Commit Graph

2629 Commits

Author SHA1 Message Date
Rémy Léone 9b7176dd9d [DOC] Fix broken links 2016-03-23 12:45:34 -07:00
giorgiop 328ebfa865 ENH RandomizedPCA collapsed into PCA 2016-03-11 09:10:37 +11:00
Tim Head 07cede74ca Multitarget regression meta estimator
Register OneVsRestRegressor as meta estimator

Rename to a more sensible name

Parallel predict and sparse support

Started MultiOutput documentation

Move code to new file multioutput.py

Continuing the move to new multioutput module

Added sample weight support

Better test for sample weights and actually support weights

Added a new test using weighted vs repeated samples to
test sample weight support. Uncovered that weights
were not actually passed on to underlying estimator.

Comment on multiprocess overheads

Move parallel_helper to utils.fixes

This helper works around a python2 limitation on pickling
instance methods

Example of multi-output regression with gradient boosting

Switch to uniform weighted score and updated example

The example now uses a RF with and without the MultiOutput
meta estimator

Added note for removing `score` method

Addressing comments on MultiOutputRegressor

MultiOutputregressor better test for weighted samples

Fix ups

Use explicit keyword argument for passing sample weights and
fix random_state on train-test split in the example
2016-03-10 16:06:08 -05:00
Lars Buitinck 2e4aafd19c MAINT remove my email address
I'm getting too many individual support requests. People should
use the mailing list.
2016-03-04 10:43:41 +01:00
MechCoder 7e79adca9d Huber regressor
Add gradient calculation in _huber_loss_and_gradient

Add tests to check the correctness of the loss and gradient

Fix for old scipy

Add parameter sigma for robust linear regression

Add gradient formula to robust _huber_loss_and_gradient

Add fit_intercept option and fix tests

Add docs to HuberRegressor and the helper functions

Add example demonstrating ridge_regression vs huber_regression

Add sample_weight implementation

Add scaling invariant huber test

Remove exp and add bounds to fmin_l_bfgs_b

Add sparse data support

Add more tests and refactoring of code

Add narrative docs

review huber regressor

Minor additions to docs and tests

Minor fixes that deals with dealing with NaN values in targets
and old verions of SciPy and NumPy

Add HuberRegressor to robust estimator

Refactored computation of gradient and make docs render properly

Temp

Remove float64 dtype conversion

trivial optimizations and add a note about R

Remove sample_weights special_casing

address @amueller comments
2016-02-25 16:31:08 -05:00
YenChenLin 46fc1be145 Remove redundant words in sklearn 2016-02-23 16:54:03 +08:00
YenChenLin 2d8eb008d2 Fix broken link of Wainwright's paper 2016-02-18 01:09:20 +08:00
alyssaq d2b6c7a37d Fixed legend text and pep8 warnings 2016-02-15 14:12:25 +08:00
Andreas Mueller c761ba7661 Merge pull request #6260 from ogrisel/pr-5920-followup
[MRG] Updated examples and tests that use scipy's lena
2016-02-11 10:53:51 -05:00
Gilles Louppe 88b96a762d Merge pull request #5675 from AlexanderFabisch/gmm_clustering
[MRG+1] Make clear that GMM is a clustering algorithm
2016-02-11 10:49:46 +01:00
Nelson Liu fcfaa5fc37 Updated examples and tests that use scipy's lena
scipy.misc.lena will be removed in scipy version 0.17.
This changes the example to use scipy.misc.face instead.
2016-02-11 09:13:40 +01:00
govin-vatsan 9c511d04cc Changes to be committed:
modified:   examples/applications/svm_gui.py

For some reason, the Tkinter package is not compatible with Python 3.

	try:
    	    import Tkinter as Tk #works with Python 2
	except ImportError:
	    import tkinter as Tk #works with Python 3

