Skip to content

GitLab

Unverified Commit f5afaba1 authored by Liwen Fan's avatar Liwen Fan Committed by GitHub
Browse files

Merge branch 'master' into 1492

parents b1ec44fa 1437ce8b
Hide whitespace changes
Inline Side-by-side
Showing with 497 additions and 172 deletions
.appveyor.yml
View file @ f5afaba1
......@@ -59,14 +59,6 @@ test_script:
- IF "%COMPILER%"=="MINGW" appveyor exit # skip all further steps
- cd ../../python-package && python setup.py bdist_wheel --plat-name=win-amd64 --universal
after_test:
- cd ../.nuget
- python create_nuget.py
- nuget.exe pack LightGBM.nuspec
nuget:
project_feed: true
artifacts:
- path: Release/lib_lightgbm.dll
name: Library
......@@ -74,15 +66,13 @@ artifacts:
name: Exe
- path: python-package/dist/*
name: Pip
- path: .nuget/*.nupkg
name: Nuget
deploy:
release: $(APPVEYOR_REPO_TAG_NAME)
provider: GitHub
auth_token:
secure: KR44XwtxY0cLlVpQwY726BvC6gzT0cYTf0ahJ4cSvvS0UVoSJxkR900ICfVXHRoT
artifact: Library,Exe,Pip,Nuget
artifact: Library,Exe,Pip
force_update: true
draft: true
on:
......
.gitignore
View file @ f5afaba1
......@@ -181,6 +181,7 @@ BundleArtifacts/
ClientBin/
~$*
*~
.*.swp
*.dbmdl
*.dbproj.schemaview
*.pfx
......
.nuget/create_nuget.py
View file @ f5afaba1
import os
import sys
import distutils
from distutils import file_util
if not os.path.exists("lib"):
os.makedirs("lib")
if not os.path.exists("lib/native"):
os.makedirs("lib/native")
if not os.path.exists("lib/net40"):
os.makedirs("lib/net40")
if not os.path.exists("lib/net45"):
os.makedirs("lib/net45")
distutils.file_util.copy_file("../Release/lightgbm.exe", "./lib/")
distutils.file_util.copy_file("../Release/lib_lightgbm.dll", "./lib/")
version = open('../VERSION.txt').read().strip()
nuget_str = '''<?xml version="1.0"?>
<package xmlns="http://schemas.microsoft.com/packaging/2013/05/nuspec.xsd">
<metadata>
<id>LightGBM</id>
<version>%s</version>
<authors>Guolin Ke</authors>
<owners>Guolin Ke</owners>
<licenseUrl>https://github.com/Microsoft/LightGBM/blob/master/LICENSE</licenseUrl>
<projectUrl>https://github.com/Microsoft/LightGBM</projectUrl>
<requireLicenseAcceptance>false</requireLicenseAcceptance>
<description>A fast, distributed, high performance gradient boosting framework</description>
<copyright>Copyright 2017 @ Microsoft</copyright>
<tags>machine-learning data-mining distributed native boosting gbdt</tags>
<dependencies> </dependencies>
</metadata>
<files>
<file src="lib\**" target="lib"/>
</files>
</package>
''' % (version)
nuget_file = open("LightGBM.nuspec", "w")
nuget_file.write(nuget_str)
nuget_file.close()
from distutils.file_util import copy_file
if __name__ == "__main__":
source = sys.argv[1]
current_dir = os.path.abspath(os.path.dirname(__file__))
if not os.path.exists(os.path.join(current_dir, "runtimes/linux-x64/native")):
os.makedirs(os.path.join(current_dir, "runtimes/linux-x64/native"))
if not os.path.exists(os.path.join(current_dir, "runtimes/osx-x64/native")):
os.makedirs(os.path.join(current_dir, "runtimes/osx-x64/native"))
if not os.path.exists(os.path.join(current_dir, "runtimes/win-x64/native")):
os.makedirs(os.path.join(current_dir, "runtimes/win-x64/native"))
copy_file(os.path.join(source, "lib_lightgbm.so"), os.path.join(current_dir, "runtimes/linux-x64/native/lib_lightgbm.so"))
copy_file(os.path.join(source, "lib_lightgbm.dylib"), os.path.join(current_dir, "runtimes/osx-x64/native/lib_lightgbm.dylib"))
copy_file(os.path.join(source, "lib_lightgbm.dll"), os.path.join(current_dir, "runtimes/win-x64/native/lib_lightgbm.dll"))
version = open(os.path.join(current_dir, '../VERSION.txt')).read().strip()
nuget_str = '''<?xml version="1.0"?>
<package xmlns="http://schemas.microsoft.com/packaging/2013/05/nuspec.xsd">
<metadata>
<id>LightGBM</id>
<version>%s</version>
<authors>Guolin Ke</authors>
<owners>Guolin Ke</owners>
<licenseUrl>https://github.com/Microsoft/LightGBM/blob/master/LICENSE</licenseUrl>
<projectUrl>https://github.com/Microsoft/LightGBM</projectUrl>
<requireLicenseAcceptance>false</requireLicenseAcceptance>
<description>A fast, distributed, high performance gradient boosting framework</description>
<copyright>Copyright 2018 @ Microsoft</copyright>
<tags>machine-learning data-mining distributed native boosting gbdt</tags>
<dependencies> </dependencies>
</metadata>
<files>
<file src="runtimes\**" target="runtimes"/>
</files>
</package>
''' % (version)
with open(os.path.join(current_dir, "LightGBM.nuspec"), "w") as nuget_file:
nuget_file.write(nuget_str)
.vsts-ci.yml
View file @ f5afaba1
phases:
###########################################
- phase: Linux
###########################################
variables:
PYTHON_VERSION: 3.6
CONDA_ENV: test-env
queue:
name: 'Hosted Linux Preview'
parallel: 9
matrix:
regular:
TASK: regular
mpi:
TASK: mpi
PYTHON_VERSION: 2.7
pylint:
TASK: pylint
inference:
TASK: if-else
sdist:
TASK: sdist
PYTHON_VERSION: 3.4
bdist:
TASK: bdist
PYTHON_VERSION: 3.5
gpu_1:
TASK: gpu
METHOD: source
gpu_2:
TASK: gpu
METHOD: pip
steps:
- task: CondaEnvironment@0
inputs:
environmentName: $(CONDA_ENV)
packageSpecs: 'python=$(PYTHON_VERSION)' # Optional
createOptions: '-q'
- script: |
sudo apt-get update
export LGB_VER=$(head -n 1 VERSION.txt)
export AMDAPPSDK=$HOME/AMDAPPSDK
export LD_LIBRARY_PATH="$AMDAPPSDK/lib/x86_64:$LD_LIBRARY_PATH"
export OPENCL_VENDOR_PATH=$AMDAPPSDK/etc/OpenCL/vendors
if [[ $TASK == "mpi" ]]; then
sudo apt-get install -y libopenmpi-dev openmpi-bin
fi
if [[ $TASK == "gpu" ]]; then
sudo apt-get install --no-install-recommends -y ocl-icd-opencl-dev libboost-dev libboost-system-dev libboost-filesystem-dev
wget -q https://github.com/Microsoft/LightGBM/releases/download/v2.0.12/AMD-APP-SDKInstaller-v3.0.130.136-GA-linux64.tar.bz2
tar -xjf AMD-APP-SDK*.tar.bz2
mkdir -p $OPENCL_VENDOR_PATH
sh AMD-APP-SDK*.sh --tar -xf -C $AMDAPPSDK
mv $AMDAPPSDK/lib/x86_64/sdk/* $AMDAPPSDK/lib/x86_64/
echo libamdocl64.so > $OPENCL_VENDOR_PATH/amdocl64.icd
fi
bash .vsts-ci/test.sh
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: PackageAssets
artifactType: container
###########################################
- phase: MacOS
###########################################
variables:
PYTHON_VERSION: 3.6
CONDA_ENV: test-env
queue:
name: 'Hosted macOS Preview'
parallel: 3
matrix:
regular:
TASK: regular
PYTHON_VERSION: 2.7
sdist:
TASK: sdist
PYTHON_VERSION: 3.4
bdist:
TASK: bdist
PYTHON_VERSION: 3.5
steps:
- script: |
test -n $CC && unset CC
test -n $CXX && unset CXX
rm '/usr/local/include/c++'
brew install gcc@8
export CXX=g++-8
export CC=gcc-8
wget -O conda.sh https://repo.continuum.io/miniconda/Miniconda${PYTHON_VERSION:0:1}-latest-MacOSX-x86_64.sh
bash conda.sh -b -p $HOME/miniconda
export PATH=$HOME/miniconda/bin:$PATH
conda config --set always_yes yes --set changeps1 no
conda create -q -n $CONDA_ENV python=$PYTHON_VERSION
source activate $CONDA_ENV
export LGB_VER=$(head -n 1 VERSION.txt)
bash .vsts-ci/test.sh
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: PackageAssets
artifactType: container
###########################################
- phase: Windows
###########################################
variables:
PYTHON_VERSION: 3.6
CONDA_ENV: test-env
queue:
name: 'Hosted VS2017'
parallel: 4
matrix:
regular:
TASK: regular
sdist:
TASK: sdist
PYTHON_VERSION: 2.7
bdist:
TASK: bdist
PYTHON_VERSION: 3.5
# mingw:
# TASK: mingw
steps:
- task: CondaEnvironment@0
inputs:
environmentName: $(CONDA_ENV)
packageSpecs: 'python=$(PYTHON_VERSION)' # Optional
createOptions: '-q'
- powershell: |
conda install -q -y -n $env:CONDA_ENV numpy nose scipy scikit-learn pandas matplotlib python-graphviz pytest
if ("$env:TASK" -eq "regular") {
mkdir build; cd build
cmake -DCMAKE_GENERATOR_PLATFORM=x64 .. ; cmake --build . --target ALL_BUILD --config Release
cd ../python-package; python setup.py install -p
cd ..
pytest tests/c_api_test/test_.py
cp Release/lib_lightgbm.dll $env:BUILD_ARTIFACTSTAGINGDIRECTORY
}
elseif ("$env:TASK" -eq "sdist"){
cd python-package; python setup.py sdist --formats gztar
cd dist; pip install @(Get-ChildItem *.gz) -v
cd ../..
