huge docs update incoming

Author: TryingToLearnGitAgain

docs/api/datasets.rst

@@ -16,6 +16,8 @@ Datasets
     datasets/pyhealth.datasets.OMOPDataset
     datasets/pyhealth.datasets.SHHSDataset
     datasets/pyhealth.datasets.SleepEDFDataset
+    datasets/pyhealth.datasets.EHRShotDataset
+    datasets/pyhealth.datasets.COVID19CXRDataset
     datasets/pyhealth.datasets.TUABDataset
     datasets/pyhealth.datasets.TUEVDataset
     datasets/pyhealth.datasets.splitter

docs/api/datasets/pyhealth.datasets.COVID19CXRDataset.rst

@@ -0,0 +1,11 @@
+pyhealth.datasets.COVID19CXRDataset
+===================================
+
+The COVID-19 Radiography chest X-ray dataset. Kaggle: `https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database <https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database>`_.
+
+.. autoclass:: pyhealth.datasets.COVID19CXRDataset
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+

docs/api/datasets/pyhealth.datasets.EHRShotDataset.rst

@@ -0,0 +1,11 @@
+pyhealth.datasets.EHRShotDataset
+===================================
+
+The EHRShot dataset. Website: `https://som-shahlab.github.io/ehrshot-website/ <https://som-shahlab.github.io/ehrshot-website/>`_.
+
+.. autoclass:: pyhealth.datasets.EHRShotDataset
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+

docs/how_to_contribute.rst

@@ -162,6 +162,19 @@ Every contribution must include two types of test cases:
 
 All unit tests should be placed in the `tests/` directory following the existing structure, with 'tests/core/' for core functionality tests.
 
+Writing Fast and Performant Tests
+---------------------------------
+
+Guidelines for authoring test cases:
+
+- Keep tests fast: avoid large data processing; prefer tiny, synthetic fixtures.
+- Place core unit tests in ``tests/core/`` and name files ``test_*.py``.
+- Avoid network access and external services; use local, in-memory data.
+- Use small configurations: minimal sample sizes, tiny models, small batch sizes, and ``epochs=1``.
+- Make tests deterministic: set random seeds and avoid time-based randomness.
+- Stub or monkeypatch heavy components (I/O, model training) when the logic under test allows.
+- Skip or gate any heavyweight tests behind explicit markers; by default, all tests must run quickly in CI.
+
 Pull Request Guidelines
 =======================
 

docs/how_to_get_started.rst

@@ -1,10 +1,17 @@
 .. _how_to_get_started:
 
 =====================
-How to Get Started with PyHealth
+Getting Started with PyHealth
 =====================
 
-Welcome to PyHealth! This guide will help you build machine learning pipelines for healthcare tasks using PyHealth.
+Welcome to PyHealth! This guide will help you get up and running with healthcare AI development. PyHealth makes it easy to build, test, and deploy healthcare machine learning models with minimal code.
+
+🚀 **New to PyHealth?** Start here. This guide walks you from install to first modeling.
+
+Introduction `[Video] <https://www.youtube.com/watch?v=1Ir6hzU4Nro&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=1>`_
+--------------------------------------------------------------------------------------------------------------
+
+Prefer video? Watch a short introduction to PyHealth before you start.
 
 Installing PyHealth
 ===================
@@ -23,7 +30,7 @@ To install the latest development version from GitHub:
    cd PyHealth
    pip install -e .
 
-Ensure you have the required dependencies installed before proceeding.
+Ensure you have the required dependencies installed before proceeding. See :doc:`install` for detailed installation instructions.
 
 Overview of ML Pipelines
 =========================
@@ -127,4 +134,31 @@ Example:
    from pyhealth.metrics.binary import binary_metrics_fn
 
    y_true, y_prob, loss = trainer.inference(test_loader)
-   binary_metrics_fn(y_true, y_prob, metrics=["pr_auc", "roc_auc"])
+   binary_metrics_fn(y_true, y_prob, metrics=["pr_auc", "roc_auc"])
+
+Essential Guides
+================
+
+Now that you understand the basics, dive deeper into PyHealth's capabilities:
+
+📚 **Core Guides**
+------------------
+
+- :doc:`why_pyhealth` - Discover why PyHealth is the best choice for healthcare AI
+- :doc:`medical_standards` - Learn how to translate between medical coding systems (ICD, CPT, NDC, ATC)
+- :doc:`why_pyhealth` - Discover why PyHealth is the best choice for healthcare AI
+
+🛠️ **Advanced Topics**
+----------------------
+
+- :doc:`tutorials` - Interactive Jupyter notebooks with real examples
+- :doc:`api/models` - Complete documentation of all available models
+- :doc:`api/datasets` - Working with healthcare datasets
+- :doc:`api/tasks` - Defining custom healthcare prediction tasks
+
+🤝 **Community & Support**
+--------------------------
+
+- :doc:`how_to_contribute` - Join our community of healthcare AI developers
+- :doc:`faq` - Frequently asked questions and troubleshooting
+- `Discord Community <https://discord.gg/mpb835EHaX>`_ - Chat with other users and developers

docs/index.rst

@@ -1,33 +1,33 @@
 Installation
 ============
 
-You could install from PyPi:
+You could install from PyPi for the older stable version of PyHealth:
 
 .. code-block:: bash
 
     pip install pyhealth
 
 
-or from github source:
+or from github source for the latest version of PyHealth:
 
 .. code-block:: bash
 
    git clone https://github.com/sunlabuiuc/PyHealth.git
    cd pyhealth
-   pip install .
+   pip install -e .
 
 
-**Required Dependencies**\ :
+.. **Required Dependencies**\ :
 
-.. code-block:: bash
+.. .. code-block:: bash
 
-    python>=3.8
-    torch>=1.8.0
-    rdkit>=2022.03.4
-    scikit-learn>=0.24.2
-    networkx>=2.6.3
-    pandas>=1.3.2
-    tqdm
+..     python>=3.8
+..     torch>=1.8.0
+..     rdkit>=2022.03.4
+..     scikit-learn>=0.24.2
+..     networkx>=2.6.3
+..     pandas>=1.3.2
+..     tqdm
 
 **Warning 1**\ :
 
@@ -38,9 +38,11 @@ If you want to use neural-net based models, please make sure PyTorch is installe
 Similarly, models depending on **xgboost** would **NOT** enforce xgboost installation by default.
 
 
+
+
 **CUDA Setting**\ :
 
-To run PyHealth, you also need CUDA and cudatoolkit that support your GPU well. `More info <https://developer.nvidia.com/cuda-gpus/>`_
+To run PyHealth, you may also need CUDA and cudatoolkit that supports your GPU. `More info <https://developer.nvidia.com/cuda-gpus/>`_
 
 For example, if you use NVIDIA RTX A6000 as your GPU for training, you should install a compatible cudatoolkit using: