Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Document tree method for feature weights. (#6312)

Browse Source
This commit is contained in:
Jiaming Yuan 2020-10-29 04:42:13 +08:00 committed by GitHub
parent 143b278267
commit e8884c4637
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 12 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
doc/parameter.rst
View File

@ -108,9 +108,10 @@ Parameters for Tree Booster
'colsample_bynode':0.5}`` with 64 features will leave 8 features to choose from at 'colsample_bynode':0.5}`` with 64 features will leave 8 features to choose from at
each split. each split.
On Python interface, one can set the ``feature_weights`` for DMatrix to define the On Python interface, when using ``hist``, ``gpu_hist`` or ``exact`` tree method, one
probability of each feature being selected when using column sampling. There's a can set the ``feature_weights`` for DMatrix to define the probability of each feature
similar parameter for ``fit`` method in sklearn interface. being selected when using column sampling. There's a similar parameter for ``fit``
method in sklearn interface.
* ``lambda`` [default=1, alias: ``reg_lambda``] * ``lambda`` [default=1, alias: ``reg_lambda``]

14
python-package/xgboost/sklearn.py
View File

@ -499,9 +499,10 @@ class XGBModel(XGBModelBase):
A list of the form [L_1, L_2, ..., L_n], where each L_i is a list of A list of the form [L_1, L_2, ..., L_n], where each L_i is a list of
instance weights on the i-th validation set. instance weights on the i-th validation set.
feature_weights: array_like feature_weights: array_like
Weight for each feature, defines the probability of each feature Weight for each feature, defines the probability of each feature being
being selected when colsample is being used. All values must be selected when colsample is being used. All values must be greater than 0,
greater than 0, otherwise a `ValueError` is thrown. otherwise a `ValueError` is thrown. Only available for `hist`, `gpu_hist` and
`exact` tree methods.
callbacks : list of callback functions callbacks : list of callback functions
List of callback functions that are applied at end of each iteration. List of callback functions that are applied at end of each iteration.
It is possible to use predefined callbacks by using :ref:`callback_api`. It is possible to use predefined callbacks by using :ref:`callback_api`.
@ -1237,9 +1238,10 @@ class XGBRanker(XGBModel):
file name of stored XGBoost model or 'Booster' instance XGBoost file name of stored XGBoost model or 'Booster' instance XGBoost
model to be loaded before training (allows training continuation). model to be loaded before training (allows training continuation).
feature_weights: array_like feature_weights: array_like
Weight for each feature, defines the probability of each feature Weight for each feature, defines the probability of each feature being
being selected when colsample is being used. All values must be selected when colsample is being used. All values must be greater than 0,
greater than 0, otherwise a `ValueError` is thrown. otherwise a `ValueError` is thrown. Only available for `hist`, `gpu_hist` and
`exact` tree methods.
callbacks : list of callback functions callbacks : list of callback functions
List of callback functions that are applied at end of each List of callback functions that are applied at end of each
iteration. It is possible to use predefined callbacks by using iteration. It is possible to use predefined callbacks by using