pandas-plots 0.11.4__tar.gz → 0.11.6__tar.gz

{pandas_plots-0.11.4/src/pandas_plots.egg-info → pandas_plots-0.11.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.11.4
+Version: 0.11.6
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -24,8 +24,8 @@ Requires-Dist: plotly>=5.18.0
 Requires-Dist: matplotlib>=3.8.2
 Requires-Dist: matplotlib-venn>=0.11.10
 Requires-Dist: seaborn>=0.13.2
-Requires-Dist: Jinja2>=3.1.3
-Requires-Dist: requests>=2.31.0
+Requires-Dist: Jinja2>=3.1.4
+Requires-Dist: requests>=2.32.0
 Requires-Dist: numpy<2.0.0
 
 # pandas-plots
@@ -77,16 +77,16 @@ tbl.show_num_df(
 - `tbl` utilities for table descriptions
   - 🌟`show_num_df()` displays a table as styled version with additional information
   - `describe_df()` an alternative version of pandas `describe()` function
-  - `pivot_df()` gets a pivot table of a 3 column dataframe
+  - `pivot_df()` gets a pivot table of a 3 column dataframe (or 2 columns if no weights are given)
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plot_stacked_bars()` shortcut to stacked bars 😄
   - `plots_bars()` a standardized bar plot for a **categorical** column
-    - features convidence intervals via `use_ci` option
-  - 🆕 `plot_histogram()` histogram for one or more **numerical** columns
-  - 🆕 `plot_joints()` a joint plot for **exactly two numerical** columns
+    - features confidence intervals via `use_ci` option
+  - `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
 
 - `ven` offers functions for _venn diagrams_
@@ -100,7 +100,11 @@ tbl.show_num_df(
   - `replace_delimiter_outside_quotes()` when manual import of csv files is needed: replaces delimiters only outside of quotes
   - `create_barcode_from_url()` creates a barcode from a given URL
   - `add_datetime_col()` adds a datetime columns to a dataframe
-  - 🆕 `show_package_version` prints version of a list of packages
+  - `show_package_version` prints version of a list of packages
+  - `get_os` helps to identify and ensure operating system at runtime
+
+- `pii` has routines for handling of personally identifiable information
+  - `remove_pii()` logs and deletes pii from a series
 
 > note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
 

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/README.md

@@ -47,16 +47,16 @@ tbl.show_num_df(
 - `tbl` utilities for table descriptions
   - 🌟`show_num_df()` displays a table as styled version with additional information
   - `describe_df()` an alternative version of pandas `describe()` function
-  - `pivot_df()` gets a pivot table of a 3 column dataframe
+  - `pivot_df()` gets a pivot table of a 3 column dataframe (or 2 columns if no weights are given)
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plot_stacked_bars()` shortcut to stacked bars 😄
   - `plots_bars()` a standardized bar plot for a **categorical** column
-    - features convidence intervals via `use_ci` option
-  - 🆕 `plot_histogram()` histogram for one or more **numerical** columns
-  - 🆕 `plot_joints()` a joint plot for **exactly two numerical** columns
+    - features confidence intervals via `use_ci` option
+  - `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
 
 - `ven` offers functions for _venn diagrams_
@@ -70,7 +70,11 @@ tbl.show_num_df(
   - `replace_delimiter_outside_quotes()` when manual import of csv files is needed: replaces delimiters only outside of quotes
   - `create_barcode_from_url()` creates a barcode from a given URL
   - `add_datetime_col()` adds a datetime columns to a dataframe
-  - 🆕 `show_package_version` prints version of a list of packages
+  - `show_package_version` prints version of a list of packages
+  - `get_os` helps to identify and ensure operating system at runtime
+
+- `pii` has routines for handling of personally identifiable information
+  - `remove_pii()` logs and deletes pii from a series
 
 > note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
 

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pandas-plots
-version = 0.11.4
+version = 0.11.6
 author = smeisegeier
 author_email = dexterDSDo@googlemail.com
 description = A collection of helper for table handling and vizualization
@@ -30,8 +30,8 @@ install_requires =
 	matplotlib >= 3.8.2
 	matplotlib-venn >= 0.11.10
 	seaborn >= 0.13.2
-	Jinja2 >= 3.1.3
-	requests >= 2.31.0
+	Jinja2 >= 3.1.4
+	requests >= 2.32.0
 	numpy < 2.0.0
 
