pandas-plots 0.15.2__tar.gz → 0.15.4__tar.gz

{pandas_plots-0.15.2 → pandas_plots-0.15.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pandas-plots
-Version: 0.15.2
+Version: 0.15.4
 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
@@ -16,7 +16,7 @@ Classifier: Programming Language :: Python :: 3
 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

{pandas_plots-0.15.2 → pandas_plots-0.15.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pandas-plots"
-version = "0.15.2"
+version = "0.15.4"
 description = "A collection of helper for table handling and visualization"
 long_description = "file: README.md"
 long_description_content_type = "text/markdown"
@@ -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-0.15.2 → pandas_plots-0.15.4}/src/pandas_plots/pls.py

@@ -375,19 +375,24 @@ def plot_stacked_bars(
     caption = _set_caption(caption)
 
     # * after grouping add cols for pct and formatting
-    df["cnt_pct_all_only"] = df["value"].apply(lambda x: f"{(x / n) * 100:.{precision}f}%")
-    df["cnt_pct_bar_only"] = (df["value"] / bar_totals * 100).apply(lambda x: f"{x:.{precision}f}%")
+    df["cnt_pct_all_only"] = (df["value"] / n * 100).apply(lambda x: f"{(x):.{precision}f}%")
+    df["cnt_pct_bar_only"] = (df["value"] / bar_totals * 100).apply(lambda x: f"{(x):.{precision}f}%")
 
     # * format output
     df["cnt_str"] = df["value"].apply(lambda x: f"{x:_.{precision}f}")
 
     divider2 = "<br>" if orientation == "v" else " "
     
+    # Modify this section
     df["cnt_pct_all_str"] = df.apply(
-        lambda row: f"{row['cnt_str']}{divider2}({row['cnt_pct_all_only']})", axis=1
+        lambda row: f"{row['cnt_str']}{divider2}({row['cnt_pct_all_only']})"
+        if (row["value"] / n * 100) >= 5 else row["cnt_str"],
+        axis=1
     )
     df["cnt_pct_bar_str"] = df.apply(
-        lambda row: f"{row['cnt_str']}{divider2}({row['cnt_pct_bar_only']})", axis=1
+        lambda row: f"{row['cnt_str']}{divider2}({row['cnt_pct_bar_only']})"
+        if (row["value"] / bar_totals.loc[row.name] * 100) >= 5 else row["cnt_str"],
+        axis=1
     )
 
     text_to_show = "cnt_str"
@@ -564,13 +569,21 @@ 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 +1207,10 @@ 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-0.15.2 → pandas_plots-0.15.4}/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(