}
# elseif ("$env:TASK" -eq "mingw"){
# cd python-package; python setup.py sdist --formats gztar
# cd dist; pip install @(Get-ChildItem *.gz) --install-option=--mingw -v
# cd ../..
# }
else {
cd python-package
python setup.py bdist_wheel --plat-name=win-amd64 --universal
cd dist; pip install @(Get-ChildItem *.whl)
cp @(Get-ChildItem *.whl) $env:BUILD_ARTIFACTSTAGINGDIRECTORY
cd ../..
}
pytest tests/python_package_test
cd examples/python-guide
@("import matplotlib", "matplotlib.use('Agg')") + (Get-Content "plot_example.py") | Set-Content "plot_example.py"
(Get-Content "plot_example.py").replace('graph.render(view=True)', 'graph.render(view=False)') | Set-Content "plot_example.py"
foreach ($file in @(Get-ChildItem *.py)) {
python $file
if ($LastExitCode -ne 0) { $host.SetShouldExit($LastExitCode) }
} # run all examples
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: PackageAssets
artifactType: container
################################################################################
- phase: Package
################################################################################
dependsOn:
- Linux
- MacOS
- Windows
queue:
name: 'Hosted VS2017'
steps:
# Download all agent packages from all previous phases
- task: DownloadBuildArtifacts@0
displayName: Download package assets
inputs:
artifactName: PackageAssets
downloadPath: $(Build.SourcesDirectory)/binaries
- powershell: |
$client = new-object System.Net.WebClient
$client.DownloadFile("https://dist.nuget.org/win-x86-commandline/latest/nuget.exe",".nuget/nuget.exe")
- script: |
cd .nuget
python create_nuget.py %BUILD_SOURCESDIRECTORY%/binaries/PackageAssets
nuget.exe pack LightGBM.nuspec
xcopy *.nupkg %BUILD_ARTIFACTSTAGINGDIRECTORY%
- task: PublishBuildArtifacts@1
inputs:
pathtoPublish: '$(Build.ArtifactStagingDirectory)'
artifactName: Nuget
artifactType: container
.vsts-ci/test.sh 0 → 100644
View file @ f5afaba1
#!/bin/bash
cd ${BUILD_REPOSITORY_LOCALPATH}
if [[ $TASK == "check-docs" ]]; then
if [[ $AGENT_OS == "Linux" ]]; then
sudo apt-get install linkchecker -y
fi
if [[ ${PYTHON_VERSION} == "2.7" ]]; then
conda install -y -n $CONDA_ENV mock
fi
conda install -y -n $CONDA_ENV sphinx "sphinx_rtd_theme>=0.3" # html5validator
pip install rstcheck
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package
rstcheck --report warning `find . -type f -name "*.rst"` || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/docs
rstcheck --report warning --ignore-directives=autoclass,autofunction `find . -type f -name "*.rst"` || exit -1
make html || exit -1
find ./_build/html/ -type f -name '*.html' -exec \
sed -i -e 's;\(\.\/[^.]*\.\)rst\([^[:space:]]*\);\1html\2;g' {} \; # emulate js function
# html5validator --root ./_build/html/ || exit -1
if [[ $AGENT_OS == "Linux" ]]; then
linkchecker --config=.linkcheckerrc ./_build/html/*.html || exit -1
fi
exit 0
fi
if [[ $TASK == "pylint" ]]; then
conda install -y -n $CONDA_ENV pycodestyle
pycodestyle --ignore=E501,W503 --exclude=./compute,./docs,./.nuget . || exit -1
exit 0
fi
if [[ $TASK == "if-else" ]]; then
conda install -y -n $CONDA_ENV numpy
mkdir build && cd build && cmake .. && make lightgbm || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/tests/cpp_test && ../../lightgbm config=train.conf convert_model_language=cpp convert_model=../../src/boosting/gbdt_prediction.cpp && ../../lightgbm config=predict.conf output_result=origin.pred || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/build && make lightgbm || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/tests/cpp_test && ../../lightgbm config=predict.conf output_result=ifelse.pred && python test.py || exit -1
exit 0
fi
conda install -q -y -n $CONDA_ENV numpy nose scipy scikit-learn pandas matplotlib python-graphviz pytest
if [[ $TASK == "sdist" ]]; then
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py sdist || exit -1
pip install ${BUILD_REPOSITORY_LOCALPATH}/python-package/dist/lightgbm-$LGB_VER.tar.gz -v || exit -1
cp ${BUILD_REPOSITORY_LOCALPATH}/python-package/dist/lightgbm-$LGB_VER.tar.gz ${BUILD_ARTIFACTSTAGINGDIRECTORY}/lightgbm-$LGB_VER.tar.gz
pytest ${BUILD_REPOSITORY_LOCALPATH}/tests/python_package_test || exit -1
exit 0
elif [[ $TASK == "bdist" ]]; then
if [[ $AGENT_OS == "Darwin" ]]; then
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py bdist_wheel --plat-name=macdarwin --universal || exit -1
cp dist/lightgbm-$LGB_VER-py2.py3-none-macdarwin.whl ${BUILD_ARTIFACTSTAGINGDIRECTORY}/lightgbm-$LGB_VER-py2.py3-none-macosx_10_6_x86_64.macosx_10_7_x86_64.macosx_10_8_x86_64.macosx_10_9_x86_64.macosx_10_10_x86_64.macosx_10_11_x86_64.macosx_10_12_x86_64.macosx_10_13_x86_64.whl
mv dist/lightgbm-$LGB_VER-py2.py3-none-macdarwin.whl dist/lightgbm-$LGB_VER-py2.py3-none-macosx_10_6_x86_64.macosx_10_7_x86_64.macosx_10_8_x86_64.macosx_10_9_x86_64.macosx_10_10_x86_64.macosx_10_11_x86_64.macosx_10_12_x86_64.macosx_10_13_x86_64.whl
else
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py bdist_wheel --plat-name=manylinux1_x86_64 --universal || exit -1
cp dist/lightgbm-$LGB_VER-py2.py3-none-manylinux1_x86_64.whl ${BUILD_ARTIFACTSTAGINGDIRECTORY}/lightgbm-$LGB_VER-py2.py3-none-manylinux1_x86_64.whl
fi
pip install ${BUILD_REPOSITORY_LOCALPATH}/python-package/dist/*.whl || exit -1
pytest ${BUILD_REPOSITORY_LOCALPATH}/tests/python_package_test || exit -1
exit 0
fi
if [[ $TASK == "gpu" ]]; then
sed -i 's/std::string device_type = "cpu";/std::string device_type = "gpu";/' ${BUILD_REPOSITORY_LOCALPATH}/include/LightGBM/config.h
grep -q 'std::string device_type = "gpu"' ${BUILD_REPOSITORY_LOCALPATH}/include/LightGBM/config.h || exit -1 # make sure that changes were really done
if [[ $METHOD == "pip" ]]; then
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py sdist || exit -1
pip install ${BUILD_REPOSITORY_LOCALPATH}/python-package/dist/lightgbm-$LGB_VER.tar.gz -v --install-option=--gpu --install-option="--opencl-include-dir=$AMDAPPSDK/include/" || exit -1
pytest ${BUILD_REPOSITORY_LOCALPATH}/tests/python_package_test || exit -1
exit 0
fi
fi
mkdir build && cd build
if [[ $TASK == "mpi" ]]; then
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py sdist || exit -1
pip install ${BUILD_REPOSITORY_LOCALPATH}/python-package/dist/lightgbm-$LGB_VER.tar.gz -v --install-option=--mpi || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/build
cmake -DUSE_MPI=ON ..
elif [[ $TASK == "gpu" ]]; then
cmake -DUSE_GPU=ON -DOpenCL_INCLUDE_DIR=$AMDAPPSDK/include/ ..
else
cmake ..
fi
make _lightgbm || exit -1
cd ${BUILD_REPOSITORY_LOCALPATH}/python-package && python setup.py install --precompile || exit -1
pytest ${BUILD_REPOSITORY_LOCALPATH} || exit -1
if [[ $TASK == "regular" ]]; then
if [[ $AGENT_OS == "Darwin" ]]; then
cp ${BUILD_REPOSITORY_LOCALPATH}/lib_lightgbm.so ${BUILD_ARTIFACTSTAGINGDIRECTORY}/lib_lightgbm.dylib
else
cp ${BUILD_REPOSITORY_LOCALPATH}/lib_lightgbm.so ${BUILD_ARTIFACTSTAGINGDIRECTORY}/lib_lightgbm.so
fi
cd ${BUILD_REPOSITORY_LOCALPATH}/examples/python-guide
sed -i'.bak' '/import lightgbm as lgb/a\
import matplotlib\
matplotlib.use\(\"Agg\"\)\
' plot_example.py # prevent interactive window mode
sed -i 's/graph.render(view=True)/graph.render(view=False)/' plot_example.py
for f in *.py; do python $f || exit -1; done # run all examples
fi
CMakeLists.txt
View file @ f5afaba1
......@@ -124,12 +124,12 @@ if(MSVC)
CMAKE_CXX_FLAGS_RELEASE
CMAKE_CXX_FLAGS_RELWITHDEBINFO
)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /W4 /O2 /Ob2 /Oi /Ot /Oy /GL")
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /W4 /O2 /Ob2 /Oi /Ot /Oy /GL /MP")
else()
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -funroll-loops")
endif()
SET(LightGBM_HEADER_DIR ${PROJECT_SOURCE_DIR}/include)
SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_SOURCE_DIR})
......
