chore: add the mlp_engine option

[njzjz]

I am going to use DP-GEN to develop models trained by other MLP software. This may or may not be merged into the main branch, but I think a general mlp_engine option can be added anyway.

Summary by CodeRabbit

• New Features

  • Introduced handling for multiple ML potential engines with specialized training argument functions.

• Improvements

  • Enhanced training initialization by splitting into common and engine-specific functions.
  • Improved error handling for unsupported ML potential engines.

• Bug Fixes

  • Corrected logic to differentiate between dp and other engine values during training and model initialization.

[coderabbitai]

Walkthrough

Walkthrough

The recent updates involve refining the training_args() function into training_args_common() and training_args_dp() to distinguish between different machine learning potential engines. Additionally, there are extended error handling and model suffix determination based on mlp_engine in run.py, and adjustments in how arguments are handled in simplify/arginfo.py and simplify/simplify.py.

Changes

Files	Change Summaries
dpgen/generator/arginfo.py	Split training_args() into training_args_common() and training_args_dp(). Added a new training_args() function returning Variant.
dpgen/generator/run.py	Modified make_train, run_train, post_train to handle mlp_engine parameter, added error handling for unsupported engines.
	Updated _get_model_suffix to determine suffix based on mlp_engine value.
dpgen/simplify/arginfo.py	Updated simplify_jdata_arginfo to use training_args_common() and added training_args() in sub_variants section.
dpgen/simplify/simplify.py	Split init_model into init_model and init_model_dp, checking mlp_engine and invoking appropriate initialization.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant System
    participant EngineA
    participant EngineB

    User->>System: Call training_args()
    alt mlp_engine == 'dp'
        System->>EngineA: Call specific methods for DP engine
        EngineA-->>System: Return results
    else
        System->>EngineB: Call specific methods for other engines
        EngineB-->>System: Return results
    end
    System-->>User: Return results

Loading

---

Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 8782483 and c1e8412.

Files selected for processing (4)

• dpgen/generator/arginfo.py (5 hunks)
• dpgen/generator/run.py (4 hunks)
• dpgen/simplify/arginfo.py (2 hunks)
• dpgen/simplify/simplify.py (1 hunks)

Additional comments not posted (13)

dpgen/simplify/arginfo.py (2)

15-15: LGTM!

The import statement for training_args_common is correctly added.

---

205-209: LGTM!

The inclusion of training_args_common and training_args() in the simplify_jdata_arginfo function is appropriate and consistent with the changes in the codebase.

dpgen/simplify/simplify.py (2)

106-111: LGTM!

The init_model function appropriately handles the mlp_engine parameter and includes error handling for unsupported engines.

---

113-113: LGTM!

The init_model_dp function is well-structured and aligns with the overall functionality.

dpgen/generator/arginfo.py (4)

82-87: LGTM!

The training_args_common function is well-structured and provides a clear list of common training arguments.

---

Line range hint 89-232:
LGTM!

The training_args_dp function is well-structured and provides a comprehensive list of training arguments specific to the dp engine.

---

232-243: LGTM!

The training_args function is well-structured and appropriately uses the Variant type to manage different MLP engines.

---

1008-1013: LGTM!

The inclusion of training_args_common and training_args in the run_jdata_arginfo function is appropriate and consistent with the changes in the codebase.

dpgen/generator/run.py (5)

131-133: Good use of default value for mlp_engine.

The default value for mlp_engine is set to "dp", which is a good practice to avoid key errors.

---

132-143: Ensure all required mlp_engine values are handled.

The function currently raises an error for unsupported engines. Ensure that all required mlp_engine values are handled in the future.

Verification successful

---

Ensure all required mlp_engine values are handled.

The current implementation only supports "dp" as the mlp_engine value. Ensure that all required mlp_engine values are handled in the future.

