Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add new ensembler component #2653

Merged
merged 34 commits into from
Sep 23, 2021
Merged

Add new ensembler component #2653

merged 34 commits into from
Sep 23, 2021

Conversation

christopherbunn
Copy link
Contributor

Resolves #1930

@codecov
Copy link

codecov bot commented Aug 18, 2021

Codecov Report

Merging #2653 (5359ef0) into main (5e62757) will increase coverage by 0.1%.
The diff coverage is 99.4%.

Impacted file tree graph

@@           Coverage Diff           @@
##            main   #2653     +/-   ##
=======================================
+ Coverage   99.8%   99.8%   +0.1%     
=======================================
  Files        297     302      +5     
  Lines      27741   28128    +387     
=======================================
+ Hits       27664   28050    +386     
- Misses        77      78      +1     
Impacted Files Coverage Δ
evalml/automl/automl_search.py 99.9% <ø> (ø)
evalml/pipelines/__init__.py 100.0% <ø> (ø)
evalml/utils/gen_utils.py 99.1% <ø> (ø)
evalml/tests/component_tests/test_utils.py 95.3% <40.0%> (ø)
evalml/tests/automl_tests/test_automl_algorithm.py 97.4% <50.0%> (-2.6%) ⬇️
evalml/automl/automl_algorithm/automl_algorithm.py 100.0% <100.0%> (ø)
...valml/automl/automl_algorithm/default_algorithm.py 100.0% <100.0%> (ø)
...lml/automl/automl_algorithm/iterative_algorithm.py 100.0% <100.0%> (ø)
evalml/automl/engine/engine_base.py 100.0% <100.0%> (ø)
evalml/pipelines/component_graph.py 99.8% <100.0%> (ø)
... and 20 more

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 5e62757...5359ef0. Read the comment docs.

@christopherbunn christopherbunn force-pushed the 1930_custom_ensembler branch 6 times, most recently from 9bc885c to 23fe8f9 Compare August 24, 2021 15:28
@christopherbunn christopherbunn marked this pull request as ready for review August 24, 2021 15:50
Comment on lines 42 to 48
n_components = 54
elif is_using_windows and not is_running_py_39_or_above:
# No prophet
n_components = 53
n_components = 55
elif is_using_windows and is_running_py_39_or_above:
# No detrender, no arima, no prophet
n_components = 51
n_components = 53
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since these are Windows/Conda tests, we might just not get coverage for this section until we merge to main.

@christopherbunn christopherbunn requested review from a team and angela97lin August 24, 2021 17:06
@christopherbunn
Copy link
Contributor Author

christopherbunn commented Sep 7, 2021

Here is the ensembler performance test doc that I have so far. I think that once I get in this PR for looking glass we can get into a deeper analysis of the results and see where the new ensembler ends up relative to the old one.

9/17 - Updated looking glass doc here:

Copy link
Contributor

@eccabay eccabay left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice, this continues to be awesome work! Just left a couple small suggestions and nits.

evalml/automl/automl_algorithm/automl_algorithm.py Outdated Show resolved Hide resolved
evalml/automl/automl_algorithm/automl_algorithm.py Outdated Show resolved Hide resolved
evalml/automl/engine/engine_base.py Outdated Show resolved Hide resolved
evalml/pipelines/utils.py Outdated Show resolved Hide resolved
# The total number of minimal components is 42
# The total number of components is 53
# The total number of minimal components is 43
# The total number of components is 56
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure 56 is the correct value?

@christopherbunn christopherbunn force-pushed the 1930_custom_ensembler branch 3 times, most recently from a7a13b7 to 5068338 Compare September 8, 2021 20:49
@christopherbunn christopherbunn dismissed freddyaboulton’s stale review September 23, 2021 19:27

Addressed comments in this review.

@christopherbunn christopherbunn merged commit b01444a into main Sep 23, 2021
@freddyaboulton freddyaboulton deleted the 1930_custom_ensembler branch May 13, 2022 15:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Build ensembler component
5 participants