зеркало из https://github.com/microsoft/LightGBM.git
[docs] unify language and make small improvements in some param descriptions (#6618)
This commit is contained in:
Nikita Titov
GitHub
Родитель
5fa615bc48
Коммит
a9df7f113f
|
|
@ -127,10 +127,10 @@ Core Parameters
|
|||
|
||||
- ``custom``
|
||||
|
||||
- **Note**: Not supported in CLI version
|
||||
|
||||
- must be passed through parameters explicitly in the C API
|
||||
|
||||
- **Note**: cannot be used in CLI version
|
||||
|
||||
- ``boosting`` :raw-html:`<a id="boosting" title="Permalink to this parameter" href="#boosting">🔗︎</a>`, default = ``gbdt``, type = enum, options: ``gbdt``, ``rf``, ``dart``, aliases: ``boosting_type``, ``boost``
|
||||
|
||||
- ``gbdt``, traditional Gradient Boosting Decision Tree, aliases: ``gbrt``
|
||||
|
|
@ -225,7 +225,7 @@ Core Parameters
|
|||
|
||||
- **Note**: for the faster speed, GPU uses 32-bit float point to sum up by default, so this may affect the accuracy for some tasks. You can set ``gpu_use_dp=true`` to enable 64-bit float point, but it will slow down the training
|
||||
|
||||
- **Note**: refer to `Installation Guide <./Installation-Guide.rst#build-gpu-version>`__ to build LightGBM with GPU support
|
||||
- **Note**: refer to `Installation Guide <./Installation-Guide.rst>`__ to build LightGBM with GPU or CUDA support
|
||||
|
||||
- ``seed`` :raw-html:`<a id="seed" title="Permalink to this parameter" href="#seed">🔗︎</a>`, default = ``None``, type = int, aliases: ``random_seed``, ``random_state``
|
||||
|
||||
|
|
@ -358,7 +358,7 @@ Learning Control Parameters
|
|||
|
||||
- frequency for bagging
|
||||
|
||||
- ``0`` means disable bagging; ``k`` means perform bagging at every ``k`` iteration. Every ``k``-th iteration, LightGBM will randomly select ``bagging_fraction * 100 %`` of the data to use for the next ``k`` iterations
|
||||
- ``0`` means disable bagging; ``k`` means perform bagging at every ``k`` iteration. Every ``k``-th iteration, LightGBM will randomly select ``bagging_fraction * 100%`` of the data to use for the next ``k`` iterations
|
||||
|
||||
- **Note**: bagging is only effective when ``0.0 < bagging_fraction < 1.0``
|
||||
|
||||
|
|
@ -470,7 +470,7 @@ Learning Control Parameters
|
|||
|
||||
- used only in ``dart``
|
||||
|
||||
- set this to ``true``, if you want to use xgboost dart mode
|
||||
- set this to ``true``, if you want to use XGBoost DART mode
|
||||
|
||||
- ``uniform_drop`` :raw-html:`<a id="uniform_drop" title="Permalink to this parameter" href="#uniform_drop">🔗︎</a>`, default = ``false``, type = bool
|
||||
|
||||
|
|
@ -498,6 +498,8 @@ Learning Control Parameters
|
|||
|
||||
- ``min_data_per_group`` :raw-html:`<a id="min_data_per_group" title="Permalink to this parameter" href="#min_data_per_group">🔗︎</a>`, default = ``100``, type = int, constraints: ``min_data_per_group > 0``
|
||||
|
||||
- used for the categorical features
|
||||
|
||||
- minimal number of data per categorical group
|
||||
|
||||
- ``max_cat_threshold`` :raw-html:`<a id="max_cat_threshold" title="Permalink to this parameter" href="#max_cat_threshold">🔗︎</a>`, default = ``32``, type = int, constraints: ``max_cat_threshold > 0``
|
||||
|
|
@ -522,6 +524,8 @@ Learning Control Parameters
|
|||
|
||||
- ``max_cat_to_onehot`` :raw-html:`<a id="max_cat_to_onehot" title="Permalink to this parameter" href="#max_cat_to_onehot">🔗︎</a>`, default = ``4``, type = int, constraints: ``max_cat_to_onehot > 0``
|
||||
|
||||
- used for the categorical features
|
||||
|
||||
