Skip to content

GitLab

Unverified Commit e95d5ab8 authored by Nikita Titov's avatar Nikita Titov Committed by GitHub
Browse files

add param aliases from scikit-learn (#4637)

parent 2543c8ed
Hide whitespace changes
Inline Side-by-side
Showing with 41 additions and 21 deletions
R-package/R/aliases.R
View file @ e95d5ab8
......@@ -18,6 +18,7 @@
, "cat_feature"
, "categorical_column"
, "cat_column"
, "categorical_features"
)
, "data_random_seed" = c(
"data_random_seed"
......@@ -61,7 +62,10 @@
"linear_tree"
, "linear_trees"
)
, "max_bin" = "max_bin"
, "max_bin" = c(
"max_bin"
, "max_bins"
)
, "max_bin_by_feature" = "max_bin_by_feature"
, "min_data_in_bin" = "min_data_in_bin"
, "pre_partition" = c(
......@@ -111,6 +115,7 @@
, "num_rounds"
, "num_boost_round"
, "n_estimators"
, "max_iter"
)
)
return(c(learning_params, .DATASET_PARAMETERS()))
......
docs/Parameters.rst
View file @ e95d5ab8
......@@ -73,7 +73,7 @@ Core Parameters
- **Note**: can be used only in CLI version; for language-specific packages you can use the correspondent functions
- ``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``, ``gamma``, ``tweedie``, ``binary``, ``multiclass``, ``multiclassova``, ``cross_entropy``, ``cross_entropy_lambda``, ``lambdarank``, ``rank_xendcg``, 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``, ``gamma``, ``tweedie``, ``binary``, ``multiclass``, ``multiclassova``, ``cross_entropy``, ``cross_entropy_lambda``, ``lambdarank``, ``rank_xendcg``, aliases: ``objective_type``, ``app``, ``application``, ``loss``
- regression application
......@@ -153,7 +153,7 @@ Core Parameters
- **Note**: can be used only in CLI version
- ``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``, ``n_iter``, ``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``, ``n_iter``, ``num_tree``, ``num_trees``, ``num_round``, ``num_rounds``, ``num_boost_round``, ``n_estimators``, ``max_iter``, constraints: ``num_iterations >= 0``
- number of boosting iterations
......@@ -165,7 +165,7 @@ Core Parameters
- in ``dart``, it also affects on normalization weights of dropped trees
- ``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``, ``max_leaves``, ``max_leaf``, constraints: ``1 < num_leaves <= 131072``
- ``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``, ``max_leaves``, ``max_leaf``, ``max_leaf_nodes``, constraints: ``1 < num_leaves <= 131072``
- max number of leaves in one tree
......@@ -282,7 +282,7 @@ Learning Control Parameters
- ``<= 0`` means no limit
- ``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``
- ``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``, ``min_samples_leaf``, constraints: ``min_data_in_leaf >= 0``
- minimal number of data in one leaf. Can be used to deal with over-fitting
......@@ -402,11 +402,11 @@ Learning Control Parameters
- the final max output of leaves is ``learning_rate * max_delta_step``
- ``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``
- ``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``, ``l1_regularization``, constraints: ``lambda_l1 >= 0.0``
- L1 regularization
- ``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``, ``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``, ``lambda``, ``l2_regularization``, constraints: ``lambda_l2 >= 0.0``
- L2 regularization
......@@ -504,7 +504,7 @@ Learning Control Parameters
- set this to larger value for more accurate result, but it will slow down the training speed
- ``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``
- ``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``, ``monotonic_cst``
- used for constraints of monotonic features
......@@ -672,7 +672,7 @@ Dataset Parameters
- **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">&#x1F517;&#xFE0E;</a>`, 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, aliases: ``max_bins``, constraints: ``max_bin > 1``
- max number of bins that feature values will be bucketed in
......@@ -806,7 +806,7 @@ Dataset Parameters
- **Note**: despite the fact that specified columns will be completely ignored during the training, they still should have a valid format allowing LightGBM to load file successfully
- ``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``
- ``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``, ``categorical_features``
- used to specify categorical features
......
