Hi,
I added an Ipython notebook with example code to the repo.
Johannes
Quoting Alexandre Gramfort (2014-04-11 11:24:00)
> hi Johannes,
>
> I am personally interested by this code. Can you make it a bit
> more userfriendly adding an example as we do with sklearn?
>
> for sklearn, to start, wha
Hi,
I've some knowledge of Apriori and FP growth algorithms and I'd like to use
those to contribute a new association rule classifier to Sklearn.
What would be a good published paper to refer to for working on this?
Has anyone been doing work in this area already, in that case I'd like to
work w
it is used in the get_support method.
https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/linear_model/randomized_l1.py#L121
A
--
Put Bad Developers to Shame
Dominate Development with Jenkins Continuous Inte
2014-04-11 10:55 GMT+02:00 Daniel Vainsencher :
> In any case, the approximate nature of the search raises the possibility
> of going a step further: index the data points, and adjust each cluster
> to its ANNs (in this case, for a very long list of candidates). This is
> no longer k-means (closer
hi Johannes,
I am personally interested by this code. Can you make it a bit
more userfriendly adding an example as we do with sklearn?
for sklearn, to start, what I recommend is to adapt it to use the sklearn API
and add it to the wiki page of related projects.
best,
Alex
On Fri, Apr 11, 2014
Hi there,
Over the last days I implemented Bayesian Changepoint Detection (online &
offline versions). The code is not polished yet, but I wondered if there is
interest in me getting the code to a state s.t. it could be included to scikit
learn?
For the online version I basically translated a mat
Hi,
this is my first post so I hope I am using the mail list correctly.
I was wondering about the variable* selection_threshold: float, optional*:
in RandomLasso.
http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RandomizedLasso.html
I think that this variable is actually nev
Yes. I agree. But after all, we cannot guarantee that any of the clustering
algorithms will perform well on every setting of data. So don't you think
it is worth trying to apply ANN methods on these applications?
On Fri, Apr 11, 2014 at 2:25 PM, Daniel Vainsencher <
daniel.vainsenc...@gmail.com>
Indexing the clusters has the down side that the clusters change over
time, requiring the index to be reconstructed. This might be a speed up
or not, depending on the relation of clusters to data point cardinality
and on the exact speed of data structures.
In any case, the approximate nature of
In the current implementation of dbscan, algorithms in
`neighbors.NearestNeighbors` are used to train a model. That model will be
used to compute pointwise distances and find nearest neighbors later in the
code. LSH-based ANN module can be used for the same scenario in order to
achieve improved spe
10 matches
Mail list logo
