[MRG+1] Add prominent mention of Laplacian Eigenmaps #8155
Conversation
| @@ -305,7 +305,7 @@ The overall complexity of standard HLLE is | |||
| Spectral Embedding | |||
| ==================== | |||
|
|
|||
| Spectral Embedding (also known as Laplacian Eigenmaps) is one method | |||
| Spectral Embedding (specifically, Laplacian Eigenmaps) is one method | |||
There was a problem hiding this comment.
Perhaps "Spectral Embedding is an approach to calculating a non-linear embedding. Scikit-learn implements Laplacian Eigenmaps, which finds a low dimensional representation ..."
but this is not an area of my expertise.
There was a problem hiding this comment.
@amueller Thoughts?
a8b09c0 to
5c9a6c4
Compare
|
@jnothman updated! |
|
LGTM, but I don't know this part of the library well enough so I'll leave it for a second reviewer to confirm. |
| @@ -319,7 +319,7 @@ function :func:`spectral_embedding` or its object-oriented counterpart | |||
| Complexity | |||
| ---------- | |||
|
|
|||
| The Spectral Embedding algorithm comprises three stages: | |||
| The Laplacian Eigenmaps algorithm comprises three stages: | |||
There was a problem hiding this comment.
I would prefer "The Spectral Embedding (Laplacian Eigenmaps) algorithm..."
Spectral embedding is an algorithm commonly used to denote this problem (see for instance
http://www.cs.cmu.edu/~aarti/Class/10701/readings/Luxburg06_TR.pdf
that has 4000 citations)
| @@ -189,7 +191,7 @@ def spectral_embedding(adjacency, n_components=8, eigen_solver=None, | |||
|
|
|||
| Notes | |||
| ----- | |||
| Spectral embedding is most useful when the graph has one connected | |||
| Laplacian Eigenmaps is most useful when the graph has one connected | |||
… Spectral Embedding implements
|
Edited and squashed! |
|
Thanks, though squashing is no longer necessary and indeed can be harmful to reviewing. |
|
I fixed a line length issue and am merging |
|
@jnothman are there any guidelines for squashing? |
|
Don't squash, the merger will?
…On 18 January 2017 at 12:38, Samson Tan ***@***.***> wrote:
@jnothman <https://github.com/jnothman> are there any guidelines for
squashing?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#8155 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAEz63K3983hWjZ9yaOG64v9L2WDY0BFks5rTW0PgaJpZM4Lbxuq>
.
|
|
@jnothman got it! Apologies, I was told to squash my commits in another repo |
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
* Add prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements
Fixes #5875
Adds prominent mention of Laplacian Eigenmaps being the algorithm that Spectral Embedding implements