[MRG] Regression label for 2d classification data generation #69
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
the main bug that has been changes was due to the y.astype(int) in the return that rounded the float values when using regression labels
BuenoRuben
changed the title
BuenoRuben
changed the title
tgnassou
reviewed
Feb 1, 2024
|
Your tests are not passing |
BuenoRuben
changed the title
the test as using a method that has been changed, thus raising errors
the two tests that got removed were checking that the y-values were between 0 and 1, which should not necessarely be the case in regression
I just changed the size of the colorbar so that we have better looking plots next to it
now _generate_data_2d_classif_subspace use the label that has been given in parametter instead of "binary" everytimes, additionally the example for the regression label use the subspace shift
the main issue was that the y vlues that were generated weren't of the correct size (note the same as the X values)
BuenoRuben
changed the title
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## main #69 +/- ##
==========================================
+ Coverage 86.82% 87.16% +0.34%
==========================================
Files 38 38
Lines 2398 2439 +41
==========================================
+ Hits 2082 2126 +44
+ Misses 316 313 -3 ☔ View full report in Codecov by Sentry. |
this test should cover the change over generate_data_2d_classif_subspace when using 'multiclass' or 'regression' label
with subset shift, the values are twice smaller for the default case
this was needed with teh previous changes
tgnassou
reviewed
Feb 7, 2024
| elif label == 'multiclass': | ||
| y = np.zeros(n1) | ||
| for i in range(4): | ||
| y = np.concatenate((y, (i + 1) * np.ones(n2)), 0) | ||
| y = y.astype(int) | ||
| elif label == 'regression': | ||
| # create label y with gaussian distribution |
There was a problem hiding this comment.
Maybe it could be nice to have the possibility to modify the mu and the Sigma1 as we want. So just put it in the parameters of the function with default values.
There was a problem hiding this comment.
And change the name to mu_regression, sigma_regression
| for i in range(k): | ||
| y = np.concatenate((y, (i + 1) * np.ones(n1//k)), 0) | ||
| y = y.astype(int) | ||
| elif label == 'regression': |
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.
In this branch, I added the 'regression' label to both
_generate_data_2d_classifand_generate_data_2d_classif_subspacein skada/datasets/_sample_generator.py, added a new example for this label: examples/datasets/plot_shifted_dataset_regression.pyand added a new test:
test_make_shifted_datasets_regressionin skada\datasets\tests\test_samples_generator.py