From c2dcdfb3b1f4e2c6a33b871dcc3c5090aa626488 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lu=C3=A3=20Bida=20Vacaro?= Date: Tue, 19 May 2026 14:01:05 -0300 Subject: [PATCH] docs: fix docs on CI --- .github/workflows/release.yaml | 5 +- docs/requirements.txt | 8 +- docs/source/api.rst | 7 + docs/source/conf.py | 362 +------------------------ docs/source/databases/data-sources.rst | 12 +- docs/source/index.rst | 32 ++- docs/source/installation.rst | 83 ++++++ docs/source/tutorials.rst | 106 ++++++++ pysus/api/ftp/client.py | 2 +- readthedocs.yaml | 2 +- 10 files changed, 248 insertions(+), 371 deletions(-) create mode 100644 docs/source/installation.rst create mode 100644 docs/source/tutorials.rst diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml index 68c77178..0ba68d4e 100644 --- a/.github/workflows/release.yaml +++ b/.github/workflows/release.yaml @@ -111,9 +111,8 @@ jobs: - name: Install dependencies run: | - pip install poetry poetry-plugin-export - poetry config virtualenvs.create false - poetry install --with docs --extras dbc + pip install poetry wget + poetry install --no-root --with docs - name: Build docs run: | diff --git a/docs/requirements.txt b/docs/requirements.txt index f2df05cd..ccd88874 100644 --- a/docs/requirements.txt +++ b/docs/requirements.txt @@ -1,4 +1,4 @@ -nbsphinx -sphinx -sphinx-rtd-theme -standard-imghdr +nbsphinx>=0.9,<1 +sphinx>=7,<9 +sphinx-rtd-theme>=2,<4 +standard-imghdr>=1,<2 diff --git a/docs/source/api.rst b/docs/source/api.rst index b4a507e4..ac272833 100644 --- a/docs/source/api.rst +++ b/docs/source/api.rst @@ -58,6 +58,13 @@ Types :members: :undoc-members: +Utilities +--------- + +.. automodule:: pysus.api.utils + :members: + :undoc-members: + File Format Handlers -------------------- diff --git a/docs/source/conf.py b/docs/source/conf.py index 61426cec..7c1af8b5 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -1,31 +1,12 @@ -#!/usr/bin/env python3 -# -# PySUS documentation build configuration file, created by -# sphinx-quickstart on Thu Aug 25 10:37:19 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 sys sys.path.insert(0, os.path.abspath("../..")) -# -- General configuration ------------------------------------------------ +from pysus import get_version -# If your documentation needs a minimal Sphinx version, state it here. -# -# needs_sphinx = '1.0' +# -- General configuration ------------------------------------------------ -# 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.ext.autodoc", "sphinx.ext.mathjax", @@ -38,286 +19,53 @@ "sqlalchemy": ("https://docs.sqlalchemy.org/en/20/", None), } -# Add any paths that contain templates here, relative to this directory. templates_path = ["_templates"] - -# The suffix(es) of source filenames. -# You can specify multiple suffix as a list of string: -# -# source_suffix = ['.rst', '.md'] 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 = "PySUS" copyright = "2016, Flavio Codeco Coelho" author = "Flavio Codeco Coelho" -# 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 = "0.1.13" -# The full version, including alpha/beta/rc tags. -release = "0.1.13" +version = get_version() +release = version -# The language for content autogenerated by Sphinx. Refer to documentation -# for a list of supported languages. -# -# This is also used if you do content translation via gettext catalogs. -# Usually you set "language" from the command line for these cases. -language = 'en' +language = "en" -locale_dirs = ['locale'] +locale_dirs = ["locale"] gettext_compact = False -# 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. -# This patterns also effect to html_static_path and html_extra_path exclude_patterns = ["_build", "**.ipynb_checkpoints"] -# The reST default role (used for this markup: `text`) to use for all -# documents. -# -# default_role = None - -# 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 - -# If true, `todo` and `todoList` produce output, else they produce nothing. -todo_include_todos = 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 = [] - -# The name for this