README.md
View file @ f5afaba1
LightGBM, Light Gradient Boosting Machine
=========================================
[![Build Status](https://lightgbm.visualstudio.com/LightGBM-Build/_apis/build/status/LightGBM-Build-CI&branchName=master)]()
[![Build Status](https://travis-ci.org/Microsoft/LightGBM.svg?branch=master)](https://travis-ci.org/Microsoft/LightGBM)
[![Windows Build Status](https://ci.appveyor.com/api/projects/status/1ys5ot401m0fep6l/branch/master?svg=true)](https://ci.appveyor.com/project/guolinke/lightgbm/branch/master)
[![Documentation Status](https://readthedocs.org/projects/lightgbm/badge/?version=latest)](https://lightgbm.readthedocs.io/)
......
docs/Features.rst
View file @ f5afaba1
......@@ -201,9 +201,9 @@ LightGBM supports the following metrics:
- MAP
- Multi class log loss
- Multi-class log loss
- Multi class error rate
- Multi-class error rate
- Fair
......
docs/Parameters.rst
View file @ f5afaba1
.. List of parameters is auto generated by LightGBM\helper\parameter_generator.py from LightGBM\include\LightGBM\config.h file.
.. role:: raw-html(raw)
:format: html
Parameters
==========
......@@ -30,13 +33,13 @@ If one parameter appears in both command line and config file, LightGBM will use
Core Parameters
---------------
- ``config``, default = ``""``, type = string, aliases: ``config_file``
- ``config`` :raw-html:`<a id="config" title="Permalink to this parameter" href="#config">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``config_file``
- path of config file
- **Note**: can be used only in CLI version
- ``task``, default = ``train``, type = enum, options: ``train``, ``predict``, ``convert_model``, ``refit``, aliases: ``task_type``
- ``task`` :raw-html:`<a id="task" title="Permalink to this parameter" href="#task">&#x1F517;&#xFE0E;</a>`, default = ``train``, type = enum, options: ``train``, ``predict``, ``convert_model``, ``refit``, aliases: ``task_type``
- ``train``, for training, aliases: ``training``
......@@ -48,7 +51,7 @@ Core Parameters
- **Note**: can be used only in CLI version
- ``objective``, default = ``regression``, type = enum, options: ``regression``, ``regression_l1``, ``huber``, ``fair``, ``poisson``, ``quantile``, ``mape``, ``gammma``, ``tweedie``, ``binary``, ``multiclass``, ``multiclassova``, ``xentropy``, ``xentlambda``, ``lambdarank``, aliases: ``objective_type``, ``app``, ``application``
- ``objective`` :raw-html:`<a id="objective" title="Permalink to this parameter" href="#objective">&#x1F517;&#xFE0E;</a>`, default = ``regression``, type = enum, options: ``regression``, ``regression_l1``, ``huber``, ``fair``, ``poisson``, ``quantile``, ``mape``, ``gammma``, ``tweedie``, ``binary``, ``multiclass``, ``multiclassova``, ``xentropy``, ``xentlambda``, ``lambdarank``, aliases: ``objective_type``, ``app``, ``application``
- regression application
......@@ -96,7 +99,7 @@ Core Parameters
- all values in ``label`` must be smaller than number of elements in ``label_gain``
- ``boosting``, default = ``gbdt``, type = enum, options: ``gbdt``, ``gbrt``, ``rf``, ``random_forest``, ``dart``, ``goss``, aliases: ``boosting_type``, ``boost``
- ``boosting`` :raw-html:`<a id="boosting" title="Permalink to this parameter" href="#boosting">&#x1F517;&#xFE0E;</a>`, default = ``gbdt``, type = enum, options: ``gbdt``, ``gbrt``, ``rf``, ``random_forest``, ``dart``, ``goss``, aliases: ``boosting_type``, ``boost``
- ``gbdt``, traditional Gradient Boosting Decision Tree, aliases: ``gbrt``
......@@ -106,13 +109,13 @@ Core Parameters
- ``goss``, Gradient-based One-Side Sampling
- ``data``, default = ``""``, type = string, aliases: ``train``, ``train_data``, ``data_filename``
- ``data`` :raw-html:`<a id="data" title="Permalink to this parameter" href="#data">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``train``, ``train_data``, ``data_filename``
- path of training data, LightGBM will train from this data
- **Note**: can be used only in CLI version
- ``valid``, default = ``""``, type = string, aliases: ``test``, ``valid_data``, ``valid_data_file``, ``test_data``, ``valid_filenames``
- ``valid`` :raw-html:`<a id="valid" title="Permalink to this parameter" href="#valid">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``test``, ``valid_data``, ``valid_data_file``, ``test_data``, ``valid_filenames``
- path(s) of validation/test data, LightGBM will output metrics for these data
......@@ -120,7 +123,7 @@ Core Parameters
- **Note**: can be used only in CLI version
- ``num_iterations``, default = ``100``, type = int, aliases: ``num_iteration``, ``num_tree``, ``num_trees``, ``num_round``, ``num_rounds``, ``num_boost_round``, ``n_estimators``, constraints: ``num_iterations >= 0``
- ``num_iterations`` :raw-html:`<a id="num_iterations" title="Permalink to this parameter" href="#num_iterations">&#x1F517;&#xFE0E;</a>`, default = ``100``, type = int, aliases: ``num_iteration``, ``num_tree``, ``num_trees``, ``num_round``, ``num_rounds``, ``num_boost_round``, ``n_estimators``, constraints: ``num_iterations >= 0``
- number of boosting iterations
......@@ -128,17 +131,17 @@ Core Parameters
- **Note**: internally, LightGBM constructs ``num_class * num_iterations`` trees for multi-class classification problems
- ``learning_rate``, default = ``0.1``, type = double, aliases: ``shrinkage_rate``, constraints: ``learning_rate > 0.0``
- ``learning_rate`` :raw-html:`<a id="learning_rate" title="Permalink to this parameter" href="#learning_rate">&#x1F517;&#xFE0E;</a>`, default = ``0.1``, type = double, aliases: ``shrinkage_rate``, constraints: ``learning_rate > 0.0``
- shrinkage rate
- in ``dart``, it also affects on normalization weights of dropped trees
- ``num_leaves``, default = ``31``, type = int, aliases: ``num_leaf``, constraints: ``num_leaves > 1``
- ``num_leaves`` :raw-html:`<a id="num_leaves" title="Permalink to this parameter" href="#num_leaves">&#x1F517;&#xFE0E;</a>`, default = ``31``, type = int, aliases: ``num_leaf``, constraints: ``num_leaves > 1``
- max number of leaves in one tree
- ``tree_learner``, default = ``serial``, type = enum, options: ``serial``, ``feature``, ``data``, ``voting``, aliases: ``tree``, ``tree_learner_type``
- ``tree_learner`` :raw-html:`<a id="tree_learner" title="Permalink to this parameter" href="#tree_learner">&#x1F517;&#xFE0E;</a>`, default = ``serial``, type = enum, options: ``serial``, ``feature``, ``data``, ``voting``, aliases: ``tree``, ``tree_learner_type``
- ``serial``, single machine tree learner
......@@ -150,7 +153,7 @@ Core Parameters
- refer to `Parallel Learning Guide <./Parallel-Learning-Guide.rst>`__ to get more details
- ``num_threads``, default = ``0``, type = int, aliases: ``num_thread``, ``nthread``, ``nthreads``
- ``num_threads`` :raw-html:`<a id="num_threads" title="Permalink to this parameter" href="#num_threads">&#x1F517;&#xFE0E;</a>`, default = ``0``, type = int, aliases: ``num_thread``, ``nthread``, ``nthreads``
- number of threads for LightGBM
......@@ -164,7 +167,7 @@ Core Parameters
- for parallel learning, do not use all CPU cores because this will cause poor performance for the network communication
- ``device_type``, default = ``cpu``, type = enum, options: ``cpu``, ``gpu``, aliases: ``device``
- ``device_type`` :raw-html:`<a id="device_type" title="Permalink to this parameter" href="#device_type">&#x1F517;&#xFE0E;</a>`, default = ``cpu``, type = enum, options: ``cpu``, ``gpu``, aliases: ``device``
- device for the tree learning, you can use GPU to achieve the faster learning
......@@ -174,7 +177,7 @@ Core Parameters
- **Note**: refer to `Installation Guide <./Installation-Guide.rst#build-gpu-version>`__ to build LightGBM with GPU support
- ``seed``, default = ``0``, type = int, aliases: ``random_seed``
- ``seed`` :raw-html:`<a id="seed" title="Permalink to this parameter" href="#seed">&#x1F517;&#xFE0E;</a>`, default = ``0``, type = int, aliases: ``random_seed``
- this seed is used to generate other seeds, e.g. ``data_random_seed``, ``feature_fraction_seed``
......@@ -183,21 +186,21 @@ Core Parameters
Learning Control Parameters
---------------------------
- ``max_depth``, default = ``-1``, type = int
- ``max_depth`` :raw-html:`<a id="max_depth" title="Permalink to this parameter" href="#max_depth">&#x1F517;&#xFE0E;</a>`, default = ``-1``, type = int
- limit the max depth for tree model. This is used to deal with over-fitting when ``#data`` is small. Tree still grows leaf-wise
- ``< 0`` means no limit
- ``min_data_in_leaf``, default = ``20``, type = int, aliases: ``min_data_per_leaf``, ``min_data``, ``min_child_samples``, constraints: ``min_data_in_leaf >= 0``
- ``min_data_in_leaf`` :raw-html:`<a id="min_data_in_leaf" title="Permalink to this parameter" href="#min_data_in_leaf">&#x1F517;&#xFE0E;</a>`, default = ``20``, type = int, aliases: ``min_data_per_leaf``, ``min_data``, ``min_child_samples``, constraints: ``min_data_in_leaf >= 0``
- minimal number of data in one leaf. Can be used to deal with over-fitting
- ``min_sum_hessian_in_leaf``, default = ``1e-3``, type = double, aliases: ``min_sum_hessian_per_leaf``, ``min_sum_hessian``, ``min_hessian``, ``min_child_weight``, constraints: ``min_sum_hessian_in_leaf >= 0.0``
- ``min_sum_hessian_in_leaf`` :raw-html:`<a id="min_sum_hessian_in_leaf" title="Permalink to this parameter" href="#min_sum_hessian_in_leaf">&#x1F517;&#xFE0E;</a>`, default = ``1e-3``, type = double, aliases: ``min_sum_hessian_per_leaf``, ``min_sum_hessian``, ``min_hessian``, ``min_child_weight``, constraints: ``min_sum_hessian_in_leaf >= 0.0``
