[ENH] Optimize QUANTTransformer by using shape calculation in _fit method to avoid unnecessary computations #2727
Conversation
This file contains 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
shinymack
requested review from
MatthewMiddlehurst and
TonyBagnall
as code owners
aeon-actions-bot
bot
added
enhancement
Thank you for contributing to
|
Ok, i'll run this on some other datasets and post the results here. |
|
Used this script for testing the output of the new one v/s the old one for different datasets and also different parameters. from aeon.transformations.collection.interval_based import QUANTTransformer_old, QUANTTransformer
from aeon.testing.data_generation import make_example_3d_numpy
from aeon.datasets import load_italy_power_demand, load_classification
datasets = [
("Example", make_example_3d_numpy(n_cases=10, n_channels=1, n_timepoints=12, random_state=0)[0]),
("ItalyPowerDemand", load_italy_power_demand()[0]),
("ArrowHead", load_classification("ArrowHead")[0]),
("BasicMotions", load_classification("BasicMotions")[0]),
("Beef", load_classification("Beef")[0])
]
parameter_sets = [
[2,8],[4,4],[1,2]
]
for dataset_name, X in datasets:
print(f"\nDataset: {dataset_name}")
print(f"Input shape: {X.shape}")
for params in parameter_sets:
print(f"\nParameters: interval_depth={params[0]}, quantile_divisor={params[1]}")
q = QUANTTransformer(interval_depth=params[0], quantile_divisor=params[1])
qo = QUANTTransformer_old(interval_depth=params[0], quantile_divisor=params[1])
q.fit(X)
qo.fit(X)
qt = q.transform(X)
qot = qo.transform(X)
print("Old shape:", qot.shape)
print("New shape:", qt.shape)
diff = abs(qt - qot)
if diff.max() == 0 and diff.min() == 0:
print("Values: Same")
else:
print("Values max diff:", diff.max())
print("Values mean diff:", diff.mean())Got same result for all of them |
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.
Reference Issues/PRs
Fixes #2722
What does this implement/fix? Explain your changes.
Used direct shape calculations for
representation_functionsin_fitmethod ofQUANTTransformerinstead of unnecessary operations as only the output shapes are required to create the intervals.Does your contribution introduce a new dependency? If yes, which one?
No
Any other comments?
The output correctly matches for the example given in the docstring.
PR checklist
For all contributions
For new estimators and functions
__maintainer__at the top of relevant files and want to be contacted regarding its maintenance. Unmaintained files may be removed. This is for the full file, and you should not add yourself if you are just making minor changes or do not want to help maintain its contents.For developers with write access