 [egg_info]

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/src/pandas_plots/hlp.py

@@ -3,6 +3,11 @@ import numpy as np
 import scipy.stats
 import importlib.metadata as md
 from platform import python_version
+from typing import Literal, List
+
+from enum import Enum, auto
+import platform
+import os
 
 from io import BytesIO
 from matplotlib import pyplot as plt
@@ -149,10 +154,10 @@ def wrap_text(
     if is_text:
         # ! when splitting the text later by blanks, newlines are not correctly handled
         # * to detect them, they must be followed by a blank:
-        pattern = r'(\n)(?=\S)' # *forward lookup for newline w/ no blank
+        pattern = r"(\n)(?=\S)"  # *forward lookup for newline w/ no blank
         # * add blank after these newlines
         new_text = re.sub(pattern, r"\1 ", text)
-        text=new_text
+        text = new_text
 
         # * then strip and build word list
         text = (
@@ -265,23 +270,78 @@ def add_datetime_columns(df: pd.DataFrame, date_column: str = None) -> pd.DataFr
     return df_
 
 
-def show_package_version(packages: list[str] = ["pandas","numpy","duckdb","pandas-plots", "connection_helper"], sep: str = " | ") -> None:
+def show_package_version(
+    packages: list[str] = [],
+    sep: str = " | ",
+    include_demo_packages: bool = True,
+) -> None:
     """
     Display the versions of the specified packages.
 
     Parameters:
         packages (list[str], optional): A list of package names. Defaults to ["pandas","numpy","duckdb","pandas-plots", "connection_helper"].
         sep (str, optional): The separator to use when joining the package names and versions. Defaults to " | ".
+        include_demo_packages: If True, inlude all demo packages
 
     Returns:
         None
     """
+    if not isinstance(packages, List):
+        print(f"❌ A list of str must be provided")
+        return
+    demo = [
+        "pandas",
+        "numpy",
+        "duckdb",
+        "pandas-plots",
+        "connection_helper",
+    ]
     items = []
     items.append(f"🐍 {python_version()}")
+    if include_demo_packages:
+        packages.extend(demo)
+
     for item in packages:
         try:
             version = md.version(item)
             items.append(f"📦 {item}: {version}")
         except md.PackageNotFoundError:
-            items.append(f"❌ {item}: Package not found")
-    print(sep.join(items))
+            items.append(f"❌ {item}: Not found")
+    print(sep.join(items))
+    return
+
+class OperatingSystem(Enum):
+    WINDOWS = auto()
+    LINUX = auto()
+    MAC = auto()
+
+
+def get_os(desired_os: OperatingSystem = None) -> bool:
+    """
+    A function that checks the operating system and returns a boolean value based on the desired operating system.
+
+    Parameters:
+        desired_os (OperatingSystem): The desired operating system to check against. Defaults to None.
+        Values are
+            - OperatingSystem.WINDOWS
+            - OperatingSystem.LINUX
+            - OperatingSystem.MAC
+
+    Returns:
+        bool: True if the desired operating system matches the current operating system, False otherwise. Returns None if desired_os is None.
+    """
+    print(
+        f"💻 os: {os.name} | 🎯 system: {platform.system()} | 💽 release: {platform.release()}"
+    )
+
+    if desired_os is None:
+        return None
+
+    if desired_os == OperatingSystem.WINDOWS and platform.system() == "Windows":
+        return True
+    elif desired_os == OperatingSystem.LINUX and platform.system() == "Linux":
+        return True
+    elif desired_os == OperatingSystem.MAC and platform.system() == "Darwin":
+        return True
+    else:
+        return False

pandas_plots-0.11.6/src/pandas_plots/pii.py

@@ -0,0 +1,71 @@
+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 .pii.log
+    - custom_regex: Regex that is injected into detection
+
+    Returns:
+    - the given series w/o detected pii elements
+    """
+
+    # * 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:
+        with open(".pii.log", "w") as f:
+            f.write(str(col.loc[idx_all]))
+
+    return col.drop(idx_all)

