upsetplot-bombcell 0.10.0__py3-none-any.whl

doc/conf.py

@@ -0,0 +1,289 @@
+# project-template documentation build configuration file, created by
+# sphinx-quickstart on Mon Jan 18 14:44:12 2016.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import os
+import re
+import sys
+import warnings
+
+# project root
+sys.path.insert(0, os.path.abspath(".."))
+
+import matplotlib  # noqa
+
+matplotlib.use("agg")
+warnings.filterwarnings(
+    "ignore",
+    category=UserWarning,
+    message="Matplotlib is currently using agg, which is a"
+    " non-GUI backend, so cannot show the figure."
+    "|(\n|.)*is non-interactive, and thus cannot be shown",
+)
+
+import sphinx_rtd_theme  # noqa
+from sphinx_gallery.sorting import ExampleTitleSortKey  # noqa
+from upsetplot import __version__ as release  # noqa
+
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx_gallery.gen_gallery",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autosummary",
+    "sphinx.ext.doctest",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.todo",
+    "numpydoc",
+    "sphinx.ext.ifconfig",
+    "sphinx.ext.viewcode",
+    "sphinx_issues",
+    "nbsphinx",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix of source filenames.
+source_suffix = ".rst"
+
+# The encoding of source files.
+# source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "upsetplot"
+copyright = "2018-2024, Joel Nothman"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+
+version = re.match(r"^\d+(\.\d+)*", release).group()
+
+# version = upsetplot.__version__
+# The full version, including alpha/beta/rc tags.
+# release = version
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+# language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+# today = ''
+# Else, today_fmt is used as the format for a strftime call.
+# today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ["_build"]
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+default_role = "any"
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+# add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+# add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+# show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# A list of ignored prefixes for module index sorting.
+# modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+# keep_warnings = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+# html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+# html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+# html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+# html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+# html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+# Add any extra paths that contain custom files (such as robots.txt or
+# .htaccess) here, relative to this directory. These files are copied
+# directly to the root of the documentation.
+# html_extra_path = []
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+# html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+# html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+# html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+# html_additional_pages = {}
+
+# If false, no module index is generated.
+# html_domain_indices = True
+
+# If false, no index is generated.
+# html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+# html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+# html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+# html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+# html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+# html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+# html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "project-templatedoc"
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    # 'preamble': '',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    ("index", "upsetplot.tex", "upsetplot Documentation", "Joel Nothman", "manual"),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+# latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+# latex_use_parts = False
+
+# If true, show page references after internal links.
+# latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+# latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+# latex_appendices = []
+
+# If false, no module index is generated.
+# latex_domain_indices = True
+
+# Documents to append as an appendix to all manuals.
+# texinfo_appendices = []
+
+# If false, no module index is generated.
+# texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+# texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+# texinfo_no_detailmenu = False
+
+
+# Example configuration for intersphinx: refer to the Python standard library.
+intersphinx_mapping = {
+    "python": ("http://docs.python.org/", None),
+    "numpy": ("https://docs.scipy.org/doc/numpy/", None),
+    "matplotlib": ("https://matplotlib.org/", None),
+    "pandas": ("https://pandas.pydata.org/pandas-docs/stable/", None),
+}
+
+
+# Config for sphinx_issues
+
+issues_uri = "https://github.com/jnothman/upsetplot/issues/{issue}"
+issues_github_path = "jnothman/upsetplot"
+issues_user_uri = "https://github.com/{user}"
+
+
+sphinx_gallery_conf = {
+    # path to your examples scripts
+    "examples_dirs": "../examples",
+    # path where to save gallery generated examples
+    "gallery_dirs": "auto_examples",
+    "backreferences_dir": "_modules",
+    "within_subsection_order": ExampleTitleSortKey,
+}

examples/plot_customize_after_plot.py

@@ -0,0 +1,22 @@
+"""
+===============================
+Design: Customizing axis labels
+===============================
+
+This example illustrates how the return value of the plot method can be used
+to customize aspects of the plot, such as axis labels, legend position, etc.
+"""
+
+from matplotlib import pyplot as plt
+
+from upsetplot import generate_counts, plot
+
+example = generate_counts()
+print(example)
+
+##########################################################################
+
+plot_result = plot(example)
+plot_result["intersections"].set_ylabel("Subset size")
+plot_result["totals"].set_xlabel("Category size")
+plt.show()

