Draft
Conversation
Collaborator
ckmah
commented
Feb 25, 2025
ckmah
commented
- point features
- shape features Extend shape features #168
- rename "features" to something less generic
- Introduced `pytest.ini` for test discovery and logging configuration. - Updated `_utils.py` to persist points in Dask. - Enhanced image measurement module with new functions: `mean_intensity`, `regionprops`, and `moments_optimized`. - Added clustering functionality in `_cluster.py` for unsupervised learning on point features. - Implemented density and distance calculations in `_density.py` and `_distance.py`. - Introduced optimized measurement engine in `_measure_optimized.py` using Polars and Numba. - Added tests for optimized measure functions in `test_measure_optimized.py` to ensure functionality and performance benchmarks. - Updated shape measures in `_measure.py` to support parallel processing and improved logging.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
… ripley metrics - Created SVG files for distance, polarity, moments, and ripley benchmarks to visualize performance metrics. - Added corresponding JSON files to store benchmark results and machine information. - Introduced new plotting scripts to generate benchmark analysis and summary plots. - Updated dependencies in `pyproject.toml` to include `polars` for enhanced data processing capabilities.
… data - Removed `xgboost` from dependencies and updated `scikit-learn` to a more flexible version. - Consolidated development dependencies under a new `dev` section in `pyproject.toml`. - Enhanced the synthetic dataset creation function to unify shapes, points, and optional images/labels for testing. - Updated tests to utilize the new synthetic data generation approach, ensuring consistency across shape and point feature tests. - Improved logging in test fixtures for better traceability during test execution.
…lity Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
- Keep data in sparse format throughout computation where possible - Add chunk_size parameter for controlling memory usage during writes - Update set_points_metadata to preserve sparse DataFrame columns - Add automatic zarr writing for efficient storage via ome-zarr - Improve memory efficiency with sparse-aware operations Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
- Create raster grid programmatically from shape bounds - Store flux results as multi-channel 2D image with chunked dask arrays - Channels include: gene values, embeddings, color RGB, and counts - Leverage ome-zarr native chunked writing via Image2DModel - Update tests to validate image-based storage - Remove dependency on pre-existing raster points Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
- Add adaptive scale factors based on image dimensions - Only create multiscale pyramid if image is large enough - Prevents errors with small images in tests - Ensures proper ome-zarr metadata for all image sizes Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
…ning - Introduced functions for creating raster grids and computing cell flux values. - Implemented SVD model training for dimensionality reduction of flux data. - Added support for streaming computation with zarr-backed SpatialData. - Updated flux function to handle batch processing and efficient writing to zarr. - Adjusted parameters for training size and improved memory management during processing. Co-authored-by: ckmah <3103744+ckmah@users.noreply.github.com>
…ithm Refactor flux algorithm to use Image2DModel with chunked ome-zarr storage
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
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.