Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,839 Commits 32 Branches 59 Tags
Commit Graph

165 Commits

Author SHA1 Message Date
chanis
d8876b0b73 [python-package] modify __init__.py (#1587) 
* Update Makefile

* Update Makefile

* modify __init__.py
 2016-09-19 09:43:36 -07:00
闻波
8cdfec71b3 remove a redundant sentence, and a word 'and' (#1526) 
* fix a typo

* fix a typo and some code format

* Update training.py

* delete redundant sentence
 2016-08-31 11:51:40 -07:00
kiselev1189
53ce511be3 Fix how maximize_metric value is determined in early_stop (#1451) 
* Update callback.py

* Update callback.py
 2016-08-27 13:09:24 -07:00
Preston Parry
0627213544 Fixes typo "candicate" (#1508) 2016-08-26 14:00:27 -07:00
Preston Parry
cf4951b0b0 Fixes another typo "candicate" (#1509) 2016-08-26 14:00:23 -07:00
Dan Harbin
78ae772f2c Make python package wheelable (#1500) 
Currently xgboost can only be installed by running:

    python setup.py install

Now it can be packaged (in binary form) as a wheel and installed like:

    pip install xgboost-0.6-py2-none-any.whl

distutils and wheel install `data_files` differently than setuptools.
setuptools will install the `data_files` in the package directory whereas the
others install it in `sys.prefix`. By adding `sys.prefix` to the list of
directories to check for the shared library, xgboost can now be distributed as
a wheel.
 2016-08-26 14:00:11 -07:00
Hongliang Liu
c5a2b79558 PyPI (pip installation) setup for 0.6 code (#1445) 
* force gcc-5 or clang-omp for Mac OS, prepare for pip pack

* add sklearn dep, make -j4

* finalize PyPI submission

* revert to Xcode clang for passing build #1468

* force to clang, try to solve cmake travis error

* remove sklearn dependency
 2016-08-10 07:45:56 -05:00
Tianqi Chen
4a8d63b6c8 Tag version 0.6 (#1422) 2016-07-29 11:23:06 -07:00
Yuan (Terry) Tang
c60a356273 Remove pypi downloads badge (#1365) 2016-07-16 13:36:05 -04:00
Titouan Lorieul
75d9be55de [py] fix label encoding of eval sets in sklearn API (#1244) 2016-07-11 05:29:46 -05:00
Vladimir
aaf0a73486 fixed error when eval False (#1271) 2016-06-12 09:36:36 -07:00
Antonio Augusto Santos
19129b289c Preserve the actal objective used on the booster 
Save the actual objective used on xgboost.train.

Not saving it was giving problem in predict_proba, as issue  #1215
 2016-05-31 19:01:10 -03:00
Alberto Torres
af2e9ebd82 Update sklearn.py 2016-05-25 15:00:11 +02:00
tqchen
149589c583 [PYTHON] Refactor trainnig API to use callback 2016-05-19 21:31:23 -07:00
Vadim Khotilovich
ffed95eec0 py: replace attr_names() with attributes() 2016-05-15 22:04:38 -05:00
Vadim Khotilovich
a13a3a4d76 attr_names for python interface; attribute deletion via set_attr 2016-05-15 02:05:10 -05:00
Shayne Kang
bf24d6ae98 fix VisibleDeprecationWarning 2016-05-08 01:44:04 +09:00
Borun Dev Chowdhury
fc02f8a2dc cosmetic change 
cosmetic change of putting space after comma compared to previous edit.
 2016-05-07 12:33:37 +02:00
borundev
95bcff90af XGBModel.fit had a call to DMatrix without missing=self.missing. fixed that 2016-05-07 12:32:03 +02:00
Titouan Lorieul
3ab8f0b13d [py] added apply function in sklearn API to return the predicted leaves 2016-05-04 12:27:30 +02:00
Alistair Johnson
6750c8b743 Added other feature importances in python package (#1135) 
* added new function to calculate other feature importances

