def very_basic_xgboost_test():
X, y, w = generate_classification_data(n_classes=2)
clf = XGBoostClassifier(n_estimators=10).fit(X, y)
clf.predict(X)
clf.predict_proba(X)
# testing that returned features in importances are correct and in the same order
assert numpy.all(clf.features == clf.get_feature_importances().index)
def test_basic_xgboost():
X, y, w = generate_classification_data(n_classes=2)
clf = XGBoostClassifier(n_estimators=10).fit(X, y)
clf.predict(X)
clf.predict_proba(X)
# testing that returned features in importances are correct and in the same order
assert numpy.all(clf.features == clf.get_feature_importances().index)
def test_xgboost_feature_importance():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=1, max_depth=1)
clf.fit(X, y)
importances = clf.get_feature_importances()
original_features = set(X.columns)
importances_features = set(importances.index)
print(original_features, importances_features)
assert original_features == importances_features, 'feature_importances_ return something wrong'
assert len(original_features) == len(clf.feature_importances_)
def test_xgboost_feature_importance():
X, y, weights = generate_classification_data(n_classes=2, distance=5)
clf = XGBoostClassifier(n_estimators=1, max_depth=1)
clf.fit(X, y)
importances = clf.get_feature_importances()
original_features = set(X.columns)
importances_features = set(importances.index)
print(original_features, importances_features)
assert original_features == importances_features, 'feature_importances_ return something wrong'
assert len(original_features) == len(clf.feature_importances_)
