ScalableCytometryImageProcessing / SCIP

Scalable Cytometry Image Processing (SCIP) is an open-source tool that implements an image processing pipeline on top of Dask, a distributed computing framework written in Python. SCIP performs projection, illumination correction, image segmentation and masking, and feature extraction.
https://scalable-cytometry-image-processing.readthedocs.io/en/latest/
GNU General Public License v3.0
7 stars 0 forks source link

Refactor #52

Closed MaximLippeveld closed 2 years ago

MaximLippeveld commented 2 years ago

Major refactor to improve maintainability and mix-and-matching of pipeline steps for all input file types. The latter is achieved by moving preprocessing steps out of data loaders into separate modules.

codecov-commenter commented 2 years ago

Codecov Report

Merging #52 (dcabe7e) into master (baafc1a) will decrease coverage by 2.48%. The diff coverage is 56.98%.

@@            Coverage Diff             @@
##           master      #52      +/-   ##
==========================================
- Coverage   49.27%   46.79%   -2.49%     
==========================================
  Files          23       24       +1     
  Lines        1106     1030      -76     
==========================================
- Hits          545      482      -63     
+ Misses        561      548      -13     
Impacted Files Coverage Δ
src/scip/masking/sobel.py 0.00% <0.00%> (ø)
src/scip/masking/watershed.py 0.00% <0.00%> (-32.36%) :arrow_down:
src/scip/projection/op.py 66.66% <ø> (ø)
src/scip/segmentation/cellpose.py 15.87% <ø> (-3.83%) :arrow_down:
src/scip/features/intensity.py 41.81% <11.76%> (-1.32%) :arrow_down:
src/scip/masking/spot.py 29.26% <29.26%> (ø)
src/scip/masking/circle.py 36.36% <36.36%> (ø)
src/scip/masking/threshold.py 31.57% <40.00%> (+1.57%) :arrow_up:
src/scip/loading/util.py 38.88% <50.00%> (-55.56%) :arrow_down:
src/scip/loading/zarr.py 48.93% <50.00%> (-17.74%) :arrow_down:
... and 14 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.