chore(deps): bump chemprop from 2.0.0 to 2.2.3

[dependabot]

Bumps chemprop from 2.0.0 to 2.2.3.

Release notes

Sourced from chemprop's releases.

v2.2.3

Notable changes

This patch version fixes a bug that prevented using the CLI code from a Jupyter Notebook (#1346). While we don't recommend importing and using the CLI functions, a package on chemprop-contrib did and needed this fix.

Support for python 3.13 was added in #1343 and support for pandas 3 was added in #1329.

A new CLI flag --save-data-splits was added in #1283. This flag splits the input data files into separate train/val/test files for easier calculation of model performance.

What's Changed

• Make MAB with missing values work in pandas 3 by @​KnathanM in chemprop/chemprop#1329
• Expand cuik-molmaker support by @​sveccham in chemprop/chemprop#1319
• add v2.2.2 requirements by @​KnathanM in chemprop/chemprop#1332
• Update 2.2.2_requirements.txt by @​UnixJunkie in chemprop/chemprop#1333
• Use raw strings for math docs by @​c-w-feldmann in chemprop/chemprop#1342
• fix python 3.13+ compat by @​JacksonBurns in chemprop/chemprop#1343
• fix type of _T_default_criterion and _T_default_metric in _FFNPredictorBase by @​c-w-feldmann in chemprop/chemprop#1341
• Remove exit line mistake by @​KnathanM in chemprop/chemprop#1346
• Rework & expand --save-smiles-splits by @​jxl26 in chemprop/chemprop#1283

New Contributors

• @​UnixJunkie made their first contribution in chemprop/chemprop#1333

Full Changelog: chemprop/chemprop@v2.2.2...v2.2.3

Chemprop v2.2.2

Chemprop Patch Release 2.2.2

This patch release of Chemprop introduces a number of bug fixes, including:

• support for current versions of ray[tune] and lightning
• bugs with loading previously trained models on different hardware
• hpopt on Apple Silicon

and others!

This release also includes some exciting new features:

• multiprocessing will now parallelize feature calculation, in addition to Molecule creation as was done before
• new PointQuantile and NLogProbEnrichment loss functions
• --message-hidden-dim and --depth now accept multiple arguments to support customizing encoders in multicomponent MPNNs separately
• validation size can now be set to zero and training, validation, and testing sets can be specified separately in the --data-path argument

Full list of PRs is below - thanks to all of the contributors!

What's Changed

• Specify versions of RDKit and Torch in docker build for cuik-molmaker by @​KnathanM in chemprop/chemprop#1284
• fix: fix storing of multiclass predictions in CLI by @​m-volk in chemprop/chemprop#1245
• Allow multiprocess loading. by @​miha-skalic in chemprop/chemprop#1234
• Fix device allocation in metrics weights by @​Kuzaiherba in chemprop/chemprop#1296
• Allow overriding automatic drop_last Detection by @​JacksonBurns in chemprop/chemprop#1299
• Fix GPU/CPU Incremental Pretraining (and the CI) by @​JacksonBurns in chemprop/chemprop#1306

... (truncated)

Commits

• c83f483 Bump version: 2.2.2 → 2.2.3
• ec8adf6 Rework & expand --save-smiles-splits (#1283)
• ccd47c7 Remove exit line mistake (#1346)
• 5e37ac6 fix type of _T_default_criterion and _T_default_metric in `_FFNPredictorB...
• bcab5b3 fix python 3.13+ compat (#1343)
• 9dfa701 Use raw strings for math docs (#1342)
• e3c13f0 Update 2.2.2_requirements.txt (#1333)
• a28cd35 add v2.2.2 requirements (#1332)
• b75ace5 Expand cuik-molmaker support (#1319)
• 398b2e8 Make MAB with missing values work in pandas 3 (#1329)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Labels

The following labels could not be found: automated, dependencies. Please create them before Dependabot can add them to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.