docstring for the dicodile function

[rprimet]

Draft docstring for the dicodile function to start a discussion :)

[codecov[bot]]

Codecov Report

Merging #14 (4ce90ee) into main (1b54bac) will increase coverage by 0.11%. The diff coverage is 88.88%.

@@            Coverage Diff             @@
##             main      #14      +/-   ##
==========================================
+ Coverage   74.06%   74.18%   +0.11%     
==========================================
  Files          40       41       +1     
  Lines        2564     2572       +8     
==========================================
+ Hits         1899     1908       +9     
+ Misses        665      664       -1     

Flag	Coverage Δ
unittests	74.18% <88.88%> (+0.11%)	:arrow_up:

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
dicodile/_dicodile.py	79.26% <87.50%> (+0.95%)	:arrow_up:
dicodile/tests/test_dicodile.py	100.00% <100.00%> (ø)
dicodile/update_z/dicod.py	77.96% <0.00%> (-0.13%)	:arrow_down:
dicodile/workers/dicod_worker.py	93.47% <0.00%> (ø)
dicodile/__init__.py	100.00% <0.00%> (ø)
dicodile/update_z/distributed_sparse_encoder.py	76.34% <0.00%> (+0.25%)	:arrow_up:
dicodile/utils/shape_helpers.py	74.41% <0.00%> (+4.97%)	:arrow_up:

---

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 1b54bac...4ce90ee. Read the comment docs.

[rprimet]

Any thoughts on how to document the window argument? (and when it should be set to False...)

[tomMoral]

For the window parameter, I would say:

If set to True, the learned atoms are multiplied by a Tukey
window that set its border to 0. This can help having patterns
localized in the middle of the atom support and reduces
border effects.