pandas-plots 0.11.14__tar.gz → 0.11.16__tar.gz

{pandas_plots-0.11.14/src/pandas_plots.egg-info → pandas_plots-0.11.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.11.14
+Version: 0.11.16
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -22,7 +22,7 @@ License-File: LICENSE
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: plotly>=5.18.0
 Requires-Dist: matplotlib>=3.8.2
-Requires-Dist: matplotlib-venn>=0.11.10
+Requires-Dist: matplotlib-venn==0.11.10
 Requires-Dist: seaborn>=0.13.2
 Requires-Dist: Jinja2>=3.1.4
 Requires-Dist: requests>=2.32.0
@@ -83,6 +83,7 @@ tbl.show_num_df(
   - `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)
+  - `print_summary()` shows statistics for a pandas DataFrame or Series
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option

{pandas_plots-0.11.14 → pandas_plots-0.11.16}/README.md

@@ -49,6 +49,7 @@ tbl.show_num_df(
   - `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)
+  - `print_summary()` shows statistics for a pandas DataFrame or Series
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option

{pandas_plots-0.11.14 → pandas_plots-0.11.16}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pandas-plots
-version = 0.11.14
+version = 0.11.16
 author = smeisegeier
 author_email = dexterDSDo@googlemail.com
 description = A collection of helper for table handling and vizualization
@@ -28,7 +28,7 @@ install_requires =
 	pandas >= 2.0.0
 	plotly >= 5.18.0
 	matplotlib >= 3.8.2
-	matplotlib-venn >= 0.11.10
+	matplotlib-venn == 0.11.10
 	seaborn >= 0.13.2
 	Jinja2 >= 3.1.4
 	requests >= 2.32.0

{pandas_plots-0.11.14 → pandas_plots-0.11.16}/src/pandas_plots/pls.py

@@ -11,6 +11,7 @@ from matplotlib import pyplot as plt
 from plotly import express as px
 
 from .hlp import *
+from .tbl import print_summary
 
 
 def _set_caption(caption: str) -> str:
@@ -757,6 +758,7 @@ def plot_box(
     height: int = 200,
     width: int = 1200,
     annotations: bool = True,
+    summary: bool = True,
     caption: str = None,
     title: str = None,
     violin: bool = False,
@@ -776,6 +778,7 @@ def plot_box(
         violin: Use violin plot or not
         x_min: The minimum value for the x-axis scale (max and min must be set)
         x_max: The maximum value for the x-axis scale (max and min must be set)
+        summary: Whether to add a summary table to the plot
 
     Returns:
         None
@@ -885,6 +888,8 @@ def plot_box(
         )
 
     fig.show("png")
+    if summary:
+        print_summary(ser)
     return
 
 
@@ -896,6 +901,7 @@ def plot_boxes(
     height: int = 600,
     width: int = 800,
     annotations: bool = True,
+    summary: bool = True,
     title: str = None,
 ) -> None:
     """
@@ -909,6 +915,7 @@ def plot_boxes(
         height (int): The height of the plot.
         width (int): The width of the plot.
         annotations (bool): Whether to add annotations to the plot.
+        summary (bool): Whether to add a summary to the plot.
 
     Returns:
         None
@@ -1022,6 +1029,8 @@ def plot_boxes(
     fig.update_yaxes(title_text=df.columns[1])
 
     fig.show("png")
+    if summary:
+        print_summary(df)
     return
 
 

{pandas_plots-0.11.14 → pandas_plots-0.11.16}/src/pandas_plots/tbl.py

@@ -112,18 +112,19 @@ def describe_df(
         header = f"🟠 {col}({len(unis):_}|{df[col].dtype})"
         return unis, header
 
-    # * show all columns
+    # hack this block somehow interferes with the plotly renderer. so its run even when use_columns=False
     if use_columns:
         print("--- column uniques (all)")
         print(f"🟠 index {wrap_text(df.index.tolist()[:top_n_uniques])}")
-        for col in df.columns[:]:
-            _u, _h = get_uniques_header(col)
-            # * check col type
-            is_str = df.loc[:, col].dtype.kind == "O"
-            # * wrap output
-            print(
-                f"{_h} {wrap_text(_u[:top_n_uniques], max_items_in_line=70, use_apo=is_str)}"
-            )
+    for col in df.columns[:]:
+        _u, _h = get_uniques_header(col)
+        # * check col type
+        is_str = df.loc[:, col].dtype.kind == "O"
+        # * wrap output
+        if use_columns:
+                print(
+                    f"{_h} {wrap_text(_u[:top_n_uniques], max_items_in_line=70, use_apo=is_str)}"
+                )
 
     print("--- column stats (numeric)")
     # * only show numerics
@@ -131,9 +132,10 @@ def describe_df(
         _u, _h = get_uniques_header(col)
 
