Merge pull request dmlc#528 from terrytangyuan/test

More Unit Tests for Python Package

CONTRIBUTORS.md

@@ -33,8 +33,9 @@ List of Contributors
   - Skipper is the major contributor to the scikit-learn module of xgboost.
 * [Zygmunt Zając](https://github.com/zygmuntz)
   - Zygmunt is the master behind the early stopping feature frequently used by kagglers.
-* [Ajinkya Kale](https://github.com/ajkl)
 * [Yuan Tang](https://github.com/terrytangyuan)
+  - Yuan is the major contributor to unit tests in R and Python. 
+* [Ajinkya Kale](https://github.com/ajkl)
 * [Boliang Chen](https://github.com/cblsjtu)
 * [Vadim Khotilovich](https://github.com/khotilov)
 * [Yangqing Men](https://github.com/yanqingmen)

tests/python/test_basic.py

@@ -5,6 +5,7 @@
 
 
 dpath = 'demo/data/'
+rng = np.random.RandomState(1994)
 
 class TestBasic(unittest.TestCase):
 

tests/python/test_early_stopping.py

@@ -0,0 +1,19 @@
+import xgboost as xgb
+import numpy as np
+from sklearn.datasets import load_digits
+from sklearn.cross_validation import KFold, train_test_split
+
+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. ")
+
+# TODO: parallel test for early stopping
+# TODO: comment out for now. Will re-visit later

tests/python/test_models.py

@@ -5,6 +5,8 @@
 dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
 dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
 
+rng = np.random.RandomState(1994)
+
 def test_glm():
 	param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear', 'alpha': 0.0001, 'lambda': 1 }
 	watchlist  = [(dtest,'eval'), (dtrain,'train')]
@@ -29,11 +31,32 @@ def logregobj(preds, dtrain):
 	def evalerror(preds, dtrain):
 		labels = dtrain.get_label()
 		return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
+
+	# test custom_objective in training
 	bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
 	assert isinstance(bst, xgb.core.Booster)
 	preds = bst.predict(dtest)
 	labels = dtest.get_label()
 	err = sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) / float(len(preds))
 	assert err < 0.1
 
+	# test custom_objective in cross-validation
+	xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
+       obj = logregobj, feval=evalerror)
+
+def test_fpreproc():
+	param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+	num_round = 2
+	def fpreproc(dtrain, dtest, param):
+		label = dtrain.get_label()
+		ratio = float(np.sum(label == 0)) / np.sum(label==1)
+		param['scale_pos_weight'] = ratio
+		return (dtrain, dtest, param)
+	xgb.cv(param, dtrain, num_round, nfold=5,
+       metrics={'auc'}, seed = 0, fpreproc = fpreproc)
 
+def test_show_stdv():
+	param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
+	num_round = 2
+	xgb.cv(param, dtrain, num_round, nfold=5,
+       metrics={'error'}, seed = 0, show_stdv = False)

tests/python/test_with_sklearn.py

@@ -0,0 +1,57 @@
+import xgboost as xgb
+import numpy as np
+from sklearn.cross_validation import KFold, train_test_split
+from sklearn.metrics import mean_squared_error
+from sklearn.grid_search import GridSearchCV
+from sklearn.datasets import load_iris, load_digits, load_boston
+
+rng = np.random.RandomState(1994)
+
+def test_binary_classification():
+	digits = load_digits(2)
+	y = digits['target']
+	X = digits['data']
+	kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
+	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])
+	    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 < 0.1
+
+def test_multiclass_classification():
+	iris = load_iris()
+	y = iris['target']
+	X = iris['data']
+	kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
+	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])
+	    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
+
+def test_boston_housing_regression():
+	boston = load_boston()
+	y = boston['target']
+	X = boston['data']
+	kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
+	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])
+	    labels = y[test_index]
+	assert mean_squared_error(preds, labels) < 15
+
+def test_parameter_tuning():
+	boston = load_boston()
+	y = boston['target']
+	X = boston['data']
+	xgb_model = xgb.XGBRegressor()
+	clf = GridSearchCV(xgb_model,
+	                   {'max_depth': [2,4,6],
+	                    'n_estimators': [50,100,200]}, verbose=1)
+	clf.fit(X,y)
+	assert clf.best_score_ < 0.7
+	assert clf.best_params_ == {'n_estimators': 100, 'max_depth': 4}
+
+