[docs] updated docs about output values (#3037)

python-package/lightgbm/basic.py

@@ -2133,6 +2133,7 @@ class Booster(object):
                 hess : list or numpy 1-D array
                     The value of the second order derivative (Hessian) for each sample point.
 
+            For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
             For multi-class task, the preds is group by class_id first, then group by row_id.
             If you want to get i-th row preds in j-th class, the access way is score[j * num_data + i]
             and you should group grad and hess in this way as well.
@@ -2181,6 +2182,7 @@ class Booster(object):
 
         .. note::
 
+            For binary task, the score is probability of positive class (or margin in case of custom objective).
             For multi-class task, the score is group by class_id first, then group by row_id.
             If you want to get i-th row score in j-th class, the access way is score[j * num_data + i]
             and you should group grad and hess in this way as well.
@@ -2321,6 +2323,7 @@ class Booster(object):
                 is_higher_better : bool
                     Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+            For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
             For multi-class task, the preds is group by class_id first, then group by row_id.
             If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
 
@@ -2367,6 +2370,7 @@ class Booster(object):
                 is_higher_better : bool
                     Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+            For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
             For multi-class task, the preds is group by class_id first, then group by row_id.
             If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
 
@@ -2398,6 +2402,7 @@ class Booster(object):
                 is_higher_better : bool
                     Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+            For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
             For multi-class task, the preds is group by class_id first, then group by row_id.
             If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
 

python-package/lightgbm/engine.py

@@ -50,6 +50,7 @@ def train(params, train_set, num_boost_round=100,
             hess : list or numpy 1-D array
                 The value of the second order derivative (Hessian) for each sample point.
 
+        For binary task, the preds is margin.
         For multi-class task, the preds is group by class_id first, then group by row_id.
         If you want to get i-th row preds in j-th class, the access way is score[j * num_data + i]
         and you should group grad and hess in this way as well.
@@ -70,6 +71,7 @@ def train(params, train_set, num_boost_round=100,
             is_higher_better : bool
                 Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+        For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
         For multi-class task, the preds is group by class_id first, then group by row_id.
         If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
         To ignore the default metric corresponding to the used objective,
@@ -418,6 +420,7 @@ def cv(params, train_set, num_boost_round=100,
             hess : list or numpy 1-D array
                 The value of the second order derivative (Hessian) for each sample point.
 
+        For binary task, the preds is margin.
         For multi-class task, the preds is group by class_id first, then group by row_id.
         If you want to get i-th row preds in j-th class, the access way is score[j * num_data + i]
         and you should group grad and hess in this way as well.
@@ -438,6 +441,7 @@ def cv(params, train_set, num_boost_round=100,
             is_higher_better : bool
                 Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+        For binary task, the preds is probability of positive class (or margin in case of specified ``fobj``).
         For multi-class task, the preds is group by class_id first, then group by row_id.
         If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
         To ignore the default metric corresponding to the used objective,

python-package/lightgbm/sklearn.py

@@ -43,6 +43,7 @@ class _ObjectiveFunctionWrapper(object):
 
         .. note::
 
+            For binary task, the y_pred is margin.
             For multi-class task, the y_pred is group by class_id first, then group by row_id.
             If you want to get i-th row y_pred in j-th class, the access way is y_pred[j * num_data + i]
             and you should group grad and hess in this way as well.
@@ -130,6 +131,7 @@ class _EvalFunctionWrapper(object):
 
         .. note::
 
+            For binary task, the y_pred is probability of positive class (or margin in case of custom ``objective``).
             For multi-class task, the y_pred is group by class_id first, then group by row_id.
             If you want to get i-th row y_pred in j-th class, the access way is y_pred[j * num_data + i].
         """
@@ -292,6 +294,7 @@ class LGBMModel(_LGBMModelBase):
             hess : array-like of shape = [n_samples] or shape = [n_samples * n_classes] (for multi-class task)
                 The value of the second order derivative (Hessian) for each sample point.
 
+        For binary task, the y_pred is margin.
         For multi-class task, the y_pred is group by class_id first, then group by row_id.
         If you want to get i-th row y_pred in j-th class, the access way is y_pred[j * num_data + i]
         and you should group grad and hess in this way as well.
@@ -477,6 +480,7 @@ class LGBMModel(_LGBMModelBase):
             is_higher_better : bool
                 Is eval result higher better, e.g. AUC is ``is_higher_better``.
 
+        For binary task, the y_pred is probability of positive class (or margin in case of custom ``objective``).
         For multi-class task, the y_pred is group by class_id first, then group by row_id.
         If you want to get i-th row y_pred in j-th class, the access way is y_pred[j * num_data + i].
         """