• dpgen/simplify/simplify.py
• dpgen/generator/run.py
• dpgen/generator/arginfo.py

Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurances of "dp" or other supported values.
rg --type python $'"mlp_engine"'

Length of output: 64

---

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurrences of "dp" or other supported values.
rg '"mlp_engine"' | grep -E '\.py'

Length of output: 439

---

Script:

#!/bin/bash
# Description: Extract context around `mlp_engine` occurrences to verify all possible values.

# Extract context around `mlp_engine` in dpgen/simplify/simplify.py
rg -C 3 '"mlp_engine"' dpgen/simplify/simplify.py

# Extract context around `mlp_engine` in dpgen/generator/run.py
rg -C 3 '"mlp_engine"' dpgen/generator/run.py

# Extract context around `mlp_engine` in dpgen/generator/arginfo.py
rg -C 3 '"mlp_engine"' dpgen/generator/arginfo.py

Length of output: 1438

---

277-281: Ensure all required mlp_engine values are handled.

The function currently raises an error for unsupported engines. Ensure that all required mlp_engine values are handled in the future.

Verification successful

---

Ensure all required mlp_engine values are handled.

The code currently supports only the "dp" engine and raises an error for any other value. Ensure that all required mlp_engine values are handled in the future.

• dpgen/simplify/simplify.py (line 6)
• dpgen/generator/arginfo.py (line 6)
• dpgen/generator/run.py (lines 6, 11, 16, 21, 26)

Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurances of "dp" or other supported values.
rg --type python $'"mlp_engine"'

Length of output: 64

---

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurrences of "dp" or other supported values.
rg '"mlp_engine"'

Length of output: 422

---

Script:

#!/bin/bash
# Description: Extract and analyze lines around occurrences of `mlp_engine` to identify all possible values.

# Extract 5 lines before and after each occurrence of `mlp_engine`
rg '"mlp_engine"' -A 5 -B 5

Length of output: 3653

---

729-733: Ensure all required mlp_engine values are handled.

The function currently raises an error for unsupported engines. Ensure that all required mlp_engine values are handled in the future.

Verification successful

---

Ensure all required mlp_engine values are handled.

The function currently raises an error for unsupported engines, and only the "dp" engine is handled. Future implementations should ensure to handle any new mlp_engine values that may be introduced.

• Locations where mlp_engine is checked:
  • dpgen/simplify/simplify.py
  • dpgen/generator/run.py
  • dpgen/generator/arginfo.py

Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurances of "dp" or other supported values.
rg --type python $'"mlp_engine"'

Length of output: 64

---

Script:

#!/bin/bash
# Description: Verify all possible `mlp_engine` values used in the codebase.

# Test: Search for the `mlp_engine` key. Expect: Only occurrences of "dp" or other supported values.
rg '"mlp_engine"'

Length of output: 422

---

Script:

#!/bin/bash
# Description: Extract lines around occurrences of `mlp_engine` to understand its usage.

# Extract lines around occurrences of `mlp_engine` in the mentioned files.
rg -C 5 '"mlp_engine"' dpgen/generator/arginfo.py dpgen/generator/run.py dpgen/simplify/simplify.py

Length of output: 3725

---

922-926: Ensure all required mlp_engine values are handled.

The function currently raises an error for unsupported engines. Ensure that all required mlp_engine values are handled in the future.

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

• X
• Mastodon
• Reddit
• LinkedIn

Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai generate interesting stats about this repository and render them as a table.
  • @coderabbitai show all the console.log statements in this repository.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[codecov]

Codecov Report

Attention: Patch coverage is 67.56757% with 12 lines in your changes missing coverage. Please review.

Project coverage is 49.02%. Comparing base (8782483) to head (c1e8412).
Report is 32 commits behind head on devel.

Files with missing lines	Patch %	Lines
dpgen/generator/run.py	66.66%	8 Missing ⚠️
dpgen/simplify/simplify.py	20.00%	4 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##            devel    #1576      +/-   ##
==========================================
- Coverage   49.57%   49.02%   -0.55%     
==========================================
  Files          83       83              
  Lines       14815    14844      +29     
==========================================
- Hits         7344     7278      -66     
- Misses       7471     7566      +95     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.