pandas-plots 0.12.4__py3-none-any.whl → 0.12.6__py3-none-any.whl

pandas_plots/pls.py

@@ -78,7 +78,7 @@ def assign_column_colors(columns, color_palette, null_label):
         raise ValueError(f"Invalid color palette: {color_palette}")
     
     colors = {col: palette[i % len(palette)] for i, col in enumerate(sorted(columns))}
-    colors[null_label] = "gray"
+    colors[null_label] = "lightgray"
     return colors
 
 ### main functions
@@ -192,12 +192,32 @@ def plot_stacked_bars(
 ) -> object:
     """
     Generates a stacked bar plot using the provided DataFrame.
-    Updated to assign colors using `assign_column_colors` with nulls colored grey.
 
     Parameters:
-    All parameters are similar to the original function, with the addition of:
-    - color_palette: str - Name of the color palette.
-    - null_label: str - Label for null values.
+    - df (pd.DataFrame): The input DataFrame with at least two categorical columns and one numerical column.
+    - top_n_index (int): Limit the number of categories displayed on the index axis.
+    - top_n_color (int): Limit the number of categories displayed in the color legend.
+    - dropna (bool): If True, removes rows with missing values; otherwise, replaces them with `null_label`.
+    - swap (bool): If True, swaps the first two columns.
+    - normalize (bool): If True, normalizes numerical values between 0 and 1.
+    - relative (bool): If True, normalizes the bars to a percentage scale.
+    - orientation (Literal["h", "v"]): Defines the orientation of the bars ("v" for vertical, "h" for horizontal).
+    - height (int): Height of the plot.
+    - width (int): Width of the plot.
+    - title (str): Custom title for the plot.
+    - renderer (Literal["png", "svg", None]): Defines the output format.
+    - caption (str): Optional caption for additional context.
+    - sort_values (bool): 
+        - If True, sorts bars by the sum of their values (descending).
+        - If False, sorts bars alphabetically.
+    - show_total (bool): If True, adds a row with the total sum of all categories.
+    - precision (int): Number of decimal places for numerical values.
+    - png_path (Path | str): If specified, saves the plot as a PNG file.
+    - color_palette (str): Name of the color palette to use.
+    - null_label (str): Label for null values.
+    
+    Returns:
+    - A Plotly figure object representing the stacked bar chart.
     """
     BAR_LENGTH_MULTIPLIER = 1.05
 
@@ -211,6 +231,8 @@ def plot_stacked_bars(
         print("❌ first 2 columns must be str")
         return
 
+    df = df.copy()  # Copy the input DataFrame to avoid modifying the original
+
     # * add count column[2] as a service if none is present
     if len(df.columns) == 2:
         df["cnt"] = 1
@@ -234,16 +256,6 @@ def plot_stacked_bars(
     col_index = df.columns[0] if not swap else df.columns[1]
     col_color = df.columns[1] if not swap else df.columns[0]
 
-    # * assign colors to columns
-    unique_colors = sorted(df[col_color].unique())
-    column_colors = assign_column_colors(unique_colors, color_palette, null_label)
-
-    # * add total as aggregation of df
-    if show_total:
-        df_total = df.copy()
-        df_total[col_index] = " TOTAL"  # add space to make this item first
-        df = pd.concat([df, df_total])
-
     # * ensure df is grouped to prevent false aggregations
     df = (
         df.groupby([df.columns[0], df.columns[1]])
@@ -251,6 +263,39 @@ def plot_stacked_bars(
         .sum()
         .reset_index()
     )
+    
+    # * Sorting logic based on sort_values
+    if sort_values:
+        sort_order = (
+            df.groupby(col_index)[df.columns[2]].sum().sort_values(ascending=False).index
+        )
+    else:
+        sort_order = sorted(df[col_index].unique())  # Alphabetical order
+    df[col_index] = pd.Categorical(df[col_index], categories=sort_order, ordered=True)
+
+    # * add total as aggregation of df
+    if show_total:
+        df_total = df.copy()
+        df_total[col_index] = " TOTAL"  # add space to make this item first
+        df = pd.concat([df, df_total])
+
+    # * Convert to categorical with explicit ordering
+    df[col_index] = pd.Categorical(df[col_index], categories=sort_order, ordered=True)
+
+    if top_n_index > 0 and len(sort_order) > top_n_index:
+        top_categories = sort_order[:top_n_index]
+        df[col_index] = df[col_index].apply(lambda x: x if x in top_categories else "<other>")
+
+    unique_colors = sorted(df[col_color].unique())
+    if top_n_color > 0 and len(unique_colors) > top_n_color:
+        top_colors = unique_colors[:top_n_color]
+        df[col_color] = df[col_color].apply(lambda x: x if x in top_colors else "<other>")
+    
+    column_colors = assign_column_colors(sorted(df[col_color].unique()), color_palette, null_label)
+
+    # # * assign colors to columns
+    # unique_colors = sorted(df[col_color].unique())
+    # column_colors = assign_column_colors(unique_colors, color_palette, null_label)
 
