegeier <dsexterDSDo@googlemail.com>
-License: Copyright 2024 smeisegeier
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-        
-Project-URL: homepage, https://github.com/smeisegeier/pandas-plots
-Project-URL: repository, https://github.com/smeisegeier/pandas-plots
-Keywords: tables,pivot,plotly,venn,plot,vizualization
+Home-page: https://github.com/smeisegeier/pandas-plots
+Author: smeisegeier
+Author-email: dexterDSDo@googlemail.com
+License: MIT License
+Project-URL: Documentation, https://github.com/smeisegeier/pandas-plots
+Project-URL: Source Code, https://github.com/smeisegeier/pandas-plots
+Project-URL: Bug Tracker, https://github.com/smeisegeier/pandas-plots/issues
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
@@ -47,7 +42,7 @@ pip install pandas-plots -U
 include in python
 
 ```python
-from pandas_plots import tbl, plt, ven
+from pandas_plots import tbl, pls, ven
 ```
 
 ## example
@@ -57,7 +52,7 @@ from pandas_plots import tbl, plt, ven
 import seaborn as sb
 df = sb.load_dataset('taxis')
 
-plt.plot_box(df['fare'], height=400, violin=True)
+pls.plot_box(df['fare'], height=400, violin=True)
 ```
 
 ![plot_box](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-13-00-40-27.png?raw=true)
@@ -73,7 +68,7 @@ It is subdivided into:
   - `pivot_df()` gets a pivot table of a 3 column dataframe
   - 🆕 `show_num_df()` displays a table as styled version with additional information
 
-- `plt` for plotly visualizations
+- `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plots_bars()` a standardized bar plot
@@ -90,6 +85,8 @@ It is subdivided into:
 - `txt` includes some text based utilities
   - `wrap` formats strings or lists to a given width to fit nicely on the screen
 
+> note: theming can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+
 ## more examples
 
 ```python
@@ -110,24 +107,22 @@ tbl.pivot_df(df[['color', 'payment', 'fare']])
 # show venn diagram for 3 sets
 from pandas_plots import ven
 
-set_a = set(df.pickup_zone)
-set_b = set(df.dropoff_zone)
-set_c = set(df['pickup_borough'])
+set_a = {'ford','ferrari','mercedes', 'bmw'}
+set_b = {'opel','bmw','bentley','audi'}
+set_c = {'ferrari','bmw','chrysler','renault','peugeot','fiat'}
 _df, _details = ven.show_venn3(
-    "taxis",
-    set_a,
-    "pick",
-    set_b,
-    "drop",
+    title="taxis",
+    a_set=set_a,
+    a_label="cars1",
+    b_set=set_b,
+    b_label="cars2",
     c_set=set_c,
-    c_label="borough",
+    c_label="cars3",
     verbose=0,
     size=8,
 )
 ```
 
-![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-17-11-43-46.png?raw=true)
+![venn](https://github.com/smeisegeier/pandas-plots/blob/main/img/2024-02-19-20-49-52.png?raw=true)
 
 ## dependencies
-
-<!-- todo add themeing hint -->

{pandas-plots-0.8.2 → pandas-plots-0.8.3}/src/pandas_plots.egg-info/SOURCES.txt

@@ -1,8 +1,9 @@
 LICENSE
 README.md
 pyproject.toml
+setup.cfg
 src/pandas_plots/__init__.py
-src/pandas_plots/plt.py
+src/pandas_plots/pls.py
 src/pandas_plots/sql.py
 src/pandas_plots/tbl.py
 src/pandas_plots/txt.py

pandas-plots-0.8.2/pyproject.toml

@@ -1,41 +0,0 @@
-[build-system]
-requires      = ["setuptools"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "pandas-plots"
-version = "0.8.2"
-requires-python = ">=3.10"
-description = "A collection of helper for table handling and vizualization"
-readme = "README.md"
-authors = [{ name = "smeisegeier", email = "dsexterDSDo@googlemail.com" }]
-license = { file = "LICENSE" }
-classifiers = [
-    "License :: OSI Approved :: MIT License",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
-    'Development Status :: 4 - Beta',
-    'Intended Audience :: Science/Research',
-    'Operating System :: OS Independent',
-    'Topic :: Scientific/Engineering'    
-]
-keywords = ["tables", "pivot", "plotly", "venn", "plot", "vizualization"]
-dependencies = [
-    "pandas >= 2.0.0",
-    "plotly >= 5.18.0",
-    "matplotlib >= 3.8.2",
-    "matplotlib-venn >= 0.11.10",
-    "seaborn >= 0.13.2",
-    "sqlalchemy < 2.0.0",
-    "Jinja2 >= 3.1.3",
-]
-
-# [project.optional-dependencies]
-# dev = ["black", "bumpver", "isort", "pip-tools", "pytest"]
-
-[project.urls]
-homepage = "https://github.com/smeisegeier/pandas-plots"
-repository = "https://github.com/smeisegeier/pandas-plots"
-
-# [project.scripts]
-# realpython = "reader.__main__:main"

pandas-plots-0.8.2/setup.cfg

@@ -1,4 +0,0 @@
-[egg_info]
-tag_build = 
-tag_date = 0
-