[python][R-package][docs] fix support of XE_NDCG_MART obj in language wrappers and docs (#2726)

R-package/R/utils.R

@@ -209,6 +209,11 @@ lgb.check.obj <- function(params, obj) {
     , "mape"
     , "gamma"
     , "tweedie"
+    , "rank_xendcg"
+    , "xendcg"
+    , "xe_ndcg"
+    , "xe_ndcg_mart"
+    , "xendcg_mart"
   )
 
   # Check whether the objective is empty or not, and take it from params if needed

docs/Parameters.rst

@@ -91,17 +91,13 @@ Core Parameters
 
       -  label is anything in interval [0, 1]
 
-   -  ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ application
+   -  ranking application
 
-      -  label should be ``int`` type in lambdarank tasks, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
+      -  ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ objective. `label_gain <#objective-parameters>`__ 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``
 
-      -  `label_gain <#objective-parameters>`__ can be used to set the gain (weight) of ``int`` label
+      -  ``rank_xendcg``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function. To obtain reproducible results, you should disable parallelism by setting ``num_threads`` to 1, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
 
-      -  all values in ``label`` must be smaller than number of elements in ``label_gain``
-
-   -  ``rank_xendcg``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
-
-      -  to obtain reproducible results, you should disable parallelism by setting ``num_threads`` to 1
+      -  label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
 
 -  ``boosting`` :raw-html:`<a id="boosting" title="Permalink to this parameter" href="#boosting">&#x1F517;&#xFE0E;</a>`, default = ``gbdt``, type = enum, options: ``gbdt``, ``rf``, ``dart``, ``goss``, aliases: ``boosting_type``, ``boost``
 
@@ -878,10 +874,10 @@ Objective Parameters
 
 -  ``objective_seed`` :raw-html:`<a id="objective_seed" title="Permalink to this parameter" href="#objective_seed">&#x1F517;&#xFE0E;</a>`, default = ``5``, type = int
 
-   -  random seed for objectives
-
    -  used only in the ``rank_xendcg`` objective
 
+   -  random seed for objectives
+
 Metric Parameters
 -----------------
 
@@ -915,7 +911,7 @@ Metric Parameters
 
       -  ``tweedie``, negative log-likelihood for **Tweedie** regression
 
-      -  ``ndcg``, `NDCG <https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG>`__, aliases: ``lambdarank``
+      -  ``ndcg``, `NDCG <https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG>`__, aliases: ``lambdarank``, ``rank_xendcg``, ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
 
       -  ``map``, `MAP <https://makarandtapaswi.wordpress.com/2012/07/02/intuition-behind-average-precision-and-map/>`__, aliases: ``mean_average_precision``
 
@@ -1079,7 +1075,7 @@ Also, you can include weight column in your data file. Please refer to the ``wei
 Query Data
 ~~~~~~~~~~
 
-For LambdaRank learning, it needs query information for training data.
+For learning to rank, it needs query information for training data.
 LightGBM uses an additional file to store query data, like the following:
 
 ::

include/LightGBM/config.h

@@ -123,12 +123,10 @@ struct Config {
   // descl2 = ``cross_entropy``, objective function for cross-entropy (with optional linear weights), aliases: ``xentropy``
   // descl2 = ``cross_entropy_lambda``, alternative parameterization of cross-entropy, aliases: ``xentlambda``
   // descl2 = label is anything in interval [0, 1]
-  // desc = ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ application
-  // descl2 = label should be ``int`` type in lambdarank tasks, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
-  // descl2 = `label_gain <#objective-parameters>`__ can be used to set the gain (weight) of ``int`` label
-  // descl2 = all values in ``label`` must be smaller than number of elements in ``label_gain``
-  // desc = ``rank_xendcg``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
-  // descl2 = to obtain reproducible results, you should disable parallelism by setting ``num_threads`` to 1
+  // desc = ranking application
+  // descl2 = ``lambdarank``, `lambdarank <https://papers.nips.cc/paper/2971-learning-to-rank-with-nonsmooth-cost-functions.pdf>`__ objective. `label_gain <#objective-parameters>`__ 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``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function. To obtain reproducible results, you should disable parallelism by setting ``num_threads`` to 1, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
+  // descl2 = label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
   std::string objective = "regression";
 
   // [doc-only]
@@ -763,8 +761,8 @@ struct Config {
   // desc = separate by ``,``
   std::vector<double> label_gain;
 
-  // desc = random seed for objectives
   // desc = used only in the ``rank_xendcg`` objective
+  // desc = random seed for objectives
   int objective_seed = 5;
 
   #pragma endregion
@@ -789,7 +787,7 @@ struct Config {
   // descl2 = ``gamma``, negative log-likelihood for **Gamma** regression
   // descl2 = ``gamma_deviance``, residual deviance for **Gamma** regression
   // descl2 = ``tweedie``, negative log-likelihood for **Tweedie** regression
-  // descl2 = ``ndcg``, `NDCG <https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG>`__, aliases: ``lambdarank``
+  // descl2 = ``ndcg``, `NDCG <https://en.wikipedia.org/wiki/Discounted_cumulative_gain#Normalized_DCG>`__, aliases: ``lambdarank``, ``rank_xendcg``, ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
   // descl2 = ``map``, `MAP <https://makarandtapaswi.wordpress.com/2012/07/02/intuition-behind-average-precision-and-map/>`__, aliases: ``mean_average_precision``
   // descl2 = ``auc``, `AUC <https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve>`__
   // descl2 = ``binary_logloss``, `log loss <https://en.wikipedia.org/wiki/Cross_entropy>`__, aliases: ``binary``

python-package/lightgbm/engine.py

@@ -314,10 +314,12 @@ def _make_n_folds(full_data, folds, nfold, params, seed, fpreproc=None, stratifi
                 flatted_group = np.zeros(num_data, dtype=np.int32)
             folds = folds.split(X=np.zeros(num_data), y=full_data.get_label(), groups=flatted_group)
     else:
-        if any(params.get(obj_alias, "") == "lambdarank" for obj_alias in _ConfigAliases.get("objective")):
+        if any(params.get(obj_alias, "") in {"lambdarank", "rank_xendcg", "xendcg",
+                                             "xe_ndcg", "xe_ndcg_mart", "xendcg_mart"}
+               for obj_alias in _ConfigAliases.get("objective")):
             if not SKLEARN_INSTALLED:
-                raise LightGBMError('Scikit-learn is required for lambdarank cv.')
-            # lambdarank task, split according to groups
+                raise LightGBMError('Scikit-learn is required for ranking cv.')
+            # ranking task, split according to groups
             group_info = np.array(full_data.get_group(), dtype=np.int32, copy=False)
             flatted_group = np.repeat(range_(len(group_info)), repeats=group_info)
             group_kfold = _LGBMGroupKFold(n_splits=nfold)