Metadata-Version: 2.4
Name: fitsearchcv
Version: 1.0.0
Summary: An extension to sklearn.GridSearchCV and RandomizedSearchCV to reduce over and underfitting
Home-page: https://github.com/yourusername/fitsearchcv
Author: Swastik Verma
Author-email: swastik.yash29052005@gmail.com
License: MIT
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: joblib
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# fitsearchcv— A smarter `refit` selector for scikit-learn searches

`selector-mean` is a tiny utility that helps reduce **overfitting** and **underfitting** when tuning hyperparameters with scikit-learn’s `GridSearchCV` or `RandomizedSearchCV`.

It provides a single function:

- **`selector_mean(cv_results_, metric=None, use_abs_gap=True, clip01=True)`**  
  A callable you pass to `refit=...` that picks the parameter set balancing **high test performance** and **small train–test gap**.

---

## Why?

Vanilla `GridSearchCV` usually selects the highest mean test score, which can sometimes favor models with high variance.  
`selector_mean` instead minimizes: `0.5 * (|train - test|) + 0.5 * (1 - test)`


