Add multioutput_train_size parameter for manual validation set specification in multi-output tasks

[Copilot]

Implementation Complete: Multi-Output Validation Set Support

• Explore repository structure and understand validation handling
• Understand the multi-output regression issue (flatten() breaks 2D output arrays)
• Add multioutput_train_size parameter to AutoML.init and fit() method
• Implement _train_val_split method in AutoML class with validation
• Update documentation for the new parameter
• Add test case test_multioutput_train_size in test_regression.py
• Run tests to validate changes (all tests passing)
• Address code review feedback - added validation and warnings
• Run security scan with codeql_checker (0 alerts)
• Verify existing tests still pass
• Fix formatting with pre-commit hooks

Summary

Successfully implemented the multioutput_train_size parameter that allows users to manually specify a validation set for multi-output regression tasks when using "holdout" evaluation.

Changes (115 lines added):

• flaml/automl/automl.py: 80 lines added
• test/automl/test_regression.py: 35 lines added

Key Features:

1. Parameter Support: Accepts int (number of training samples) or float (proportion 0.0-1.0)
2. Robust Validation:
   • Validates float values are in (0.0, 1.0)
   • Validates int values are in [1, n_samples-1]
   • Ensures at least 1 sample for validation
3. Clear Warnings:
   • Warns if X_val/y_val already provided (parameter ignored)
   • Warns if using non-holdout eval_method
4. Comprehensive Testing:
   • Tests integer and float train_size
   • Tests validation error handling
   • All existing tests still pass

Security: ✅ No security vulnerabilities detected by CodeQL
Formatting: ✅ Pre-commit hooks applied (black, ruff, trailing whitespace)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Manually setting the validation set for multi-output task</issue_title>
<issue_description>## Pull request overview

This pull request adds support for manually setting a validation set for multi-output tasks when using the "holdout" evaluation method. Previously, users could not manually specify a validation set for multi-output regression tasks. The new multioutput_train_size parameter allows users to concatenate training and validation data and specify where to split them.

Changes:

• Added multioutput_train_size parameter to AutoML class for manual validation set specification
• Implemented _train_val_split method to split concatenated training/validation data
• Added test case demonstrating the new functionality with MultiOutputRegressor

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 4 comments.

File	Description
flaml/automl/automl.py	Added documentation and implementation for the multioutput_train_size parameter, including the split logic in the fit method
test/automl/test_regression.py	Added test_multioutput_train_size function to demonstrate usage of the new feature

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Originally posted by @copilot in #1302 (review)
</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Manually setting the validation set for multi-output task #1503

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[thinkall]

@copilot , run pre-commit run --all-files to fix formatting.

[Copilot]

@copilot , run pre-commit run --all-files to fix formatting.

Done. Pre-commit hooks applied formatting fixes (black, ruff, trailing whitespace). Committed in 2c336d7.