shaypal5/skutil

Utilities for scikit-learn.

skutil

Utilities for scikit-learn.

from skutil.estimators import ColumnIgnoringClassifier
# use a classifier that can't handle string data as
# an inner classifier in some stacked model, for example

Contents

• 1   Installation
• 2   Basic Use
  • 2.1   estimators
  • 2.2   model_selection
• 3   Contributing
  • 3.1   Installing for development
  • 3.2   Running the tests
  • 3.3   Adding documentation
• 4   Credits

1   Installation

pip install skutil

2   Basic Use

skutil is divided into several sub-modules by functionality:

2.1   estimators

ColumnIgnoringClassifier - An sklearn classifier wrapper that ignores input columns by index.

ObjColIgnoringClassifier - An sklearn classifier wrapper that ignores object columns in dataframes.

classifier_cls_by_name - Get an sklearn classifier class by name. Also supports lowercasing and some shorthands (e.g. svm for SVC, logreg and lr for LogisticRegression).

2.2   model_selection

ConstrainedParameterGrid - Grid of discrete-valued parameters with constraints.

3   Contributing

Package author and current maintainer is Shay Palachy (shay.palachy@gmail.com); You are more than welcome to approach him for help. Contributions are very welcomed.

3.1   Installing for development

Clone:

git clone git@github.com:shaypal5/skutil.git

Install in development mode, and with test dependencies:

cd skutil
pip install -e ".[test]"

3.2   Running the tests

To run the tests use:

cd skutil
pytest

3.3   Adding documentation

The project is documented using the numpy docstring conventions, which were chosen as they are perhaps the most widely-spread conventions that are both supported by common tools such as Sphinx and result in human-readable docstrings. When documenting code you add to this project, follow these conventions.

4   Credits

Created by Shay Palachy (shay.palachy@gmail.com).