[MRG+1] Issue #8173 - Passing n_neighbors to compute MI #8181
Conversation
This file contains hidden or 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
glemaitre
changed the title
|
@jnothman Do you see additional unit test(s) or this is enough. |
jnothman
reviewed
Jan 11, 2017
| @@ -5,7 +5,8 @@ | |||
| from scipy.sparse import csr_matrix | |||
|
|
|||
| from sklearn.utils.testing import (assert_array_equal, assert_almost_equal, | |||
| assert_false, assert_raises, assert_equal) | |||
| assert_false, assert_raises, assert_equal, | |||
| assert_array_almost_equal) | |||
There was a problem hiding this comment.
I think the preference is for assert_allclose
I did it and then I had a second thought. |
ogrisel
reviewed
Jan 17, 2017
| assert_allclose(mi, [0.06987399, 0.03197151, 0.21946924], rtol=1e-6) | ||
| mi_7 = mutual_info_classif(X, y, discrete_features=[2], n_neighbors=7, | ||
| random_state=0) | ||
| assert_allclose(mi_7, [0.0735522, 0.0343685, 0.2194692], rtol=1e-5) |
There was a problem hiding this comment.
I don't really like tests that hardcode numerical values that are true only for randomly generated but with fixed see data. Is there a better way to test the impact of n_neighbors without hardcoding the values?
|
I think checking that the MI changes with n_neighbors would be fine?
…On 18 January 2017 at 02:24, Olivier Grisel ***@***.***> wrote:
***@***.**** commented on this pull request.
------------------------------
In sklearn/feature_selection/tests/test_mutual_info.py
<#8181 (review)>
:
> assert_array_equal(np.argsort(-mi), [2, 0, 1])
+ assert_allclose(mi, [0.06987399, 0.03197151, 0.21946924], rtol=1e-6)
+ mi_7 = mutual_info_classif(X, y, discrete_features=[2], n_neighbors=7,
+ random_state=0)
+ assert_allclose(mi_7, [0.0735522, 0.0343685, 0.2194692], rtol=1e-5)
I don't really like tests that hardcode numerical values that are true
only for randomly generated but with fixed see data. Is there a better way
to test the impact of n_neighbors without hardcoding the values?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#8181 (review)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAEz6zKiPLJMV8BChk0v2M8CddRWNG5Kks5rTN0xgaJpZM4Lfpn9>
.
|
jnothman
reviewed
Jan 18, 2017
| for n_neighbors in [5, 7, 9]: | ||
| mi_nn = mutual_info_classif(X, y, discrete_features=[2], | ||
| n_neighbors=n_neighbors, random_state=0) | ||
| # Check that the continuous values have an higher MI |
There was a problem hiding this comment.
I think it would help to say "with greater n_neighbors"
glemaitre
force-pushed
the
is/8173
branch
2 times, most recently
from
ce35545 to
05d0585
Compare
jnothman
approved these changes
Jan 18, 2017
|
LGTM |
jnothman
changed the title
|
@ogrisel for a second review |
|
LGTM thanks @glemaitre |
sergeyf
pushed a commit
to sergeyf/scikit-learn
that referenced
this pull request
Feb 28, 2017
Closed
Sundrique
pushed a commit
to Sundrique/scikit-learn
that referenced
this pull request
Jun 14, 2017
NelleV
pushed a commit
to NelleV/scikit-learn
that referenced
this pull request
Aug 11, 2017
paulha
pushed a commit
to paulha/scikit-learn
that referenced
this pull request
Aug 19, 2017
maskani-moh
pushed a commit
to maskani-moh/scikit-learn
that referenced
this pull request
Nov 15, 2017
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 Issue
Fixes #8173
What does this implement/fix? Explain your changes.
The parameters
n_neighborsis passed to the functioncompute_miin_estimate_mi.Previously this parameter was not given to
compute_mi. The user could not set thisparameter as indicated in the documentation.
Any other comments?
A single test has been added in a classification case.
The computation of the mutual information was in fact correct since it was already tested
for different neighbours