     # * calculate n
     divider = 2 if show_total else 1
@@ -264,7 +309,7 @@ def plot_stacked_bars(
     caption = _set_caption(caption)
 
     # * plot
-    _fig = px.bar(
+    fig = px.bar(
         df,
         x=col_index if orientation == "v" else df.columns[2],
         y=df.columns[2] if orientation == "v" else col_index,
@@ -277,6 +322,9 @@ def plot_stacked_bars(
         width=width,
         height=height,
         color_discrete_map=column_colors,  # Use assigned colors
+        category_orders={col_index: list(df[col_index].cat.categories)},  # <- Add this line
+        # category_orders={col_index: df[col_index].categories.tolist() if isinstance(df[col_index].dtype, pd.CategoricalDtype) else sorted(df[col_index].unique())}
+
     )
         # * get longest bar
     bar_max = (
@@ -286,14 +334,14 @@ def plot_stacked_bars(
     # * ignore if bar mode is on
     if not relative:
         if orientation == "v":
-            _fig.update_yaxes(range=[0, bar_max])
+            fig.update_yaxes(range=[0, bar_max])
         else:
-            _fig.update_xaxes(range=[0, bar_max])
+            fig.update_xaxes(range=[0, bar_max])
     else:
-        _fig.update_layout(barnorm="percent")
+        fig.update_layout(barnorm="percent")
 
     # * set title properties
-    _fig.update_layout(
+    fig.update_layout(
         title={
             # 'x': 0.1,
             "y": 0.95,
@@ -308,27 +356,27 @@ def plot_stacked_bars(
     # * set dtick
     if orientation == "h":
         if relative:
-            _fig.update_xaxes(dtick=5)
-        elif normalize:
-            _fig.update_xaxes(dtick=0.05)
+            fig.update_xaxes(dtick=5)
+        # bug dticks are ultra dense
+        # elif normalize:
+        #     fig.update_xaxes(dtick=0.05)
     else:
         if relative:
-            _fig.update_yaxes(dtick=5)
-        elif normalize:
-            _fig.update_yaxes(dtick=0.05)
+            fig.update_yaxes(dtick=5)
+        # elif normalize:
+        #     fig.update_yaxes(dtick=0.05)
 
     # * show grids, set to smaller distance on pct scale
-    _fig.update_xaxes(showgrid=True, gridwidth=1)
-    _fig.update_yaxes(showgrid=True, gridwidth=1)
+    fig.update_xaxes(showgrid=True, gridwidth=1)
+    fig.update_yaxes(showgrid=True, gridwidth=1)
 
     # * save to png if path is provided
     if png_path is not None:
-        _fig.write_image(Path(png_path).as_posix())
-
-    _fig.show(renderer)
+        fig.write_image(Path(png_path).as_posix())
 
-    return _fig
+    fig.show(renderer=renderer)
 
