We have developed a high-level user-oriented machine-learning library julearn in Python (>=3.6). This library provides users with the possibility of testing ML models directly from pandas dataframes, while keeping the flexibiliy of using scikit-learn’s models. You can create pipelines with preprocessing steps. In addition, we also provide the functionality to remove confounds in a cross-validation consistent manner.
julearn is under active development but its already useful and we wanted to share it with the community. Feel free to try it and we will be happy to receive feedback.
install it: pip install -U julearn
See the documentation with many examples.