- minimal sum hessian in one leaf. Like ``min_data_in_leaf``, it can be used to deal with over-fitting
- ``bagging_fraction``, default = ``1.0``, type = double, aliases: ``sub_row``, ``subsample``, ``bagging``, constraints: ``0.0 < bagging_fraction <= 1.0``
- ``bagging_fraction`` :raw-html:`<a id="bagging_fraction" title="Permalink to this parameter" href="#bagging_fraction">&#x1F517;&#xFE0E;</a>`, default = ``1.0``, type = double, aliases: ``sub_row``, ``subsample``, ``bagging``, constraints: ``0.0 < bagging_fraction <= 1.0``
- like ``feature_fraction``, but this will randomly select part of data without resampling
......@@ -207,7 +210,7 @@ Learning Control Parameters
- **Note**: to enable bagging, ``bagging_freq`` should be set to a non zero value as well
- ``bagging_freq``, default = ``0``, type = int, aliases: ``subsample_freq``
- ``bagging_freq`` :raw-html:`<a id="bagging_freq" title="Permalink to this parameter" href="#bagging_freq">&#x1F517;&#xFE0E;</a>`, default = ``0``, type = int, aliases: ``subsample_freq``
- frequency for bagging
......@@ -215,11 +218,11 @@ Learning Control Parameters
- **Note**: to enable bagging, ``bagging_fraction`` should be set to value smaller than ``1.0`` as well
- ``bagging_seed``, default = ``3``, type = int, aliases: ``bagging_fraction_seed``
- ``bagging_seed`` :raw-html:`<a id="bagging_seed" title="Permalink to this parameter" href="#bagging_seed">&#x1F517;&#xFE0E;</a>`, default = ``3``, type = int, aliases: ``bagging_fraction_seed``
- random seed for bagging
- ``feature_fraction``, default = ``1.0``, type = double, aliases: ``sub_feature``, ``colsample_bytree``, constraints: ``0.0 < feature_fraction <= 1.0``
- ``feature_fraction`` :raw-html:`<a id="feature_fraction" title="Permalink to this parameter" href="#feature_fraction">&#x1F517;&#xFE0E;</a>`, default = ``1.0``, type = double, aliases: ``sub_feature``, ``colsample_bytree``, constraints: ``0.0 < feature_fraction <= 1.0``
- LightGBM will randomly select part of features on each iteration if ``feature_fraction`` smaller than ``1.0``. For example, if you set it to ``0.8``, LightGBM will select 80% of features before training each tree
......@@ -227,17 +230,17 @@ Learning Control Parameters
- can be used to deal with over-fitting
- ``feature_fraction_seed``, default = ``2``, type = int
- ``feature_fraction_seed`` :raw-html:`<a id="feature_fraction_seed" title="Permalink to this parameter" href="#feature_fraction_seed">&#x1F517;&#xFE0E;</a>`, default = ``2``, type = int
- random seed for ``feature_fraction``
- ``early_stopping_round``, default = ``0``, type = int, aliases: ``early_stopping_rounds``, ``early_stopping``
- ``early_stopping_round`` :raw-html:`<a id="early_stopping_round" title="Permalink to this parameter" href="#early_stopping_round">&#x1F517;&#xFE0E;</a>`, default = ``0``, type = int, aliases: ``early_stopping_rounds``, ``early_stopping``
- will stop training if one metric of one validation data doesn't improve in last ``early_stopping_round`` rounds
- ``<= 0`` means disable
- ``max_delta_step``, default = ``0.0``, type = double, aliases: ``max_tree_output``, ``max_leaf_output``
- ``max_delta_step`` :raw-html:`<a id="max_delta_step" title="Permalink to this parameter" href="#max_delta_step">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, aliases: ``max_tree_output``, ``max_leaf_output``
- used to limit the max output of tree leaves
......@@ -245,25 +248,25 @@ Learning Control Parameters
- the final max output of leaves is ``learning_rate * max_delta_step``
- ``lambda_l1``, default = ``0.0``, type = double, aliases: ``reg_alpha``, constraints: ``lambda_l1 >= 0.0``
- ``lambda_l1`` :raw-html:`<a id="lambda_l1" title="Permalink to this parameter" href="#lambda_l1">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, aliases: ``reg_alpha``, constraints: ``lambda_l1 >= 0.0``
- L1 regularization
- ``lambda_l2``, default = ``0.0``, type = double, aliases: ``reg_lambda``, constraints: ``lambda_l2 >= 0.0``
- ``lambda_l2`` :raw-html:`<a id="lambda_l2" title="Permalink to this parameter" href="#lambda_l2">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, aliases: ``reg_lambda``, constraints: ``lambda_l2 >= 0.0``
- L2 regularization
- ``min_gain_to_split``, default = ``0.0``, type = double, aliases: ``min_split_gain``, constraints: ``min_gain_to_split >= 0.0``
- ``min_gain_to_split`` :raw-html:`<a id="min_gain_to_split" title="Permalink to this parameter" href="#min_gain_to_split">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, aliases: ``min_split_gain``, constraints: ``min_gain_to_split >= 0.0``
- the minimal gain to perform split
- ``drop_rate``, default = ``0.1``, type = double, constraints: ``0.0 <= drop_rate <= 1.0``
- ``drop_rate`` :raw-html:`<a id="drop_rate" title="Permalink to this parameter" href="#drop_rate">&#x1F517;&#xFE0E;</a>`, default = ``0.1``, type = double, constraints: ``0.0 <= drop_rate <= 1.0``
- used only in ``dart``
- dropout rate
- ``max_drop``, default = ``50``, type = int
- ``max_drop`` :raw-html:`<a id="max_drop" title="Permalink to this parameter" href="#max_drop">&#x1F517;&#xFE0E;</a>`, default = ``50``, type = int
- used only in ``dart``
......@@ -271,75 +274,75 @@ Learning Control Parameters
- ``<=0`` means no limit
- ``skip_drop``, default = ``0.5``, type = double, constraints: ``0.0 <= skip_drop <= 1.0``
- ``skip_drop`` :raw-html:`<a id="skip_drop" title="Permalink to this parameter" href="#skip_drop">&#x1F517;&#xFE0E;</a>`, default = ``0.5``, type = double, constraints: ``0.0 <= skip_drop <= 1.0``
- used only in ``dart``
- probability of skipping drop
- ``xgboost_dart_mode``, default = ``false``, type = bool
- ``xgboost_dart_mode`` :raw-html:`<a id="xgboost_dart_mode" title="Permalink to this parameter" href="#xgboost_dart_mode">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- used only in ``dart``
- set this to ``true``, if you want to use xgboost dart mode
- ``uniform_drop``, default = ``false``, type = bool
- ``uniform_drop`` :raw-html:`<a id="uniform_drop" title="Permalink to this parameter" href="#uniform_drop">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- used only in ``dart``
- set this to ``true``, if you want to use uniform drop
- ``drop_seed``, default = ``4``, type = int
- ``drop_seed`` :raw-html:`<a id="drop_seed" title="Permalink to this parameter" href="#drop_seed">&#x1F517;&#xFE0E;</a>`, default = ``4``, type = int
- used only in ``dart``
- random seed to choose dropping models
- ``top_rate``, default = ``0.2``, type = double, constraints: ``0.0 <= top_rate <= 1.0``
- ``top_rate`` :raw-html:`<a id="top_rate" title="Permalink to this parameter" href="#top_rate">&#x1F517;&#xFE0E;</a>`, default = ``0.2``, type = double, constraints: ``0.0 <= top_rate <= 1.0``
- used only in ``goss``
- the retain ratio of large gradient data
- ``other_rate``, default = ``0.1``, type = double, constraints: ``0.0 <= other_rate <= 1.0``
- ``other_rate`` :raw-html:`<a id="other_rate" title="Permalink to this parameter" href="#other_rate">&#x1F517;&#xFE0E;</a>`, default = ``0.1``, type = double, constraints: ``0.0 <= other_rate <= 1.0``
- used only in ``goss``
- the retain ratio of small gradient data
- ``min_data_per_group``, default = ``100``, type = int, constraints: ``min_data_per_group > 0``
- ``min_data_per_group`` :raw-html:`<a id="min_data_per_group" title="Permalink to this parameter" href="#min_data_per_group">&#x1F517;&#xFE0E;</a>`, default = ``100``, type = int, constraints: ``min_data_per_group > 0``
- minimal number of data per categorical group
- ``max_cat_threshold``, default = ``32``, type = int, constraints: ``max_cat_threshold > 0``
- ``max_cat_threshold`` :raw-html:`<a id="max_cat_threshold" title="Permalink to this parameter" href="#max_cat_threshold">&#x1F517;&#xFE0E;</a>`, default = ``32``, type = int, constraints: ``max_cat_threshold > 0``
- used for the categorical features
- limit the max threshold points in categorical features
- ``cat_l2``, default = ``10.0``, type = double, constraints: ``cat_l2 >= 0.0``
- ``cat_l2`` :raw-html:`<a id="cat_l2" title="Permalink to this parameter" href="#cat_l2">&#x1F517;&#xFE0E;</a>`, default = ``10.0``, type = double, constraints: ``cat_l2 >= 0.0``
- used for the categorical features
- L2 regularization in categorcial split
- ``cat_smooth``, default = ``10.0``, type = double, constraints: ``cat_smooth >= 0.0``
- ``cat_smooth`` :raw-html:`<a id="cat_smooth" title="Permalink to this parameter" href="#cat_smooth">&#x1F517;&#xFE0E;</a>`, default = ``10.0``, type = double, constraints: ``cat_smooth >= 0.0``
- used for the categorical features
- this can reduce the effect of noises in categorical features, especially for categories with few data
- ``max_cat_to_onehot``, default = ``4``, type = int, constraints: ``max_cat_to_onehot > 0``
- ``max_cat_to_onehot`` :raw-html:`<a id="max_cat_to_onehot" title="Permalink to this parameter" href="#max_cat_to_onehot">&#x1F517;&#xFE0E;</a>`, default = ``4``, type = int, constraints: ``max_cat_to_onehot > 0``
- when number of categories of one feature smaller than or equal to ``max_cat_to_onehot``, one-vs-other split algorithm will be used
- ``top_k``, default = ``20``, type = int, aliases: ``topk``, constraints: ``top_k > 0``
- ``top_k`` :raw-html:`<a id="top_k" title="Permalink to this parameter" href="#top_k">&#x1F517;&#xFE0E;</a>`, default = ``20``, type = int, aliases: ``topk``, constraints: ``top_k > 0``
- used in `Voting parallel <./Parallel-Learning-Guide.rst#choose-appropriate-parallel-algorithm>`__
