feat(property): add draft PropertyTrainer helper#5406
Draft
njzjz-bot wants to merge 2 commits intodeepmodeling:masterfrom
Draft
feat(property): add draft PropertyTrainer helper#5406njzjz-bot wants to merge 2 commits intodeepmodeling:masterfrom
njzjz-bot wants to merge 2 commits intodeepmodeling:masterfrom
Conversation
Problem - issue deepmodeling#5376 needs a first high-level property-training entry point without introducing a new CLI surface - model_name should refer to a pretrained model name/alias rather than a new backend-specific concept Change - add deepmd.property with draft PropertyTrainer/PropertyPredictor helpers built on the existing PT training/inference flow - interpret model_name as a pretrained model alias and keep a low-level from_systems(...) path for prepared DeePMD property datasets - expose DeepProperty/property helpers and add focused unit tests for config generation and model alias resolution Notes - this draft intentionally does not implement high-level fit(data=...) for SMILES/CSV inputs yet - local smoke checks used py_compile only; full test execution is left to CI because this environment lacks the built package metadata/test runner Authored by OpenClaw (model: gpt-5.4)
for more information, see https://pre-commit.ci
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #5406 +/- ##
==========================================
- Coverage 80.35% 80.34% -0.01%
==========================================
Files 819 820 +1
Lines 85445 85566 +121
Branches 4139 4139
==========================================
+ Hits 68661 68750 +89
- Misses 15508 15540 +32
Partials 1276 1276 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
model_nameshould represent a pretrained model name/alias, but the current prototype still felt too close to low-level DeePMD dataset plumbingChange
deepmd.propertywith draftPropertyTrainer/PropertyPredictorhelpers on top of the existing PT training/inference flowmodel_nameas the pretrained model name/alias and keepfrom_systems(...)as the low-level path for already-prepared DeePMD property datasetsDeepPropertyand add focused tests for config generation plus pretrained alias resolutionNotes
fit(data=...)support for SMILES/CSV inputs is not implemented yet; that should come in follow-up issues/PRspython -m py_compile; full tests are expected to run in CIAuthored by OpenClaw (model: gpt-5.4)