         # * extra care for scipy metrics, these are very vulnarable to nan
-        print(
-            f"{_h} min: {round(df[col].min(),3):_} | max: {round(df[col].max(),3):_} | median: {round(df[col].median(),3):_} | mean: {round(df[col].mean(),3):_} | std: {round(df[col].std(),3):_} | cv: {round(df[col].std() / df[col].mean(),3):_} | sum: {round(df[col].sum(),3):_} | skew: {round(stats.skew(df[col].dropna().tolist()),3)} | kurto: {round(stats.kurtosis(df[col].dropna().tolist()),3)}"
-        )
+        # print(
+        #     f"{_h} min: {round(df[col].min(),3):_} | max: {round(df[col].max(),3):_} | median: {round(df[col].median(),3):_} | mean: {round(df[col].mean(),3):_} | std: {round(df[col].std(),3):_} | cv: {round(df[col].std() / df[col].mean(),3):_} | sum: {round(df[col].sum(),3):_} | skew: {round(stats.skew(df[col].dropna().tolist()),3)} | kurto: {round(stats.kurtosis(df[col].dropna().tolist()),3)}"
+        # )
+        print_summary(df[col], _h)
 
     #  * show first 3 rows
     display(df[:3])
@@ -619,3 +621,57 @@ def show_num_df(
         )
 
     return out
+
+def print_summary(df: pd.DataFrame | pd.Series, name: str="🟠 "):
+    """
+    Print statistical summary for a pandas DataFrame or Series.
+
+    The function computes and prints various statistics for each numeric column in a DataFrame 
+    or for a Series. Statistics include minimum, lower bound, 25th percentile (Q1), median, mean, 
+    75th percentile (Q3), upper bound, maximum, standard deviation, coefficient of variation, 
+    sum, skewness, and kurtosis. The interquartile range (IQR) is used to compute the lower 
+    and upper bounds, which are adjusted not to exceed the min and max of the data.
+
+    Args:
+        df (Union[pd.DataFrame, pd.Series]): Input DataFrame or Series. Only numeric columns 
+        in DataFrame are considered.
+    """
+    if df.empty:
+        return 
+
+    def print_summary_ser(ser: pd.Series, name: str=""):
+        # Calculate IQR and pass `rng=(25, 75)` to get the interquartile range
+        iqr_value = stats.iqr(ser)
+
+        # Using the iqr function, we still calculate the bounds manually
+        q1 = stats.scoreatpercentile(ser, 25)
+        q3 = stats.scoreatpercentile(ser, 75)
+
+        # Calculate upper bound directly
+        min = round(ser.min(),3)
+        med = round(ser.median(),3)
+        upper = round(q3 + 1.5 * iqr_value,3)
+        lower = round(q1 - 1.5 * iqr_value,3)
+        mean = round(ser.mean(),3)
+        std = round(ser.std(),3)
+        cv = round(ser.std() / ser.mean(),3)
+        max = round(ser.max(),3)
+        sum = round(ser.sum(),3)
+        skew = round(stats.skew(ser.dropna().tolist()),3)
+        kurto = round(stats.kurtosis(ser.dropna().tolist()),3)
+        
+        lower = min if lower < min else lower
+        upper = max if upper > max else upper
+
+        # * extra care for scipy metrics, these are very vulnarable to nan
+        print(
+            f"""{name} min: {min:_} | lower: {lower:_} | q25: {q1:_} | median: {med:_} | mean: {mean:_} | q75: {q3:_} | upper: {upper:_} | max: {max:_} | std: {std:_} | cv: {cv:_} | sum: {sum:_} | skew: {skew} | kurto: {kurto}""")
+
+    if isinstance(df, pd.Series):
+        print_summary_ser(df, name)
+        return
+    if isinstance(df, pd.DataFrame):
+        # * only show numerics
+        for col in df.select_dtypes("number").columns:
+            print_summary_ser(ser=df[col], name=col)
+    return

{pandas_plots-0.11.14 → pandas_plots-0.11.16/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.11.14
+Version: 0.11.16
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -22,7 +22,7 @@ License-File: LICENSE
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: plotly>=5.18.0
 Requires-Dist: matplotlib>=3.8.2
-Requires-Dist: matplotlib-venn>=0.11.10
+Requires-Dist: matplotlib-venn==0.11.10
 Requires-Dist: seaborn>=0.13.2
 Requires-Dist: Jinja2>=3.1.4
 Requires-Dist: requests>=2.32.0
@@ -83,6 +83,7 @@ tbl.show_num_df(
   - `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)
+  - `print_summary()` shows statistics for a pandas DataFrame or Series
 
 - `pls` for plotly visualizations
   - `plot_box()` auto annotated boxplot w/ violin option

{pandas_plots-0.11.14 → pandas_plots-0.11.16}/src/pandas_plots.egg-info/requires.txt

@@ -1,7 +1,7 @@
 pandas>=2.0.0
 plotly>=5.18.0
 matplotlib>=3.8.2
-matplotlib-venn>=0.11.10
+matplotlib-venn==0.11.10
 seaborn>=0.13.2
 Jinja2>=3.1.4
 requests>=2.32.0