# Speed comparison between different dataset processing chains

**URL:** <https://discourse.flucoma.org/t/speed-comparison-between-different-dataset-processing-chains/807>\
**Category:** Pre-Release Toolbox2 Code Sharing\
**Created:** [March 5, 2021, 7:19pm UTC](https://discourse.flucoma.org/t/speed-comparison-between-different-dataset-processing-chains/807 "2021-03-05T19:19:19Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![rodrigo.constanzo](https://discourse.flucoma.org/user_avatar/discourse.flucoma.org/rodrigo.constanzo/32/12_2.png) [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)\
**Post date:** [March 8, 2021, 12:06am UTC](https://discourse.flucoma.org/t/speed-comparison-between-different-dataset-processing-chains/807/2 "2021-03-08T00:06:29Z")

</div>

Well color me interested.

Based on [@weefuzzy’s comments in the LTE thread](https://discourse.flucoma.org/t/lte-an-alternative-to-lpt-for-people-who-dont-care-about-pitch/605/12), I benchmarked UMAP vs PCA and the results are really impressive:

 ![Screenshot 2021-03-08 at 12.02.11 am](https://discourse.flucoma.org/uploads/default/original/2X/4/4d31a2b5f4cfd4e6df371856d5e6a972a426ab1c.png)

And from my understanding, UMAP is “better” than PCA in just about every way (particularly with lumpy(/musical) data)(?).

It definitely takes a bit longer to do the initial `fittransform`, but I’m not bothered by that at all since you only really need to do that once (and it’s nowhere near as long as MLP).

[Archive.zip](https://discourse.flucoma.org/uploads/short-url/cmlCZqEi7vyDdVNFw0uXQOmGLZt.zip) (151.0 KB)

---

_[View the full topic](https://discourse.flucoma.org/t/speed-comparison-between-different-dataset-processing-chains/807)._