Fix
* fix(cluster): compute_optimal_n_cluster now handles less then 8 assets ([`d9ed4a4`](https://github.com/skfolio/skfolio/commit/d9ed4a4a4cbb096a45d8f09089c9d72c481edd45))
* fix(plotly): remove global pandas plot backend setting ([`4ff07c3`](https://github.com/skfolio/skfolio/commit/4ff07c37692c83388cd1a45175e661a51726ddbd))
* fix(plotly): remove fix of create_dendrogram following new plotly release ([`2e712c8`](https://github.com/skfolio/skfolio/commit/2e712c8647f943b33958ec2fb3accbdb97542102))
* fix(pre-processing): param drop_inceptions_nan ([`75d8013`](https://github.com/skfolio/skfolio/commit/75d8013952e86fb96666e1f6f7436edceb05cde6))
* fix(pre-processing): drop_interceptions_nan param added to prices_to_returns (57)
Observations at the beginning are dropped if any of the asset values are missing, otherwise we keep the NaNs. ([`ba74842`](https://github.com/skfolio/skfolio/commit/ba7484263ad315d38601250d2e8d1dae5269149c))