examples/plot_diabetes.py

@@ -0,0 +1,77 @@
+"""
+==========================================
+Data Vis: Feature distribution in Diabetes
+==========================================
+
+Explore above-average attributes in the Diabetes dataset (Efron et al, 2004).
+
+Here we take some features correlated with disease progression, and look at the
+distribution of that disease progression value when each of these features is
+above average.
+
+The most correlated features are:
+
+  - bmi body mass index
+  - bp average blood pressure
+  - s4 tch, total cholesterol / HDL
+  - s5 ltg, possibly log of serum triglycerides level
+  - s6 glu, blood sugar level
+
+This kind of dataset analysis may not be a practical use of UpSet, but helps
+to illustrate the :meth:`UpSet.add_catplot` feature.
+"""
+
+import pandas as pd
+from matplotlib import pyplot as plt
+from sklearn.datasets import load_diabetes
+
+from upsetplot import UpSet
+
+# Load the dataset into a DataFrame
+diabetes = load_diabetes()
+diabetes_df = pd.DataFrame(diabetes.data, columns=diabetes.feature_names)
+
+# Get five features most correlated with median house value
+correls = diabetes_df.corrwith(
+    pd.Series(diabetes.target), method="spearman"
+).sort_values()
+top_features = correls.index[-5:]
+
+# Get a binary indicator of whether each top feature is above average
+diabetes_above_avg = diabetes_df > diabetes_df.median(axis=0)
+diabetes_above_avg = diabetes_above_avg[top_features]
+diabetes_above_avg = diabetes_above_avg.rename(columns=lambda x: x + ">")
+
+# Make this indicator mask an index of diabetes_df
+diabetes_df = pd.concat([diabetes_df, diabetes_above_avg], axis=1)
+diabetes_df = diabetes_df.set_index(list(diabetes_above_avg.columns))
+
+# Also give us access to the target (median house value)
+diabetes_df = diabetes_df.assign(progression=diabetes.target)
+
+##########################################################################
+
+# UpSet plot it!
+upset = UpSet(diabetes_df, subset_size="count", intersection_plot_elements=3)
+upset.add_catplot(value="progression", kind="strip", color="blue")
+print(diabetes_df)
+upset.add_catplot(value="bmi", kind="strip", color="black")
+upset.plot()
+plt.title("UpSet with catplots, for orientation='horizontal'")
+plt.show()
+
+##########################################################################
+
+# And again in vertical orientation
+
+upset = UpSet(
+    diabetes_df,
+    subset_size="count",
+    intersection_plot_elements=3,
+    orientation="vertical",
+)
+upset.add_catplot(value="progression", kind="strip", color="blue")
+upset.add_catplot(value="bmi", kind="strip", color="black")
+upset.plot()
+plt.suptitle("UpSet with catplots, for orientation='vertical'")
+plt.show()

examples/plot_discrete.py

@@ -0,0 +1,39 @@
+"""
+===========================================================
+Data Vis: Plotting discrete variables as stacked bar charts
+===========================================================
+
+Currently, a somewhat contrived example of `add_stacked_bars`.
+"""
+
+import pandas as pd
+from matplotlib import cm
+from matplotlib import pyplot as plt
+
+from upsetplot import UpSet
+
+TITANIC_URL = (
+    "https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"  # noqa
+)
+df = pd.read_csv(TITANIC_URL)
+# Show UpSet on survival and first classs
+df = df.set_index(df.Survived == 1).set_index(df.Pclass == 1, append=True)
+
+upset = UpSet(df, intersection_plot_elements=0)  # disable the default bar chart
+upset.add_stacked_bars(
+    by="Sex", colors=cm.Pastel1, title="Count by gender", elements=10
+)
+upset.plot()
+plt.suptitle("Gender for first class and survival on Titanic")
+plt.show()
+
+
+upset = UpSet(
+    df, show_counts=True, orientation="vertical", intersection_plot_elements=0
+)
+upset.add_stacked_bars(
+    by="Sex", colors=cm.Pastel1, title="Count by gender", elements=10
+)
+upset.plot()
+plt.suptitle("Same, but vertical, with counts shown")
+plt.show()

examples/plot_generated.py

@@ -0,0 +1,52 @@
+"""
+===================================
+Basic: Examples with generated data
+===================================
+
+This example illustrates basic plotting functionality using generated data.
+"""
+
+import matplotlib
+from matplotlib import pyplot as plt
+
+from upsetplot import generate_counts, plot
+
+example = generate_counts()
+print(example)
+
+##########################################################################
+
+plot(example)
+plt.suptitle("Ordered by degree")
+plt.show()
+
+##########################################################################
+
+plot(example, sort_by="cardinality")
+plt.suptitle("Ordered by cardinality")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts="{:,}")
+plt.suptitle("With counts shown, using a thousands separator")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts="%d", show_percentages=True)
+plt.suptitle("With counts and % shown")
+plt.show()
+
+##########################################################################
+
+plot(example, show_percentages="{:.2%}")
+plt.suptitle("With fraction shown in custom format")
+plt.show()
+
+##########################################################################
+
+matplotlib.rcParams["font.size"] = 6
+plot(example, show_percentages="{:.2%}")
+plt.suptitle("With a smaller font size")
+plt.show()

