pandas-plots 0.12.19__py3-none-any.whl → 0.12.21__py3-none-any.whl

pandas_plots/hlp.py

@@ -22,29 +22,34 @@ from PIL import Image
 URL_REGEX = r"^(?:http|ftp)s?://"  # https://stackoverflow.com/a/1617386
 
 
-def mean_confidence_interval(df, confidence=0.95):
+def mean_confidence_interval(df, confidence=0.95, use_median=False):
     """
-    Calculate the mean and confidence interval of the input dataframe.
-    source: https://stackoverflow.com/questions/15033511/compute-a-confidence-interval-from-sample-data
+    Calculate the mean or median and confidence interval of the input dataframe.
+    Source: https://stackoverflow.com/questions/15033511/compute-a-confidence-interval-from-sample-data
 
     Parameters:
     df (array-like): The input dataframe.
     confidence (float, optional): The confidence level for the interval. Defaults to 0.95.
+    use_median (bool, optional): If True, calculates median and confidence interval instead of mean. Defaults to False.
 
     Returns:
-    tuple: A tuple containing the mean, interval, lower bound, and upper bound.
+    tuple: A tuple containing the central value (mean or median), interval, lower bound, and upper bound.
     """
     df = to_series(df)
     if df is None:
         return None
     a = 1.0 * np.array(df)
     n = len(a)
-    mean, se = np.mean(a), scipy.stats.sem(a)
-    # * calculate the margin of error for the confidence interval using the t-distribution with the specified confidence level.
-    margin = se * scipy.stats.t.ppf((1 + confidence) / 2.0, n - 1)
-    lower = mean - margin
-    upper = mean + margin
-    return mean, margin, lower, upper
+
+    if use_median:
+        median = np.median(a)
+        se = 1.253 * scipy.stats.sem(a)  # Approximate standard error for median
+        margin = se * scipy.stats.t.ppf((1 + confidence) / 2.0, n - 1)
+        return median, margin, median - margin, median + margin
+    else:
+        mean, se = np.mean(a), scipy.stats.sem(a)
+        margin = se * scipy.stats.t.ppf((1 + confidence) / 2.0, n - 1)
+        return mean, margin, mean - margin, mean + margin
 
     # # * Alternative
     # # from statistics import NormalDist
@@ -522,33 +527,47 @@ def find_cols(all_cols: list[str], stubs: list[str] = None) -> list[str]:
 # * extend objects to enable chaining
 pd.DataFrame.find_cols = find_cols
 
-def add_measures_to_pyg_config(json_path: str, nodes: list[tuple[str, str]]) -> None:
+
+def add_measures_to_pyg_config(json_path: str, nodes: list[tuple[str, str]] = [("cnt_tum", "count(distinct z_tum_id)")], strict: bool = False) -> None:
     """
-    Reads a pygwalker json config file, adds new measures from given nodes if not already present, and writes back to the file.
+    Reads a pygwalker JSON config file, adds new measures from given nodes if not already present, and writes back to the file.
 
     Parameters
     ----------
     json_path : `str`
-        The path to the pyg_json config file.
-    nodes : `list[tuple[str, str]]`
-        A list of tuples, where the first element in the tuple is the name of the measure and the second element is the SQL expression that defines the measure.
+        The path to the pygwalker JSON config file.
+    nodes : `list[tuple[str, str]]`, optional
+        A list of tuples, where the first element in the tuple is the name of the measure and the second element is the SQL expression that defines the measure. Default is `[('cnt_tum', 'count(distinct z_tum_id)')]`.
+    strict : `bool`, optional
+        If True, raises an error if the file does not exist or if JSON parsing fails. If False, the function exits silently in such cases. Default is False.
 
     Returns
     -------
     None
-    
+
     Example
     -------
-    `node = [("cnt_tum", "count(distinct z_tum_id)")]`
-    """
+    default: `add_measures_to_pyg_config('config.json', [('cnt_tum', 'count(distinct z_tum_id)')], strict=True)`
     
-    with open(json_path, "r", encoding="utf-8") as file:
-        config = json.load(file)
+    usage: start pygwalker with empty config file but defined config path. make changes on the chart, save the config file. then run this function again - measures will be added
+    """
+    if not os.path.exists(json_path):
+        if strict:
+            raise FileNotFoundError(f"File not found: {json_path}")
+        return
+
+    try:
+        with open(json_path, "r", encoding="utf-8") as file:
+            config = json.load(file)
+    except json.JSONDecodeError:
+        if strict:
+            raise
+        return
 
     for node in nodes:
         fid = uuid.uuid4().hex
         
-        # Define the measure
+        # * Define the measure
         new_json_node = {
             "analyticType": "measure",
             "fid": f"{fid}",
@@ -563,13 +582,13 @@ def add_measures_to_pyg_config(json_path: str, nodes: list[tuple[str, str]]) ->
             }
         }
 
-        # Get the measures list
-        measures = config["config"][0]["encodings"]["measures"]
+        # * Get the measures list
+        measures = config.get("config", [{}])[0].get("encodings", {}).get("measures", [])
 
-        # Ensure the measure is present
+        # * Ensure the measure is present
         if not any(measure.get("name") == node[0] for measure in measures):
             measures.append(new_json_node)
 
