You are on page 1of 1

XGBoost Parameters — xgboost 1.5.0-dev documentation https://xgboost.readthedocs.io/en/latest/parameter.

html

The path of test data to do prediction


XGBoost ( index.html)
save_period [default=0]
TABLE OF CONTENTS
The period to save the model. Setting save_period=10 means that for every 10
rounds XGBoost will save the model. Setting it to 0 means not saving any model
Installation Guide (install.html)
during the training.
Building From Source (build.html)
task [default= train ] options: train , pred , eval , dump
Get Started with XGBoost
train : training using data
(get_started.html)

XGBoost Tutorials pred : making prediction for test:data


(tutorials/index.html) eval : for evaluating statistics specified by eval[name]=filename
Frequently Asked Questions
dump : for dump the learned model into text format
(faq.html)
model_in [default=NULL]
XGBoost User Forum
(https://discuss.xgboost.ai) Path to input model, needed for test , eval , dump tasks. If it is specified in
training, XGBoost will continue training from the input model.
GPU Support (gpu/index.html)

XGBoost Parameters model_out [default=NULL]

Prediction (prediction.html) Path to output model after training finishes. If not specified, XGBoost will output files
with such names as 0003.model where 0003 is number of boosting rounds.
XGBoost Tree Methods
(treemethod.html) model_dir [default= models/ ]

Python Package The output directory of the saved models during training
(python/index.html)
fmap
R Package (R-package/index.html)
Feature map, used for dumping model
JVM Package (jvm/index.html)
dump_format [default= text ] options: text , json
Ruby Package (https://github.com
/ankane/xgb) Format of model dump file

Swift Package (https://github.com name_dump [default= dump.txt ]


/kongzii/SwiftXGBoost)
Name of model dump file
Julia Package (julia.html)
name_pred [default= pred.txt ]
C Package (c.html)
Name of prediction file, used in pred mode
C++ Interface (c%2B%2B.html)
pred_margin [default=0]
CLI Interface (cli.html)
Predict margin instead of transformed probability
Contribute to XGBoost
(contrib/index.html)

XGBoost GPU Support (gpu/index.html) Prediction (prediction.html)

© Copyright 2020, xgboost developers. Created using Sphinx (http://sphinx.pocoo.org/).

11 of 11 8/7/21, 4:08 PM

You might also like