pandas-plots 0.15.1__tar.gz → 0.15.3__tar.gz

pandas_plots-0.15.3/.python-version

@@ -0,0 +1 @@
+3.12

{pandas_plots-0.15.1 → pandas_plots-0.15.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pandas-plots
-Version: 0.15.1
+Version: 0.15.3
 Summary: A collection of helper for table handling and visualization
 Project-URL: Homepage, https://github.com/smeisegeier/pandas-plots
 Project-URL: Repository, https://github.com/smeisegeier/pandas-plots
@@ -13,10 +13,10 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.10
-Requires-Dist: connection-helper>=0.11.2
+Requires-Dist: connection-helper>=0.12
 Requires-Dist: dataframe-image>=0.2.6
 Requires-Dist: duckdb>=1.3.0
 Requires-Dist: jinja2>=3.1.4
@@ -41,7 +41,9 @@ Description-Content-Type: text/markdown
 install / update package
 
 ```bash
-pip install pandas-plots -U
+uv add -U pandas-plots
+# if no uv is available:
+# pip install pandas-plots -U
 ```
 
 include in python
@@ -79,7 +81,7 @@ tbl.show_num_df(
 `pandas-plots` is a package to help you examine and visualize data that are organized in a pandas DataFrame. It provides a high level api to pandas / plotly with some selected functions and predefined options:
 
 - `tbl` utilities for table descriptions
-  - 🌟`show_num_df()` displays a table as styled version with additional information
+  - `show_num_df()` displays a table as styled version with additional information
   - `describe_df()` an alternative version of pandas `describe()` function
   - `descr_db()` a very short descr for a `duckdb` relation
   - `pivot_df()` gets a pivot table of a 3 column dataframe (or 2 columns if no weights are given)
@@ -89,7 +91,7 @@ tbl.show_num_df(
 - `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 😄
+  - `plot_stacked_bars()` shortcut to stacked bars
   - `plots_bars()` a standardized bar plot for a **categorical** column
     - features confidence intervals via `use_ci` option
   - `plot_histogram()` histogram for one or more **numerical** columns
@@ -105,7 +107,7 @@ tbl.show_num_df(
 <br>
 
 - `hlp` contains some (variety) helper functions
-  - `to_series()` converts a dataframe to a series (`🚨 breaking change`)
+  - `to_series()` converts a dataframe to a series
   - `mean_confidence_interval()` calculates mean and confidence interval for a series
   - `wrap_text()` formats strings or lists to a given width to fit nicely on the screen
   - `replace_delimiter_outside_quotes()` when manual import of csv files is needed: replaces delimiters only outside of quotes
@@ -118,7 +120,13 @@ tbl.show_num_df(
   - `add_measures_to_pyg_config()` adds measures to a pygwalker config file to avoid frequent manual update
 <br>
 
-> note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+> note: theme setting ☀️ 🌔 can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+
+## prerequisites
+
+- ⚠️ for static image generation, this package uses Plotly's kaleido engine, which requires a system-wide installation of the Chrome or Chromium browser
+- if image generation fails, it may be because a compatible browser is missing
+- in such cases, please run `kaleido_get_chrome` from your terminal to install the necessary dependency.
 
 ## more examples
 

{pandas_plots-0.15.1 → pandas_plots-0.15.3}/README.md

@@ -7,7 +7,9 @@
 install / update package
 
 ```bash
-pip install pandas-plots -U
+uv add -U pandas-plots
+# if no uv is available:
+# pip install pandas-plots -U
 ```
 
 include in python
@@ -45,7 +47,7 @@ tbl.show_num_df(
 `pandas-plots` is a package to help you examine and visualize data that are organized in a pandas DataFrame. It provides a high level api to pandas / plotly with some selected functions and predefined options:
 
 - `tbl` utilities for table descriptions
-  - 🌟`show_num_df()` displays a table as styled version with additional information
+  - `show_num_df()` displays a table as styled version with additional information
   - `describe_df()` an alternative version of pandas `describe()` function
   - `descr_db()` a very short descr for a `duckdb` relation
   - `pivot_df()` gets a pivot table of a 3 column dataframe (or 2 columns if no weights are given)
@@ -55,7 +57,7 @@ tbl.show_num_df(
 - `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 😄
+  - `plot_stacked_bars()` shortcut to stacked bars
   - `plots_bars()` a standardized bar plot for a **categorical** column
     - features confidence intervals via `use_ci` option
   - `plot_histogram()` histogram for one or more **numerical** columns
@@ -71,7 +73,7 @@ tbl.show_num_df(
 <br>
 
