Update Python custom objective demo. (#5981)

demo/guide-python/custom_objective.py

@@ -1,28 +1,28 @@
-import os
-import numpy as np
-import xgboost as xgb
 ###
 # advanced: customized loss function
 #
+import os
+import numpy as np
+import xgboost as xgb
+
 print('start running example to used customized objective function')
 
 CURRENT_DIR = os.path.dirname(__file__)
 dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
 dtest = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.test'))
 
-# note: for customized objective function, we leave objective as default
-# note: what we are getting is margin value in prediction
-# you must know what you are doing
-param = {'max_depth': 2, 'eta': 1}
+# note: what we are getting is margin value in prediction you must know what
+# you are doing
+param = {'max_depth': 2, 'eta': 1, 'objective': 'reg:logistic'}
 watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-num_round = 2
+num_round = 10
 
 
 # user define objective function, given prediction, return gradient and second
 # order gradient this is log likelihood loss
 def logregobj(preds, dtrain):
     labels = dtrain.get_label()
-    preds = 1.0 / (1.0 + np.exp(-preds))
+    preds = 1.0 / (1.0 + np.exp(-preds))  # transform raw leaf weight
     grad = preds - labels
     hess = preds * (1.0 - preds)
     return grad, hess
@@ -31,20 +31,31 @@ def logregobj(preds, dtrain):
 # user defined evaluation function, return a pair metric_name, result
 
 # NOTE: when you do customized loss function, the default prediction value is
-# margin. this may make builtin evaluation metric not function properly for
-# example, we are doing logistic loss, the prediction is score before logistic
-# transformation the builtin evaluation error assumes input is after logistic
-# transformation Take this in mind when you use the customization, and maybe
-# you need write customized evaluation function
+# margin, which means the prediction is score before logistic transformation.
 def evalerror(preds, dtrain):
     labels = dtrain.get_label()
+    preds = 1.0 / (1.0 + np.exp(-preds))  # transform raw leaf weight
     # return a pair metric_name, result. The metric name must not contain a
-    # colon (:) or a space since preds are margin(before logistic
-    # transformation, cutoff at 0)
-    return 'my-error', float(sum(labels != (preds > 0.0))) / len(labels)
+    # colon (:) or a space
+    return 'my-error', float(sum(labels != (preds > 0.5))) / len(labels)
+
 
+py_evals_result = {}
 
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst = xgb.train(param, dtrain, num_round, watchlist, obj=logregobj,
-                feval=evalerror)
+py_params = param.copy()
+py_params.update({'disable_default_eval_metric': True})
+py_logreg = xgb.train(py_params, dtrain, num_round, watchlist, obj=logregobj,
+                      feval=evalerror, evals_result=py_evals_result)
+
+evals_result = {}
+params = param.copy()
+params.update({'eval_metric': 'error'})
+logreg = xgb.train(params, dtrain, num_boost_round=num_round, evals=watchlist,
+                   evals_result=evals_result)
+
+
+for i in range(len(py_evals_result['train']['my-error'])):
+    np.testing.assert_almost_equal(py_evals_result['train']['my-error'],
+                                   evals_result['train']['error'])

tests/python/test_basic_models.py

@@ -197,9 +197,9 @@ def test_boost_from_prediction(self):
         assert np.all(np.abs(predt_2 - predt_1) < 1e-6)
 
     def test_custom_objective(self):
-        param = {'max_depth': 2, 'eta': 1, 'verbosity': 0}
+        param = {'max_depth': 2, 'eta': 1, 'objective': 'reg:logistic'}
         watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-        num_round = 2
+        num_round = 10
 
         def logregobj(preds, dtrain):
             labels = dtrain.get_label()
@@ -210,10 +210,12 @@ def logregobj(preds, dtrain):
 
         def evalerror(preds, dtrain):
             labels = dtrain.get_label()
+            preds = 1.0 / (1.0 + np.exp(-preds))
             return 'error', float(sum(labels != (preds > 0.5))) / len(labels)
 
         # test custom_objective in training
-        bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
+        bst = xgb.train(param, dtrain, num_round, watchlist, obj=logregobj,
+                        feval=evalerror)
         assert isinstance(bst, xgb.core.Booster)
         preds = bst.predict(dtest)
         labels = dtest.get_label()
@@ -230,7 +232,8 @@ def neg_evalerror(preds, dtrain):
             labels = dtrain.get_label()
             return 'error', float(sum(labels == (preds > 0.0))) / len(labels)
 
-        bst2 = xgb.train(param, dtrain, num_round, watchlist, logregobj, neg_evalerror, maximize=True)
+        bst2 = xgb.train(param, dtrain, num_round, watchlist, logregobj,
+                         neg_evalerror, maximize=True)
         preds2 = bst2.predict(dtest)
         err2 = sum(1 for i in range(len(preds2))
                    if int(preds2[i] > 0.5) != labels[i]) / float(len(preds2))