Testing Philosophy (Read This First)

Each module in IPSL-AID comes with its own dedicated tests.

The repository currently includes test suites for:

IPSL_AID, covering diffusion-based climate downscaling;
AID_BC, covering bias correction using Quantile Mapping and Optimal Transport.

Before running large-scale training or bias-correction experiments, users are strongly encouraged to:

Explore the test suite
Understand data handling and normalization
Validate diffusion and architecture choices
Tune hyperparameters using small debug runs

This approach minimizes wasted compute time and ensures correct scientific usage.

Why Testing is Essential

Climate downscaling and bias-correction workflows involve:

Complex neural architectures
Sophisticated diffusion formulations
Large-scale data processing
Multi-GPU parallelization
Numerical precision requirements
Statistical bias-correction methods

Without proper testing, errors can:

Waste computational resources (days of GPU time)
Produce scientifically invalid results
Mask underlying implementation bugs
Compromise reproducibility

Recommended Workflow

Run the complete test suite

The global test runner executes both the IPSL_AID and AID_BC test suites:
```
python -m tests.test_all
```

Run one test suite independently

# IPSL_AID
python -m tests.IPSL_AID.test_runner

# AID_BC
python -m tests.AID_BC.test_runner

Run targeted tests

Individual modules, classes, or test methods can be executed directly.

# IPSL_AID module
python -m unittest tests.IPSL_AID.test_utils

# IPSL_AID class
python -m unittest tests.IPSL_AID.test_utils.TestEasyDict

# IPSL_AID single test
python -m unittest \
  tests.IPSL_AID.test_utils.TestEasyDict.test_empty_initialization

# AID_BC module
python -m unittest tests.AID_BC.test_quantile_mapping

Integration Tests: Test data loading and model initialization
```
python tests/IPSL_AID/test_integration.py
```

Small-scale Debug Runs: Train on a small subset

# Use debug mode in setup script
debug=true
num_epochs=1
batch_size=4

Validation: Check against known baselines

Test Coverage

The IPSL_AID test suite covers:

Data loading and preprocessing
Diffusion model implementations (VE, VP, EDM, iDDPM)
UNet architectures and variants
Loss functions and training loops
Inference and sampling procedures
Evaluation metrics and diagnostics

The AID_BC test suite covers:

ERA5 and CMIP6 data loading
ERA5-on-CMIP6 preprocessing
Quantile Mapping
Optimal Transport
Bias-correction workflows
Evaluation metrics and diagnostics

Debugging Tips

Use torch.autograd.set_detect_anomaly(True) during development
Monitor GPU memory usage with nvidia-smi
Check numerical stability with gradient norms
Validate data normalization and scaling

Remember: Test first, scale later. A few hours of testing can save days of wasted computation.