plot-misc 2.0.3__tar.gz → 2.1.0__tar.gz

plot_misc-2.1.0/MANIFEST.in

@@ -0,0 +1,16 @@
+# include top-level metadata
+include README.md LICENSE
+include requirements.txt
+include requirements-dev.txt
+
+# ship the example datasets explicitly
+recursive-include plot_misc/example_data/example_datasets *.tsv.gz *.txt
+
+# drop these 
+prune tests
+prune resources
+
+# drop the rest
+global-exclude .*
+global-exclude *.py[cod]
+global-exclude __pycache__/*

{plot_misc-2.0.3 → plot_misc-2.1.0}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: plot-misc
-Version: 2.0.3
+Version: 2.1.0
 Summary: Various plotting templates built on top of matplotlib
 Author-email: A Floriaan Schmidt <floriaanschmidt@gmail.com>
 License-Expression: GPL-3.0-or-later
 Project-URL: Homepage, https://gitlab.com/SchmidtAF/plot-misc
+Project-URL: Documentation, https://schmidtaf.gitlab.io/plot-misc/
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
@@ -14,20 +15,30 @@ Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: pandas
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: scipy
-Requires-Dist: scikit-learn
-Requires-Dist: adjustText
+Requires-Dist: pandas>=1.3
+Requires-Dist: numpy>=1.21
+Requires-Dist: matplotlib>=3.5
+Requires-Dist: seaborn>=0.11
+Requires-Dist: scipy>=1.5
+Requires-Dist: statsmodels>=0.1
+Requires-Dist: scikit-learn>=1.4
+Requires-Dist: adjustText>=1.3
 Provides-Extra: dev
+Requires-Dist: python-build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
-Requires-Dist: build; extra == "dev"
+Requires-Dist: setuptools; extra == "dev"
+Requires-Dist: wheel; extra == "dev"
+Requires-Dist: pytest>=6; extra == "dev"
+Requires-Dist: pytest-mock>=3; extra == "dev"
+Requires-Dist: pytest-dependency>=0.5; extra == "dev"
+Requires-Dist: bump2version>=1; extra == "dev"
+Requires-Dist: jupyter; extra == "dev"
 Dynamic: license-file
 
+<img src="https://schmidtaf.gitlab.io/plot-misc/_images/icon.png" alt="plot-misc icon" width="250"/>
+
 # A collection of plotting functions
-__version__: `2.0.3`
+__version__: `2.1.0`
 
 This repository collects plotting modules written on top of `matplotlib`.
 The functions are intended to set up light-touch, basic illustrations that
@@ -60,7 +71,7 @@ To install from this channel, run:
 
 
 ```sh
-conda install afschmidt::plot_misc
+conda install afschmidt::plot-misc
 ```
 
 ### Installation using gitlab

{plot_misc-2.0.3 → plot_misc-2.1.0}/README.md

@@ -1,5 +1,7 @@
+<img src="https://schmidtaf.gitlab.io/plot-misc/_images/icon.png" alt="plot-misc icon" width="250"/>
+
 # A collection of plotting functions
-__version__: `2.0.3`
+__version__: `2.1.0`
 
 This repository collects plotting modules written on top of `matplotlib`.
 The functions are intended to set up light-touch, basic illustrations that
@@ -32,7 +34,7 @@ To install from this channel, run:
 
 
 ```sh
-conda install afschmidt::plot_misc
+conda install afschmidt::plot-misc
 ```
 
 ### Installation using gitlab

plot_misc-2.1.0/plot_misc/_version.py

@@ -0,0 +1 @@
+__version__ = '2.1.0'

