pandas-plots 0.12.5__tar.gz → 0.12.6__tar.gz

{pandas_plots-0.12.5/src/pandas_plots.egg-info → pandas_plots-0.12.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.5
+Version: 0.12.6
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier

{pandas_plots-0.12.5 → pandas_plots-0.12.6}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pandas-plots
-version = 0.12.5
+version = 0.12.6
 author = smeisegeier
 author_email = dexterDSDo@googlemail.com
 description = A collection of helper for table handling and visualization

pandas_plots-0.12.6/src/pandas_plots/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-0.12.5 → pandas_plots-0.12.6}/src/pandas_plots/pls.py

@@ -256,16 +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]])
@@ -281,10 +271,31 @@ def plot_stacked_bars(
         )
     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
@@ -312,6 +323,8 @@ def plot_stacked_bars(
         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 = (
@@ -344,13 +357,14 @@ def plot_stacked_bars(
     if orientation == "h":
         if relative:
             fig.update_xaxes(dtick=5)
-        elif normalize:
-            fig.update_xaxes(dtick=0.05)
+        # 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)
+        # elif normalize:
+        #     fig.update_yaxes(dtick=0.05)
 
     # * show grids, set to smaller distance on pct scale
     fig.update_xaxes(showgrid=True, gridwidth=1)
@@ -961,7 +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:
@@ -1175,8 +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(

{pandas_plots-0.12.5 → pandas_plots-0.12.6/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.5
+Version: 0.12.6
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier

{pandas_plots-0.12.5 → pandas_plots-0.12.6}/src/pandas_plots.egg-info/SOURCES.txt

@@ -10,5 +10,6 @@ src/pandas_plots/ven.py
 src/pandas_plots.egg-info/PKG-INFO
 src/pandas_plots.egg-info/SOURCES.txt
 src/pandas_plots.egg-info/dependency_links.txt
+src/pandas_plots.egg-info/pii.py
 src/pandas_plots.egg-info/requires.txt
 src/pandas_plots.egg-info/top_level.txt