Re: [Scikit-learn-general] Unpickle doesn't work when upgrading from 14.1 to 15.1.

Looks like this was resolved in a previous version. Check this link: https://github.com/ilastik/ilastik/issues/793. Regards, Pranav. On 8/25/14, 10:14 PM, "Pranav Sharma" wrote: >Is there a workaround other than creating a new model with v15.1? > >Sent from my iPhone > >> On Aug 25, 2014,

Re: [Scikit-learn-general] Unpickle doesn't work when upgrading from 14.1 to 15.1.

Is there a workaround other than creating a new model with v15.1? Sent from my iPhone > On Aug 25, 2014, at 9:57 PM, "Gael Varoquaux" > wrote: > >> On Tue, Aug 26, 2014 at 02:42:02AM +, Pranav Sharma wrote: >> I just upgraded scikit from 14.1 to 15.1 to take advantage of the speed >> impro

Re: [Scikit-learn-general] Unpickle doesn't work when upgrading from 14.1 to 15.1.

On Tue, Aug 26, 2014 at 02:42:02AM +, Pranav Sharma wrote: > I just upgraded scikit from 14.1 to 15.1 to take advantage of the speed > improvements in the random forest classifier. However, when I tried loading > the > model created (using 14.1), it fails to load it. That's expected: pickle w

[Scikit-learn-general] Unpickle doesn't work when upgrading from 14.1 to 15.1.

I just upgraded scikit from 14.1 to 15.1 to take advantage of the speed improvements in the random forest classifier. However, when I tried loading the model created (using 14.1), it fails to load it. Here is the error. Please advice. I’m simply loading it as follows. Thanks a lot. Code: w

[Scikit-learn-general] Unpickle doesn't work when upgrading from 14.1 to 15.1.

I just upgraded scikit from 14.1 to 15.1 to take advantage of the speed improvements in the random forest classifier. However, when I tried loading the model created (using 14.1), it fails to load it. Here is the error. Please advice. I’m simply loading it as follows. Thanks a lot. Code: w

[Scikit-learn-general] Machine learning proves the Earth is flat

Apparently, there are still people who believe the Earth is flat: http://www.iflscience.com/space/there-are-still-people-who-believe-earth-flat-usa After reading some theory on support vector machines I have come to the conclusion that they are right. Any manifold can be expressed as a plane in a

[Scikit-learn-general] one-class SVM and multivariate novelty detection

w.r.t. the one-class SVM example http://scikit-learn.org/stable/auto_examples/svm/plot_oneclass.html#example-svm-plot-oneclass-py is there a reason why cross-validation is not used? Also, is novelty detection with multivariate Gaussian distribution available in sklearn? Thank you, --

[Scikit-learn-general] alphas value in lasso_stability_path

Hi, I was looking to the implementation of lasso_stability_path and how can be clearly seen here http://scikit-learn.org/0.13/auto_examples/linear_model/plot_sparse_recovery.html the alphas values returned by the algorithm are normalize. While this is closer to what is reported in the paper I thin

Re: [Scikit-learn-general] error in grid search for KNN

Hi, This is a bug, and is related to https://github.com/scikit-learn/scikit-learn/issues/2609 Jake Jake VanderPlas Director of Research – Physical Sciences eScience Institute, University of Washington http://www.vanderplas.com On Mon, Aug 25, 2014 at 8:12 AM, Sheila the angel wrote: > H

Re: [Scikit-learn-general] error in grid search for KNN

2014-08-25 17:50 GMT+02:00 Lars Buitinck : > 2014-08-25 17:46 GMT+02:00 Sheila the angel : >> I think the problem is in KNeighborsClassifier not in the grid_search. > > You're right. https://github.com/scikit-learn/scikit-learn/pull/3093 fixes it. It's just been fixed in master. -

Re: [Scikit-learn-general] error in grid search for KNN

2014-08-25 17:46 GMT+02:00 Sheila the angel : > I think the problem is in KNeighborsClassifier not in the grid_search. You're right. https://github.com/scikit-learn/scikit-learn/pull/3093 fixes it. -- Slashdot TV. Video

Re: [Scikit-learn-general] error in grid search for KNN

I think the problem is in KNeighborsClassifier not in the grid_search. This code runs without error >>>clf = KNeighborsClassifier(n_neighbors=3, metric="euclidean") >>>clf.fit(iris.data, iris.target) While setting metric value later gives error >>>clf = KNeighborsClassifier(n_neighbors=3)

Re: [Scikit-learn-general] error in grid search for KNN

2014-08-25 17:12 GMT+02:00 Sheila the angel : iris = datasets.load_iris() gp = {"n_neighbors":[2,3], "metric":['euclidean']} clf = GridSearchCV(KNeighborsClassifier(), gp, cv=4).fit(iris.data, iris.target) > > > TypeError: __init__() got an unexpected keyword argument 'p' > > > Why

[Scikit-learn-general] error in grid search for KNN

Hello all, In case of grid search for KNN I got the error. >>>iris = datasets.load_iris() >>>gp = {"n_neighbors":[2,3], "metric":['euclidean']} >>>clf = GridSearchCV(KNeighborsClassifier(), gp, cv=4).fit(iris.data, iris.target) TypeError: __init__() got an unexpected keyword argument 'p' Why

Re: [Scikit-learn-general] delta idf and bm25

2014-08-23 17:06 GMT+02:00 Lars Buitinck : > [3] This paper from a guy at HP Research that I cannot find right now. Found it: Forman et al., Feature Shaping for Linear SVM Classifiers, http://www.hpl.hp.com/techreports/2009/HPL-2009-31R1.pdf (SIGKDD 2009).