* added capability to plot other feature importance measures

* changed plotting default to fscore

* added info on importance_type to boilerplate comment

* updated text of error statement

* added self module name to fix call

* added unit test for feature importances

* style fixes
 2016-05-02 12:25:24 -05:00
sinhrks
9da2f3e613 DOC/TST: Fix Python sklearn dep 2016-05-01 17:27:43 +09:00
Faron
ad3f49e881 [py] eta decay bugfix 2016-04-30 15:51:57 +02:00
sinhrks
6bab164d80 Bug mixing DMatrix's with and without feature names 2016-04-30 14:42:57 +09:00
Faron
cf607e2448 [py] split value histograms 2016-04-28 20:26:21 +02:00
sinhrks
c55cc809e5 BUG: XGBClassifier.feature_importances_ raises ValueError if input is pandas DataFrame 2016-04-27 21:50:03 +09:00
Tianqi Chen
4149854633 Merge pull request #1068 from Laurae2/master 
Updated obsolete installation instructions
 2016-04-26 19:50:06 -07:00
sinhrks
8fc2456c87 Enable flake8 2016-04-24 17:32:31 +09:00
tqchen
49f3892942 allow common python output in single node 2016-04-11 15:48:16 -07:00
zyxue
79b35da308 improved docstring for folds in cv function 2016-04-09 10:21:56 -07:00
Laurae2
77136baf2c Updated obsolete installation instructions 
Fixed local compilation, and installation for R package and Python
package. Modified the according documents.
 2016-03-30 17:43:54 +02:00
Julian Quick
bbb9ce1641 Verbose message: which fields have impropper data types 
A more verbose error message letting the user know which fields have impropper data types
 2016-03-22 14:13:29 -06:00
Julian Quick
2cd109fb98 a more verbose field mismatch error message 
This error message can be hard to understand when there are several fields, as shown in the example below. This improves the error message, letting the user know which fields were unexpected or missing.

    import xgboost as xgb
    import pandas as pd
    train = pd.DataFrame({'a':[1], 'b':[2], 'c':[3], 'd':[4], 'f':[2], 'g':2, 'etc etc etc':[11]})
    dtrain = xgb.DMatrix(train.drop('d', axis=1), train.d)
    test = pd.DataFrame({'a':[1], 'b':[2], 'c':[1], 'd':[4], 'e':[2], 'f':[2], 'g':2, 'etc etc etc':[11]})
    dtest = xgb.DMatrix(test)
    modl = xgb.train({}, dtrain)
    modl.predict(dtest)
    
    
    # ValueError: feature_names mismatch: [u'a', u'b', u'c', u'etc etc etc', u'f', u'g'] [u'a', u'b', u'c', u'd', u'e', u'etc etc etc', u'f', u'g']
 2016-03-17 18:13:30 -06:00
DAndrey
311f7c8f47 change type of xgbclassifier.classes_ from list to numpy array 2016-03-17 16:54:33 +03:00
tqchen
bec7332eea Fix rabit 2016-03-06 20:54:27 -08:00
tqchen
ced6d45e01 Update rabit 2016-03-02 20:53:34 -08:00
tqchen
ecb3a271be [PYTHON-DIST] Distributed xgboost python training API. 2016-02-29 16:54:13 -08:00
Yuan (Terry) Tang
fdd520d774 Merge branch 'master' into sklearn 2016-02-29 10:50:55 -06:00
Paulo Alves
b7985466a4 Merge remote-tracking branch 'upstream/master' 2016-02-29 08:53:48 -03:00
terrytangyuan
803a6fe474 Separate dependencies and lightweight test env for Python 2016-02-28 20:11:10 -06:00
tqchen
4a16b729fc [PYTHON] Simplify training logic, update rabit lib 2016-02-28 13:20:55 -08:00
Chris Barker
ed5781fa55 fix PyPi Description issue 
the description field was set to what should be the long_description field -- making a bit of a mess on PyPi
 2016-02-26 16:54:13 -08:00
Paulo Alves
592004b38f XGBClassifier.feature_importances_ compatible with sklearn RFECV 2016-02-26 08:56:07 -03:00
tqchen
ebc802756f temp compatibility with sklearn 2016-02-25 21:57:00 -08:00
tqchen
a71ba04109 [DIST] Add Distributed XGBoost on AWS Tutorial 2016-02-25 21:51:37 -08:00
catena
790dc877c3 return best_ntree_limit if early stopped 2016-02-25 13:42:19 +05:30
Tianqi Chen
d063eaccb1 Delete training.py 2016-02-23 08:48:50 -08:00
ivallesp
c17d0ef560 changed the param show_progress by verbose_eval in cv and aggcv functions 2016-02-21 01:28:55 +01:00
ivallesp
ed5c98f0ee re-using the verbose-eval parameter in the cv and aggcv methods and tests adapted 2016-02-19 17:14:57 +01:00
Alexis Mignon
a46706c82e Merge branch 'master' into master 2016-02-17 09:35:30 +01:00