- set this to larger value for more accurate result, but it will slow down the training speed
- ``monotone_constraints``, default = ``None``, type = multi-int, aliases: ``mc``, ``monotone_constraint``
- ``monotone_constraints`` :raw-html:`<a id="monotone_constraints" title="Permalink to this parameter" href="#monotone_constraints">&#x1F517;&#xFE0E;</a>`, default = ``None``, type = multi-int, aliases: ``mc``, ``monotone_constraint``
- used for constraints of monotonic features
......@@ -347,13 +350,13 @@ Learning Control Parameters
- you need to specify all features in order. For example, ``mc=-1,0,1`` means decreasing for 1st feature, non-constraint for 2nd feature and increasing for the 3rd feature
- ``feature_contri``, default = ``None``, type = multi-double, aliases: ``fc``, ``fp``, ``feature_penalty``
- ``feature_contri`` :raw-html:`<a id="feature_contri" title="Permalink to this parameter" href="#feature_contri">&#x1F517;&#xFE0E;</a>`, default = ``None``, type = multi-double, aliases: ``fc``, ``fp``, ``feature_penalty``
- used to control feature's split gain, will use ``gain[i] = max(0, feature_contri[i]) * gain[i]`` to replace the split gain of i-th feature
- you need to specify all features in order
- ``forcedsplits_filename``, default = ``""``, type = string, aliases: ``fs``, ``forced_splits_filename``, ``forced_splits_file``, ``forced_splits``
- ``forcedsplits_filename`` :raw-html:`<a id="forcedsplits_filename" title="Permalink to this parameter" href="#forcedsplits_filename">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``fs``, ``forced_splits_filename``, ``forced_splits_file``, ``forced_splits``
- path to a ``.json`` file that specifies splits to force at the top of every decision tree before best-first learning commences
......@@ -366,13 +369,13 @@ Learning Control Parameters
IO Parameters
-------------
- ``verbosity``, default = ``1``, type = int, aliases: ``verbose``
- ``verbosity`` :raw-html:`<a id="verbosity" title="Permalink to this parameter" href="#verbosity">&#x1F517;&#xFE0E;</a>`, default = ``1``, type = int, aliases: ``verbose``
- controls the level of LightGBM's verbosity
- ``< 0``: Fatal, ``= 0``: Error (Warn), ``> 0``: Info
- ``max_bin``, default = ``255``, type = int, constraints: ``max_bin > 1``
- ``max_bin`` :raw-html:`<a id="max_bin" title="Permalink to this parameter" href="#max_bin">&#x1F517;&#xFE0E;</a>`, default = ``255``, type = int, constraints: ``max_bin > 1``
- max number of bins that feature values will be bucketed in
......@@ -380,13 +383,13 @@ IO Parameters
- LightGBM will auto compress memory according to ``max_bin``. For example, LightGBM will use ``uint8_t`` for feature value if ``max_bin=255``
- ``min_data_in_bin``, default = ``3``, type = int, constraints: ``min_data_in_bin > 0``
- ``min_data_in_bin`` :raw-html:`<a id="min_data_in_bin" title="Permalink to this parameter" href="#min_data_in_bin">&#x1F517;&#xFE0E;</a>`, default = ``3``, type = int, constraints: ``min_data_in_bin > 0``
- minimal number of data inside one bin
- use this to avoid one-data-one-bin (potential over-fitting)
- ``bin_construct_sample_cnt``, default = ``200000``, type = int, aliases: ``subsample_for_bin``, constraints: ``bin_construct_sample_cnt > 0``
- ``bin_construct_sample_cnt`` :raw-html:`<a id="bin_construct_sample_cnt" title="Permalink to this parameter" href="#bin_construct_sample_cnt">&#x1F517;&#xFE0E;</a>`, default = ``200000``, type = int, aliases: ``subsample_for_bin``, constraints: ``bin_construct_sample_cnt > 0``
- number of data that sampled to construct histogram bins
......@@ -394,23 +397,23 @@ IO Parameters
- set this to larger value if data is very sparse
- ``histogram_pool_size``, default = ``-1.0``, type = double
- ``histogram_pool_size`` :raw-html:`<a id="histogram_pool_size" title="Permalink to this parameter" href="#histogram_pool_size">&#x1F517;&#xFE0E;</a>`, default = ``-1.0``, type = double
- max cache size in MB for historical histogram
- ``< 0`` means no limit
- ``data_random_seed``, default = ``1``, type = int
- ``data_random_seed`` :raw-html:`<a id="data_random_seed" title="Permalink to this parameter" href="#data_random_seed">&#x1F517;&#xFE0E;</a>`, default = ``1``, type = int
- random seed for data partition in parallel learning (excluding the ``feature_parallel`` mode)
- ``output_model``, default = ``LightGBM_model.txt``, type = string, aliases: ``model_output``, ``model_out``
- ``output_model`` :raw-html:`<a id="output_model" title="Permalink to this parameter" href="#output_model">&#x1F517;&#xFE0E;</a>`, default = ``LightGBM_model.txt``, type = string, aliases: ``model_output``, ``model_out``
- filename of output model in training
- **Note**: can be used only in CLI version
- ``snapshot_freq``, default = ``-1``, type = int
- ``snapshot_freq`` :raw-html:`<a id="snapshot_freq" title="Permalink to this parameter" href="#snapshot_freq">&#x1F517;&#xFE0E;</a>`, default = ``-1``, type = int
- frequency of saving model file snapshot
......@@ -418,7 +421,7 @@ IO Parameters
- **Note**: can be used only in CLI version
- ``input_model``, default = ``""``, type = string, aliases: ``model_input``, ``model_in``
- ``input_model`` :raw-html:`<a id="input_model" title="Permalink to this parameter" href="#input_model">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``model_input``, ``model_in``
- filename of input model
......@@ -428,13 +431,13 @@ IO Parameters
- **Note**: can be used only in CLI version
- ``output_result``, default = ``LightGBM_predict_result.txt``, type = string, aliases: ``predict_result``, ``prediction_result``
- ``output_result`` :raw-html:`<a id="output_result" title="Permalink to this parameter" href="#output_result">&#x1F517;&#xFE0E;</a>`, default = ``LightGBM_predict_result.txt``, type = string, aliases: ``predict_result``, ``prediction_result``
- filename of prediction result in ``prediction`` task
- **Note**: can be used only in CLI version
- ``initscore_filename``, default = ``""``, type = string, aliases: ``init_score_filename``, ``init_score_file``, ``init_score``, ``input_init_score``
- ``initscore_filename`` :raw-html:`<a id="initscore_filename" title="Permalink to this parameter" href="#initscore_filename">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``init_score_filename``, ``init_score_file``, ``init_score``, ``input_init_score``
- path of file with training initial scores
......@@ -442,7 +445,7 @@ IO Parameters
- **Note**: can be used only in CLI version
- ``valid_data_initscores``, default = ``""``, type = string, aliases: ``valid_data_init_scores``, ``valid_init_score_file``, ``valid_init_score``
- ``valid_data_initscores`` :raw-html:`<a id="valid_data_initscores" title="Permalink to this parameter" href="#valid_data_initscores">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``valid_data_init_scores``, ``valid_init_score_file``, ``valid_init_score``
- path(s) of file(s) with validation initial scores
......@@ -452,19 +455,19 @@ IO Parameters
- **Note**: can be used only in CLI version
- ``pre_partition``, default = ``false``, type = bool, aliases: ``is_pre_partition``
- ``pre_partition`` :raw-html:`<a id="pre_partition" title="Permalink to this parameter" href="#pre_partition">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``is_pre_partition``
- used for parallel learning (excluding the ``feature_parallel`` mode)
- ``true`` if training data are pre-partitioned, and different machines use different partitions
- ``enable_bundle``, default = ``true``, type = bool, aliases: ``is_enable_bundle``, ``bundle``
- ``enable_bundle`` :raw-html:`<a id="enable_bundle" title="Permalink to this parameter" href="#enable_bundle">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool, aliases: ``is_enable_bundle``, ``bundle``
- set this to ``false`` to disable Exclusive Feature Bundling (EFB), which is described in `LightGBM: A Highly Efficient Gradient Boosting Decision Tree <https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree>`__
- **Note**: disabling this may cause the slow training speed for sparse datasets
- ``max_conflict_rate``, default = ``0.0``, type = double, constraints: ``0.0 <= max_conflict_rate < 1.0``
- ``max_conflict_rate`` :raw-html:`<a id="max_conflict_rate" title="Permalink to this parameter" href="#max_conflict_rate">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, constraints: ``0.0 <= max_conflict_rate < 1.0``
- max conflict rate for bundles in EFB
......@@ -472,45 +475,45 @@ IO Parameters
- set this to a larger value to achieve faster speed
- ``is_enable_sparse``, default = ``true``, type = bool, aliases: ``is_sparse``, ``enable_sparse``, ``sparse``
- ``is_enable_sparse`` :raw-html:`<a id="is_enable_sparse" title="Permalink to this parameter" href="#is_enable_sparse">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool, aliases: ``is_sparse``, ``enable_sparse``, ``sparse``
- used to enable/disable sparse optimization
- ``sparse_threshold``, default = ``0.8``, type = double, constraints: ``0.0 < sparse_threshold <= 1.0``
- ``sparse_threshold`` :raw-html:`<a id="sparse_threshold" title="Permalink to this parameter" href="#sparse_threshold">&#x1F517;&#xFE0E;</a>`, default = ``0.8``, type = double, constraints: ``0.0 < sparse_threshold <= 1.0``
- the threshold of zero elements precentage for treating a feature as a sparse one
- ``use_missing``, default = ``true``, type = bool
- ``use_missing`` :raw-html:`<a id="use_missing" title="Permalink to this parameter" href="#use_missing">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool
- set this to ``false`` to disable the special handle of missing value
- ``zero_as_missing``, default = ``false``, type = bool
- ``zero_as_missing`` :raw-html:`<a id="zero_as_missing" title="Permalink to this parameter" href="#zero_as_missing">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- set this to ``true`` to treat all zero as missing values (including the unshown values in libsvm/sparse matrics)
- set this to ``false`` to use ``na`` for representing missing values
- ``two_round``, default = ``false``, type = bool, aliases: ``two_round_loading``, ``use_two_round_loading``
- ``two_round`` :raw-html:`<a id="two_round" title="Permalink to this parameter" href="#two_round">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``two_round_loading``, ``use_two_round_loading``
- set this to ``true`` if data file is too big to fit in memory
- by default, LightGBM will map data file to memory and load features from memory. This will provide faster data loading speed, but may cause run out of memory error when the data file is very big
- ``save_binary``, default = ``false``, type = bool, aliases: ``is_save_binary``, ``is_save_binary_file``
- ``save_binary`` :raw-html:`<a id="save_binary" title="Permalink to this parameter" href="#save_binary">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``is_save_binary``, ``is_save_binary_file``
- if ``true``, LightGBM will save the dataset (including validation data) to a binary file. This speed ups the data loading for the next time
- ``enable_load_from_binary_file``, default = ``true``, type = bool, aliases: ``load_from_binary_file``, ``binary_load``, ``load_binary``
- ``enable_load_from_binary_file`` :raw-html:`<a id="enable_load_from_binary_file" title="Permalink to this parameter" href="#enable_load_from_binary_file">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool, aliases: ``load_from_binary_file``, ``binary_load``, ``load_binary``
- set this to ``true`` to enable autoloading from previous saved binary datasets
- set this to ``false`` to ignore binary datasets
- ``header``, default = ``false``, type = bool, aliases: ``has_header``
- ``header`` :raw-html:`<a id="header" title="Permalink to this parameter" href="#header">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``has_header``
- set this to ``true`` if input data has header
- ``label_column``, default = ``""``, type = int or string, aliases: ``label``
- ``label_column`` :raw-html:`<a id="label_column" title="Permalink to this parameter" href="#label_column">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = int or string, aliases: ``label``
- used to specify the label column
......@@ -518,7 +521,7 @@ IO Parameters
- add a prefix ``name:`` for column name, e.g. ``label=name:is_click``
- ``weight_column``, default = ``""``, type = int or string, aliases: ``weight``
- ``weight_column`` :raw-html:`<a id="weight_column" title="Permalink to this parameter" href="#weight_column">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = int or string, aliases: ``weight``
- used to specify the weight column
......@@ -528,7 +531,7 @@ IO Parameters
- **Note**: index starts from ``0`` and it doesn't count the label column when passing type is ``int``, e.g. when label is column\_0, and weight is column\_1, the correct parameter is ``weight=0``
- ``group_column``, default = ``""``, type = int or string, aliases: ``group``, ``group_id``, ``query_column``, ``query``, ``query_id``
- ``group_column`` :raw-html:`<a id="group_column" title="Permalink to this parameter" href="#group_column">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = int or string, aliases: ``group``, ``group_id``, ``query_column``, ``query``, ``query_id``
- used to specify the query/group id column
......@@ -540,7 +543,7 @@ IO Parameters
- **Note**: index starts from ``0`` and it doesn't count the label column when passing type is ``int``, e.g. when label is column\_0 and query\_id is column\_1, the correct parameter is ``query=0``
- ``ignore_column``, default = ``""``, type = multi-int or string, aliases: ``ignore_feature``, ``blacklist``
- ``ignore_column`` :raw-html:`<a id="ignore_column" title="Permalink to this parameter" href="#ignore_column">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = multi-int or string, aliases: ``ignore_feature``, ``blacklist``
- used to specify some ignoring columns in training
......@@ -552,7 +555,7 @@ IO Parameters
- **Note**: index starts from ``0`` and it doesn't count the label column when passing type is ``int``
- ``categorical_feature``, default = ``""``, type = multi-int or string, aliases: ``cat_feature``, ``categorical_column``, ``cat_column``
- ``categorical_feature`` :raw-html:`<a id="categorical_feature" title="Permalink to this parameter" href="#categorical_feature">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = multi-int or string, aliases: ``cat_feature``, ``categorical_column``, ``cat_column``
- used to specify categorical features
......@@ -568,7 +571,7 @@ IO Parameters
- **Note**: the negative values will be treated as **missing values**
- ``predict_raw_score``, default = ``false``, type = bool, aliases: ``is_predict_raw_score``, ``predict_rawscore``, ``raw_score``
- ``predict_raw_score`` :raw-html:`<a id="predict_raw_score" title="Permalink to this parameter" href="#predict_raw_score">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``is_predict_raw_score``, ``predict_rawscore``, ``raw_score``
- used only in ``prediction`` task
......@@ -576,13 +579,13 @@ IO Parameters
- set this to ``false`` to predict transformed scores
- ``predict_leaf_index``, default = ``false``, type = bool, aliases: ``is_predict_leaf_index``, ``leaf_index``
- ``predict_leaf_index`` :raw-html:`<a id="predict_leaf_index" title="Permalink to this parameter" href="#predict_leaf_index">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``is_predict_leaf_index``, ``leaf_index``
- used only in ``prediction`` task
- set this to ``true`` to predict with leaf index of all trees
- ``predict_contrib``, default = ``false``, type = bool, aliases: ``is_predict_contrib``, ``contrib``
- ``predict_contrib`` :raw-html:`<a id="predict_contrib" title="Permalink to this parameter" href="#predict_contrib">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``is_predict_contrib``, ``contrib``
- used only in ``prediction`` task
......@@ -590,7 +593,7 @@ IO Parameters
- produces ``#features + 1`` values where the last value is the expected value of the model output over the training data
- ``num_iteration_predict``, default = ``-1``, type = int
- ``num_iteration_predict`` :raw-html:`<a id="num_iteration_predict" title="Permalink to this parameter" href="#num_iteration_predict">&#x1F517;&#xFE0E;</a>`, default = ``-1``, type = int
- used only in ``prediction`` task
......@@ -598,25 +601,25 @@ IO Parameters
- ``<= 0`` means no limit
- ``pred_early_stop``, default = ``false``, type = bool
- ``pred_early_stop`` :raw-html:`<a id="pred_early_stop" title="Permalink to this parameter" href="#pred_early_stop">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- used only in ``prediction`` task
- if ``true``, will use early-stopping to speed up the prediction. May affect the accuracy
- ``pred_early_stop_freq``, default = ``10``, type = int
- ``pred_early_stop_freq`` :raw-html:`<a id="pred_early_stop_freq" title="Permalink to this parameter" href="#pred_early_stop_freq">&#x1F517;&#xFE0E;</a>`, default = ``10``, type = int
- used only in ``prediction`` task
- the frequency of checking early-stopping prediction
- ``pred_early_stop_margin``, default = ``10.0``, type = double
- ``pred_early_stop_margin`` :raw-html:`<a id="pred_early_stop_margin" title="Permalink to this parameter" href="#pred_early_stop_margin">&#x1F517;&#xFE0E;</a>`, default = ``10.0``, type = double
- used only in ``prediction`` task
- the threshold of margin in early-stopping prediction
- ``convert_model_language``, default = ``""``, type = string
- ``convert_model_language`` :raw-html:`<a id="convert_model_language" title="Permalink to this parameter" href="#convert_model_language">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string
- used only in ``convert_model`` task
......@@ -626,7 +629,7 @@ IO Parameters
- **Note**: can be used only in CLI version
- ``convert_model``, default = ``gbdt_prediction.cpp``, type = string, aliases: ``convert_model_file``
- ``convert_model`` :raw-html:`<a id="convert_model" title="Permalink to this parameter" href="#convert_model">&#x1F517;&#xFE0E;</a>`, default = ``gbdt_prediction.cpp``, type = string, aliases: ``convert_model_file``
- used only in ``convert_model`` task
......@@ -637,11 +640,11 @@ IO Parameters
Objective Parameters
--------------------
- ``num_class``, default = ``1``, type = int, aliases: ``num_classes``, constraints: ``num_class > 0``
- ``num_class`` :raw-html:`<a id="num_class" title="Permalink to this parameter" href="#num_class">&#x1F517;&#xFE0E;</a>`, default = ``1``, type = int, aliases: ``num_classes``, constraints: ``num_class > 0``
- used only in ``multi-class`` classification application
- ``is_unbalance``, default = ``false``, type = bool, aliases: ``unbalanced_sets``
- ``is_unbalance`` :raw-html:`<a id="is_unbalance" title="Permalink to this parameter" href="#is_unbalance">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``unbalanced_sets``
- used only in ``binary`` application
......@@ -649,7 +652,7 @@ Objective Parameters
- **Note**: this parameter cannot be used at the same time with ``scale_pos_weight``, choose only **one** of them