set of Sphinx documents. -# " v documentation" by default. -# -# html_title = 'PySUS v1.3.1' - -# 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 (relative to this directory) to use as a 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 None, a 'Last updated on:' timestamp is inserted at every page -# bottom, using the given strftime format. -# The empty string is equivalent to '%b %d, %Y'. -# -# html_last_updated_fmt = None - -# 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 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 - -# Language to be used for generating the HTML full-text search index. -# Sphinx supports the following languages: -# 'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja' -# 'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh' -# -# html_search_language = 'en' - -# A dictionary with options for the search language support, empty by default. -# 'ja' uses this config value. -# 'zh' user can custom change `jieba` dictionary path. -# -# html_search_options = {'type': 'default'} - -# The name of a javascript file (relative to the configuration directory) that -# implements a search results scorer. If empty, the default will be used. -# -# html_search_scorer = 'scorer.js' - -# Output file base name for HTML help builder. htmlhelp_basename = "PySUSdoc" -# -- 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': '', - # Latex figure (float) alignment - # - # 'figure_align': 'htbp', -} +# -- Options for LaTeX output --------------------------------------------- -# 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 = [ ( master_doc, "PySUS.tex", "PySUS Documentation", "Flavio Codeco Coelho", - "manual" + "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 - # -- Options for manual page output --------------------------------------- -# One entry per manual page. List of tuples -# (source start file, name, description, authors, manual section). man_pages = [(master_doc, "pysus", "PySUS Documentation", [author], 1)] -# If true, show URL addresses after external links. -# -# man_show_urls = False - # -- Options for Texinfo output ------------------------------------------- -# Grouping the document tree into Texinfo files. List of tuples -# (source start file, target name, title, author, -# dir menu entry, description, category) texinfo_documents = [ ( master_doc, @@ -325,108 +73,16 @@ "PySUS Documentation", author, "PySUS", - "One line description of project.", + "Python package for accessing and analyzing Brazil's public health data.", "Miscellaneous", ), ] -# 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 - # -- Options for Epub output ---------------------------------------------- -# Bibliographic Dublin Core info. epub_title = project epub_author = author epub_publisher = author epub_copyright = copyright - -# The basename for the epub file. It defaults to the project name. -# epub_basename = project - -# The HTML theme for the epub output. Since the default themes are not -# optimized for small screen space, using the same theme for HTML and epub -# output is usually not wise. This defaults to 'epub', a theme designed to save -# visual space. -# -# epub_theme = 'epub' - -# The language of the text. It defaults to the language option -# or 'en' if the language is not set. -# -# epub_language = '' - -# The scheme of the identifier. Typical schemes are ISBN or URL. -# epub_scheme = '' - -# The unique identifier of the text. This can be a ISBN number -# or the project homepage. -# -# epub_identifier = '' - -# A unique identification for the text. -# -# epub_uid = '' - -# A tuple containing the cover image and cover page html template filenames. -# -# epub_cover = () - -# A sequence of (type, uri, title) tuples for the guide element of content.opf. -# -# epub_guide = () - -# HTML files that should be inserted before the pages created by sphinx. -# The format is a list of tuples containing the path and title. -# -# epub_pre_files = [] - -# HTML files that should be inserted after the pages created by sphinx. -# The format is a list of tuples containing