def test_data_split_identical():
X_, y_ = X[:40], np.array([0] * 20 + [1] * 20)
for md in [
model.SVM(),
model.KNN(),
model.XGBoost(),
model.LinearModel(),
model.DecisionTree()
]:
a = evaluation.estimate(md, X_train, X_test, y_train, y_test)
b = evaluation.estimate(md, X_train, X_test, y_train, y_test)
assert a == b
a = evaluation.cross_validation(md,
X_,
y_,
scoring='both',
n_splits=2,
n_jobs=1)
b = evaluation.cross_validation(md,
X_,
y_,
scoring='both',
n_splits=2,
n_jobs=1)
assert np.all(a['f1'] == b['f1'])
assert np.all(a['roc_auc'] == b['roc_auc'])
def test_estimate():
for md in [
model.SVM(),
model.KNN(),
model.XGBoost(),
model.LinearModel(),
model.DecisionTree()
]:
evaluation.estimate(md, X_train, X_test, y_train, y_test)
def test_clone():
models = [
model.LinearModel(),
model.SVM(),
model.DecisionTree(),
model.MultiClassesLearner('KNN', {'n_neighbors': 1}),
model.KNN(),
model.XGBoost(),
]
from sklearn.base import clone
for md in models:
clone(md)
def test_cross_validation():
for md in [
model.SVM(),
model.MultiClassesLearner('KNN', {'n_neighbors': 1}),
model.KNN(),
model.XGBoost(),
model.LinearModel(),
model.DecisionTree(),
]:
try:
evaluation.cross_validation(md,
X,
y,
scoring='both',
n_jobs=1,
n_splits=2)
except Exception as e:
print(md.__class__)
raise e
def test_get_params():
models = [
model.LinearModel(),
model.SVM(),
model.DecisionTree(),
model.MultiClassesLearner('KNN', {'n_neighbors': 1}),
model.KNN(),
model.XGBoost(),
]
for md in models:
params = md.get_params()
try:
assert 'normalizer_name' in params
assert 'sample_method' in params
if not isinstance(md, model.KNN):
assert 'balanced_learning' in params
except AssertionError as e:
print(params)
print(md.__class__)
raise e
def test_xgboost():
m = model.XGBoost(n_jobs=1)
print(evaluation.cross_validation(m, X, y, n_jobs=1))