- 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`` :raw-html:`<a id="top_k" title="Permalink to this parameter" href="#top_k">🔗︎</a>`, default = ``20``, type = int, aliases: ``topk``, constraints: ``top_k > 0``
|
||||
|
|
@ -536,7 +540,7 @@ Learning Control Parameters
|
|||
|
||||
- ``1`` means increasing, ``-1`` means decreasing, ``0`` means non-constraint
|
||||
|
||||
- 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
|
||||
- you need to specify all features in order. For example, ``mc=-1,0,1`` means decreasing for the 1st feature, non-constraint for the 2nd feature and increasing for the 3rd feature
|
||||
|
||||
- ``monotone_constraints_method`` :raw-html:`<a id="monotone_constraints_method" title="Permalink to this parameter" href="#monotone_constraints_method">🔗︎</a>`, default = ``basic``, type = enum, options: ``basic``, ``intermediate``, ``advanced``, aliases: ``monotone_constraining_method``, ``mc_method``
|
||||
|
||||
|
|
@ -544,11 +548,11 @@ Learning Control Parameters
|
|||
|
||||
- monotone constraints method
|
||||
|
||||
- ``basic``, the most basic monotone constraints method. It does not slow the library at all, but over-constrains the predictions
|
||||
- ``basic``, the most basic monotone constraints method. It does not slow down the training speed at all, but over-constrains the predictions
|
||||
|
||||
- ``intermediate``, a `more advanced method <https://hal.science/hal-02862802/document>`__, which may slow the library very slightly. However, this method is much less constraining than the basic method and should significantly improve the results
|
||||
- ``intermediate``, a `more advanced method <https://hal.science/hal-02862802/document>`__, which may slow down the training speed very slightly. However, this method is much less constraining than the basic method and should significantly improve the results
|
||||
|
||||
- ``advanced``, an `even more advanced method <https://hal.science/hal-02862802/document>`__, which may slow the library. However, this method is even less constraining than the intermediate method and should again significantly improve the results
|
||||
- ``advanced``, an `even more advanced method <https://hal.science/hal-02862802/document>`__, which may slow down the training speed. However, this method is even less constraining than the intermediate method and should again significantly improve the results
|
||||
|
||||
- ``monotone_penalty`` :raw-html:`<a id="monotone_penalty" title="Permalink to this parameter" href="#monotone_penalty">🔗︎</a>`, default = ``0.0``, type = double, aliases: ``monotone_splits_penalty``, ``ms_penalty``, ``mc_penalty``, constraints: ``monotone_penalty >= 0.0``
|
||||
|
||||
|
|
@ -608,7 +612,7 @@ Learning Control Parameters
|
|||
|
||||
- helps prevent overfitting on leaves with few samples
|
||||
|
||||
- if set to zero, no smoothing is applied
|
||||
- if ``0.0`` (the default), no smoothing is applied
|
||||
|
||||
- if ``path_smooth > 0`` then ``min_data_in_leaf`` must be at least ``2``
|
||||
|
||||
|
|
@ -628,7 +632,7 @@ Learning Control Parameters
|
|||
|
||||
- for Python-package, list of lists, e.g. ``[[0, 1, 2], [2, 3]]``
|
||||
|
||||
- for R-package, list of character or numeric vectors, e.g. ``list(c("var1", "var2", "var3"), c("var3", "var4"))`` or ``list(c(1L, 2L, 3L), c(3L, 4L))``. Numeric vectors should use 1-based indexing, where ``1L`` is the first feature, ``2L`` is the second feature, etc
|
||||
- for R-package, list of character or numeric vectors, e.g. ``list(c("var1", "var2", "var3"), c("var3", "var4"))`` or ``list(c(1L, 2L, 3L), c(3L, 4L))``. Numeric vectors should use 1-based indexing, where ``1L`` is the first feature, ``2L`` is the second feature, etc.
|
||||
|
||||
- any two features can only appear in the same branch only if there exists a constraint containing both features
|
||||
|
||||
|
|
@ -680,35 +684,41 @@ Learning Control Parameters
|
|||
|
||||
- gradient quantization can accelerate training, with little accuracy drop in most cases
|
||||
|
||||
- **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
- **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
|
||||
- *New in version 4.0.0*
|
||||
|
||||
- ``num_grad_quant_bins`` :raw-html:`<a id="num_grad_quant_bins" title="Permalink to this parameter" href="#num_grad_quant_bins">🔗︎</a>`, default = ``4``, type = int
|
||||
|
||||
- used only if ``use_quantized_grad=true``
|
||||
|
||||
- number of bins to quantization gradients and hessians
|
||||
|
||||
- with more bins, the quantized training will be closer to full precision training
|
||||
|
||||
- **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
- **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
|
||||
- *New in version 4.0.0*
|
||||
|
||||
- ``quant_train_renew_leaf`` :raw-html:`<a id="quant_train_renew_leaf" title="Permalink to this parameter" href="#quant_train_renew_leaf">🔗︎</a>`, default = ``false``, type = bool
|
||||
|
||||
- used only if ``use_quantized_grad=true``
|
||||
|
||||
- whether to renew the leaf values with original gradients when quantized training
|
||||
|
||||
- renewing is very helpful for good quantized training accuracy for ranking objectives
|
||||
|
||||
- **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
- **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
|
||||
- *New in version 4.0.0*
|
||||
|
||||
- ``stochastic_rounding`` :raw-html:`<a id="stochastic_rounding" title="Permalink to this parameter" href="#stochastic_rounding">🔗︎</a>`, default = ``true``, type = bool
|
||||
|
||||
- used only if ``use_quantized_grad=true``
|
||||
|
||||
- whether to use stochastic rounding in gradient quantization
|
||||
|
||||
- **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
- **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
|
||||
- *New in version 4.0.0*
|
||||
|
||||
|
|
@ -722,25 +732,25 @@ Dataset Parameters
|
|||
|
||||
- fit piecewise linear gradient boosting tree
|
||||
|
||||
- tree splits are chosen in the usual way, but the model at each leaf is linear instead of constant
|
||||
- tree splits are chosen in the usual way, but the model at each leaf is linear instead of constant
|
||||
|
||||
- the linear model at each leaf includes all the numerical features in that leaf's branch
|
||||
- the linear model at each leaf includes all the numerical features in that leaf's branch
|
||||
|
||||
- the first tree has constant leaf values
|
||||
- the first tree has constant leaf values
|
||||
|
||||
- categorical features are used for splits as normal but are not used in the linear models
|
||||
- categorical features are used for splits as normal but are not used in the linear models
|
||||
|
||||
- missing values should not be encoded as ``0``. Use ``np.nan`` for Python, ``NA`` for the CLI, and ``NA``, ``NA_real_``, or ``NA_integer_`` for R
|
||||
- missing values should not be encoded as ``0``. Use ``np.nan`` for Python, ``NA`` for the CLI, and ``NA``, ``NA_real_``, or ``NA_integer_`` for R
|
||||
|
||||
- it is recommended to rescale data before training so that features have similar mean and standard deviation
|
||||
- it is recommended to rescale data before training so that features have similar mean and standard deviation
|
||||
|
||||
- **Note**: only works with CPU and ``serial`` tree learner
|
||||
- **Note**: works only with ``cpu`` device type and ``serial`` tree learner
|
||||
|
||||
- **Note**: ``regression_l1`` objective is not supported with linear tree boosting
|
||||
- **Note**: ``regression_l1`` objective is not supported with linear tree boosting
|
||||
|
||||
- **Note**: setting ``linear_tree=true`` significantly increases the memory use of LightGBM
|
||||
- **Note**: setting ``linear_tree=true`` significantly increases the memory use of LightGBM
|
||||
|
||||
- **Note**: if you specify ``monotone_constraints``, constraints will be enforced when choosing the split points, but not when fitting the linear models on leaves
|
||||
- **Note**: if you specify ``monotone_constraints``, constraints will be enforced when choosing the split points, but not when fitting the linear models on leaves
|
||||
|
||||
- ``max_bin`` :raw-html:`<a id="max_bin" title="Permalink to this parameter" href="#max_bin">🔗︎</a>`, default = ``255``, type = int, aliases: ``max_bins``, constraints: ``max_bin > 1``
|
||||
|
||||
|
|
@ -1005,13 +1015,13 @@ Predict Parameters
|
|||
|
||||
- ``pred_early_stop_freq`` :raw-html:`<a id="pred_early_stop_freq" title="Permalink to this parameter" href="#pred_early_stop_freq">🔗︎</a>`, default = ``10``, type = int
|
||||
|
||||
- used only in ``prediction`` task
|
||||
- used only in ``prediction`` task and if ``pred_early_stop=true``
|
||||
|
||||
- the frequency of checking early-stopping prediction
|
||||
|
||||
- ``pred_early_stop_margin`` :raw-html:`<a id="pred_early_stop_margin" title="Permalink to this parameter" href="#pred_early_stop_margin">🔗︎</a>`, default = ``10.0``, type = double
|
||||
|
||||
- used only in ``prediction`` task
|
||||
- used only in ``prediction`` task and if ``pred_early_stop=true``
|
||||
|
||||
- the threshold of margin in early-stopping prediction
|
||||
|
||||
|
|
@ -1151,7 +1161,9 @@ Objective Parameters
|
|||
|
||||
- ``lambdarank_position_bias_regularization`` :raw-html:`<a id="lambdarank_position_bias_regularization" title="Permalink to this parameter" href="#lambdarank_position_bias_regularization">🔗︎</a>`, default = ``0.0``, type = double, constraints: ``lambdarank_position_bias_regularization >= 0.0``
|
||||
|
||||
- used only in ``lambdarank`` application when positional information is provided and position bias is modeled. Larger values reduce the inferred position bias factors.
|
||||
- used only in ``lambdarank`` application when positional information is provided and position bias is modeled
|
||||
|
||||
- larger values reduce the inferred position bias factors
|
||||
|
||||
- *New in version 4.1.0*
|
||||
|
||||
|
|
@ -1263,7 +1275,7 @@ Network Parameters
|
|||
|
||||
- the number of machines for distributed learning application
|
||||
|
||||
- this parameter is needed to be set in both **socket** and **mpi** versions
|
||||
- this parameter is needed to be set in both **socket** and **MPI** versions
|
||||
|
||||
- ``local_listen_port`` :raw-html:`<a id="local_listen_port" title="Permalink to this parameter" href="#local_listen_port">🔗︎</a>`, default = ``12400 (random for Dask-package)``, type = int, aliases: ``local_port``, ``port``, constraints: ``local_listen_port > 0``
|
||||
|
||||
|
|
@ -1292,6 +1304,8 @@ GPU Parameters
|
|||
|
||||
- ``gpu_platform_id`` :raw-html:`<a id="gpu_platform_id" title="Permalink to this parameter" href="#gpu_platform_id">🔗︎</a>`, default = ``-1``, type = int
|
||||
|
||||
- used only with ``gpu`` device type
|
||||
|
||||
- OpenCL platform ID. Usually each GPU vendor exposes one OpenCL platform
|
||||
|
||||
- ``-1`` means the system-wide default platform
|
||||
|
|
@ -1300,7 +1314,7 @@ GPU Parameters
|
|||
|
||||
- ``gpu_device_id`` :raw-html:`<a id="gpu_device_id" title="Permalink to this parameter" href="#gpu_device_id">🔗︎</a>`, default = ``-1``, type = int
|
||||
|
||||
- OpenCL device ID in the specified platform. Each GPU in the selected platform has a unique device ID
|
||||
- OpenCL device ID in the specified platform or CUDA device ID. Each GPU in the selected platform has a unique device ID
|
||||
|
||||
- ``-1`` means the default device in the selected platform
|
||||
|
||||
|
|
@ -1310,13 +1324,13 @@ GPU Parameters
|
|||
|
||||
- set this to ``true`` to use double precision math on GPU (by default single precision is used)
|
||||
|
||||
- **Note**: can be used only in OpenCL implementation, in CUDA implementation only double precision is currently supported
|
||||
- **Note**: can be used only in OpenCL implementation (``device_type="gpu"``), in CUDA implementation only double precision is currently supported
|
||||
|
||||
- ``num_gpu`` :raw-html:`<a id="num_gpu" title="Permalink to this parameter" href="#num_gpu">🔗︎</a>`, default = ``1``, type = int, constraints: ``num_gpu > 0``
|
||||
|
||||
- number of GPUs
|
||||
|
||||
- **Note**: can be used only in CUDA implementation
|
||||
- **Note**: can be used only in CUDA implementation (``device_type="cuda"``)
|
||||
|
||||
.. end params list
|
||||
|
||||
|
|
|
|||
|
|
@ -160,8 +160,8 @@ struct Config {
|
|||
// descl2 = label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
|
||||
// desc = custom objective function (gradients and hessians not computed directly by LightGBM)
|
||||
// descl2 = ``custom``
|
||||
// descl2 = **Note**: Not supported in CLI version
|
||||
// descl2 = must be passed through parameters explicitly in the C API
|
||||
// descl2 = **Note**: cannot be used in CLI version
|
||||
std::string objective = "regression";
|
||||
|
||||
// [no-automatically-extract]
|
||||
|
|
@ -249,7 +249,7 @@ struct Config {
|
|||
// desc = ``gpu`` can be faster than ``cpu`` and works on a wider range of GPUs than CUDA
|
||||
// desc = **Note**: it is recommended to use the smaller ``max_bin`` (e.g. 63) to get the better speed up
|
||||
// desc = **Note**: for the faster speed, GPU uses 32-bit float point to sum up by default, so this may affect the accuracy for some tasks. You can set ``gpu_use_dp=true`` to enable 64-bit float point, but it will slow down the training
|
||||
// desc = **Note**: refer to `Installation Guide <./Installation-Guide.rst#build-gpu-version>`__ to build LightGBM with GPU support
|
||||
// desc = **Note**: refer to `Installation Guide <./Installation-Guide.rst>`__ to build LightGBM with GPU or CUDA support
|
||||
std::string device_type = "cpu";
|
||||
|
||||
// [no-automatically-extract]
|
||||
|
|
@ -350,7 +350,7 @@ struct Config {
|
|||
|
||||
// alias = subsample_freq
|
||||
// desc = frequency for bagging
|
||||
// desc = ``0`` means disable bagging; ``k`` means perform bagging at every ``k`` iteration. Every ``k``-th iteration, LightGBM will randomly select ``bagging_fraction * 100 %`` of the data to use for the next ``k`` iterations
|
||||
// desc = ``0`` means disable bagging; ``k`` means perform bagging at every ``k`` iteration. Every ``k``-th iteration, LightGBM will randomly select ``bagging_fraction * 100%`` of the data to use for the next ``k`` iterations
|
||||
// desc = **Note**: bagging is only effective when ``0.0 < bagging_fraction < 1.0``
|
||||
int bagging_freq = 0;
|
||||
|
||||
|
|
@ -447,7 +447,7 @@ struct Config {
|
|||
double skip_drop = 0.5;
|
||||
|
||||
// desc = used only in ``dart``
|
||||
// desc = set this to ``true``, if you want to use xgboost dart mode
|
||||
// desc = set this to ``true``, if you want to use XGBoost DART mode
|
||||
bool xgboost_dart_mode = false;
|
||||
|
||||
// desc = used only in ``dart``
|
||||
|
|
@ -471,6 +471,7 @@ struct Config {
|
|||
double other_rate = 0.1;
|
||||
|
||||
// check = >0
|
||||
// desc = used for the categorical features
|
||||
// desc = minimal number of data per categorical group
|
||||
int min_data_per_group = 100;
|
||||
|
||||
|
|
@ -491,6 +492,7 @@ struct Config {
|
|||
double cat_smooth = 10.0;
|
||||
|
||||
// check = >0
|
||||
// desc = used for the categorical features
|
||||
// desc = when number of categories of one feature smaller than or equal to ``max_cat_to_onehot``, one-vs-other split algorithm will be used
|
||||
int max_cat_to_onehot = 4;
|
||||
|
||||
|
|
@ -505,7 +507,7 @@ struct Config {
|
|||
// default = None
|
||||
// desc = used for constraints of monotonic features
|
||||
// desc = ``1`` means increasing, ``-1`` means decreasing, ``0`` means non-constraint
|
||||
// desc = 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
|
||||
// desc = you need to specify all features in order. For example, ``mc=-1,0,1`` means decreasing for the 1st feature, non-constraint for the 2nd feature and increasing for the 3rd feature
|
||||
std::vector<int8_t> monotone_constraints;
|
||||
|
||||
// type = enum
|
||||
|
|
@ -513,9 +515,9 @@ struct Config {
|
|||
// options = basic, intermediate, advanced
|
||||
// desc = used only if ``monotone_constraints`` is set
|
||||
// desc = monotone constraints method
|
||||
// descl2 = ``basic``, the most basic monotone constraints method. It does not slow the library at all, but over-constrains the predictions
|
||||
// descl2 = ``intermediate``, a `more advanced method <https://hal.science/hal-02862802/document>`__, which may slow the library very slightly. However, this method is much less constraining than the basic method and should significantly improve the results
|
||||
// descl2 = ``advanced``, an `even more advanced method <https://hal.science/hal-02862802/document>`__, which may slow the library. However, this method is even less constraining than the intermediate method and should again significantly improve the results
|
||||
// descl2 = ``basic``, the most basic monotone constraints method. It does not slow down the training speed at all, but over-constrains the predictions
|
||||
// descl2 = ``intermediate``, a `more advanced method <https://hal.science/hal-02862802/document>`__, which may slow down the training speed very slightly. However, this method is much less constraining than the basic method and should significantly improve the results
|
||||
// descl2 = ``advanced``, an `even more advanced method <https://hal.science/hal-02862802/document>`__, which may slow down the training speed. However, this method is even less constraining than the intermediate method and should again significantly improve the results
|
||||
std::string monotone_constraints_method = "basic";
|
||||
|
||||
// alias = monotone_splits_penalty, ms_penalty, mc_penalty
|
||||
|
|
@ -569,7 +571,7 @@ struct Config {
|
|||
// check = >= 0.0
|
||||
// desc = controls smoothing applied to tree nodes
|
||||
// desc = helps prevent overfitting on leaves with few samples
|
||||
// desc = if set to zero, no smoothing is applied
|
||||
// desc = if ``0.0`` (the default), no smoothing is applied
|
||||
// desc = if ``path_smooth > 0`` then ``min_data_in_leaf`` must be at least ``2``
|
||||
// desc = larger values give stronger regularization
|
||||
// descl2 = the weight of each node is ``w * (n / path_smooth) / (n / path_smooth + 1) + w_p / (n / path_smooth + 1)``, where ``n`` is the number of samples in the node, ``w`` is the optimal node weight to minimise the loss (approximately ``-sum_gradients / sum_hessians``), and ``w_p`` is the weight of the parent node
|
||||
|
|
@ -580,7 +582,7 @@ struct Config {
|
|||
// desc = by default interaction constraints are disabled, to enable them you can specify
|
||||
// descl2 = for CLI, lists separated by commas, e.g. ``[0,1,2],[2,3]``
|
||||
// descl2 = for Python-package, list of lists, e.g. ``[[0, 1, 2], [2, 3]]``
|
||||
// descl2 = for R-package, list of character or numeric vectors, e.g. ``list(c("var1", "var2", "var3"), c("var3", "var4"))`` or ``list(c(1L, 2L, 3L), c(3L, 4L))``. Numeric vectors should use 1-based indexing, where ``1L`` is the first feature, ``2L`` is the second feature, etc
|
||||
// descl2 = for R-package, list of character or numeric vectors, e.g. ``list(c("var1", "var2", "var3"), c("var3", "var4"))`` or ``list(c(1L, 2L, 3L), c(3L, 4L))``. Numeric vectors should use 1-based indexing, where ``1L`` is the first feature, ``2L`` is the second feature, etc.
|
||||
// desc = any two features can only appear in the same branch only if there exists a constraint containing both features
|
||||
std::string interaction_constraints = "";
|
||||
|
||||
|
|
@ -619,24 +621,27 @@ struct Config {
|
|||
// desc = enabling this will discretize (quantize) the gradients and hessians into bins of ``num_grad_quant_bins``
|
||||
// desc = with quantized training, most arithmetics in the training process will be integer operations
|
||||
// desc = gradient quantization can accelerate training, with little accuracy drop in most cases
|
||||
// desc = **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
// desc = **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
// desc = *New in version 4.0.0*
|
||||
bool use_quantized_grad = false;
|
||||
|
||||
// desc = used only if ``use_quantized_grad=true``
|
||||
// desc = number of bins to quantization gradients and hessians
|
||||
// desc = with more bins, the quantized training will be closer to full precision training
|
||||
// desc = **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
// desc = **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
// desc = *New in version 4.0.0*
|
||||
int num_grad_quant_bins = 4;
|
||||
|
||||
// desc = used only if ``use_quantized_grad=true``
|
||||
// desc = whether to renew the leaf values with original gradients when quantized training
|
||||
// desc = renewing is very helpful for good quantized training accuracy for ranking objectives
|
||||
// desc = **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
// desc = **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
// desc = *New in version 4.0.0*
|
||||
bool quant_train_renew_leaf = false;
|
||||
|
||||
// desc = used only if ``use_quantized_grad=true``
|
||||
// desc = whether to use stochastic rounding in gradient quantization
|
||||
// desc = **Note**: can be used only with ``device_type = cpu`` and ``device_type=cuda``
|
||||
// desc = **Note**: works only with ``cpu`` and ``cuda`` device type
|
||||
// desc = *New in version 4.0.0*
|
||||
bool stochastic_rounding = true;
|
||||
|
||||
|
|
@ -650,16 +655,16 @@ struct Config {
|
|||
|
||||
// alias = linear_trees
|
||||
// desc = fit piecewise linear gradient boosting tree
|
||||
// descl2 = tree splits are chosen in the usual way, but the model at each leaf is linear instead of constant
|
||||
// descl2 = the linear model at each leaf includes all the numerical features in that leaf's branch
|
||||
// descl2 = the first tree has constant leaf values
|
||||
// descl2 = categorical features are used for splits as normal but are not used in the linear models
|
||||
// descl2 = missing values should not be encoded as ``0``. Use ``np.nan`` for Python, ``NA`` for the CLI, and ``NA``, ``NA_real_``, or ``NA_integer_`` for R
|
||||
// descl2 = it is recommended to rescale data before training so that features have similar mean and standard deviation
|
||||
// descl2 = **Note**: only works with CPU and ``serial`` tree learner
|
||||
// descl2 = **Note**: ``regression_l1`` objective is not supported with linear tree boosting
|
||||
// descl2 = **Note**: setting ``linear_tree=true`` significantly increases the memory use of LightGBM
|
||||
// descl2 = **Note**: if you specify ``monotone_constraints``, constraints will be enforced when choosing the split points, but not when fitting the linear models on leaves
|
||||
// desc = tree splits are chosen in the usual way, but the model at each leaf is linear instead of constant
|
||||
// desc = the linear model at each leaf includes all the numerical features in that leaf's branch
|
||||
// desc = the first tree has constant leaf values
|
||||
// desc = categorical features are used for splits as normal but are not used in the linear models
|
||||
// desc = missing values should not be encoded as ``0``. Use ``np.nan`` for Python, ``NA`` for the CLI, and ``NA``, ``NA_real_``, or ``NA_integer_`` for R
|
||||