- ``scale_pos_weight``, default = ``1.0``, type = double, constraints: ``scale_pos_weight > 0.0``
- ``scale_pos_weight`` :raw-html:`<a id="scale_pos_weight" title="Permalink to this parameter" href="#scale_pos_weight">&#x1F517;&#xFE0E;</a>`, default = ``1.0``, type = double, constraints: ``scale_pos_weight > 0.0``
- used only in ``binary`` application
......@@ -657,19 +660,19 @@ Objective Parameters
- **Note**: this parameter cannot be used at the same time with ``is_unbalance``, choose only **one** of them
- ``sigmoid``, default = ``1.0``, type = double, constraints: ``sigmoid > 0.0``
- ``sigmoid`` :raw-html:`<a id="sigmoid" title="Permalink to this parameter" href="#sigmoid">&#x1F517;&#xFE0E;</a>`, default = ``1.0``, type = double, constraints: ``sigmoid > 0.0``
- used only in ``binary`` and ``multiclassova`` classification and in ``lambdarank`` applications
- parameter for the sigmoid function
- ``boost_from_average``, default = ``true``, type = bool
- ``boost_from_average`` :raw-html:`<a id="boost_from_average" title="Permalink to this parameter" href="#boost_from_average">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool
- used only in ``regression``, ``binary`` and ``cross-entropy`` applications
- adjusts initial score to the mean of labels for faster convergence
- ``reg_sqrt``, default = ``false``, type = bool
- ``reg_sqrt`` :raw-html:`<a id="reg_sqrt" title="Permalink to this parameter" href="#reg_sqrt">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- used only in ``regression`` application
......@@ -677,25 +680,25 @@ Objective Parameters
- might be useful in case of large-range labels
- ``alpha``, default = ``0.9``, type = double, constraints: ``alpha > 0.0``
- ``alpha`` :raw-html:`<a id="alpha" title="Permalink to this parameter" href="#alpha">&#x1F517;&#xFE0E;</a>`, default = ``0.9``, type = double, constraints: ``alpha > 0.0``
- used only in ``huber`` and ``quantile`` ``regression`` applications
- parameter for `Huber loss <https://en.wikipedia.org/wiki/Huber_loss>`__ and `Quantile regression <https://en.wikipedia.org/wiki/Quantile_regression>`__
- ``fair_c``, default = ``1.0``, type = double, constraints: ``fair_c > 0.0``
- ``fair_c`` :raw-html:`<a id="fair_c" title="Permalink to this parameter" href="#fair_c">&#x1F517;&#xFE0E;</a>`, default = ``1.0``, type = double, constraints: ``fair_c > 0.0``
- used only in ``fair`` ``regression`` application
- parameter for `Fair loss <https://www.kaggle.com/c/allstate-claims-severity/discussion/24520>`__
- ``poisson_max_delta_step``, default = ``0.7``, type = double, constraints: ``poisson_max_delta_step > 0.0``
- ``poisson_max_delta_step`` :raw-html:`<a id="poisson_max_delta_step" title="Permalink to this parameter" href="#poisson_max_delta_step">&#x1F517;&#xFE0E;</a>`, default = ``0.7``, type = double, constraints: ``poisson_max_delta_step > 0.0``
- used only in ``poisson`` ``regression`` application
- parameter for `Poisson regression <https://en.wikipedia.org/wiki/Poisson_regression>`__ to safeguard optimization
- ``tweedie_variance_power``, default = ``1.5``, type = double, constraints: ``1.0 <= tweedie_variance_power < 2.0``
- ``tweedie_variance_power`` :raw-html:`<a id="tweedie_variance_power" title="Permalink to this parameter" href="#tweedie_variance_power">&#x1F517;&#xFE0E;</a>`, default = ``1.5``, type = double, constraints: ``1.0 <= tweedie_variance_power < 2.0``
- used only in ``tweedie`` ``regression`` application
......@@ -705,13 +708,13 @@ Objective Parameters
- set this closer to ``1`` to shift towards a **Poisson** distribution
- ``max_position``, default = ``20``, type = int, constraints: ``max_position > 0``
- ``max_position`` :raw-html:`<a id="max_position" title="Permalink to this parameter" href="#max_position">&#x1F517;&#xFE0E;</a>`, default = ``20``, type = int, constraints: ``max_position > 0``
- used only in ``lambdarank`` application
- optimizes `NDCG <https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG>`__ at this position
- ``label_gain``, default = ``0,1,3,7,15,31,63,...,2^30-1``, type = multi-double
- ``label_gain`` :raw-html:`<a id="label_gain" title="Permalink to this parameter" href="#label_gain">&#x1F517;&#xFE0E;</a>`, default = ``0,1,3,7,15,31,63,...,2^30-1``, type = multi-double
- used only in ``lambdarank`` application
......@@ -722,7 +725,7 @@ Objective Parameters
Metric Parameters
-----------------
- ``metric``, default = ``""``, type = multi-enum, aliases: ``metrics``, ``metric_types``
- ``metric`` :raw-html:`<a id="metric" title="Permalink to this parameter" href="#metric">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = multi-enum, aliases: ``metrics``, ``metric_types``
- metric(s) to be evaluated on the evaluation sets **in addition** to what is provided in the training arguments
......@@ -774,15 +777,15 @@ Metric Parameters
- support multiple metrics, separated by ``,``
- ``metric_freq``, default = ``1``, type = int, aliases: ``output_freq``, constraints: ``metric_freq > 0``
- ``metric_freq`` :raw-html:`<a id="metric_freq" title="Permalink to this parameter" href="#metric_freq">&#x1F517;&#xFE0E;</a>`, default = ``1``, type = int, aliases: ``output_freq``, constraints: ``metric_freq > 0``
- frequency for metric output
- ``is_provide_training_metric``, default = ``false``, type = bool, aliases: ``training_metric``, ``is_training_metric``, ``train_metric``
- ``is_provide_training_metric`` :raw-html:`<a id="is_provide_training_metric" title="Permalink to this parameter" href="#is_provide_training_metric">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool, aliases: ``training_metric``, ``is_training_metric``, ``train_metric``
- set this to ``true`` to output metric result over training dataset
- ``eval_at``, default = ``1,2,3,4,5``, type = multi-int, aliases: ``ndcg_eval_at``, ``ndcg_at``
- ``eval_at`` :raw-html:`<a id="eval_at" title="Permalink to this parameter" href="#eval_at">&#x1F517;&#xFE0E;</a>`, default = ``1,2,3,4,5``, type = multi-int, aliases: ``ndcg_eval_at``, ``ndcg_at``
- used only with ``ndcg`` and ``map`` metrics
......@@ -791,48 +794,48 @@ Metric Parameters
Network Parameters
------------------
- ``num_machines``, default = ``1``, type = int, aliases: ``num_machine``, constraints: ``num_machines > 0``
- ``num_machines`` :raw-html:`<a id="num_machines" title="Permalink to this parameter" href="#num_machines">&#x1F517;&#xFE0E;</a>`, default = ``1``, type = int, aliases: ``num_machine``, constraints: ``num_machines > 0``
- the number of machines for parallel learning application
- this parameter is needed to be set in both **socket** and **mpi** versions
- ``local_listen_port``, default = ``12400``, type = int, aliases: ``local_port``, ``port``, constraints: ``local_listen_port > 0``
- ``local_listen_port`` :raw-html:`<a id="local_listen_port" title="Permalink to this parameter" href="#local_listen_port">&#x1F517;&#xFE0E;</a>`, default = ``12400``, type = int, aliases: ``local_port``, ``port``, constraints: ``local_listen_port > 0``
- TCP listen port for local machines
- **Note**: don't forget to allow this port in firewall settings before training
- ``time_out``, default = ``120``, type = int, constraints: ``time_out > 0``
- ``time_out`` :raw-html:`<a id="time_out" title="Permalink to this parameter" href="#time_out">&#x1F517;&#xFE0E;</a>`, default = ``120``, type = int, constraints: ``time_out > 0``
- socket time-out in minutes
- ``machine_list_filename``, default = ``""``, type = string, aliases: ``machine_list_file``, ``machine_list``, ``mlist``
- ``machine_list_filename`` :raw-html:`<a id="machine_list_filename" title="Permalink to this parameter" href="#machine_list_filename">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``machine_list_file``, ``machine_list``, ``mlist``
- path of file that lists machines for this parallel learning application
- each line contains one IP and one port for one machine. The format is ``ip port`` (space as a separator)
- ``machines``, default = ``""``, type = string, aliases: ``workers``, ``nodes``
- ``machines`` :raw-html:`<a id="machines" title="Permalink to this parameter" href="#machines">&#x1F517;&#xFE0E;</a>`, default = ``""``, type = string, aliases: ``workers``, ``nodes``
- list of machines in the following format: ``ip1:port1,ip2:port2``
GPU Parameters
--------------
- ``gpu_platform_id``, default = ``-1``, type = int
- ``gpu_platform_id`` :raw-html:`<a id="gpu_platform_id" title="Permalink to this parameter" href="#gpu_platform_id">&#x1F517;&#xFE0E;</a>`, default = ``-1``, type = int
- OpenCL platform ID. Usually each GPU vendor exposes one OpenCL platform
- ``-1`` means the system-wide default platform
- ``gpu_device_id``, default = ``-1``, type = int
- ``gpu_device_id`` :raw-html:`<a id="gpu_device_id" title="Permalink to this parameter" href="#gpu_device_id">&#x1F517;&#xFE0E;</a>`, default = ``-1``, type = int
- OpenCL device ID in the specified platform. Each GPU in the selected platform has a unique device ID
- ``-1`` means the default device in the selected platform
- ``gpu_use_dp``, default = ``false``, type = bool
- ``gpu_use_dp`` :raw-html:`<a id="gpu_use_dp" title="Permalink to this parameter" href="#gpu_use_dp">&#x1F517;&#xFE0E;</a>`, default = ``false``, type = bool
- set this to ``true`` to use double precision math on GPU (by default single precision is used)
......@@ -855,9 +858,12 @@ LightGBM supports continued training with initial scores. It uses an additional
It means the initial score of the first data row is ``0.5``, second is ``-0.1``, and so on.