+    return fig
 
 
 def plot_bars(
@@ -927,7 +975,8 @@ def plot_box(
     fig.show("png")
 
     if summary:
-        print_summary(ser)
+        # * if only series is provided, col name is None
+        print_summary(ser.to_frame())
 
     # * save to png if path is provided
     if png_path is not None:
@@ -1141,8 +1190,23 @@ def plot_facet_stacked_bars(
 
     aggregated_df = aggregate_data(df, top_n_index, top_n_columns, top_n_facet, null_label)
 
-    facets = aggregated_df['facet'].unique()
-    columns = sorted(aggregated_df['col'].unique())
+    # facets = aggregated_df['facet'].unique()
+    facets = sorted(aggregated_df['facet'].unique())  # Ensure facets are sorted consistently
+
+    if top_n_columns > 0:
+        top_columns = aggregated_df.groupby('col', observed=True)['value'].sum().nlargest(top_n_columns).index.tolist()
+        # aggregated_df['col'] = aggregated_df['col'].apply(lambda x: x if x in top_columns else "<other>")
+        # aggregated_df['col'] = pd.Categorical(aggregated_df['col'], categories=top_columns + ["<other>"], ordered=True)
+        # aggregated_df['col'] = pd.Categorical(
+        #     aggregated_df['col'].map(lambda x: x if x in top_columns else "<other>"),
+        #     categories=top_columns + ["<other>"],
+        #     ordered=True
+        # )
+        aggregated_df['col'] = aggregated_df['col'].apply(lambda x: x if x in top_columns else "<other>")
+
+
+    # columns = sorted(aggregated_df['col'].unique())
+    columns = aggregated_df.groupby('col', observed=True)['value'].sum().sort_values(ascending=False).index.tolist()
     column_colors = assign_column_colors(columns, color_palette, null_label)
 
     fig = make_subplots(
@@ -1189,17 +1253,17 @@ def plot_facet_stacked_bars(
     unique_rows = len(aggregated_df)
     axis_details = []
     if top_n_index > 0:
-        axis_details.append(f"top {top_n_index} [{original_column_names[0]}]")
+        axis_details.append(f"TOP {top_n_index} [{original_column_names[0]}]")
     else:
         axis_details.append(f"[{original_column_names[0]}]")
 
     if top_n_columns > 0:
-        axis_details.append(f"top {top_n_columns} [{original_column_names[1]}]")
+        axis_details.append(f"TOP {top_n_columns} [{original_column_names[1]}]")
     else:
         axis_details.append(f"[{original_column_names[1]}]")
 
     if top_n_facet > 0:
-        axis_details.append(f"top {top_n_facet} [{original_column_names[2]}]")
+        axis_details.append(f"TOP {top_n_facet} [{original_column_names[2]}]")
     else:
         axis_details.append(f"[{original_column_names[2]}]")
 
@@ -1218,6 +1282,6 @@ def plot_facet_stacked_bars(
         png_path = Path(png_path)
         fig.write_image(str(png_path))
 
-    fig.show(renderer)
+    fig.show(renderer=renderer)
 
     return fig

{pandas_plots-0.12.4.dist-info → pandas_plots-0.12.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.4
+Version: 0.12.6
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -20,7 +20,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pandas>=2.0.0
-Requires-Dist: plotly>=5.18.0
+Requires-Dist: plotly<6
 Requires-Dist: matplotlib>=3.8.2
 Requires-Dist: matplotlib-venn==0.11.10
 Requires-Dist: seaborn>=0.13.2
@@ -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_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_

pandas_plots-0.12.6.dist-info/RECORD

@@ -0,0 +1,11 @@
+pandas_plots/hlp.py,sha256=N6NrbFagVMMX-ZnV0rIBEz82SeSoOkksfMcCap55W7E,16588
+pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots/pls.py,sha256=DsFnWbGNmMnZ8a2qnZFwXH6VekwPFaIwZEQ9TVp6xCg,43997
+pandas_plots/tbl.py,sha256=4VvjLisPT1gSvgsLClcrhC7LIJ-_FPNla8nomGflGag,30509
+pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
+pandas_plots-0.12.6.dist-info/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
+pandas_plots-0.12.6.dist-info/METADATA,sha256=-mCMgoWTwG6HSL8JtuYvwM1LCkzglJm3aIocaUMijO4,7358
+pandas_plots-0.12.6.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+pandas_plots-0.12.6.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots-0.12.6.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
+pandas_plots-0.12.6.dist-info/RECORD,,

