Scikit-longitudinal

A specialised Python library for longitudinal data analysis built on Scikit-learn

⚙️ Project Status	☎️ Contacts

🌟 Exciting Update: We're delighted to introduce the brand new v0.1 documentation for Scikit-longitudinal! For a deep dive into the library's capabilities and features, please visit here.

🎉 PyPi is available!: We published Scikit-Longitudinal, here!

💡 About The Project

Scikit-longitudinal (Sklong) is a machine learning library designed to analyse longitudinal data (Classification tasks focussed as of today). It offers tools and models for processing, analysing, and predicting longitudinal data, with a user-friendly interface that integrates with the Scikit-learn ecosystem.

Please for further information, visit the official documentation.

🛠️ Installation

To install Sklong, take these two easy steps:

1. ✅ Install the latest version of Sklong:

pip install Scikit-longitudinal

You could also install different versions of the library by specifying the version number, e.g. pip install Scikit-longitudinal==0.0.1. Refer to Release Notes

2. 📦 [MANDATORY] Update the required dependencies (Why? See here)

Scikit-longitudinal incorporates a modified version of Scikit-Learn called Scikit-Lexicographical-Trees, which can be found at this Pypi link.

This revised version guarantees compatibility with the unique features of Scikit-longitudinal. Nevertheless, conflicts may occur with other dependencies in Scikit-longitudinal that also require Scikit-Learn. Follow these steps to prevent any issues when running your project.

🫵 Simple Setup: Command Line Installation

Say you want to try Sklong in a very simple environment. Such as without a proper project.toml file (Poetry, PDM, etc). Run the following command:

pip uninstall scikit-learn scikit-lexicographical-trees && pip install scikit-lexicographical-trees

Note: Although the main installation command install both, yet it’s advisable to verify the correct versions used is Scikit-Lexicographical-trees to prevent conflicts.

🫵 Project Setup: Using `PDM` (or any other such as `Poetry`, etc.)

Imagine you have a project being managed by PDM, or any other package manager. The example below demonstrates PDM. Nevertheless, the process is similar for Poetry and others. Consult their documentation for instructions on excluding a package.

Therefore, to prevent dependency conflicts, you can exclude Scikit-Learn by adding the provided configuration to your pyproject.toml file.

[tool.pdm.resolution]
excludes = ["scikit-learn"]

This exclusion ensures Scikit-Lexicographical-Trees (used as Scikit-learn) is used seamlessly within your project.

💻 Developer Notes

For developers looking to contribute, please refer to the Contributing section of the official documentation.

🛠️ Supported Operating Systems

Scikit-longitudinal is compatible with the following operating systems:

• MacOS 
• Linux 🐧
• Windows via Docker only (Docker uses Linux containers) 🪟 (To try without but we haven't tested it)

🚀 Getting Started

To perform longitudinal analysis with Scikit-Longitudinal, use the LongitudinalDataset class to prepare the dataset. To analyse your data, use the LexicoGradientBoostingClassifier (i.e. Gradient Boosting variant for Longitudinal Data) or another available estimator/preprocessor.

Following that, you can apply the popular fit, predict, prodict_proba, or transform methods in the same way that Scikit-learn does, as shown in the example below.

from scikit_longitudinal.data_preparation import LongitudinalDataset
from scikit_longitudinal.estimators.ensemble.lexicographical.lexico_gradient_boosting import LexicoGradientBoostingClassifier

dataset = LongitudinalDataset('./stroke.csv')
dataset.load_data_target_train_test_split(
  target_column="class_stroke_wave_4",
)

# Pre-set or manually set your temporal dependencies 
dataset.setup_features_group(input_data="Elsa")

model = LexicoGradientBoostingClassifier(
  features_group=dataset.feature_groups(),
  threshold_gain=0.00015
)

model.fit(dataset.X_train, dataset.y_train)
y_pred = model.predict(dataset.X_test)

# Classification report
print(classification_report(y_test, y_pred))

📝 How to Cite?

Paper has been submitted to a conference. In the meantime, for the repository, utilise the button top right corner of the repository "How to cite?", or open the following citation file: CITATION.cff.

🔐 License

MIT License