chore: reorganize timing.py into per-category tables, collapse test boilerplate

Reworks the ad hoc, partly-commented-out timing script (which had been
manually re-enabled with a couple of tweaks, uncommitted, sitting in
the working tree across several perf PRs this session) into something
that's actually a useful reference:

- Split into separate tables, one per category (SO(3)/SE(3) base
  functions, SE3 class, quaternion base functions, UnitQuaternion
  class, twist/exponential-map base functions, Twist3 class, NumPy
  baseline), printed with a plain header between each. Base-level
  (module functions on raw arrays) and class-level (constructors/
  operators/properties on instances) are now consistently separated
  throughout, rather than mixed together - the old Twist3 section in
  particular had base functions (skew, trlog, trexp, rodrigues, ...)
  interleaved with class-level operations.
- Fixed a corrupted docstring header left over from a bad find/replace
  on upstream (`# -*- coding", t)` / `@author", t)`), unrelated to any
  of this but noticed while rewriting the file.
- Fixed mislabelled/ambiguous rows: `inner()` -> `np.inner(s, s).sum()`,
  bare `cross()` -> `base.cross(a, b)` (paired explicitly against
  `np.cross(a, b)`), and rows comparing decomposed-(R,t) vs full-4x4
  composition that had identical labels for different code paths.
- Added coverage that didn't exist before: SE3 <-> RPY, SE3 <-> Euler,
  SE3 -> UnitQuaternion, UnitQuaternion <-> rotation matrix,
  UnitQuaternion -> SE3, and SE3 @ SE3 (normalized compose) alongside
  SE3 * SE3.
- Collapsed the `timeit.timeit(...); result(...)` two-line-per-test
  boilerplate into a single `timeit(stmt, label, setup)` call (module
  import aliased to `_timeit` to free up the name). Replaced the
  single `timeit.timeit(..., number=N)` run per test with
  `min(timeit.repeat(..., number=N, repeat=REPEATS))` - a single long
  run doesn't distinguish real cost from a GC pause or OS scheduling
  hiccup, min-of-repeats does. N dropped from 100_000 to 10_000 (an
  arbitrary starting point either way) since the repeats now do the
  work of suppressing noise that a bigger N was being used for.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Author: petercorke