pandas_plots-0.12.6.dist-info/pii.py

@@ -0,0 +1,76 @@
+import pandas as pd
+import re
+
+
+def remove_pii(
+    series: pd.Series,
+    verbose: bool = True,
+    logging: bool = False,
+    custom_regex="",
+) -> pd.Index:
+    """
+    Remove personally identifiable information (PII) from the given column.
+
+    Parameters:
+    - series: A pandas Series representing a column in a DataFrame.
+    - verbose: If True, print pii items
+    - logging: If True, write pii items into the file .pii.log
+    - custom_regex: Regex that is injected into detection
+
+    Returns:
+    - index object with indexes of all pii items
+    
+    Remarks:
+    - df.drop(axis=0, index=result, inplace=True)
+    """
+
+    # * reject empty columns
+    assert len(series) > 0
+
+    col = series.copy()
+
+    # * na must be dropped to ensure processsing
+    col.dropna(inplace=True)
+
+    # * find terms
+    _terms = frozenset(["lösch", "herr", "frau", "strasse", "klinik"])
+    idx_terms = col[
+        col.str.contains(
+            "|".join(_terms),
+            case=False,
+            regex=True,
+        )
+    ].index
+
+    # # * optional: search for terms in whole df
+    # df.apply(lambda row: row.astype(str).str.contains('test', case=False, regex=True).any(), axis=1)
+
+    # # * find dates
+    ptr_date = r"\d{2}\.\d{2}\.\d{4}"
+    idx_date = col[col.str.contains(ptr_date, regex=True)].index
+
+    # * dr
+    ptr_dr = r"[D|d][R|r]\. | Fr\. | Hr\. | PD "
+    idx_dr = col[col.str.contains(ptr_dr, regex=True)].index
+
+    # * custom
+    idx_custom = (
+        col[col.str.contains(custom_regex, regex=True)].index
+        if custom_regex
+        else pd.Index([])
+    )
+
+    idx_all = idx_terms.union(idx_date).union(idx_dr).union(idx_custom)
+
+    if verbose:
+        # print(f"found: {idx_dr.__len__()} dr | {idx_date.__len__()} date | {idx_terms.__len__()} terms")
+        print(f"found {idx_all.__len__():_} pii items:")
+        print(col.loc[idx_all].tolist())
+
+    if logging:  # Assuming logging is defined and has the correct value
+        data = col.loc[idx_all]  # Assuming col and idx_all are defined
+        with open(".pii.log", "w") as f:
+            # ! when using str(), it will give only a summary!
+            f.write(data.to_string(index=True))
+
+    return idx_all

pandas_plots-0.12.4.dist-info/RECORD

@@ -1,10 +0,0 @@
-pandas_plots/hlp.py,sha256=N6NrbFagVMMX-ZnV0rIBEz82SeSoOkksfMcCap55W7E,16588
-pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots/pls.py,sha256=isveg6_frLZC3Gt3VEsdOLiLw7aTf3riUahmJLHiEq8,40265
-pandas_plots/tbl.py,sha256=4VvjLisPT1gSvgsLClcrhC7LIJ-_FPNla8nomGflGag,30509
-pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
-pandas_plots-0.12.4.dist-info/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
-pandas_plots-0.12.4.dist-info/METADATA,sha256=WZUfWOid_eYMtuS2V_P_C_ChaD1dTqDfuectlxzAJe8,7358
-pandas_plots-0.12.4.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-pandas_plots-0.12.4.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
-pandas_plots-0.12.4.dist-info/RECORD,,