pandas-plots 0.12.6__py3-none-any.whl → 0.12.7__py3-none-any.whl

pandas_plots/pls.py

@@ -12,6 +12,7 @@ from matplotlib import pyplot as plt
 from plotly import express as px
 import plotly.graph_objects as go
 from plotly.subplots import make_subplots
+import plotly # needed for return types
 
 from .hlp import *
 from .tbl import print_summary
@@ -189,7 +190,7 @@ def plot_stacked_bars(
     png_path: Path | str = None,
     color_palette: str = "Plotly",
     null_label: str = "<NA>",
-) -> object:
+) -> plotly.graph_objects:
     """
     Generates a stacked bar plot using the provided DataFrame.
 
@@ -220,7 +221,7 @@ def plot_stacked_bars(
     - A Plotly figure object representing the stacked bar chart.
     """
     BAR_LENGTH_MULTIPLIER = 1.05
-
+    
     # * 2 axis means at least 2 columns
     if len(df.columns) < 2 or len(df.columns) > 3:
         print("❌ df must have exactly 2 or 3 columns")
@@ -263,39 +264,47 @@ def plot_stacked_bars(
         .sum()
         .reset_index()
     )
+
+    # * add total as aggregation of df
+    if show_total:
+        df_total = df.groupby(df.columns[1], observed=True, as_index=False)[df.columns[2]].sum()
+        df_total[df.columns[0]] = " Total"
+        df = pd.concat([df, df_total], ignore_index=True)
+
+
+    # * apply top_n, reduce df
+    n_col = top_n_color if top_n_color > 0 else None
+    n_idx = top_n_index if top_n_index > 0 else None
+
+    unique_colors = sorted(
+        df.groupby(col_color)[df.columns[2]]
+        .sum()
+        .sort_values(ascending=False)
+        .index.tolist()[:n_col]
+    )
     
-    # * Sorting logic based on sort_values
+    unique_idx = df[col_index].sort_values().unique()[:n_idx]
+
+    df = df[df[col_color].isin(unique_colors)]#.sort_values(by=[col_index, col_color])
+    df = df[df[col_index].isin(unique_idx)]#.sort_values(by=[col_index, col_color])
+
+
+    # # * 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
+    # # * 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)
+    column_colors = assign_column_colors(
+        columns=unique_colors,
+        color_palette=color_palette, 
+        null_label=null_label
+        )
 
     # * calculate n
     divider = 2 if show_total else 1
@@ -308,13 +317,24 @@ def plot_stacked_bars(
     _title_str_n = f", n={n:_}"
     caption = _set_caption(caption)
 
+        # * after grouping add cols for pct and formatting
+    df["pct"] = df[df.columns[2]].apply(lambda x: f"{(x / n) * 100:.{precision}f}%")
+
+    # * format output
+    df["cnt_str"] = df[df.columns[2]].apply(lambda x: f"{x:_.{precision}f}")
+
+    divider2 = "<br>" if orientation == "v" else " "
+    df["cnt_pct_str"] = df.apply(
+        lambda row: f"{row['cnt_str']}{divider2}({row['pct']})", axis=1
+    )
+
     # * plot
     fig = px.bar(
         df,
         x=col_index if orientation == "v" else df.columns[2],
         y=df.columns[2] if orientation == "v" else col_index,
         color=col_color,
-        text=df.columns[2],
+        text="cnt_pct_str" if normalize else "cnt_str",
         orientation=orientation,
         title=title
         or f"{caption}{_title_str_top_index}[{col_index}] by {_title_str_top_color}[{col_color}]{_title_str_null}{_title_str_n}",
@@ -323,9 +343,9 @@ 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 = (
         df.groupby(col_index)[df.columns[2]].sum().sort_values(ascending=False).iloc[0]
@@ -488,7 +508,10 @@ def plot_bars(
 
     # * after grouping add cols for pct and formatting
     df["pct"] = df[df.columns[1]] / n
+
+    # * format output
     df["cnt_str"] = df[df.columns[1]].apply(lambda x: f"{x:_.{precision}f}")
+
     divider = "<br>" if orientation == "v" else " "
     df["cnt_pct_str"] = df.apply(
         lambda row: f"{row['cnt_str']}{divider}({row['pct']:.1%})", axis=1
@@ -991,7 +1014,7 @@ def plot_boxes(
     points: Literal["all", "outliers", "suspectedoutliers", None] = None,
     precision: int = 2,
     height: int = 600,
-    width: int = 800,
+    width: int = 1200,
     annotations: bool = True,
     summary: bool = True,
     title: str = None,
@@ -1018,7 +1041,7 @@ def plot_boxes(
     if (
         len(df.columns) != 2
         or not (
-            (pd.api.types.is_string_dtype(df.iloc[:, 0]))
+            (pd.api.types.is_object_dtype(df.iloc[:, 0]))
             or (pd.api.types.is_bool_dtype(df.iloc[:, 0]))
         )
         or not pd.api.types.is_numeric_dtype(df.iloc[:, 1])
@@ -1124,7 +1147,7 @@ def plot_boxes(
 
     fig.show("png")
     if summary:
-        print_summary(df)
+        print_summary(df=df, precision=precision)
 
     # * save to png if path is provided
     if png_path is not None:

pandas_plots/tbl.py

@@ -15,7 +15,7 @@ from plotly.subplots import make_subplots
 from scipy import stats
 import dataframe_image as dfi
 
-from .hlp import wrap_text
+from .hlp import wrap_text, to_series
 
 import duckdb as ddb
 
@@ -696,7 +696,7 @@ def show_num_df(
 
 
 
-def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str="🟠 "):
+def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str=" ", precision: int=3):
     """
     Print statistical summary for a pandas DataFrame or Series.
 
