pandas-plots 0.12.21__py3-none-any.whl → 0.12.22__py3-none-any.whl

pandas_plots/hlp.py

@@ -195,7 +195,8 @@ def wrap_text(
         line = line + word_s + " "
         # * reset if counter exceeds limit, or if word ends with newline
         if i >= max_items_in_line or str(word).endswith("\n"):
-            out = out + line + "\n"
+            # out = out + line + "\n"
+            out = out + line.rstrip() + "  \n"
             line = ""
             i = 0
         # else:

pandas_plots/pls.py

@@ -1141,7 +1141,7 @@ def plot_boxes(
         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.
-        use_log (bool): Whether to use logarithmic scale for the plot.
+        use_log (bool): Whether to use logarithmic scale for the plot (cannot show negative values).
         png_path (Path | str, optional): The path to save the image as a png file. Defaults to None.
 
     Returns:
@@ -1259,7 +1259,7 @@ def plot_boxes(
     fig.update_yaxes(title_text=df.columns[1])
     fig.update_layout(boxmode="group")  # Ensures boxes are not too compressed
     fig.update_layout(showlegend=False)
-    fig.update_traces(marker=dict(size=7), width=box_width)  # Adjust width (default ~0.5)
+    fig.update_traces(marker=dict(size=5), width=box_width)  # Adjust width (default ~0.5)
 
     fig.show("png")
     if summary:

pandas_plots/tbl.py

@@ -121,14 +121,14 @@ def describe_df(
         if df[col].notna().sum() == 0 and df[col].dtype == "float":
             df[col] = df[col].astype(str)
 
-    print(f"🔵 {'*'*3} df: {caption} {'*'*3}")
-    print(f"🟣 shape: ({df.shape[0]:_}, {df.shape[1]}) columns: {np.array(df.columns)} ")
+    print(f"🔵 {'*'*3} df: {caption} {'*'*3}  ")
+    print(f"🟣 shape: ({df.shape[0]:_}, {df.shape[1]}) columns: {np.array(df.columns)}  ")
     # print(f"🟣 shape: ({df.shape[0]:_}, {df.shape[1]}) columns: {df.columns.tolist()} ")
-    print(f"🟣 duplicates: {df.duplicated().sum():_}")
-    print(f"🟣 uniques: {wrap_text(str({col: f'{df[col].nunique():_}' for col in df})) }")
+    print(f"🟣 duplicates: {df.duplicated().sum():_}  ")
+    print(f"🟣 uniques: {wrap_text(str({col: f'{df[col].nunique():_}' for col in df})) }  ")
     # print(f"🟣 uniques: { {col: f'{df[col].nunique():_}' for col in df} }")
     # print(f"🟣 uniques: {{ {', '.join(f'{col}: {df[col].nunique():_}' for col in df)} }}")
-    print(f"🟣 missings: {wrap_text(str({col: f'{df[col].isna().sum():_}' for col in df})) }")
+    print(f"🟣 missings: {wrap_text(str({col: f'{df[col].isna().sum():_}' for col in df})) }  ")
     # print(f"🟣 missings: { {col: f'{df[col].isna().sum():_}' for col in df} }")
     # print(f"🟣 missings: {dict(df.isna().sum())}")
     
@@ -141,13 +141,13 @@ def describe_df(
         # unis = df[col].sort_values().unique()
         unis = list(df[col].value_counts().sort_index().index)
         # * get header
-        header = f"🟠 {col}({len(unis):_}|{df[col].dtype})"
+        header = f"🟠 {col}({len(unis):_}|{df[col].dtype})  "
         return unis, header
 
     # 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])}")
+        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
@@ -155,10 +155,10 @@ def describe_df(
         # * wrap output
         if use_columns:
                 print(
-                    f"{_h} {wrap_text(_u[:top_n_uniques], max_items_in_line=70, use_apo=is_str)}"
+                    f"{_h} {wrap_text(_u[:top_n_uniques], max_items_in_line=70, use_apo=is_str)}  "
                 )
 
-    print("--- column stats (numeric)")
+    print("--- column stats (numeric)  ")
     # * only show numerics
     for col in df.select_dtypes("number").columns:
         _u, _h = get_uniques_header(col)
@@ -793,7 +793,7 @@ 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,

{pandas_plots-0.12.21.dist-info → pandas_plots-0.12.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pandas-plots
-Version: 0.12.21
+Version: 0.12.22
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier

pandas_plots-0.12.22.dist-info/RECORD

@@ -0,0 +1,11 @@
+pandas_plots/hlp.py,sha256=i11Ep9P-u9O0bvexGTELRDUtmLzvNgNHxnkQTGf3DwQ,20838
+pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots/pls.py,sha256=APvF_cEYN28TtlpNNIJ2NPTA3chTP9ZHtwnVEuZ-skI,49059
+pandas_plots/tbl.py,sha256=RJWBHeKGTAhGpVCY57TsS_dYR-FpInP-TOsKW_tU4V4,32556
+pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
+pandas_plots-0.12.22.dist-info/licenses/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
+pandas_plots-0.12.22.dist-info/METADATA,sha256=0bdvEP5M1SgmSJI3QKLd8MX1RjSrwzxlXWrygQNjHaM,7564
+pandas_plots-0.12.22.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pandas_plots-0.12.22.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots-0.12.22.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
+pandas_plots-0.12.22.dist-info/RECORD,,

pandas_plots-0.12.21.dist-info/RECORD

@@ -1,11 +0,0 @@
-pandas_plots/hlp.py,sha256=uq-uXKgb9DtsrW_2cBmU-tf_akfEAcvPW2ma6YmKx7Y,20789
-pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots/pls.py,sha256=f890q1wYIGecRyzGxsMcmGPkE8v4JZmqXU56VWzC2ao,49029
-pandas_plots/tbl.py,sha256=LxMKJh4qkGuQZ1DdCZIq1tMS26F6elsqbe_uabvQx4E,32535
-pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
-pandas_plots-0.12.21.dist-info/licenses/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
-pandas_plots-0.12.21.dist-info/METADATA,sha256=UM2wZnlloV1PCL2wYPwIFUCIRE4zoVagON1AgqrSsxU,7564
-pandas_plots-0.12.21.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-pandas_plots-0.12.21.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots-0.12.21.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
-pandas_plots-0.12.21.dist-info/RECORD,,