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/barchart.py

@@ -21,9 +21,9 @@ group_bar(data, label, columns, ...)
     Plot a grouped bar chart with multiple bars per group, optionally
     with error bars.
 """
-import matplotlib.pyplot as plt
 import pandas as pd
 import numpy as np
+import matplotlib.pyplot as plt
 from plot_misc.utils.utils import _update_kwargs
 from plot_misc.errors import (
     is_type,
@@ -56,7 +56,7 @@ def bar(data:pd.DataFrame, label:str, column:str,
         The column name for the bar height values.
     error_max : `str`, default `NoneType`
         column name for the upper value of the error line segment.
-    error_min : ``str` default `NoneType`
+    error_min : `str`, default `NoneType`
         column name for the lower value of the error line segment.
     colours : `list` [`str`], default ['tab:blue', 'tab:pink']
         Colours for the bars; recycled if shorter than the number of bars.
@@ -83,6 +83,14 @@ def bar(data:pd.DataFrame, label:str, column:str,
         Matplotlib figure object.
     ax : plt.Axes
         Matplotlib axes with the rendered bar plot.
+    
+    Notes
+    -----
+    This function is essentially a helper function for the more complicated
+    bar charts in this module and simply wraps matplotlib's bar function.
+    It is included as a public function to allow people to use the same
+    interface when working with plot-misc. If one is exclusively looking to
+    use `bar` it is advisable to simply revert to matplotlib's offering.
     """
     # check input
     is_df(data)
@@ -235,30 +243,30 @@ def stack_bar(data:pd.DataFrame, label:str, columns:list[str],
                              'number of colours ({1}).'.format(
                                  len(columns), len(colours)))
     # get labels
-    labels = data[label]
+    # labels = data[label]
     # get columns
     fields=columns
     # actual plotting
     left = len(data) * [0]
     for idx, name in enumerate(fields):
+        new_kwargs = _update_kwargs(update_dict=kwargs,
+                                    edgecolor=edgecolour,
+                                    color=colours[idx],
+                                    alpha=transparency,
+                                    )
         if horizontal == False:
-            # plotting vertical bar chart
-            new_kwargs = _update_kwargs(update_dict=kwargs,
-                                        edgecolor=edgecolour,
-                                        width=wd, color=colours[idx],
-                                        alpha=transparency,
+            new_kwargs = _update_kwargs(new_kwargs, bottom=left,
                                         )
-            ax.bar(labels, height=data[name], bottom=left, **new_kwargs,
-                   )
         else:
-            # horizontal bar chart
-            new_kwargs = _update_kwargs(update_dict=kwargs, edgecolor=edgecolour,
-                                        height=wd, color=colours[idx],
-                                        alpha=transparency,
+            new_kwargs = _update_kwargs(new_kwargs, left=left,
                                         )
-            ax.barh(labels, width=data[name], left=left, **new_kwargs,
+        # The actual plotting
+        # NOTE adding wd here because it bar assigns it to either width or
+        # height depending on horizontal.
+        _, ax = bar(data=data, label=label, column=name, horizontal=horizontal,
+                    wd=wd, ax=ax, kwargs_bar=new_kwargs,
                     )
-        # update the locations
+        # updating the coordinate where the last bar stops
         left = left + data[name]
     # removing spines
     ax.spines['right'].set_visible(False)

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/example_data/examples.py

@@ -635,3 +635,92 @@ def load_mace_associations(**kwargs):
     )
     # return
     return df
+
+# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+def create_survival_data(nrows:int = 50,
+                         survival_rate:float = 0.02,
+                         ci_width:float=0.15,
+                         random_seed:int = 42,
+                         initial_n:int = 1000) -> pd.DataFrame:
+    """
+    Create pilot survival analysis data for testing.
+    
+    Parameters
+    ----------
+    nrows : int, default 50
+        Number of time points to generate
+    random_seed : int, default 42
+        Random seed for reproducibility
+    initial_n : int, default 1000
+        Initial number of subjects at risk at time zero
+        
+    Returns
+    -------
+    pd.DataFrame
+        DataFrame with survival data including survival estimates,
+        confidence intervals, and at-risk counts
+    """
+    np.random.seed(random_seed)
+    
+    # Create time points
+    time_points = np.linspace(0, 100, nrows)
+    
+    # Generate decreasing survival function with some noise
+    base_survival = np.exp(-time_points * survival_rate)  # Exponential decay
+    noise = np.random.normal(0, 0.01, nrows)
+    survival = np.clip(base_survival + noise, 0, 1)
+    
+    # Ensure monotonic decrease
+    survival = np.minimum.accumulate(survival)
+    
+    # Generate confidence intervals
+    ci_width = ci_width * survival  # CI width proportional to survival
+    lower_ci = np.clip(survival - ci_width, 0, 1)
+    upper_ci = np.clip(survival + ci_width, 0, 1)
+    
+    # Generate at-risk numbers directly from survival probabilities
+    at_risk = (survival * initial_n).astype(int)
+    
+    # Create DataFrame
+    df = pd.DataFrame({
+        'survival_estimate': survival,
+        'lower_ci_95': lower_ci,
+        'upper_ci_95': upper_ci,
+        'at_risk': at_risk,
+        'time': time_points
+    })
+    
+    df.set_index('time', inplace=True)
+    return df
+
+# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+@dataset
+def load_survival_table(**kwargs):
+    """
+    Returns a survival table with information on the `time` (in days) an event
+    occured the cummulative events per discordancy group. The time per year
+    is provided as the time_format column.
+    
+    Returns
+    -------
+    pd.DataFrame
+    """
+    # data
+    table = pd.DataFrame(
+        {
+            'time': [0, 365, 730, 1095, 1461, 1826, 2191, 2556, 2922, 3287,
+                     3652, 4017, 4383, 4748, 5113, 5478],
+            'Not Discordant': ['268,196', '263,426', '258,484', '254,009',
+                               '249,315', '244,907', '240,562', '236,574',
+                               '233,347', '230,368', '227,648', '224,916',
+                               '222,169', '172,545', '95,987', '15,280'],
+            'Discordant': ['5,749', '5,629', '5,494', '5,374',
+                                 '5,245', '5,129', '5,029', '4,935',
+                                 '4,863', '4,777', '4,714', '4,634',
+                                 '4,558', '3,586', '2,030', '346'],
+            'time_format': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]
+        }, **kwargs,
+    )
+    # return
+    return table
+

