WIP: Sparse coder #456
Merged
WIP: Sparse coder #456
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
| @@ -708,6 +708,77 @@ def transform(self, X, y=None): | ||
| return code | ||
|
|
||
|
|
||
| class SparseCoder(BaseDictionaryLearning): | ||
| """ Sparse coding |
There was a problem hiding this comment.
Please:
"""Sparse codingPEP257 :)
|
With regards to precomputing wavelets dictionnaries, I don't not think that this is a good idea, because a Wavelet transform can be implemented much faster than a dot product. In addition, it is a orthogonal basis, thus sparse coding should preferably be done using soft thresholding. Finally, this would be fairly image or signal specific, and I don't like the idea of such application-specific code creeping in a general-purpose object. |
| @@ -708,8 +708,79 @@ def transform(self, X, y=None): | ||
| return code | ||
|
|
||
|
|
||
| class SparseCoder(BaseDictionaryLearning): |
There was a problem hiding this comment.
This object should be imported in the init of decomposition.
It should also be added in docs/modules/classes.rst
|
My biggest comment is that it is missing a narrative documentation. In Gael |
| @@ -129,7 +129,8 @@ def sparse_encode(X, Y, gram=None, cov=None, algorithm='lasso_lars', | ||
| max_iter=1000) | ||
| for k in xrange(n_features): | ||
| # A huge amount of time is spent in this loop. It needs to be | ||
| # tight. | ||
| # tight | ||
|
|
|
I think it would be good if the SparseCoder would be referenced in the DictionaryLearning "see also" section. |
|
|
||
| if algorithm == 'lasso_lars': | ||
| if alpha is None: | ||
| alpha = 1. | ||
| alpha /= n_features # account for scaling |
There was a problem hiding this comment.
Note that before, dict_learning and dict_learning_online would perform very different on exactly the same data and for the same alpha. This was indeed caused by sometimes forgetting to divide by n_features and this fixes it.
…into sparse-coder Conflicts: sklearn/linear_model/least_angle.py
|
merged, thanks |
gbolmier
added a commit
to gbolmier/scikit-learn
that referenced
this pull request
May 29, 2020
# More detailed explanatory text, if necessary. Wrap it to about 72 # characters or so. In some contexts, the first line is treated as the # subject of the commit and the rest of the text as the body. The # blank line separating the summary from the body is critical (unless # you omit the body entirely); various tools like `log`, `shortlog` # and `rebase` can get confused if you run the two together. # Explain the problem that this commit is solving. Focus on why you # are making this change as opposed to how (the code explains that). # Are there side effects or other unintuitive consequences of this # change? Here's the place to explain them. # Further paragraphs come after blank lines. # - Bullet points are okay, too # - Typically a hyphen or asterisk is used for the bullet, preceded # by a single space, with blank lines in between, but conventions # vary here # If you use an issue tracker, put references to them at the bottom, # like this: # Resolves: scikit-learn#123 # See also: scikit-learn#456, scikit-learn#789
gbolmier
added a commit
to gbolmier/scikit-learn
that referenced
this pull request
May 30, 2020
# More detailed explanatory text, if necessary. Wrap it to about 72 # characters or so. In some contexts, the first line is treated as the # subject of the commit and the rest of the text as the body. The # blank line separating the summary from the body is critical (unless # you omit the body entirely); various tools like `log`, `shortlog` # and `rebase` can get confused if you run the two together. # Explain the problem that this commit is solving. Focus on why you # are making this change as opposed to how (the code explains that). # Are there side effects or other unintuitive consequences of this # change? Here's the place to explain them. # Further paragraphs come after blank lines. # - Bullet points are okay, too # - Typically a hyphen or asterisk is used for the bullet, preceded # by a single space, with blank lines in between, but conventions # vary here # If you use an issue tracker, put references to them at the bottom, # like this: # Resolves: scikit-learn#123 # See also: scikit-learn#456, scikit-learn#789
gbolmier
added a commit
to gbolmier/scikit-learn
that referenced
this pull request
Aug 9, 2020
# More detailed explanatory text, if necessary. Wrap it to about 72 # characters or so. In some contexts, the first line is treated as the # subject of the commit and the rest of the text as the body. The # blank line separating the summary from the body is critical (unless # you omit the body entirely); various tools like `log`, `shortlog` # and `rebase` can get confused if you run the two together. # Explain the problem that this commit is solving. Focus on why you # are making this change as opposed to how (the code explains that). # Are there side effects or other unintuitive consequences of this # change? Here's the place to explain them. # Further paragraphs come after blank lines. # - Bullet points are okay, too # - Typically a hyphen or asterisk is used for the bullet, preceded # by a single space, with blank lines in between, but conventions # vary here # If you use an issue tracker, put references to them at the bottom, # like this: # Resolves: scikit-learn#123 # See also: scikit-learn#456, scikit-learn#789
gbolmier
added a commit
to gbolmier/scikit-learn
that referenced
this pull request
Aug 9, 2020
# More detailed explanatory text, if necessary. Wrap it to about 72 # characters or so. In some contexts, the first line is treated as the # subject of the commit and the rest of the text as the body. The # blank line separating the summary from the body is critical (unless # you omit the body entirely); various tools like `log`, `shortlog` # and `rebase` can get confused if you run the two together. # Explain the problem that this commit is solving. Focus on why you # are making this change as opposed to how (the code explains that). # Are there side effects or other unintuitive consequences of this # change? Here's the place to explain them. # Further paragraphs come after blank lines. # - Bullet points are okay, too # - Typically a hyphen or asterisk is used for the bullet, preceded # by a single space, with blank lines in between, but conventions # vary here # If you use an issue tracker, put references to them at the bottom, # like this: # Resolves: scikit-learn#123 # See also: scikit-learn#456, scikit-learn#789
gbolmier
added a commit
to gbolmier/scikit-learn
that referenced
this pull request
Aug 9, 2020
# More detailed explanatory text, if necessary. Wrap it to about 72 # characters or so. In some contexts, the first line is treated as the # subject of the commit and the rest of the text as the body. The # blank line separating the summary from the body is critical (unless # you omit the body entirely); various tools like `log`, `shortlog` # and `rebase` can get confused if you run the two together. # Explain the problem that this commit is solving. Focus on why you # are making this change as opposed to how (the code explains that). # Are there side effects or other unintuitive consequences of this # change? Here's the place to explain them. # Further paragraphs come after blank lines. # - Bullet points are okay, too # - Typically a hyphen or asterisk is used for the bullet, preceded # by a single space, with blank lines in between, but conventions # vary here # If you use an issue tracker, put references to them at the bottom, # like this: # Resolves: scikit-learn#123 # See also: scikit-learn#456, scikit-learn#789
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.
This quick and dirty pull request aims to add an estimator (transformer) object that implements sparse coding against a fixed dictionary, in the form of the SparseCoder object.
At the same time this will address the small inconsistencies and missing info in docs that came up.