 I added in an additional import statement to add compatibility

[ci skip]
2016-02-10 15:44:59 +01:00
Olivier Grisel 637cebbdf5 FIX restore previous title layout in examples/tree/plot_iris.py 2016-02-04 16:09:36 +01:00
Olivier Grisel 864f1c06a8 Merge pull request #6264 from yenchenlin1994/fix-multioutput-regression-tree-example
[MRG+1]Fix axis label in the plot of multioutput regression tree example
2016-02-04 11:04:05 +01:00
YenChenLin e20e003be5 Fix axis label of multioutput regression tree example 2016-02-02 10:39:47 +08:00
Panos Louridas bb0a6325de move title in the bottom 2016-01-29 17:03:35 +02:00
Panos Louridas c0e4832d08 remove shuffling and standardization fix layout 2016-01-28 18:16:31 +02:00
Nikolay Mayorov 824dda3767 MAINT: Small changes to plot_f_test_vs_mi.py 2016-01-22 00:27:16 +05:00
Nikolay Mayorov 835102ab6a API: Split mutual_info into _regression and _classif 2016-01-22 00:27:15 +05:00
Nikolay Mayorov 689ed0dbba DOC: Example for mutual_information 2016-01-22 00:27:15 +05:00
Nikolay Mayorov df08defb05 ENH: Implemented mutual_info function 2016-01-22 00:27:15 +05:00
Kornel Kielczewski d3175db362 Ridge coefficients as a function of regularisation
- another perspective
2016-01-19 16:04:36 +01:00
Alexandre Gramfort 22c687b525 polish figure 2016-01-16 13:54:10 +01:00
Raghav R V 1d9186d44c ENH/FIX std error is computed for mean across a set of 3 scores, not len(X) 2016-01-16 13:50:01 +01:00
MechCoder 936ea632e6 Make ridge path with ill-conditioned matrices clearer 2016-01-09 12:29:13 -05:00
Tom Dupré la Tour 682fd8e329 Merge pull request #6102 from toastedcornflakes/denoising_doc_fix
[MRG+1] Remove useless normalization
2016-01-05 15:34:25 +01:00
Olivier Grisel 41035a0f19 ENH less verbose output in plot_partial_dependence example 2016-01-04 14:19:28 +01:00
trevorstephens eb4bd0931c fix pplot example for uneven grids 2016-01-04 14:19:27 +01:00
Gael Varoquaux 317dea8a05 Merge pull request #6005 from seales/SpellingFix
[MRG+1] General spelling fixes
2016-01-04 13:42:20 +01:00
Loïc Estève 3daab8a998 FIX fetch_california_housing
Using a different resource than lib.stat.cmu.edu which has not been fixed yet.
2016-01-04 11:52:31 +01:00
toastedcornflakes 2ff9a4b39d Remove useless normalization — fixes #6075 2015-12-30 15:02:57 +01:00
dsquareindia 80c770ffa0 FIX Eliminated the use of color_cycle in out of core example 2015-12-28 10:01:43 +01:00
Alexandre Gramfort 6ff0bbe6f1 Merge pull request #6068 from nelson-liu/rework_nearest_centroid_classification
doc/fix: edited inaccuracies in nearest centroid classification example
2015-12-20 15:29:45 +01:00
MechCoder ad758d2069 FIX: Cluster centers after fir in KMeans and MBKMeans need not be ordered in the same way 2015-12-19 23:59:32 -05:00
Manoj Kumar c2cee91520 Merge pull request #6048 from zhengqm/fix-cluster-example-bug
[MRG+1] Fix bug in mini batch kmeans example
2015-12-19 23:26:23 -05:00
Nelson Liu fc31b6438c doc/fix: edited inaccuracies in nearest centroid classification example 2015-12-19 17:54:43 -08:00
seales 0485ada58b General spelling fixes 2015-12-16 09:46:42 -08:00
Qimu Zheng 0e074a009a Fix bug in mini batch kmeans example 2015-12-16 14:19:31 +08:00
David Thaler 37bfe80e1b FIX Changed zorder so support vectors are clearly visible 2015-12-15 19:29:51 -08:00
Kvle Putnam 61a58c54a0 Fix omitted word in SVM-Anova example 2015-12-15 13:18:19 -06:00
hdmetor c865b9b9b2 Using rain_test_split and StandardScaler instead of reimplementing them 2015-12-15 08:11:19 -08:00
Andreas Mueller 37c8d0297b HOTFIX actually fixing the california housing problem 2015-12-14 11:49:41 -05:00
Andreas Mueller f9ae546a67 HOTFIX skip partial dependence plot so we can run circleci without errors. 2015-12-11 16:16:57 -05:00
Andreas Mueller 5b1aca08c2 MAINT Don't use deprecated 1d X (or deprecated matplotlib stuff) in examples. 2015-12-10 12:11:48 -05:00
Tom Dupré la Tour a6800431a3 Merge pull request #5800 from fabioticconi/patch-1
Fixed transformation of test set via RobustScaler in example
2015-12-09 16:34:09 +01:00
Alexandre Gramfort 52caed6faa Merge pull request #5949 from olologin/plot_svm_anova.py-and-"all-CPU's"
[MRG+1] DOC: plot_svm_anova.py-and-"all-CPU's" typo fix
2015-12-06 09:43:39 +01:00
Manoj Kumar 43e54541a1 Merge pull request #5251 from TomDLT/sag_multi
[MRG+1] add multinomial SAG solver for LogisticRegression
2015-12-04 13:43:08 -05:00
TomDLT 9f136ff293 ENH add multinomial SAG solver for LogisticRegression 2015-12-04 18:36:37 +01:00
kjell 50dfa8610a change comment, printed comment, and code behavior to all reflect computation of mean squared error 2015-12-03 13:17:58 -08:00
kjell 6f7e351886 residual sum of squares should be computed by summing the squared differences instead of taking the mean. 2015-12-03 10:48:02 -08:00