the path and title. -# -# epub_post_files = [] - -# A list of files that should not be packed into the epub file. epub_exclude_files = ["search.html"] - -# The depth of the table of contents in toc.ncx. -# -# epub_tocdepth = 3 - -# Allow duplicate toc entries. -# -# epub_tocdup = True - -# Choose between 'default' and 'includehidden'. -# -# epub_tocscope = 'default' - -# Fix unsupported image types using the Pillow. -# -# epub_fix_images = False - -# Scale large images. -# -# epub_max_image_width = 0 - -# How to display URL addresses: 'footnote', 'no', or 'inline'. -# -# epub_show_urls = 'inline' - -# If false, no index is generated. -# -# epub_use_index = True diff --git a/docs/source/databases/data-sources.rst b/docs/source/databases/data-sources.rst index 29027f0d..d87005ef 100644 --- a/docs/source/databases/data-sources.rst +++ b/docs/source/databases/data-sources.rst @@ -110,7 +110,7 @@ read_parquet Modes --- Dataset Descriptions -------------------- +-------------------- About SINAN ^^^^^^^^^^^ @@ -142,3 +142,13 @@ About SIA ^^^^^^^^^^ The SIA (Sistema de Informação Ambulatorial) is the system that enables local managers to process information related to outpatient care (non-hospital) recorded in the data collection applications for such services provided by public and private providers, whether contracted or affiliated with SUS. + +About PNI +^^^^^^^^^ + +The PNI (Programa Nacional de Imunizações) information system manages vaccination data across Brazil, tracking immunization coverage, vaccine doses administered, and supporting the monitoring of the National Immunization Program's goals. + +About CIHA +^^^^^^^^^^ + +The CIHA (Comunicação de Informação Hospitalar e Ambulatorial) system manages hospital admission and outpatient information, complementing the SIH system with additional data on hospital care across Brazil. diff --git a/docs/source/index.rst b/docs/source/index.rst index 9b036f3b..c6cf09cb 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -1,22 +1,38 @@ -.. PySUS documentation master file, created by - sphinx-quickstart on Thu Aug 25 10:37:19 2016. - You can adapt this file completely to your liking, but it should at least - contain the root `toctree` directive. - +================================= Welcome to PySUS documentation! ================================= -PySUS is a collection of helper codes to download & analyze data from `DATASUS `_ (Brazilian Universal Health System). Contributions are welcome! - -Contents: +.. image:: https://badge.fury.io/py/pysus.svg + :target: https://pypi.org/project/PySUS/ + :alt: PyPI version +.. image:: https://readthedocs.org/projects/pysus/badge/?version=latest + :target: https://pysus.readthedocs.io/en/latest/?badge=latest + :alt: Documentation Status +.. image:: https://zenodo.org/badge/63720586.svg + :target: https://zenodo.org/badge/latestdoi/63720586 + :alt: DOI +.. image:: https://github.com/AlertaDengue/PySUS/actions/workflows/release.yaml/badge.svg + :target: https://github.com/AlertaDengue/PySUS/actions/workflows/release.yaml + :alt: Release + +PySUS is a Python package for accessing and analyzing Brazil's public health data +(`DATASUS `_). It provides tools to download, process, +and work with health datasets including SINAN (disease notifications), SIM (mortality), +SINASC (births), SIH (hospitalizations), SIA (ambulatory), CIHA, CNES, PNI, and more. + +This documentation covers PySUS 2.0+. .. toctree:: :maxdepth: 2 + :caption: Contents + Installation Data Sources + Tutorials API Reference + Indices and tables ================== diff --git a/docs/source/installation.rst b/docs/source/installation.rst new file mode 100644 index 00000000..bbf7762b --- /dev/null +++ b/docs/source/installation.rst @@ -0,0 +1,83 @@ +============ +Installation +============ + +pip +--- + +The simplest way to install PySUS is via pip: + +.. code-block:: bash + + pip install pysus + +Extras +^^^^^^ + +For DBC file support (requires ``libffi``): + +.. code-block:: bash + + # Ubuntu/Debian + sudo apt install libffi-dev + pip install pysus[dbc] + +For the