The initial score file corresponds with data file line by line, and has per score per line.
And if the name of data file is ``train.txt``, the initial score file should be named as ``train.txt.init`` and in the same folder as the data file.
In this case LightGBM will auto load initial score file if it exists.
Otherwise, you should specify the path to the custom named file with initial scores by the ``initscore_filename`` `parameter <#initscore_filename>`__.
Weight Data
~~~~~~~~~~~
......@@ -872,10 +878,11 @@ LightGBM supports weighted training. It uses an additional file to store weight
It means the weight of the first data row is ``1.0``, second is ``0.5``, and so on.
The weight file corresponds with data file line by line, and has per weight per line.
And if the name of data file is ``train.txt``, the weight file should be named as ``train.txt.weight`` and placed in the same folder as the data file.
In this case LightGBM will load the weight file automatically if it exists.
Also, you can include weight column in your data file. Please refer to parameter ``weight`` in above.
Also, you can include weight column in your data file. Please refer to the ``weight_column`` `parameter <#weight_column>`__ in above.
Query Data
~~~~~~~~~~
......@@ -897,6 +904,6 @@ It means first ``27`` lines samples belong to one query and next ``18`` lines be
If the name of data file is ``train.txt``, the query file should be named as ``train.txt.query`` and placed in the same folder as the data file.
In this case LightGBM will load the query file automatically if it exists.
Also, you can include query/group id column in your data file. Please refer to parameter ``group`` in above.
Also, you can include query/group id column in your data file. Please refer to the ``group_column`` `parameter <#group_column>`__ in above.
.. _Laurae++ Interactive Documentation: https://sites.google.com/view/lauraepp/parameters
docs/Quick-Start.rst
View file @ f5afaba1
......@@ -37,8 +37,8 @@ For the setting details, please refer to `Parameters <./Parameters.rst>`__.
Weight and Query/Group Data
~~~~~~~~~~~~~~~~~~~~~~~~~~~
LightGBM also supports weighted training, it needs an additional `weight data <./Parameters.rst#io-parameters>`__.
And it needs an additional `query data <./Parameters.rst#io-parameters>`_ for ranking task.
LightGBM also supports weighted training, it needs an additional `weight data <./Parameters.rst#weight-data>`__.
And it needs an additional `query data <./Parameters.rst#query-data>`_ for ranking task.
Also, weight and query data could be specified as columns in training data in the same manner as label.
......
helper/parameter_generator.py
View file @ f5afaba1
......@@ -147,7 +147,7 @@ def GenParameterDescription(sections, descriptions, params_rst):
checks_str = ', constraints: ``{0} {1} {2}``'.format(name, sign, number)
else:
checks_str = ''
main_desc = '- ``{0}``, default = ``{1}``, type = {2}{3}{4}{5}'.format(name, default, param_type, options_str, aliases_str, checks_str)
main_desc = '- ``{0}`` :raw-html:`<a id="{0}" title="Permalink to this parameter" href="#{0}">&#x1F517;&#xFE0E;</a>`, default = ``{1}``, type = {2}{3}{4}{5}'.format(name, default, param_type, options_str, aliases_str, checks_str)
params_to_write.append(main_desc)
params_to_write.extend([' ' * 3 * int(desc[0][-1]) + '- ' + desc[1] for desc in param_desc['desc']])
......
python-package/lightgbm/sklearn.py
View file @ f5afaba1
......@@ -134,7 +134,7 @@ class LGBMModel(_LGBMModelBase):
min_split_gain=0., min_child_weight=1e-3, min_child_samples=20,
subsample=1., subsample_freq=0, colsample_bytree=1.,
reg_alpha=0., reg_lambda=0., random_state=None,
n_jobs=-1, silent=True, **kwargs):
n_jobs=-1, silent=True, importance_type='split', **kwargs):
"""Construct a gradient boosting model.
Parameters
......@@ -193,6 +193,10 @@ class LGBMModel(_LGBMModelBase):
Number of parallel threads.
silent : bool, optional (default=True)
Whether to print messages while running boosting.
importance_type : str, optional (default='split')
The type of feature importance to be filled into ``feature_importances_``.
If "split", result contains numbers of times the feature is used in a model.
If "gain", result contains total gains of splits which use the feature.
**kwargs : other parameters
Check http://lightgbm.readthedocs.io/en/latest/Parameters.html for more parameters.
......@@ -264,6 +268,7 @@ class LGBMModel(_LGBMModelBase):
self.random_state = random_state
self.n_jobs = n_jobs
self.silent = silent
self.importance_type = importance_type
self._Booster = None
self._evals_result = None
self._best_score = None
......@@ -399,6 +404,7 @@ class LGBMModel(_LGBMModelBase):
if 'verbose' not in params and self.silent:
params['verbose'] = 0
params.pop('silent', None)
params.pop('importance_type', None)
params.pop('n_estimators', None)
params.pop('class_weight', None)
if self._n_classes is not None and self._n_classes > 2:
......@@ -606,11 +612,13 @@ class LGBMModel(_LGBMModelBase):
Note
----
Feature importance in sklearn interface used to normalize to 1,
it's deprecated after 2.0.4 and same as Booster.feature_importance() now.
it's deprecated after 2.0.4 and is the same as Booster.feature_importance() now.
``importance_type`` attribute is passed to the function
to configure the type of importance values to be extracted.
"""
if self._n_features is None:
raise LGBMNotFittedError('No feature_importances found. Need to call fit beforehand.')
return self.booster_.feature_importance()
return self.booster_.feature_importance(importance_type=self.importance_type)
class LGBMRegressor(LGBMModel, _LGBMRegressorBase):
......
src/io/config.cpp
View file @ f5afaba1
......@@ -214,15 +214,13 @@ void Config::CheckParamConflict() {
Log::Fatal("Number of classes must be 1 for non-multiclass training");
}
}
if (is_provide_training_metric || !valid.empty()) {
for (std::string metric_type : metric) {
bool metric_type_multiclass = (CheckMultiClassObjective(metric_type)
|| metric_type == std::string("multi_logloss")
|| metric_type == std::string("multi_error"));
if ((objective_type_multiclass && !metric_type_multiclass)
|| (!objective_type_multiclass && metric_type_multiclass)) {
Log::Fatal("Objective and metrics don't match");
}
for (std::string metric_type : metric) {
bool metric_type_multiclass = (CheckMultiClassObjective(metric_type)
|| metric_type == std::string("multi_logloss")
|| metric_type == std::string("multi_error"));
if ((objective_type_multiclass && !metric_type_multiclass)
|| (!objective_type_multiclass && metric_type_multiclass)) {
Log::Fatal("Multiclass qbjective and metrics don't match");
}
}
......
tests/python_package_test/test_sklearn.py
View file @ f5afaba1
......@@ -166,6 +166,19 @@ class TestSklearn(unittest.TestCase):
importances = clf.feature_importances_
self.assertEqual(len(importances), 4)
def test_feature_importances_type(self):
clf = lgb.LGBMClassifier(n_estimators=100)
data = load_iris()
clf.fit(data.data, data.target)
clf.set_params(importance_type='split')
importances_split = clf.feature_importances_
clf.set_params(importance_type='gain')
importances_gain = clf.feature_importances_
# Test that the largest element is NOT the same, the smallest can be the same, i.e. zero
importance_split_top1 = sorted(importances_split, reverse=True)[0]
importance_gain_top1 = sorted(importances_gain, reverse=True)[0]
self.assertNotEqual(importance_split_top1, importance_gain_top1)
def test_sklearn_backward_compatibility(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment