Merge pull request #591 from terrytangyuan/test

More test coverage for Python package

CHANGES.md

@@ -42,6 +42,7 @@ on going at master
 * Python module now throw exception instead of crash terminal when a parameter error happens.
 * Python module now has importance plot and tree plot functions.
 * Python module now accepts different learning rates for each boosting round.
+* Additional parameters added for sklearn wrapper
 * Java api is ready for use
 * Added more test cases and continuous integration to make each build more robust
 * Improvements in sklearn compatible module

tests/python/test_early_stopping.py

@@ -2,18 +2,31 @@ import xgboost as xgb
 import numpy as np
 from sklearn.datasets import load_digits
 from sklearn.cross_validation import KFold, train_test_split
+import unittest
 
 rng = np.random.RandomState(1994)
 
-def test_early_stopping_nonparallel():
-	# digits = load_digits(2)
-	# X = digits['data']
-	# y = digits['target']
-	# X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
-	# clf = xgb.XGBClassifier()
-	# clf.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
-	#         eval_set=[(X_test, y_test)])
-	print("This test will be re-visited later. ")
+class TestEarlyStopping(unittest.TestCase):
+
+	def test_early_stopping_nonparallel(self):
+		digits = load_digits(2)
+		X = digits['data']
+		y = digits['target']
+		X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+		clf1 = xgb.XGBClassifier()
+		clf1.fit(X_train, y_train, early_stopping_rounds=5, eval_metric="auc",
+		        eval_set=[(X_test, y_test)])
+		clf2 = xgb.XGBClassifier()
+		clf2.fit(X_train, y_train, early_stopping_rounds=4, eval_metric="auc",
+		        eval_set=[(X_test, y_test)])
+		# should be the same
+		assert clf1.best_score == clf2.best_score
+		assert clf1.best_score != 1
+		# check overfit
+		clf3 = xgb.XGBClassifier()
+		clf3.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
+		        eval_set=[(X_test, y_test)])
+		assert clf3.best_score == 1
 
 # TODO: parallel test for early stopping
 # TODO: comment out for now. Will re-visit later

tests/python/test_with_sklearn.py

@@ -27,6 +27,10 @@ def test_multiclass_classification():
 	for train_index, test_index in kf:
 	    xgb_model = xgb.XGBClassifier().fit(X[train_index],y[train_index])
 	    preds = xgb_model.predict(X[test_index])
+		# test other params in XGBClassifier().fit
+	    preds2 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=3)
+	    preds3 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=0)
+	    preds4 = xgb_model.predict(X[test_index], output_margin=False, ntree_limit=3)
 	    labels = y[test_index]
 	    err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
 	assert err < 0.4
@@ -39,8 +43,12 @@ def test_boston_housing_regression():
 	for train_index, test_index in kf:
 	    xgb_model = xgb.XGBRegressor().fit(X[train_index],y[train_index])
 	    preds = xgb_model.predict(X[test_index])
+	    # test other params in XGBRegressor().fit
+	    preds2 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=3)
+	    preds3 = xgb_model.predict(X[test_index], output_margin=True, ntree_limit=0)
+	    preds4 = xgb_model.predict(X[test_index], output_margin=False, ntree_limit=3)
 	    labels = y[test_index]
-	assert mean_squared_error(preds, labels) < 15
+	assert mean_squared_error(preds, labels) < 25
 
 def test_parameter_tuning():
 	boston = load_boston()
@@ -54,4 +62,3 @@ def test_parameter_tuning():
 	assert clf.best_score_ < 0.7
 	assert clf.best_params_ == {'n_estimators': 100, 'max_depth': 4}
 
-