terminal user interface (TUI): + +.. code-block:: bash + + pip install pysus[tui] + +Docker +------ + +A pre-built JupyterLab image is available on Docker Hub: + +.. code-block:: bash + + docker pull alertadengue/pysus + docker run -p 8888:8888 alertadengue/pysus + +Or build locally and start the container: + +.. code-block:: bash + + docker compose -f docker/docker-compose.yaml up --build + +Then open http://127.0.0.1:8888/lab in your browser. + +Stop the container with: + +.. code-block:: bash + + docker compose -f docker/docker-compose.yaml down + +Development +----------- + +Using Conda: + +.. code-block:: bash + + conda env create -f conda/dev.yaml + conda activate pysus + +Using Poetry: + +.. code-block:: bash + + poetry install + +Configuration +------------- + +Cache Directory +^^^^^^^^^^^^^^^ + +By default, downloaded files are cached in ``~/pysus``. Override this with the +``PYSUS_CACHEPATH`` environment variable: + +.. code-block:: python + + import os + os.environ["PYSUS_CACHEPATH"] = "/my/custom/path" diff --git a/docs/source/tutorials.rst b/docs/source/tutorials.rst new file mode 100644 index 00000000..624f0275 --- /dev/null +++ b/docs/source/tutorials.rst @@ -0,0 +1,106 @@ +========= +Tutorials +========= + +Jupyter notebooks with usage examples are available in the source repository: + +* `API Overview `_ +* `DuckLake Client `_ +* `FTP Client `_ +* `DadosGov Client `_ + +Quick Start +----------- + +Simplified Database Functions +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. code-block:: python + + from pysus import sinan, sinasc, sim, sih, sia, pni, ibge, cnes, ciha + + # Download SINAN Dengue data + df = sinan(disease="deng", year=2000) + + # Multiple years + df = sinan(disease="deng", year=[2023, 2024]) + + # SINASC births for São Paulo + df = sinasc(state="SP", year=[2020, 2021, 2022, 2023]) + + # SIM mortality data + df = sim(state="SP", year=2024) + + # SIH hospitalizations with month filter + df = sih(state="SP", year=2024, month=[1, 2, 3]) + + # CNES health facilities + df = cnes(state="SP", year=2024, month=1) + +Listing Available Files +^^^^^^^^^^^^^^^^^^^^^^^ + +.. code-block:: python + + from pysus import list_files + + list_files("SINAN") + +Using the PySUS Client +^^^^^^^^^^^^^^^^^^^^^^ + +.. code-block:: python + + from pysus import PySUS + + async def main(): + async with PySUS() as pysus: + # Query DuckLake catalog + files = await pysus.query( + dataset="sinan", + group="DENG", + state="SP", + year=2024, + ) + + # Download files + for f in files: + local = await pysus.download(f) + print(local.path) + + # Read multiple parquet files + import glob + paths = glob.glob("/cache/sinan/**/*.parquet") + df = pysus.read_parquet(paths, mode="union").df() + +read_parquet Modes +^^^^^^^^^^^^^^^^^^ + +.. code-block:: python + + # Union (default) - all columns from any file + df = pysus.read_parquet(paths, mode="union").df() + + # Intersection - only common columns across all files + df = pysus.read_parquet(paths, mode="intersection").df() + + # Strict - raises error if schemas don't match + df = pysus.read_parquet(paths, mode="strict").df() + + # With custom SQL filter + df = pysus.read_parquet(paths, sql="SELECT * WHERE column > 100").df() + +Terminal User Interface (TUI) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. code-block:: bash + + pysus tui -l pt + +Or from Python: + +.. code-block:: python + + from pysus.tui.app import PySUS + app = PySUS(lang="pt") + app.run() diff --git a/pysus/api/ftp/client.py b/pysus/api/ftp/client.py index f06a8e7f..5f2f0c26 100644 --- a/pysus/api/ftp/client.py +++ b/pysus/api/ftp/client.py @@ -15,7 +15,7 @@ if TYPE_CHECKING: from pysus.api.types import State - from .models import Dataset + from pysus.api.ftp.models import Dataset class FTPGroupInfo(TypedDict): diff --git a/readthedocs.yaml b/readthedocs.yaml index 1da24e71..2dd94f77 100644 --- a/readthedocs.yaml +++ b/readthedocs.yaml @@ -7,7 +7,7 @@ version: 2 # Set the version of Python and other tools you might need build: - os: ubuntu-20.04 + os: ubuntu-22.04 tools: python: "3.11"