* Fixed DLL name on Windows in ``xgboost.libpath``
* Added support for OS X to ``xgboost.libpath``
* Use .dylib for shared library on OS X
This does not affect the JNI library, because it is not trully
cross-platform in the Makefile-build anyway.
Don't use implicit conversions to c_int, which incidentally happen to work
on (some) 64-bit platforms, but:
* may lead to truncation of the input value to a 32-bit signed int,
* cause segfaults on some 32-bit architectures (tested on Ubuntu ARM,
but is also the likely cause of issue #1707).
Also, when passing references use explicit 64-bit integers, where needed,
instead of c_ulong, which is not guaranteed to be this large.
* Added kwargs support for Sklearn API
* Updated NEWS and CONTRIBUTORS
* Fixed CONTRIBUTORS.md
* Added clarification of **kwargs and test for proper usage
* Fixed lint error
* Fixed more lint errors and clf assigned but never used
* Fixed more lint errors
* Fixed more lint errors
* Fixed issue with changes from different branch bleeding over
* Fixed issue with changes from other branch bleeding over
* Added note that kwargs may not be compatible with Sklearn
* Fixed linting on kwargs note
* Added n_jobs and random_state to keep up to date with sklearn API.
Deprecated nthread and seed. Added tests for new params and
deprecations.
* Fixed docstring to reflect updates to n_jobs and random_state.
* Fixed whitespace issues and removed nose import.
* Added deprecation note for nthread and seed in docstring.
* Attempted fix of deprecation tests.
* Second attempted fix to tests.
* Set n_jobs to 1.
* Add option to choose booster in scikit intreface (gbtree by default)
* Add option to choose booster in scikit intreface: complete docstring.
* Fix XGBClassifier to work with booster option
* Added test case for gblinear booster
* Add prediction of feature contributions
This implements the idea described at http://blog.datadive.net/interpreting-random-forests/
which tries to give insight in how a prediction is composed of its feature contributions
and a bias.
* Support multi-class models
* Calculate learning_rate per-tree instead of using the one from the first tree
* Do not rely on node.base_weight * learning_rate having the same value as the node mean value (aka leaf value, if it were a leaf); instead calculate them (lazily) on-the-fly
* Add simple test for contributions feature
* Check against param.num_nodes instead of checking for non-zero length
* Loop over all roots instead of only the first
verbose_eval docs claim it will log the last iteration (http://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.train). this is also consistent w/the behavior from 0.4. not a huge deal but I found it handy to see the last iter's result b/c my period is usually large.
this doesn't address logging the last stage found by early_stopping (as noted in docs) as I'm not sure how to do that.
* A fix regarding the compatibility with python 2.6
the syntax of {n: self.attr(n) for n in attr_names} is illegal in python 2.6
* Update core.py
add a space after comma
* added the max_features parameter to the plot_importance function.
* renamed max_features parameter to max_num_features for better understanding
* removed unwanted character in docstring
* option to shuffle data in mknfolds
* removed possibility to run as stand alone test
* split function def in 2 lines for lint
* option to shuffle data in mknfolds
* removed possibility to run as stand alone test
* split function def in 2 lines for lint
* Fix various typos
* Add override to functions that are overridden
gcc gives warnings about functions that are being overridden by not
being marked as oveirridden. This fixes it.
* Use bst_float consistently
Use bst_float for all the variables that involve weight,
leaf value, gradient, hessian, gain, loss_chg, predictions,
base_margin, feature values.
In some cases, when due to additions and so on the value can
take a larger value, double is used.
This ensures that type conversions are minimal and reduces loss of
precision.
* Allow using learning_rates parameter when doing CV
- Create a new `callback_cv` method working when called from `xgb.cv()`
- Rename existing `callback` into `callback_train` and make it the default callback
- Get the logic out of the callbacks and place it into a common helper
* Add a learning_rates parameter to cv()
* lint
* remove caller explicit reference
* callback is aware of its calling context
* remove caller argument
* remove learning_rates param
* restore learning_rates for training, but deprecated
* lint
* lint line too long
* quick example for predefined callbacks
* Add format to the params accepted by DumpModel
Currently, only the test format is supported when trying to dump
a model. The plan is to add more such formats like JSON which are
easy to read and/or parse by machines. And to make the interface
for this even more generic to allow other formats to be added.
Hence, we make some modifications to make these function generic
and accept a new parameter "format" which signifies the format of
the dump to be created.
* Fix typos and errors in docs
* plugin: Mention all the register macros available
Document the register macros currently available to the plugin
writers so they know what exactly can be extended using hooks.
* sparce_page_source: Use same arg name in .h and .cc
* gbm: Add JSON dump
The dump_format argument can be used to specify what type
of dump file should be created. Add functionality to dump
gblinear and gbtree into a JSON file.
The JSON file has an array, each item is a JSON object for the tree.
For gblinear:
- The item is the bias and weights vectors
For gbtree:
- The item is the root node. The root node has a attribute "children"
which holds the children nodes. This happens recursively.
* core.py: Add arg dump_format for get_dump()
* make DMatrix._init_from_npy2d only copy data when necessary
When creating DMatrix from a 2d ndarray, it can unnecessarily copy the input data. This can be problematic when the data is already very large--running out of memory. The copy is temporary (going out of scope at the end of this function) but it still adds to peak memory usage.
``numpy.array`` copies its input no matter what by default. By adding ``copy=False``, it will only do so when necessary. Since XGDMatrixCreateFromMat is readonly on the input buffer, this copy is not needed.
Also added comments explaining when a copy can happen (if data ordering/layout is wrong or if type is not 32-bit float).
* remove whitespace
*Fix 1439
*Fix python_wrapper when eval set name contain '-' will cause early_stop maximize variable con't set to True propely
Change-Id: Ib0595afd4ae7b445a84c00a3a8faeccc506c6d13
* add scikit-learn v0.18 compatibility
import KFold & StratifiedKFold from sklearn.model_selection instead of sklearn.cross_validation
* change DeprecationWarning to ImportError
DeprecationWarning isn't an exception, so it should work the other way around.
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.
* 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
