| Higgs | Binary classification | `link <https://archive.ics.uci.edu/ml/datasets/HIGGS>`__ | 10,500,000 | 28 | last 500,000 samples were used as test set |
| MS LTR | Learning to rank | `link <https://www.microsoft.com/en-us/research/project/mslr/>`__ | 2,270,296 | 137 | {S1,S2,S3} as train set, {S5} as test set |
| Expo | Binary classification | `link <http://stat-computing.org/dataexpo/2009/>`__ | 11,000,000 | 700 | last 1,000,000 samples were used as test set |
| Allstate | Binary classification | `link <https://www.kaggle.com/c/ClaimPredictionChallenge>`__ | 13,184,290 | 4228 | last 1,000,000 samples were used as test set |
| Higgs | Binary classification | `link <https://archive.ics.uci.edu/dataset/280/higgs>`__ | 10,500,000 | 28 | last 500,000 samples were used as test set |
| MS LTR | Learning to rank | `link <https://www.microsoft.com/en-us/research/project/mslr/>`__ | 2,270,296 | 137 | {S1,S2,S3} as train set, {S5} as test set |
| Expo | Binary classification | `link <https://community.amstat.org/jointscsg-section/dataexpo/dataexpo2009>`__ | 11,000,000 | 700 | last 1,000,000 samples were used as test set |
| Allstate | Binary classification | `link <https://www.kaggle.com/c/ClaimPredictionChallenge>`__ | 13,184,290 | 4228 | last 1,000,000 samples were used as test set |
- ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
- ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper_files/paper/2006/file/af44c4c56f385c43f2529f9b1b018f6a-Paper.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
- ``basic``, the most basic monotone constraints method. It does not slow the library at all, but over-constrains the predictions
- ``intermediate``, a `more advanced method <https://hal.archives-ouvertes.fr/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 the library 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.archives-ouvertes.fr/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 the library. 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``
- used only if ``monotone_constraints`` is set
- `monotone penalty <https://hal.archives-ouvertes.fr/hal-02862802/document>`__: a penalization parameter X forbids any monotone splits on the first X (rounded down) level(s) of the tree. The penalty applied to monotone splits on a given depth is a continuous, increasing function the penalization parameter
- `monotone penalty <https://hal.science/hal-02862802/document>`__: a penalization parameter X forbids any monotone splits on the first X (rounded down) level(s) of the tree. The penalty applied to monotone splits on a given depth is a continuous, increasing function the penalization parameter
- if ``0.0`` (the default), no penalization is applied
...
...
@@ -564,7 +564,7 @@ Learning Control Parameters
- **Note**: the forced split logic will be ignored, if the split makes gain worse
- see `this file <https://github.com/microsoft/LightGBM/tree/master/examples/binary_classification/forced_splits.json>`__ as an example
- see `this file <https://github.com/microsoft/LightGBM/blob/master/examples/binary_classification/forced_splits.json>`__ as an example
- ``refit_decay_rate`` :raw-html:`<a id="refit_decay_rate" title="Permalink to this parameter" href="#refit_decay_rate">🔗︎</a>`, default = ``0.9``, type = double, constraints: ``0.0 <= refit_decay_rate <= 1.0``
...
...
@@ -770,7 +770,7 @@ Dataset Parameters
- ``enable_bundle`` :raw-html:`<a id="enable_bundle" title="Permalink to this parameter" href="#enable_bundle">🔗︎</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>`__
- 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_files/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
- **Note**: disabling this may cause the slow training speed for sparse datasets
...
...
@@ -894,7 +894,7 @@ Dataset Parameters
- ``.json`` file should contain an array of objects, each containing the word ``feature`` (integer feature index) and ``bin_upper_bound`` (array of thresholds for binning)
- see `this file <https://github.com/microsoft/LightGBM/tree/master/examples/regression/forced_bins.json>`__ as an example
- see `this file <https://github.com/microsoft/LightGBM/blob/master/examples/regression/forced_bins.json>`__ as an example
- ``save_binary`` :raw-html:`<a id="save_binary" title="Permalink to this parameter" href="#save_binary">🔗︎</a>`, default = ``false``, type = bool, aliases: ``is_save_binary``, ``is_save_binary_file``
...
...
