ConDo Adapter is a powerful tool designed for Confounded Domain Adaptation, addressing the challenges of batch effects while elegantly conditioning on confounding variables. This innovative approach aims to enhance the quality of your data, making it a must-have for data scientists and researchers who are committed to rigorous data analysis and model training. ConDo Adapter not only improves data integrity but also ignites joy in the otherwise mundane task of data cleaning.

Key Features:

• Batch Effect Correction: Effectively mitigates biases introduced by batch effects.
• Confounding Variable Conditioning: Validates the independence of processed data from confounding variables.

Quick Start Guide:

To get started with ConDo Adapter, you can easily create an adapter instance and utilize its capabilities within just a few lines of code. Here’s a quick example:

from condo import ConDoAdapterKLD

# Initialize the adapter
condoer = ConDoAdapterKLD()

# Generate synthetic data
import numpy as np
X_T = np.sort(np.random.uniform(0, 8, size=(100, 1)))
X_S = np.sort(np.random.uniform(4, 8, size=(100, 1)))
Y_T = np.random.normal(4 * X_T + 1, 1 * X_T + 1)
Y_Strue = np.random.normal(4 * X_S + 1, 1 * X_S + 1)
Y_S = 5 * Y_Strue + 2

# Fit the model and transform data
condoer.fit(Y_S, Y_T, X_S, X_T)
Y_S2T = condoer.transform(Y_S)

# Evaluate results
print(f"before ConDo: {np.mean((Y_S - Y_Strue) ** 2):.3f}")
print(f"after ConDo:  {np.mean((Y_S2T - Y_Strue) ** 2):.3f}")

Additional Resources:

For more examples, including detailed case studies, check out the examples directory. You can also explore the papers directory to access all the code related to our experiments.

Contribute to the Project:

We welcome contributions from the community! If you're interested in enhancing the toolkit or have an idea for improvements, please engage with the project, and you can start with our testing framework by running:

pytest

Citing ConDo Adapter:

If you find ConDo Adapter valuable for your research, please consider citing our work using the following reference:

@article{
mccarter2024towards,
  title={Towards Backwards-Compatible Data with Confounded Domain Adaptation},
  author={Calvin McCarter},
  journal={Transactions on Machine Learning Research},
  year={2024},
  url={https://openreview.net/forum?id=GSp2WC7q0r},
}

Unlock the full potential of your data with ConDo Adapter and experience the difference in your data processing and analysis!