3. FFT. Currently it is slow for larger series.
4. Column-wise Jaccard similarity + Pairwise list vs. list Jaccard similarity
5. Binarize a column
6. Computes t-statistics
**String:**
1. Freq removal. Remove rare or very common words from list of strings. (output of tokenize)
2. Infer and merge strings based on frequency
3. Extract numbers as list
7. Added parallel option and documentation. When using str_ext functions, parallel is generally faster if it is the only expression you are running and has the same caveat as the parallel parameter in .value_counts
What's Changed
* Change statistical description of standard error by mishpat in https://github.com/abstractqqq/polars_ds_extension/pull/8
* Fix/import api and more feats by abstractqqq in https://github.com/abstractqqq/polars_ds_extension/pull/7
* feat/roc_auc by abstractqqq in https://github.com/abstractqqq/polars_ds_extension/pull/9
* updated readme by abstractqqq in https://github.com/abstractqqq/polars_ds_extension/pull/10
New Contributors
* mishpat made their first contribution in https://github.com/abstractqqq/polars_ds_extension/pull/8
**Full Changelog**: https://github.com/abstractqqq/polars_ds_extension/compare/v0.1.0...v0.1.1