@@ -961,7 +961,7 @@ Predict Parameters
- produces ``#features + 1`` values where the last value is the expected value of the model output over the training data
- **Note**: if you want to get more explanation for your model's predictions using SHAP values like SHAP interaction values, you can install `shap package <https://github.com/slundberg/shap>`__
- **Note**: if you want to get more explanation for your model's predictions using SHAP values like SHAP interaction values, you can install `shap package <https://github.com/shap>`__
- **Note**: unlike the shap package, with ``predict_contrib`` we return a matrix with an extra column, where the last column is the expected value
// descl2 = ``cross_entropy_lambda``, alternative parameterization of cross-entropy, aliases: ``xentlambda``
// descl2 = label is anything in interval [0, 1]
// desc = ranking application
// descl2 = ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
// descl2 = ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper_files/paper/2006/file/af44c4c56f385c43f2529f9b1b018f6a-Paper.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
// descl2 = ``rank_xendcg`` is faster than and achieves the similar performance as ``lambdarank``
// descl2 = label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
...
...
@@ -501,14 +501,14 @@ struct Config {
// 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.archives-ouvertes.fr/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.archives-ouvertes.fr/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 = ``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
std::stringmonotone_constraints_method="basic";
// alias = monotone_splits_penalty, ms_penalty, mc_penalty
// check = >=0.0
// desc = used only if ``monotone_constraints`` is set
// desc = `monotone penalty <https://hal.archives-ouvertes.fr/hal-02862802/document>`__: a penalization parameter X forbids any monotone splits on the first X (rounded down) level(s) of the tree. The penalty applied to monotone splits on a given depth is a continuous, increasing function the penalization parameter
// desc = `monotone penalty <https://hal.science/hal-02862802/document>`__: a penalization parameter X forbids any monotone splits on the first X (rounded down) level(s) of the tree. The penalty applied to monotone splits on a given depth is a continuous, increasing function the penalization parameter
// desc = if ``0.0`` (the default), no penalization is applied
doublemonotone_penalty=0.0;
...
...
@@ -524,7 +524,7 @@ struct Config {
// desc = ``.json`` file can be arbitrarily nested, and each split contains ``feature``, ``threshold`` fields, as well as ``left`` and ``right`` fields representing subsplits
// desc = categorical splits are forced in a one-hot fashion, with ``left`` representing the split containing the feature value and ``right`` representing other values
// desc = **Note**: the forced split logic will be ignored, if the split makes gain worse
// desc = see `this file <https://github.com/microsoft/LightGBM/tree/master/examples/binary_classification/forced_splits.json>`__ as an example
// desc = see `this file <https://github.com/microsoft/LightGBM/blob/master/examples/binary_classification/forced_splits.json>`__ as an example
std::stringforcedsplits_filename="";
// check = >=0.0
...
...
@@ -683,7 +683,7 @@ struct Config {
boolis_enable_sparse=true;
// alias = is_enable_bundle, bundle
// desc = 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>`__
// desc = 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_files/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
// desc = **Note**: disabling this may cause the slow training speed for sparse datasets
boolenable_bundle=true;
...
...
@@ -770,7 +770,7 @@ struct Config {
// desc = path to a ``.json`` file that specifies bin upper bounds for some or all features
// desc = ``.json`` file should contain an array of objects, each containing the word ``feature`` (integer feature index) and ``bin_upper_bound`` (array of thresholds for binning)
// desc = see `this file <https://github.com/microsoft/LightGBM/tree/master/examples/regression/forced_bins.json>`__ as an example
// desc = see `this file <https://github.com/microsoft/LightGBM/blob/master/examples/regression/forced_bins.json>`__ as an example
std::stringforcedbins_filename="";
// [no-save]
...
...
@@ -826,7 +826,7 @@ struct Config {
// desc = used only in ``prediction`` task
// desc = set this to ``true`` to estimate `SHAP values <https://arxiv.org/abs/1706.06060>`__, which represent how each feature contributes to each prediction
// desc = produces ``#features + 1`` values where the last value is the expected value of the model output over the training data
// desc = **Note**: if you want to get more explanation for your model's predictions using SHAP values like SHAP interaction values, you can install `shap package <https://github.com/slundberg/shap>`__
// desc = **Note**: if you want to get more explanation for your model's predictions using SHAP values like SHAP interaction values, you can install `shap package <https://github.com/shap>`__
// desc = **Note**: unlike the shap package, with ``predict_contrib`` we return a matrix with an extra column, where the last column is the expected value
// desc = **Note**: this feature is not implemented for linear trees
