more tutorial and doc updates

docs/how_to_contribute.rst

@@ -0,0 +1,213 @@
+.. _how_to_contribute:
+
+=====================
+How to Contribute
+=====================
+
+We welcome contributions to PyHealth! This guide will help you get started with contributing datasets, tasks, models, bug fixes, or other improvements to the project.
+
+Getting Started
+===============
+
+Prerequisites
+-------------
+
+PyHealth uses GitHub for development, so you'll need a GitHub account to contribute.
+
+Setting Up Your Development Environment
+---------------------------------------
+
+To start contributing to PyHealth:
+
+1. **Fork the PyHealth repository** on GitHub
+2. **Clone your forked repository** to your local machine:
+
+   .. code-block:: bash
+
+      git clone https://github.com/your_username/PyHealth.git
+      cd PyHealth
+
+3. **Install dependencies**:
+
+   .. code-block:: bash
+
+      pip install mne pandarallel rdkit transformers accelerate polars
+
+4. **Implement your code** with proper test cases
+5. **Push changes** to your forked repository
+6. **Create a pull request** to the main PyHealth repository
+
+   - Target the ``main`` branch
+   - Enable edits by maintainers
+   - Rebase with the remote ``sunlabuiuc`` main branch before creating the PR
+
+Implementation Requirements
+===========================
+
+Code File Headers
+-----------------
+
+For new contributors, include the following information at the top of your code files:
+
+- Your name(s)
+- Your NetID(s) (if applicable for UIUC students)
+- Paper title (if applicable to a reproducibility contribution)
+- Paper link (if applicable)
+- Description of the task/dataset/model you're implementing
+
+Code Style and Documentation
+-----------------------------
+
+**General Guidelines:**
+
+- Use object-oriented programming with well-defined and typed functions
+- Follow snake_case naming for variables and functions (e.g., ``this_variable``)
+- Use PascalCase for class names (e.g., ``ThisClass``)
+- Follow PEP8 style with 88 character line length
+- Use Google style for docstrings
+
+**Function Documentation Requirements:**
+
+Each function must document:
+
+- **Input arguments**: Define variable types and descriptions
+- **Output arguments**: Define variable types and descriptions  
+- **High-level description** of what the function does
+- **Example use case** or where it will be called
+
+**Example Well-Documented Function:**
+
+.. code-block:: python
+
+   def parse_basic_info(self, patients: Dict[str, Patient]) -> Dict[str, Patient]:
+       """Helper functions which parses patients and admissions tables.
+
+       Will be called in `self.parse_tables()`
+
+       Docs:
+           - patients: https://mimic.mit.edu/docs/iv/modules/hosp/patients/
+           - admissions: https://mimic.mit.edu/docs/iv/modules/hosp/admissions/
+
+       Args:
+           patients: a dict of `Patient` objects indexed by patient_id.
+
+       Returns:
+           The updated patients dict.
+       """
+
+Types of Contributions
+======================
+
+Contributing a Dataset
+----------------------
+
+All datasets must follow these guidelines:
+
+- **Inherit from BaseDataset**: All datasets must inherit from the appropriate BaseDataset class
+- **Follow established patterns**: 
+
+  - For EHR datasets: See the `MIMIC4 dataset example <https://github.com/sunlabuiuc/PyHealth/blob/main/pyhealth/datasets/mimic4.py>`_
+  - For image datasets: See the `CovidCXR dataset example <https://github.com/sunlabuiuc/PyHealth/blob/main/pyhealth/datasets/covidcxr.py>`_ where each folder represents a sample
+
+- **Include a test task**: Datasets should ideally have an associated task for testing purposes
+
+**Key Requirements:**
+
+- Define all required variables outlined in the BaseDataset documentation
+- Provide clear data loading and processing methods
+- Include proper error handling and validation
+
+Contributing a Task
+-------------------
+
+Tasks must follow the established task class structure:
+
+- **Inherit from base task class**: Follow the pattern defined in existing tasks
+- **Examples to reference**:
+
+  - `Mortality prediction task <https://github.com/sunlabuiuc/PyHealth/blob/main/pyhealth/tasks/mortality_prediction.py>`_
+  - `X-ray classification task <https://github.com/sunlabuiuc/PyHealth/blob/main/pyhealth/tasks/chest_xray_classification.py>`_
+
+- **Flexibility**: Tasks can include various implementation details but must have clear inputs/outputs
+- **Test cases**: Include example test cases with defined inputs and expected outputs
+
+Contributing a Model
+--------------------
+
+Models must follow the model base class structure:
+
+- **Inherit from BaseModel**: All models must inherit from the appropriate base model class
+- **Reference implementation**: See the `RNN model example <https://github.com/sunlabuiuc/PyHealth/blob/main/pyhealth/models/rnn.py>`_
+- **Test cases**: Include example test cases with dummy inputs and expected outputs
+
+**Key Requirements:**
+
+- Implement required abstract methods from the base class
+- Provide clear forward pass implementation
+- Include proper initialization and configuration methods
+
+Test Case Requirements
+======================
+
+Every contribution must include two types of test cases:
+
+1. **Automated tests**: These will be run by our continuous integration system
+2. **Manual test cases**: You must define these yourself with:
+
+   - Clear input specifications
+   - Expected output formats
+   - Example usage demonstrating functionality
+
+**Note**: You can use frontier LLMs to help generate basic test cases, which we consider valid as long as they are reasonable and comprehensive.
+
+Pull Request Guidelines
+=======================
+
+Formatting Your Pull Request
+----------------------------
+
+Every pull request must include the following information in the comment:
+
+1. **Who you are** (include NetID if you're an Illinois student)
+2. **Type of contribution** (dataset, task, model, bug fix, etc.)
+3. **High-level description** of what you've implemented
+4. **File guide**: Quick rundown of which files to examine to test your implementation
+
+**Example PR Description:**
+
+.. code-block:: text
+
+   **Contributor:** Jane Doe (jdoe2@illinois.edu)
+
+   **Contribution Type:** New Dataset
+
+   **Description:** Added support for the XYZ Hospital dataset with patient 
+   admission records and diagnostic codes. Includes data preprocessing and 
+   sample task for mortality prediction.
+
+   **Files to Review:**
+   - `pyhealth/datasets/xyz_hospital.py` - Main dataset implementation
+   - `pyhealth/tasks/xyz_mortality.py` - Example task
+   - `tests/core/test_xyz_dataset.py` - Test cases
+
+Review Process
+--------------
+
+After submitting your pull request:
+
+1. Maintainers will review your code for style, functionality, and completeness
+2. Automated tests will be run to ensure compatibility
+3. You may be asked to make revisions based on feedback
+4. Once approved, your contribution will be merged into the main branch
+
+Getting Help
+============
+
+If you need assistance:
+
+- Check existing issues and discussions on GitHub
+- Review similar implementations in the codebase
+- Reach out to maintainers through GitHub issues
+- Consider using LLMs to help with code formatting and documentation
+
+We appreciate your contributions to making PyHealth better for the healthcare AI community!