include/LightGBM/config.h
View file @ e95d5ab8
......@@ -109,7 +109,7 @@ struct Config {
// [doc-only]
// type = enum
// options = regression, regression_l1, huber, fair, poisson, quantile, mape, gamma, tweedie, binary, multiclass, multiclassova, cross_entropy, cross_entropy_lambda, lambdarank, rank_xendcg
// alias = objective_type, app, application
// alias = objective_type, app, application, loss
// desc = regression application
// descl2 = ``regression``, L2 loss, aliases: ``regression_l2``, ``l2``, ``mean_squared_error``, ``mse``, ``l2_root``, ``root_mean_squared_error``, ``rmse``
// descl2 = ``regression_l1``, L1 loss, aliases: ``l1``, ``mean_absolute_error``, ``mae``
......@@ -161,7 +161,7 @@ struct Config {
// desc = **Note**: can be used only in CLI version
std::vector<std::string> valid;
// alias = num_iteration, n_iter, num_tree, num_trees, num_round, num_rounds, num_boost_round, n_estimators
// alias = num_iteration, n_iter, num_tree, num_trees, num_round, num_rounds, num_boost_round, n_estimators, max_iter
// check = >=0
// desc = number of boosting iterations
// desc = **Note**: internally, LightGBM constructs ``num_class * num_iterations`` trees for multi-class classification problems
......@@ -174,7 +174,7 @@ struct Config {
double learning_rate = 0.1;
// default = 31
// alias = num_leaf, max_leaves, max_leaf
// alias = num_leaf, max_leaves, max_leaf, max_leaf_nodes
// check = >1
// check = <=131072
// desc = max number of leaves in one tree
......@@ -261,7 +261,7 @@ struct Config {
// desc = ``<= 0`` means no limit
int max_depth = -1;
// alias = min_data_per_leaf, min_data, min_child_samples
// alias = min_data_per_leaf, min_data, min_child_samples, min_samples_leaf
// check = >=0
// desc = minimal number of data in one leaf. Can be used to deal with over-fitting
// desc = **Note**: this is an approximation based on the Hessian, so occasionally you may observe splits which produce leaf nodes that have less than this many observations
......@@ -360,12 +360,12 @@ struct Config {
// desc = the final max output of leaves is ``learning_rate * max_delta_step``
double max_delta_step = 0.0;
// alias = reg_alpha
// alias = reg_alpha, l1_regularization
// check = >=0.0
// desc = L1 regularization
double lambda_l1 = 0.0;
// alias = reg_lambda, lambda
// alias = reg_lambda, lambda, l2_regularization
// check = >=0.0
// desc = L2 regularization
double lambda_l2 = 0.0;
......@@ -453,7 +453,7 @@ struct Config {
int top_k = 20;
// type = multi-int
// alias = mc, monotone_constraint
// alias = mc, monotone_constraint, monotonic_cst
// default = None
// desc = used for constraints of monotonic features
// desc = ``1`` means increasing, ``-1`` means decreasing, ``0`` means non-constraint
......@@ -586,6 +586,7 @@ struct Config {
// 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
bool linear_tree = false;
// alias = max_bins
// check = >1
// desc = max number of bins that feature values will be bucketed in
// desc = small number of bins may reduce training accuracy but may increase general power (deal with over-fitting)
......@@ -691,7 +692,7 @@ struct Config {
std::string ignore_column = "";
// type = multi-int or string
// alias = cat_feature, categorical_column, cat_column
// alias = cat_feature, categorical_column, cat_column, categorical_features
// desc = used to specify categorical features
// desc = use number for index, e.g. ``categorical_feature=0,1,2`` means column\_0, column\_1 and column\_2 are categorical features
// desc = add a prefix ``name:`` for column name, e.g. ``categorical_feature=name:c1,c2,c3`` means c1, c2 and c3 are categorical features
......
python-package/lightgbm/basic.py
View file @ e95d5ab8
......@@ -331,7 +331,8 @@ class _ConfigAliases:
"categorical_feature": {"categorical_feature",
"cat_feature",
"categorical_column",
"cat_column"},
"cat_column",
"categorical_features"},
"data_random_seed": {"data_random_seed",
"data_seed"},
"early_stopping_round": {"early_stopping_round",
......@@ -371,6 +372,8 @@ class _ConfigAliases:
"machines": {"machines",
"workers",
"nodes"},
"max_bin": {"max_bin",
"max_bins"},
"metric": {"metric",
"metrics",
"metric_types"},
......@@ -384,7 +387,8 @@ class _ConfigAliases:
"num_round",
"num_rounds",
"num_boost_round",
"n_estimators"},
"n_estimators",
"max_iter"},
"num_machines": {"num_machines",
"num_machine"},
"num_threads": {"num_threads",
......@@ -395,7 +399,8 @@ class _ConfigAliases:
"objective": {"objective",
"objective_type",
"app",
"application"},
"application",
"loss"},
"pre_partition": {"pre_partition",
"is_pre_partition"},
"tree_learner": {"tree_learner",
......
src/io/config_auto.cpp
View file @ e95d5ab8
......@@ -14,6 +14,7 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"objective_type", "objective"},
{"app", "objective"},
{"application", "objective"},
{"loss", "objective"},
{"boosting_type", "boosting"},
{"boost", "boosting"},
{"train", "data"},
......@@ -34,11 +35,13 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"num_rounds", "num_iterations"},
{"num_boost_round", "num_iterations"},
{"n_estimators", "num_iterations"},
{"max_iter", "num_iterations"},
{"shrinkage_rate", "learning_rate"},
{"eta", "learning_rate"},
{"num_leaf", "num_leaves"},
{"max_leaves", "num_leaves"},
{"max_leaf", "num_leaves"},
{"max_leaf_nodes", "num_leaves"},
{"tree", "tree_learner"},
{"tree_type", "tree_learner"},
{"tree_learner_type", "tree_learner"},
......@@ -53,6 +56,7 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"min_data_per_leaf", "min_data_in_leaf"},
{"min_data", "min_data_in_leaf"},
{"min_child_samples", "min_data_in_leaf"},
{"min_samples_leaf", "min_data_in_leaf"},
{"min_sum_hessian_per_leaf", "min_sum_hessian_in_leaf"},
{"min_sum_hessian", "min_sum_hessian_in_leaf"},
{"min_hessian", "min_sum_hessian_in_leaf"},
......@@ -79,13 +83,16 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"max_tree_output", "max_delta_step"},
{"max_leaf_output", "max_delta_step"},
{"reg_alpha", "lambda_l1"},
{"l1_regularization", "lambda_l1"},
{"reg_lambda", "lambda_l2"},
{"lambda", "lambda_l2"},
{"l2_regularization", "lambda_l2"},
{"min_split_gain", "min_gain_to_split"},
{"rate_drop", "drop_rate"},
{"topk", "top_k"},
{"mc", "monotone_constraints"},
{"monotone_constraint", "monotone_constraints"},
{"monotonic_cst", "monotone_constraints"},
{"monotone_constraining_method", "monotone_constraints_method"},
{"mc_method", "monotone_constraints_method"},
{"monotone_splits_penalty", "monotone_penalty"},
......@@ -106,6 +113,7 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"model_out", "output_model"},
{"save_period", "snapshot_freq"},
{"linear_trees", "linear_tree"},
{"max_bins", "max_bin"},
{"subsample_for_bin", "bin_construct_sample_cnt"},
{"data_seed", "data_random_seed"},
{"is_sparse", "is_enable_sparse"},
......@@ -129,6 +137,7 @@ const std::unordered_map<std::string, std::string>& Config::alias_table() {
{"cat_feature", "categorical_feature"},
{"categorical_column", "categorical_feature"},
{"cat_column", "categorical_feature"},
{"categorical_features", "categorical_feature"},
{"is_save_binary", "save_binary"},
{"is_save_binary_file", "save_binary"},
{"is_predict_raw_score", "predict_raw_score"},
......
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