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/forest.py

@@ -394,9 +394,9 @@ class ForestPlot(object):
         - 'max' : float
             The upper bound of the span in data coordinates.
         - 'kwargs' : dict
-        A dictionary of keyword arguments to be passed to the span plotting
-        function (e.g., `ax.axhspan()`), such as `facecolor`, `alpha`,
-        `zorder`, etc.
+            A dictionary of keyword arguments to be passed to the span plotting
+            function (e.g., `ax.axhspan()`), such as `facecolor`, `alpha`,
+            `zorder`, etc.
     
     Notes
     -----
@@ -1000,15 +1000,15 @@ class EmpericalSupport(object):
     -----
     This implementation is based on the concept of compatibility (or
     confidence) curves, which visualise the range of parameter values supported
-    by the data across a continuum of alpha levels [1]_, [2]_.
+    by the data across a continuum of alpha levels [ES1]_, [ES2]_.
     
     References
     ----------
-    .. [1] Amrhein, V., Greenland, S., & McShane, B. B. (2019).
+    .. [ES1] Amrhein, V., Greenland, S., & McShane, B. B. (2019).
        Scientists rise up against statistical significance.
        *Nature*, 567(7748), 305–307. https://doi.org/10.1038/d41586-019-00857-9
     
-    .. [2] Van der Burg, S. H., & Gelman, A. (2020).
+    .. [ES2] Van der Burg, S. H., & Gelman, A. (2020).
        Empirical support plots and compatibility intervals.
        *BMC Medical Research Methodology*, 20, Article 109.
        https://doi.org/10.1186/s12874-020-01105-9

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/heatmap.py

@@ -28,7 +28,9 @@ from the example published in the official matplotlib gallery [1]_.
 
 References
 ----------
-.. [1] https://matplotlib.org/stable/gallery/images_contours_and_fields/image_annotated_heatmap.html
+.. [1] Matplotlib contributors. "Creating annotated heatmaps."
+Matplotlib Gallery.
+https://matplotlib.org/stable/gallery/images_contours_and_fields/image_annotated_heatmap.html
 """
 
 # modules
@@ -105,7 +107,13 @@ def heatmap(data:pd.DataFrame | np.ndarray, row_labels:list[str] | np.ndarray,
     The returned objects can be used to annotate the cells using for example
     `annotate_heatmap`.
     
-    This function is adapted from the matplotlib gallery example [1]_.
+    This function is adapted from the matplotlib gallery example [HM1]_.
+    
+    References
+    ----------
+    .. [HM1] Matplotlib contributors. "Creating annotated heatmaps."
+            Matplotlib Gallery.
+            https://matplotlib.org/stable/gallery/images_contours_and_fields/image_annotated_heatmap.html
     """
     
     # create a axes if needed

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/incidencematrix.py

@@ -61,6 +61,8 @@ def draw_incidencematrix(
     margins:tuple[float,float] | None = None,
     grid_position:Literal['outline', 'centre'] | None = 'centre',
     ax:plt.Axes | None = None,
+    x_coords:list[Real] | None = None,
+    y_coords:list[Real] | None = None,
     break_limits:tuple[float, float] = (-np.inf, np.inf),
     size_data: pd.DataFrame | None = None,
     transparency_data: pd.DataFrame | None = None,
@@ -119,6 +121,14 @@ def draw_incidencematrix(
     ax : `plt.axes` or `None`, default `None`
         If provided, the plot is drawn on this axis. Otherwise, a new figure
         and axis are created.
+    x_coords : `list` [`real`] or `None`, default `None`
+        An optional list of x-coordinates to use for plotting the dots.
+        If `None`, dots are spaced evenly. Length must match number of
+        rows in `data`.
+    y_coords : `list` [`real`] or `None`, default `None`
+        An optional list of y-coordinates to use for plotting the dots.
+        If `None`, dots are spaced evenly. Length must match number of
+        columns in `data`.
     break_limits : `tuple` [`float`, `float`], default (-np.inf, np.inf)
         Lower and upper bounds for the first and final break. Used to define
         open-ended ranges in dot colouring. Currently only uses the lower
@@ -148,8 +158,9 @@ def draw_incidencematrix(
     
     Missing or non-matching entries in the input matrix will be ignored.
     """
-    SHAPE_ERR = ('`data` and `{0}` should have the same shapes '
+    SHAPE_ERR1 = ('`data` and `{0}` should have the same shapes '
                  'not: {1} and {2}, respectively.')
+    SHAPE_ERR2 = ('Length of {0}: {1} must match number of {2}: {3}.')
     # check inputs
     is_type(dot_size, list)
     is_type(dot_colour, list)
@@ -159,6 +170,8 @@ def draw_incidencematrix(
     is_type(grid_position, (str, type(None)))
     is_type(size_data, (type(None), pd.DataFrame))
     is_type(transparency_data, (type(None), pd.DataFrame))
+    is_type(x_coords, (type(None), list))
+    is_type(y_coords, (type(None), list))
     # check literals
     EXP_GRID = [NamesIM.GRID_POS_B, NamesIM.GRID_POS_O]
     if grid_position is not None and not grid_position in EXP_GRID:
@@ -168,11 +181,11 @@ def draw_incidencematrix(
     # make sure all the data have the same shape
     if size_data is not None and data.shape != size_data.shape:
         raise IndexError(
-            SHAPE_ERR.format('size_data', data.shape, size_data.shape
+            SHAPE_ERR1.format('size_data', data.shape, size_data.shape
                              ))
     if transparency_data is not None and data.shape != transparency_data.shape:
         raise IndexError(
-            SHAPE_ERR.format('transparency_data', data.shape,
+            SHAPE_ERR1.format('transparency_data', data.shape,
                              transparency_data.shape
                              ))
     # transpose - hack to make the output match the input row,col and order.
@@ -221,9 +234,24 @@ def draw_incidencematrix(
     dot_transparency_arr = _map_attributes(
         transparency_input, new_dot_transparency,
         break_limits=break_limits)
-    # the x and y coordinates
+    # All for user supplied coordinates and check these match the data shape
     M, N = data.shape
-    x, y = np.meshgrid(np.arange(M), np.arange(N))
+    if x_coords is not None:
+        x_coords_ = np.asarray(x_coords)
+        if len(x_coords_) != M:
+            raise ValueError(SHAPE_ERR2.format('x_coords', len(x_coords_),
+                                               'rows', M))
+    else:
+        x_coords_ = np.arange(M)
+    if y_coords is not None:
+        y_coords_ = np.asarray(y_coords)
+        if len(y_coords_) != N:
+            raise ValueError(SHAPE_ERR2.format('y_coords', len(y_coords_),
+                                               'columns', N))
+    else:
+        y_coords_ = np.arange(N)
+    # get the actual coordinates
+    x, y = np.meshgrid(x_coords_, y_coords_)
     xv = x.T.ravel()
     yv = y.T.ravel()
     col_flat = dot_colours_arr.ravel()

{plot_misc-2.0.3 → plot_misc-2.1.0}/plot_misc/machine_learning.py

@@ -79,7 +79,7 @@ def lollipop(values:np.ndarray, labels:np.ndarray,
              ax:plt.Axes | None=None,
              kwargs_lines_dict:dict[Any,Any] | None=None,
              kwargs_plot_dict:dict[Any,Any] | None=None,
-             ) -> tuple[plt.Axes, plt.Figure]:
+             ) -> tuple[plt.Figure, plt.Axes]:
     """
     Plots a lollipop chart.
     
@@ -960,7 +960,6 @@ class DecisionCurve(object):
         self.NET_BENEFIT = results
         self.CALCULATED=True
     # \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\
-    # NOTE add smoother paramter to allow for a different smoothing function.
     def plot(self,
              ax: plt.Axes | None = None,
              col_dict: dict[str,str] | None = None,