docs/index.rst

@@ -302,7 +302,7 @@ GRASP                                 deep learning     ``pyhealth.models.GRASP`
 
    install
    tutorials
-   advance_tutorials
+   .. advance_tutorials
 
 
 .. toctree::
@@ -326,6 +326,7 @@ GRASP                                 deep learning     ``pyhealth.models.GRASP`
    :hidden:
    :caption: Additional Information
 
+   how_to_contribute
    live
    log
    about

docs/tutorials.rst

@@ -1,14 +1,14 @@
 Tutorials
 ========================
 
- We provide the following tutorials to help users get started with our pyhealth. Please bare with us as we update the docuemntation on how to use pyhealth.
+ We provide the following tutorials to help users get started with our pyhealth. Please bear with us as we update the documentation on how to use pyhealth 2.0.
 
 
 `Tutorial 0: Introduction to pyhealth.data <https://colab.research.google.com/drive/1y9PawgSbyMbSSMw1dpfwtooH7qzOEYdN?usp=sharing>`_  `[Video] <https://www.youtube.com/watch?v=Nk1itBoLOX8&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=2>`_ 
 
-`Tutorial 1: Introduction to pyhealth.datasets <https://colab.research.google.com/drive/18kbzEQAj1FMs_J9rTGX8eCoxnWdx4Ltn?usp=sharing>`_  `[Video] <https://www.youtube.com/watch?v=c1InKqFJbsI&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=3>`_ 
+`Tutorial 1: Introduction to pyhealth.datasets <https://colab.research.google.com/drive/1voSx7wEfzXfEf2sIfW6b-8p1KqMyuWxK?usp=sharing>`_  `[Video (PyHealth 1.6)] <https://www.youtube.com/watch?v=c1InKqFJbsI&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=3>`_ 
 
-`Tutorial 2: Introduction to pyhealth.tasks <https://colab.research.google.com/drive/1r7MYQR_5yCJGpK_9I9-A10HmpupZuIN-?usp=sharing>`_  `[Video] <https://www.youtube.com/watch?v=CxESe1gYWU4&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=4>`_ 
+`Tutorial 2: Introduction to pyhealth.tasks <https://colab.research.google.com/drive/1kKkkBVS_GclHoYTbnOtjyYnSee79hsyT?usp=sharing>`_  `[Video (PyHealth 1.6)] <https://www.youtube.com/watch?v=CxESe1gYWU4&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=4>`_ 
 
 `Tutorial 3: Introduction to pyhealth.models <https://colab.research.google.com/drive/1LcXZlu7ZUuqepf269X3FhXuhHeRvaJX5?usp=sharing>`_  `[Video] <https://www.youtube.com/watch?v=fRc0ncbTgZA&list=PLR3CNIF8DDHJUl8RLhyOVpX_kT4bxulEV&index=6>`_