 - `hlp` contains some (variety) helper functions
-  - `to_series()` converts a dataframe to a series (`🚨 breaking change`)
+  - `to_series()` converts a dataframe to a series
   - `mean_confidence_interval()` calculates mean and confidence interval for a series
   - `wrap_text()` formats strings or lists to a given width to fit nicely on the screen
   - `replace_delimiter_outside_quotes()` when manual import of csv files is needed: replaces delimiters only outside of quotes
@@ -84,7 +86,13 @@ tbl.show_num_df(
   - `add_measures_to_pyg_config()` adds measures to a pygwalker config file to avoid frequent manual update
 <br>
 
-> note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+> note: theme setting ☀️ 🌔 can be controlled through all functions by setting the environment variable `THEME` to either light or dark
+
+## prerequisites
+
+- ⚠️ for static image generation, this package uses Plotly's kaleido engine, which requires a system-wide installation of the Chrome or Chromium browser
+- if image generation fails, it may be because a compatible browser is missing
+- in such cases, please run `kaleido_get_chrome` from your terminal to install the necessary dependency.
 
 ## more examples
 

{pandas_plots-0.15.1 → pandas_plots-0.15.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pandas-plots"
-version = "0.15.1"
+version = "0.15.3"
 description = "A collection of helper for table handling and visualization"
 long_description = "file: README.md"
 long_description_content_type = "text/markdown"
@@ -14,7 +14,7 @@ authors = [
 classifiers = [
     "License :: OSI Approved :: MIT License",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.12",
     'Development Status :: 4 - Beta',
     'Intended Audience :: Science/Research',
     'Operating System :: OS Independent',
@@ -35,7 +35,7 @@ dependencies = [
     "duckdb>=1.3.0",
     "nbformat>=4.2.0",
     "dataframe_image>=0.2.6",
-    "connection-helper>=0.11.2",
+    "connection-helper>=0.12",
 ]
 
 [project.urls]

{pandas_plots-0.15.1 → pandas_plots-0.15.3}/src/pandas_plots/pls.py

@@ -564,13 +564,21 @@ def plot_bars(
 
     # * if df, check if valid
     if isinstance(df_in, pd.DataFrame):
-        if len(df_in.columns) != 2:
-            print("❌ df must have exactly 2 columns")
-            return
-        elif not (df_in.iloc[:, 0].dtype.kind in ["O", "b"]) or not (
-            df_in.iloc[:, 1].dtype.kind in ["i", "f"]
-        ):
-            print("❌ df must have string and numeric columns (in that order).")
+        if len(df_in.columns) == 1:
+            if not (df_in.iloc[:, 0].dtype.kind in ["O", "b"]):
+                print("❌ df must have 1 column of object or bool type.")
+                return
+            else:
+                df_in = df_in.value_counts(dropna=dropna).to_frame().reset_index()
+                use_ci = False
+        elif len(df_in.columns) == 2:
+            if not (df_in.iloc[:, 0].dtype.kind in ["O", "b"]) or not (
+                df_in.iloc[:, 1].dtype.kind in ["i", "f"]
+            ):
+                print("❌ df must have string and numeric columns (in that order).")
+                return
+        else:
+            print("❌ df must have exactly 1 or 2 columns")
             return
     else:
         print("❌ input must be series or dataframe.")
@@ -1194,6 +1202,10 @@ def plot_boxes(
     xlvl1 = -50
     xlvl2 = 0
     xlvl3 = 50
+    
+    # * type of col0 must be str, not object. otherwise px.box will fail since sorting will fail
+    if pd.api.types.is_object_dtype(df.iloc[:, 0]):
+        df.iloc[:, 0] = df.iloc[:, 0].astype(str)
 
     # * unique items
     # Sort the unique items alphabetically

{pandas_plots-0.15.1 → pandas_plots-0.15.3}/src/pandas_plots/tbl.py

@@ -75,6 +75,7 @@ def describe_df(
     top_n_uniques: int = 5,
     top_n_chars_in_index: int = 0,
     top_n_chars_in_columns: int = 0,
+    missing_figsize: tuple[int, int] = (26, 6),
 ):
     """
     This function takes a pandas DataFrame and a caption as input parameters and prints out the caption as a styled header, followed by the shape of the DataFrame and the list of column names. For each column, it prints out the column name, the number of unique values, and the column data type. If the column is a numeric column with more than 100 unique values, it also prints out the minimum, mean, maximum, and sum values. Otherwise, it prints out the first 100 unique values of the column.
@@ -94,6 +95,7 @@ def describe_df(
     top_n_uniques (int): number of uniques to display
     top_n_chars_in_index (int): number of characters to display on plot axis
     top_n_chars_in_columns (int): number of characters to display on plot axis. If set, minimum is 10.
+    missing_figsize (tuple[int, int]): figsize for missing plot (default (26, 6)
 
     usage:
     describe_df(
@@ -252,7 +254,7 @@ def describe_df(
     
     if use_missing:
         import missingno as msno
-        msno.matrix(df_, figsize=(12, 5))
+        msno.matrix(df_, figsize=missing_figsize)
 
 
 def pivot_df(