@@ -712,15 +712,44 @@ def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str="
         df (Union[pd.DataFrame, pd.Series]): Input DataFrame or Series. Only numeric columns 
         in DataFrame are considered.
         show (bool, optional): Whether to print the summary. Defaults to True.
-        name (str, optional): Prefix for the summary. Defaults to "🟠 "
+        name (str, optional): Prefix for the summary. Defaults to " ".
+        precision (int, optional): Number of digits to round the results to. Defaults to 3.
     """
     if df.empty:
         return 
 
     # * drop NA to keep scipy sane
-    df = df.dropna().copy()
+    df = df.dropna().copy()    
 
-    def print_summary_ser(ser: pd.Series, show: bool=True, name: str=""):
+    # display(df)
+
+    if len(df.columns) == 1:
+        df = df.to_series()
+    
+    pd.api.types.is_numeric_dtype(df) 
+
+
+    if not (
+        # * series must be numeric
+        (isinstance(df, pd.Series)
+            and pd.api.types.is_numeric_dtype(df)
+        )
+        or 
+        # * df must have 2 columns str num
+        (len(df.columns) == 2
+            and (
+                (pd.api.types.is_object_dtype(df.iloc[:, 0]))
+                or (pd.api.types.is_bool_dtype(df.iloc[:, 0]))
+                )
+            and pd.api.types.is_numeric_dtype(df.iloc[:, 1])
+        )
+    ):
+        print(f"❌ df must have 2 columns: [0] str or bool, [1] num, or be a series")
+        return
+
+
+
+    def print_summary_ser(ser: pd.Series, show: bool=True, name: str="", precision: int=3):
         # Calculate IQR and pass `rng=(25, 75)` to get the interquartile range
         iqr_value = stats.iqr(ser)
 
@@ -728,21 +757,21 @@ def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str="
         # ser.dropna(inplace=True)
 
         # Using the iqr function, we still calculate the bounds manually
-        q1 = stats.scoreatpercentile(ser, 25)
-        q3 = stats.scoreatpercentile(ser, 75)
+        q1 = round(stats.scoreatpercentile(ser, 25), precision)
+        q3 = round(stats.scoreatpercentile(ser, 75), precision)
 
         # 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)
+        min = round(ser.min(), precision)
+        med = round(ser.median(), precision)
+        upper = round(q3 + 1.5 * iqr_value, precision)
+        lower = round(q1 - 1.5 * iqr_value, precision)
+        mean = round(ser.mean(), precision)
+        std = round(ser.std(), precision)
+        cv = round(ser.std() / ser.mean(), precision)
+        max = round(ser.max(), precision)
+        sum = round(ser.sum(), precision)
+        skew = round(stats.skew(ser.dropna().tolist()), precision)
+        kurto = round(stats.kurtosis(ser.dropna().tolist()), precision)
         
         lower = min if lower < min else lower
         upper = max if upper > max else upper
@@ -750,7 +779,7 @@ def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str="
         # * extra care for scipy metrics, these are very vulnarable to nan
         if show:
             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}""")
+                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}""")
 
         summary = {
             "min": min,
@@ -770,11 +799,22 @@ def print_summary(df: pd.DataFrame | pd.Series, show: bool = True, name: str="
         return summary
 
     if isinstance(df, pd.Series):
-        return print_summary_ser(df, show=show, name=name)
+        # * print serie
+        name = df.name if df.name else "series"
+        print_summary_ser(ser=df, show=show, name=name, precision=precision)
+        return
 
     if isinstance(df, pd.DataFrame):
-        # * only show numerics
-        for col in df.select_dtypes("number").columns:
-            summary = print_summary_ser(ser=df[col],show=show, name=col)
+        # * print for all values
+        print(f"🟧 all data")
+        name = df.columns[-1]
+        summary = print_summary_ser(ser=df.iloc[:,1], show=show, name=name, precision=precision)
+
+        print(f"🟧 boxes")
+        # * print for each value
+        for item in df.iloc[:,0].unique():
+            # display(df[df.iloc[:,0] == item])
+            print_summary_ser(ser=df[df.iloc[:,0] == item].iloc[:,1], show=show, name=item, precision=precision)
 
     return summary
+

{pandas_plots-0.12.6.dist-info → pandas_plots-0.12.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pandas-plots
-Version: 0.12.6
+Version: 0.12.7
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier

pandas_plots-0.12.7.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=WpQ8hPmp8MbHvgEvSejDYFXyY_hZabLY4OLW8S6u15g,44310
+pandas_plots/tbl.py,sha256=tuTDRFaD4lKQ2fMeMCJwnJL65zXuUGVQ6uwQNVa0y6Q,31883
+pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
+pandas_plots-0.12.7.dist-info/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
+pandas_plots-0.12.7.dist-info/METADATA,sha256=9i_TsDQinaUPz9eqJO7a0L4JFZmmM3l_WzoPbmDPH0Y,7358
+pandas_plots-0.12.7.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+pandas_plots-0.12.7.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots-0.12.7.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
+pandas_plots-0.12.7.dist-info/RECORD,,

pandas_plots-0.12.6.dist-info/RECORD

@@ -1,11 +0,0 @@
-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,,