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/src/pandas_plots/tbl.py

@@ -229,6 +229,10 @@ def pivot_df(
     A function to pivot a DataFrame based on specified parameters hand over to the *show_num_df* function.
     It does not provide much added value since the built-in pivot_table function does the same thing.
     However, it can be useful in certain situations (applying top_n_index and top_n_columns).
+    
+    First two must be [index] and [columns]
+    If 3 columns are given, last one must be the weights column.
+    If 2 columns are given, column 3 will be added as flat count.
 
     Args:
         df (pd.DataFrame): The input DataFrame to be pivoted.
@@ -262,6 +266,10 @@ def pivot_df(
         print(f"❌ axis not supported")
         return
 
+    # * if only 2 are provided, add cnt col
+    if len(df.columns) == 2:
+        df = df.assign(cnt=1)
+
     if len(df.columns) != 3:
         print("❌ df must have exactly 3 columns")
         return

{pandas_plots-0.11.4 → pandas_plots-0.11.6/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.11.4
+Version: 0.11.6
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -24,8 +24,8 @@ Requires-Dist: plotly>=5.18.0
 Requires-Dist: matplotlib>=3.8.2
 Requires-Dist: matplotlib-venn>=0.11.10
 Requires-Dist: seaborn>=0.13.2
-Requires-Dist: Jinja2>=3.1.3
-Requires-Dist: requests>=2.31.0
+Requires-Dist: Jinja2>=3.1.4
+Requires-Dist: requests>=2.32.0
 Requires-Dist: numpy<2.0.0
 
 # pandas-plots
@@ -77,16 +77,16 @@ tbl.show_num_df(
 - `tbl` utilities for table descriptions
   - 🌟`show_num_df()` displays a table as styled version with additional information
   - `describe_df()` an alternative version of pandas `describe()` function
-  - `pivot_df()` gets a pivot table of a 3 column dataframe
+  - `pivot_df()` gets a pivot table of a 3 column dataframe (or 2 columns if no weights are given)
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option
   - `plot_boxes()` multiple boxplots _(annotation is experimental)_
   - `plot_stacked_bars()` shortcut to stacked bars 😄
   - `plots_bars()` a standardized bar plot for a **categorical** column
-    - features convidence intervals via `use_ci` option
-  - 🆕 `plot_histogram()` histogram for one or more **numerical** columns
-  - 🆕 `plot_joints()` a joint plot for **exactly two numerical** columns
+    - features confidence intervals via `use_ci` option
+  - `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
 
 - `ven` offers functions for _venn diagrams_
@@ -100,7 +100,11 @@ tbl.show_num_df(
   - `replace_delimiter_outside_quotes()` when manual import of csv files is needed: replaces delimiters only outside of quotes
   - `create_barcode_from_url()` creates a barcode from a given URL
   - `add_datetime_col()` adds a datetime columns to a dataframe
-  - 🆕 `show_package_version` prints version of a list of packages
+  - `show_package_version` prints version of a list of packages
+  - `get_os` helps to identify and ensure operating system at runtime
+
+- `pii` has routines for handling of personally identifiable information
+  - `remove_pii()` logs and deletes pii from a series
 
 > note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
 

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/src/pandas_plots.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ README.md
 pyproject.toml
 setup.cfg
 src/pandas_plots/hlp.py
+src/pandas_plots/pii.py
 src/pandas_plots/pls.py
 src/pandas_plots/tbl.py
 src/pandas_plots/ven.py

{pandas_plots-0.11.4 → pandas_plots-0.11.6}/src/pandas_plots.egg-info/requires.txt

@@ -3,6 +3,6 @@ plotly>=5.18.0
 matplotlib>=3.8.2
 matplotlib-venn>=0.11.10
 seaborn>=0.13.2
-Jinja2>=3.1.3
-requests>=2.31.0
+Jinja2>=3.1.4
+requests>=2.32.0
 numpy<2.0.0