News for hackers. Stuff that matters.

A comment on Polars: Fast DataFrame library for Rust and Python. Parent comment

Re:Polars: Fast DataFrame library for Rust and Python by apd_ on Thursday December 16, 2021 @08:31PM (#29586590)
> Note also that Julia would be number 1 in almost all of those benchmarks if you were to rank by speed of second run (as expected...).

Not true. If we'd rank them by second run Julia would be:

- On simple query: 1st, 1st, 4th, 1st, 5th (down 1).

- On advanced query: 3rd, 6th, 6th, 4th (up 1), - (out of memory).

> The databases (and spark) will have to read from disk. They have no chance of competing with anything that's reading from ram, no matter how slow it is.

Not true. Upon quick peek on the bench code, ClickHouse and Spark use in-memory table. I assume other engines too.

[ Parent | on HN ]

There are no comments on this comment yet.