-    # Write the updated JSON back to the file
+    # * Write the updated JSON back to the file
     with open(json_path, "w", encoding="utf-8") as file:
         json.dump(config, file, indent=2)

pandas_plots/pls.py

@@ -500,6 +500,7 @@ def plot_bars(
     width: int = 1600,
     title: str = None,
     use_ci: bool = False,
+    ci_agg: Literal["mean", "median"] = "mean",
     precision: int = 0,
     renderer: Literal["png", "svg", None] = "png",
     png_path: Path | str = None,
@@ -569,9 +570,9 @@ def plot_bars(
                 dropna=False,
             )
             .agg(
-                mean=(col_name, "mean"),
+                mean=(col_name, ci_agg),
                 # * retrieve margin from custom func
-                margin=(col_name, lambda x: mean_confidence_interval(x)[1]),
+                margin=(col_name, lambda x: mean_confidence_interval(x, use_median = (ci_agg == "median"))[1]),
             )
             .reset_index()
         )
@@ -653,7 +654,7 @@ def plot_bars(
 
     # * title str n
     _title_str_n = (
-        f", n={n_len:_} ({n:_})" if not use_ci else f", n={n_len:_})<br><sub>ci(95) on means<sub>"
+        f", n={n_len:_} ({n:_})" if not use_ci else f", n={n_len:_})<br><sub>ci(95) on {ci_agg}s<sub>"
     )
 
     # * title str na
@@ -965,6 +966,7 @@ def plot_box(
     violin: bool = False,
     x_min: float = None,
     x_max: float = None,
+    use_log: bool = False,
     png_path: Path | str = None,
 ) -> object:
     """
@@ -977,10 +979,13 @@ def plot_box(
         height: The height of the plot.
         width: The width of the plot.
         annotations: Whether to add annotations to the plot.
-        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
+        summary: Whether to add a summary table to the plot.
+        caption: The caption for the plot.
+        title: The title of the plot.
+        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).
+        use_log: Use logarithmic scale for the axis.
         png_path (Path | str, optional): The path to save the image as a png file. Defaults to None.
 
     Returns:
@@ -993,7 +998,7 @@ def plot_box(
     # * drop na to keep scipy sane
     n_ = len(ser)
     ser.dropna(inplace=True)
-    n = len(ser)
+    # n = len(ser)
 
     # hack
     median = ser.median()
@@ -1011,7 +1016,6 @@ def plot_box(
     lvl3 = height * 0.25
 
     caption = _set_caption(caption)
-
     dict = {
         "data_frame": ser,
         "orientation": "h",
@@ -1020,7 +1024,9 @@ def plot_box(
         "width": width,
         "points": points,
         # 'box':True,
-        "title": f"{caption}[{ser.name}], n = {n_:_}({n:_})" if not title else title,
+        "log_x": use_log,   # * logarithmic scale, axis is always x
+        # "notched": True,
+        "title": f"{caption}[{ser.name}], n = {n_:_}" if not title else title,
     }
 
     fig = px.violin(**{**dict, "box": True}) if violin else px.box(**dict)
@@ -1119,6 +1125,8 @@ def plot_boxes(
     annotations: bool = True,
     summary: bool = True,
     title: str = None,
+    use_log: bool = False,
+    box_width: float = 0.5,
     png_path: Path | str = None,
 ) -> object:
     """
@@ -1133,6 +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.
         png_path (Path | str, optional): The path to save the image as a png file. Defaults to None.
 
     Returns:
@@ -1170,11 +1179,14 @@ def plot_boxes(
         df,
         x=df.iloc[:, 0],
         y=df.iloc[:, 1],
+        color=df.iloc[:, 0],
         template="plotly_dark" if os.getenv("THEME") == "dark" else "plotly",
         orientation="v",
         height=height,
         width=width,
         points=points,
+        log_y=use_log,
+        # color_discrete_sequence=px.colors.qualitative.Plotly,
         title=(
             f"{caption}[{df.columns[0]}] on [{df.columns[1]}], n = {len(df):_.0f}"
             if not title
@@ -1245,6 +1257,9 @@ def plot_boxes(
 
     fig.update_xaxes(title_text=df.columns[0])
     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.show("png")
     if summary:

{pandas_plots-0.12.19.dist-info → pandas_plots-0.12.21.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: pandas-plots
-Version: 0.12.19
+Version: 0.12.21
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
 Author-email: dexterDSDo@googlemail.com
-License: "MIT"
+License: MIT
 Project-URL: Documentation, https://github.com/smeisegeier/pandas-plots
 Project-URL: Source Code, https://github.com/smeisegeier/pandas-plots
 Project-URL: Bug Tracker, https://github.com/smeisegeier/pandas-plots/issues

pandas_plots-0.12.21.dist-info/RECORD

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

{pandas_plots-0.12.19.dist-info → pandas_plots-0.12.21.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (77.0.1)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

pandas_plots-0.12.19.dist-info/RECORD

@@ -1,11 +0,0 @@
-pandas_plots/hlp.py,sha256=hlz7kKe6iDsz6Ov5YadX9zT5E01DHy7gHdVPgG8P7nQ,19656
-pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots/pls.py,sha256=S9hKQTPp8XIL9RmzvfeSQE4t2jm18bG4bejwcd-dJF4,48236
-pandas_plots/tbl.py,sha256=LxMKJh4qkGuQZ1DdCZIq1tMS26F6elsqbe_uabvQx4E,32535
-pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
-pandas_plots-0.12.19.dist-info/licenses/LICENSE,sha256=6KQ5KVAAhRaB-JJKpX4cefKvRZRgI7GUPc92_2d31XY,1051
-pandas_plots-0.12.19.dist-info/METADATA,sha256=qvKq6iuJK8dg9hXtwz8f0djqvtjdXmCQBbly_opRf40,7566
-pandas_plots-0.12.19.dist-info/WHEEL,sha256=tTnHoFhvKQHCh4jz3yCn0WPTYIy7wXx3CJtJ7SJGV7c,91
-pandas_plots-0.12.19.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots-0.12.19.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
-pandas_plots-0.12.19.dist-info/RECORD,,