// desc = it is recommended to rescale data before training so that features have similar mean and standard deviation
|
||||
// desc = **Note**: works only with ``cpu`` device type and ``serial`` tree learner
|
||||
// desc = **Note**: ``regression_l1`` objective is not supported with linear tree boosting
|
||||
// desc = **Note**: setting ``linear_tree=true`` significantly increases the memory use of LightGBM
|
||||
// desc = **Note**: if you specify ``monotone_constraints``, constraints will be enforced when choosing the split points, but not when fitting the linear models on leaves
|
||||
bool linear_tree = false;
|
||||
|
||||
// alias = max_bins
|
||||
|
|
@ -862,12 +867,12 @@ struct Config {
|
|||
bool pred_early_stop = false;
|
||||
|
||||
// [no-save]
|
||||
// desc = used only in ``prediction`` task
|
||||
// desc = used only in ``prediction`` task and if ``pred_early_stop=true``
|
||||
// desc = the frequency of checking early-stopping prediction
|
||||
int pred_early_stop_freq = 10;
|
||||
|
||||
// [no-save]
|
||||
// desc = used only in ``prediction`` task
|
||||
// desc = used only in ``prediction`` task and if ``pred_early_stop=true``
|
||||
// desc = the threshold of margin in early-stopping prediction
|
||||
double pred_early_stop_margin = 10.0;
|
||||
|
||||
|
|
@ -985,7 +990,8 @@ struct Config {
|
|||
std::vector<double> label_gain;
|
||||
|
||||
// check = >=0.0
|
||||
// desc = used only in ``lambdarank`` application when positional information is provided and position bias is modeled. Larger values reduce the inferred position bias factors.
|
||||
// desc = used only in ``lambdarank`` application when positional information is provided and position bias is modeled
|
||||
// desc = larger values reduce the inferred position bias factors
|
||||
// desc = *New in version 4.1.0*
|
||||
double lambdarank_position_bias_regularization = 0.0;
|
||||
|
||||
|
|
@ -1075,7 +1081,7 @@ struct Config {
|
|||
// check = >0
|
||||
// alias = num_machine
|
||||
// desc = the number of machines for distributed learning application
|
||||
// desc = this parameter is needed to be set in both **socket** and **mpi** versions
|
||||
// desc = this parameter is needed to be set in both **socket** and **MPI** versions
|
||||
int num_machines = 1;
|
||||
|
||||
// check = >0
|
||||
|
|
@ -1105,23 +1111,24 @@ struct Config {
|
|||
#pragma region GPU Parameters
|
||||
#endif // __NVCC__
|
||||
|
||||
// desc = used only with ``gpu`` device type
|
||||
// desc = OpenCL platform ID. Usually each GPU vendor exposes one OpenCL platform
|
||||
// desc = ``-1`` means the system-wide default platform
|
||||
// desc = **Note**: refer to `GPU Targets <./GPU-Targets.rst#query-opencl-devices-in-your-system>`__ for more details
|
||||
int gpu_platform_id = -1;
|
||||
|
||||
// desc = OpenCL device ID in the specified platform. Each GPU in the selected platform has a unique device ID
|
||||
// desc = OpenCL device ID in the specified platform or CUDA device ID. Each GPU in the selected platform has a unique device ID
|
||||
// desc = ``-1`` means the default device in the selected platform
|
||||
// desc = **Note**: refer to `GPU Targets <./GPU-Targets.rst#query-opencl-devices-in-your-system>`__ for more details
|
||||
int gpu_device_id = -1;
|
||||
|
||||
// desc = set this to ``true`` to use double precision math on GPU (by default single precision is used)
|
||||
// desc = **Note**: can be used only in OpenCL implementation, in CUDA implementation only double precision is currently supported
|
||||
// desc = **Note**: can be used only in OpenCL implementation (``device_type="gpu"``), in CUDA implementation only double precision is currently supported
|
||||
bool gpu_use_dp = false;
|
||||
|
||||
// check = >0
|
||||
// desc = number of GPUs
|
||||
// desc = **Note**: can be used only in CUDA implementation
|
||||
// desc = **Note**: can be used only in CUDA implementation (``device_type="cuda"``)
|
||||
int num_gpu = 1;
|
||||
|
||||
#ifndef __NVCC__
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче