pandas-plots 0.12.8__tar.gz → 0.12.10__tar.gz

{pandas_plots-0.12.8/src/pandas_plots.egg-info → pandas_plots-0.12.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.8
+Version: 0.12.10
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -96,7 +96,7 @@ tbl.show_num_df(
   - `plot_histogram()` histogram for one or more **numerical** columns
   - `plot_joints()` a joint plot for **exactly two numerical** columns
   - `plot_quadrants()` quickly shows a 2x2 heatmap
-  - 🆕 `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
+  - `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
 <br>
 
 - `ven` offers functions for _venn diagrams_
@@ -113,7 +113,7 @@ tbl.show_num_df(
   - `add_datetime_col()` adds a datetime columns to a dataframe (chainable)
   - `show_package_version` prints version of a list of packages
   - `get_os` helps to identify and ensure operating system at runtime
-  - `🆕 add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
+  - `add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
 <br>
 
 - `pii` has routines for handling of personally identifiable information

{pandas_plots-0.12.8 → pandas_plots-0.12.10}/README.md

@@ -61,7 +61,7 @@ tbl.show_num_df(
   - `plot_histogram()` histogram for one or more **numerical** columns
   - `plot_joints()` a joint plot for **exactly two numerical** columns
   - `plot_quadrants()` quickly shows a 2x2 heatmap
-  - 🆕 `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
+  - `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
 <br>
 
 - `ven` offers functions for _venn diagrams_
@@ -78,7 +78,7 @@ tbl.show_num_df(
   - `add_datetime_col()` adds a datetime columns to a dataframe (chainable)
   - `show_package_version` prints version of a list of packages
   - `get_os` helps to identify and ensure operating system at runtime
-  - `🆕 add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
+  - `add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
 <br>
 
 - `pii` has routines for handling of personally identifiable information

{pandas_plots-0.12.8 → pandas_plots-0.12.10}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pandas-plots
-version = 0.12.8
+version = 0.12.10
 author = smeisegeier
 author_email = dexterDSDo@googlemail.com
 description = A collection of helper for table handling and visualization

{pandas_plots-0.12.8 → pandas_plots-0.12.10}/src/pandas_plots/pls.py

@@ -1,4 +1,7 @@
 from pathlib import Path
+import warnings
+
+warnings.filterwarnings("ignore")
 
 import os
 from typing import Optional, Literal
@@ -45,7 +48,7 @@ def aggregate_data(
         sort_values (bool): Whether to sort values in descending order based on group sum. Defaults to False.
 
     Returns:
-        pd.DataFrame: Aggregated and filtered dataset.
+        pd.DataFrame: Aggregated and filtered dataset (but not sorted!)
     """
 
     for col in ["index", "col", "facet"]:  # Skip 'value' column (numeric)
@@ -62,6 +65,7 @@ def aggregate_data(
             .sort_values(ascending=False)[:top_n_index or None]
             .index
         )
+    
     else:
         top_indexes = aggregated_df["index"].sort_values().unique()[:top_n_index or None]
 
@@ -100,28 +104,6 @@ def aggregate_data(
 
     aggregated_df = aggregated_df[aggregated_df["facet"].isin(top_facets)]
 
-    # * Ensure facets are sorted alphabetically
-    aggregated_df["facet"] = pd.Categorical(
-        values=aggregated_df["facet"],
-        categories=top_facets,
-        ordered=True,
-    )
-    
-    aggregated_df["index"] = pd.Categorical(
-        values=aggregated_df["index"],
-        categories=top_indexes,
-        ordered=True,
-    )
-    
-    aggregated_df["col"] = pd.Categorical(
-        values=aggregated_df["col"],
-        categories=top_colors,
-        ordered=True,
-    )
-
-    
-    # aggregated_df = aggregated_df.sort_values(by="facet")
-
     return aggregated_df
 
 
@@ -381,14 +363,6 @@ def plot_stacked_bars(
 
     df = aggregated_df.copy()
 
-    columns = sorted(
-        df.groupby("col", observed=True)["value"]
-        .sum()
-        .sort_values(ascending=False)
-        .index.tolist()
-    )
-    column_colors = assign_column_colors(columns, color_palette, null_label)
-
     caption = _set_caption(caption)
 
     # * after grouping add cols for pct and formatting
@@ -402,34 +376,44 @@ def plot_stacked_bars(
         lambda row: f"{row['cnt_str']}{divider2}({row['cnt_pct_only']})", axis=1
     )
 
-    # # # * Sorting logic based on sort_values
-    # if sort_values_index:
-    #     sort_order = (
-    #         df.groupby("index")["value"].sum().sort_values(ascending=False).index
-    #     )
-    # else:
-    #     sort_order = sorted(df["index"].unique(), reverse=False)  # Alphabetical order
+    if sort_values_color:
+        colors_unique = (df
+            .groupby("col", observed=True)["value"]
+            .sum()
+            .sort_values(ascending=False)
+            .index.tolist()
+        )
+    else:
+        colors_unique = sorted(df["col"].unique().tolist())
 
-    # display(sort_order)
+    if sort_values_index:
+        index_unique = (df
+            .groupby("index", observed=True)["value"]
+            .sum()
+            .sort_values(ascending=False)
+            .index.tolist()
+        )
+    else:
+        index_unique = sorted(df["index"].unique().tolist())
 
-    # df["index"] = pd.Categorical(
-    #     values=df["index"],
-    #     # categories=sort_order,
-    #     ordered=True,
-    # )
-    df = (
-        df.sort_values(by="index", ascending=False)
-        if orientation == "h"
-        else df.sort_values(by="index", ascending=True)
-    )
+    color_map = assign_column_colors(colors_unique, color_palette, null_label)
+    
+
+    cat_orders = {
+        "index": index_unique,
+        "col": colors_unique,
+    }
+
+    # Ensure bl is categorical with the correct order
+    df["index"] = pd.Categorical(df["index"], categories=cat_orders["index"], ordered=True)
 
-    # display(df)
 
     # * plot
     fig = px.bar(
         df,
         x="index" if orientation == "v" else "value",
         y="value" if orientation == "v" else "index",
+        # color=columns,
         color="col",
         text="cnt_pct_str" if normalize else "cnt_str",
         orientation=orientation,
@@ -438,13 +422,15 @@ def plot_stacked_bars(
         template="plotly_dark" if os.getenv("THEME") == "dark" else "plotly",
         width=width,
         height=height,
-        color_discrete_map=column_colors,  # Use assigned colors
-        category_orders={
-            col_index: list(df["index"].cat.categories)
-        },  # <- Add this line
+        color_discrete_map=color_map,  # Use assigned colors
+        category_orders= cat_orders,
     )
 
 
+    # print(cat_orders)
+    # print(color_map)
+    # display(df)
+
     # * get longest bar
     bar_max = (
         df.groupby("index")["value"].sum().sort_values(ascending=False).iloc[0]
@@ -471,6 +457,9 @@ def plot_stacked_bars(
             },
         },
     )
+    fig.update_layout(legend_traceorder="normal") 
+    fig.update_layout(legend_title_text=col_color)
+
 
     # * set dtick
     if orientation == "h":
@@ -1274,6 +1263,7 @@ def plot_facet_stacked_bars(
     sort_values_index: bool = False,
     sort_values_color: bool = False,
     sort_values_facet: bool = False,
+    relative: bool = False,
     
 ) -> object:
     """
@@ -1297,6 +1287,7 @@ def plot_facet_stacked_bars(
         sort_values_index (bool): If True, sorts index by group sum.
         sort_values_color (bool): If True, sorts columns by group sum.
         sort_values_facet (bool): If True, sorts facet by group sum.
+        relative (bool): If True, show bars as relative proportions to 100%.
         sort_values (bool): DEPRECATED
 
 
@@ -1352,6 +1343,11 @@ def plot_facet_stacked_bars(
         subplot_titles=facets,
     )
 
+    # * relative?
+    if relative:
+        aggregated_df["value"] = aggregated_df.groupby(["facet", "index"])["value"].transform(lambda x: x / x.sum())
+        fig.update_layout(yaxis_tickformat=".0%")  # Show as percentage
+
     # * Ensure all categories appear in the legend by adding an invisible trace
     for column in columns:
         fig.add_trace(
@@ -1420,6 +1416,7 @@ def plot_facet_stacked_bars(
 
     title = f"{caption} {', '.join(axis_details)}, n = {original_rows:_}"
     template = "plotly_dark" if os.getenv("THEME") == "dark" else "plotly"
+    
     fig.update_layout(
         title=title,
         barmode="stack",

{pandas_plots-0.12.8 → pandas_plots-0.12.10/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.8
+Version: 0.12.10
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -96,7 +96,7 @@ tbl.show_num_df(
   - `plot_histogram()` histogram for one or more **numerical** columns
   - `plot_joints()` a joint plot for **exactly two numerical** columns
   - `plot_quadrants()` quickly shows a 2x2 heatmap
-  - 🆕 `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
+  - `plot_facet_stacked_bars()` shows stacked bars for a facet value as subplots 
 <br>
 
 - `ven` offers functions for _venn diagrams_
@@ -113,7 +113,7 @@ tbl.show_num_df(
   - `add_datetime_col()` adds a datetime columns to a dataframe (chainable)
   - `show_package_version` prints version of a list of packages
   - `get_os` helps to identify and ensure operating system at runtime
-  - `🆕 add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
+  - `add_bitmask_label()` adds a column to the data that resolves a bitmask column into human-readable labels
 <br>
 
 - `pii` has routines for handling of personally identifiable information