[MRG] Adding variable force_alpha to classes in naive_bayes.py #18805
+107
−13
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -537,11 +537,18 @@ def _check_alpha(self): | |||||
| "with shape [n_features]" | ||||||
| ) | ||||||
| if np.min(self.alpha) < _ALPHA_MIN: | ||||||
| if self.force_alpha: | ||||||
| warnings.warn( | ||||||
|
There was a problem hiding this comment. Is this really useful to warn when the user specifically set the parameter |
||||||
| "alpha too small will result in numeric errors. " | ||||||
| "Proceeding with alpha = %.1e, as " | ||||||
| "force_alpha was set to True." % self.alpha | ||||||
| ) | ||||||
| else: | ||||||
| warnings.warn( | ||||||
| "alpha too small will result in numeric errors, " | ||||||
|
There was a problem hiding this comment. I would add something like "use force_alpha=True to keep alpha unchanged.". |
||||||
| "setting alpha = %.1e" % _ALPHA_MIN | ||||||
| ) | ||||||
| return np.maximum(self.alpha, _ALPHA_MIN) | ||||||
| return self.alpha | ||||||
|
|
||||||
| def partial_fit(self, X, y, classes=None, sample_weight=None): | ||||||
|
|
@@ -735,7 +742,14 @@ class MultinomialNB(_BaseDiscreteNB): | |||||
| ---------- | ||||||
| alpha : float, default=1.0 | ||||||
| Additive (Laplace/Lidstone) smoothing parameter | ||||||
| (set alpha=0 and force_alpha=True, for no smoothing). | ||||||
|
|
||||||
| force_alpha : bool, default=False | ||||||
| If False and alpha is too close to 0, it will set alpha to | ||||||
| `_ALPHA_MIN`. If True, warn user about potential numeric errors | ||||||
|
There was a problem hiding this comment. I would change |
||||||
| and proceed with alpha unchanged. | ||||||
|
|
||||||
| .. versionadded:: 1.0 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| fit_prior : bool, default=True | ||||||
| Whether to learn class prior probabilities or not. | ||||||
|
|
@@ -820,8 +834,11 @@ class MultinomialNB(_BaseDiscreteNB): | |||||
| https://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html | ||||||
| """ | ||||||
|
|
||||||
| def __init__( | ||||||
| self, *, alpha=1.0, force_alpha=False, fit_prior=True, class_prior=None | ||||||
| ): | ||||||
| self.alpha = alpha | ||||||
| self.force_alpha = force_alpha | ||||||
| self.fit_prior = fit_prior | ||||||
| self.class_prior = class_prior | ||||||
|
|
||||||
|
|
@@ -862,7 +879,15 @@ class ComplementNB(_BaseDiscreteNB): | |||||
| Parameters | ||||||
| ---------- | ||||||
| alpha : float, default=1.0 | ||||||
| Additive (Laplace/Lidstone) smoothing parameter | ||||||
| (set alpha=0 and force_alpha=True, for no smoothing). | ||||||
|
|
||||||
| force_alpha : bool, default=False | ||||||
| If False and alpha is too close to 0, it will set alpha to | ||||||
| `_ALPHA_MIN`. If True, warn user about potential numeric errors | ||||||
| and proceed with alpha unchanged. | ||||||
|
|
||||||
| .. versionadded:: 1.0 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| fit_prior : bool, default=True | ||||||
| Only used in edge case with a single class in the training set. | ||||||
|
|
@@ -949,8 +974,17 @@ class ComplementNB(_BaseDiscreteNB): | |||||
| https://people.csail.mit.edu/jrennie/papers/icml03-nb.pdf | ||||||
| """ | ||||||
|
|
||||||
| def __init__( | ||||||
| self, | ||||||
| *, | ||||||
| alpha=1.0, | ||||||
| force_alpha=False, | ||||||
| fit_prior=True, | ||||||
| class_prior=None, | ||||||
| norm=False, | ||||||
| ): | ||||||
| self.alpha = alpha | ||||||
| self.force_alpha = force_alpha | ||||||
| self.fit_prior = fit_prior | ||||||
| self.class_prior = class_prior | ||||||
| self.norm = norm | ||||||
|
|
@@ -998,7 +1032,14 @@ class BernoulliNB(_BaseDiscreteNB): | |||||
| ---------- | ||||||
| alpha : float, default=1.0 | ||||||
| Additive (Laplace/Lidstone) smoothing parameter | ||||||