examples/plot_hide.py

@@ -0,0 +1,42 @@
+"""
+=============================================
+Basic: Hiding subsets based on size or degree
+=============================================
+
+This illustrates the use of ``min_subset_size``, ``max_subset_size``,
+``min_degree`` or ``max_degree``.
+"""
+
+from matplotlib import pyplot as plt
+
+from upsetplot import generate_counts, plot
+
+example = generate_counts()
+
+plot(example, show_counts=True)
+plt.suptitle("Nothing hidden")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts=True, min_subset_size=100)
+plt.suptitle("Small subsets hidden")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts=True, max_subset_size=500)
+plt.suptitle("Large subsets hidden")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts=True, min_degree=2)
+plt.suptitle("Degree <2 hidden")
+plt.show()
+
+##########################################################################
+
+plot(example, show_counts=True, max_degree=2)
+plt.suptitle("Degree >2 hidden")
+plt.show()

examples/plot_highlight.py

@@ -0,0 +1,75 @@
+"""
+=======================================
+Data Vis: Highlighting selected subsets
+=======================================
+
+Demonstrates use of the `style_subsets` method to mark some subsets as
+different.
+
+"""
+
+from matplotlib import pyplot as plt
+
+from upsetplot import UpSet, generate_counts
+
+example = generate_counts()
+
+##########################################################################
+# Subsets can be styled by the categories present in them, and a legend
+# can be optionally generated.
+
+upset = UpSet(example)
+upset.style_subsets(present=["cat1", "cat2"], facecolor="blue", label="special")
+upset.plot()
+plt.suptitle("Paint blue subsets including both cat1 and cat2; show a legend")
+plt.show()
+
+##########################################################################
+# ... or styling can be applied by the categories absent in a subset.
+
+upset = UpSet(example, orientation="vertical")
+upset.style_subsets(present="cat2", absent="cat1", edgecolor="red", linewidth=2)
+upset.plot()
+plt.suptitle("Border for subsets including cat2 but not cat1")
+plt.show()
+
+##########################################################################
+# ... or their size.
+
+upset = UpSet(example)
+upset.style_subsets(
+    min_subset_size=1000, facecolor="lightblue", hatch="xx", label="big"
+)
+upset.plot()
+plt.suptitle("Hatch subsets with size >1000")
+plt.show()
+
+##########################################################################
+# ... or degree.
+
+upset = UpSet(example)
+upset.style_subsets(min_degree=1, facecolor="blue")
+upset.style_subsets(min_degree=2, facecolor="purple")
+upset.style_subsets(min_degree=3, facecolor="red")
+upset.plot()
+plt.suptitle("Coloring by degree")
+plt.show()
+
+##########################################################################
+# Multiple stylings can be applied with different criteria in the same
+# plot.
+
+
+upset = UpSet(example, facecolor="gray")
+upset.style_subsets(present="cat0", label="Contains cat0", facecolor="blue")
+upset.style_subsets(
+    present="cat1", label="Contains cat1", hatch="xx", edgecolor="black"
+)
+upset.style_subsets(present="cat2", label="Contains cat2", edgecolor="red")
+
+# reduce legend size:
+params = {"legend.fontsize": 8}
+with plt.rc_context(params):
+    upset.plot()
+plt.suptitle("Styles for every category!")
+plt.show()

examples/plot_highlight_categories.py

@@ -0,0 +1,41 @@
+"""
+==========================================
+Data Vis: Highlighting selected categories
+==========================================
+
+Demonstrates use of the `style_categories` method to mark some
+categories differently.
+"""
+
+from matplotlib import pyplot as plt
+
+from upsetplot import UpSet, generate_counts
+
+example = generate_counts()
+
+
+##########################################################################
+# Categories can be shaded by name with the ``shading_`` parameters.
+
+upset = UpSet(example)
+upset.style_categories("cat2", shading_edgecolor="darkgreen", shading_linewidth=1)
+upset.style_categories(
+    "cat1",
+    shading_facecolor="lavender",
+)
+upset.plot()
+plt.suptitle("Shade or edge a category with color")
+plt.show()
+
+
+##########################################################################
+# Category total bars can be styled with the ``bar_`` parameters.
+# You can also specify categories using a list of names.
+
+upset = UpSet(example)
+upset.style_categories(
+    ["cat2", "cat1"], bar_facecolor="aqua", bar_hatch="xx", bar_edgecolor="black"
+)
+upset.plot()
+plt.suptitle("")
+plt.show()

examples/plot_missingness.py

@@ -0,0 +1,23 @@
+"""
+==================================================
+Basic: Plotting the distribution of missing values
+==================================================
+
+UpSet plots are often used to show which variables are missing together.
+
+Passing a callable ``indicators=pd.isna`` to :func:`from_indicators` is
+an easy way to categorise a record by the variables that are missing in it.
+"""
+
+import pandas as pd
+from matplotlib import pyplot as plt
+
+from upsetplot import from_indicators, plot
+
+TITANIC_URL = (
+    "https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"  # noqa
+)
+data = pd.read_csv(TITANIC_URL)
+
+plot(from_indicators(indicators=pd.isna, data=data), show_counts=True)
+plt.show()