| (set alpha=0 and force_alpha=True, for no smoothing). | ||||||
|
|
||||||
| force_alpha : bool, default=False | ||||||
| If False and alpha is too close to 0, it will set alpha to | ||||||
| `_ALPHA_MIN`. If True, warn user about potential numeric errors | ||||||
| and proceed with alpha unchanged. | ||||||
|
|
||||||
| .. versionadded:: 1.0 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| binarize : float or None, default=0.0 | ||||||
| Threshold for binarizing (mapping to booleans) of sample features. | ||||||
|
|
@@ -1079,8 +1120,17 @@ class BernoulliNB(_BaseDiscreteNB): | |||||
| naive Bayes -- Which naive Bayes? 3rd Conf. on Email and Anti-Spam (CEAS). | ||||||
| """ | ||||||
|
|
||||||
| def __init__( | ||||||
| self, | ||||||
| *, | ||||||
| alpha=1.0, | ||||||
| force_alpha=False, | ||||||
| binarize=0.0, | ||||||
| fit_prior=True, | ||||||
| class_prior=None, | ||||||
| ): | ||||||
| self.alpha = alpha | ||||||
| self.force_alpha = force_alpha | ||||||
| self.binarize = binarize | ||||||
| self.fit_prior = fit_prior | ||||||
| self.class_prior = class_prior | ||||||
|
|
@@ -1144,7 +1194,14 @@ class CategoricalNB(_BaseDiscreteNB): | |||||
| ---------- | ||||||
| alpha : float, default=1.0 | ||||||
| Additive (Laplace/Lidstone) smoothing parameter | ||||||
| (set alpha=0 and force_alpha=True, for no smoothing). | ||||||
|
|
||||||
| force_alpha : bool, default=False | ||||||
| If False and alpha is too close to 0, it will set alpha to | ||||||
| `_ALPHA_MIN`. If True, warn user about potential numeric errors | ||||||
| and proceed with alpha unchanged. | ||||||
|
|
||||||
| .. versionadded:: 1.0 | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| fit_prior : bool, default=True | ||||||
| Whether to learn class prior probabilities or not. | ||||||
|
|
@@ -1221,9 +1278,16 @@ class CategoricalNB(_BaseDiscreteNB): | |||||
| """ | ||||||
|
|
||||||
| def __init__( | ||||||
| self, | ||||||
| *, | ||||||
| alpha=1.0, | ||||||
| force_alpha=False, | ||||||
| fit_prior=True, | ||||||
| class_prior=None, | ||||||
| min_categories=None, | ||||||
| ): | ||||||
| self.alpha = alpha | ||||||
| self.force_alpha = force_alpha | ||||||
| self.fit_prior = fit_prior | ||||||
| self.class_prior = class_prior | ||||||
| self.min_categories = min_categories | ||||||
|
|
||||||
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -897,6 +897,31 @@ def test_alpha(): | |
| m_nb.partial_fit(X, y, classes=[0, 1]) | ||
|
|
||
|
|
||
| def test_check_alpha(): | ||
| # Non-regression test for: | ||
| # https://github.com/scikit-learn/scikit-learn/issues/10772 | ||
| # Test force_alpha if alpha < _ALPHA_MIN | ||
hongshaoyang marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| _ALPHA_MIN = 1e-10 # const | ||
| msg1 = ( | ||
| "alpha too small will result in numeric errors. " | ||
| "Proceeding with alpha = .+, as " | ||
| "force_alpha was set to True." | ||
| ) | ||
| msg2 = ( | ||
| "alpha too small will result in numeric errors, " | ||
| "setting alpha = %.1e" % _ALPHA_MIN | ||
| ) | ||
| b = BernoulliNB(alpha=0, force_alpha=True) | ||
| with pytest.warns(UserWarning, match=msg1): | ||
| assert b._check_alpha() == 0 | ||
| b = BernoulliNB(alpha=0, force_alpha=False) | ||
| with pytest.warns(UserWarning, match=msg2): | ||
| assert b._check_alpha() == _ALPHA_MIN | ||
| b = BernoulliNB(alpha=0) | ||
| with pytest.warns(UserWarning, match=msg2): | ||
| assert b._check_alpha() == _ALPHA_MIN | ||
hongshaoyang marked this conversation as resolved.
Show resolved
Hide resolved
|
||
|
|
||
|
|
||
| def test_alpha_vector(): | ||
| X = np.array([[1, 0], [1, 1]]) | ||
| y = np.array([0, 1]) | ||
|
|
||
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Because v1.0 is already released, this entry should now be moved to
v1.1.rst.