def test_folding_regressor(n_samples=100, n_features=3):
"""
checking mostly different things with quality of predictions and not using train data during predictions.
"""
from sklearn.metrics import mean_squared_error
X = numpy.random.normal(size=[n_samples, n_features])
y = numpy.random.normal(size=n_samples)
kfolder = FoldingRegressor(SklearnRegressor(GradientBoostingRegressor()),
n_folds=2)
kfolder.fit(X, y)
preds = kfolder.predict(X)
# checking that we fitted fine
assert mean_squared_error(y,
preds) > mean_squared_error(y * 0., preds) * 0.5
# shuffled predictions
p = numpy.random.permutation(n_samples)
preds2 = kfolder.predict(X[p])[numpy.argsort(p)]
# Now let's compare this with shuffled kFolding:
assert mean_squared_error(y, preds) > mean_squared_error(y, preds2) * 0.5
preds_mean = kfolder.predict(X,
vote_function=lambda x: numpy.mean(x, axis=0))
# Now let's compare this with mean prediction:
assert mean_squared_error(y, preds) > mean_squared_error(y, preds_mean)
def test_folding_regressor_functions():
"""Testing folding functions """
data, y, sample_weight = generate_classification_data()
for X in [data, numpy.array(data)]:
kfolder = FoldingRegressor(SklearnRegressor(GradientBoostingRegressor(n_estimators=5)), n_folds=2)
kfolder.fit(X, y, sample_weight=sample_weight)
preds = kfolder.predict(X)
for p in kfolder.staged_predict(X):
pass
assert numpy.allclose(p, preds)
importances = kfolder.feature_importances_
other_importances = kfolder.get_feature_importances()
def test_folding_regressor_functions():
"""Testing folding functions """
data, y, sample_weight = generate_classification_data()
for X in [data, numpy.array(data)]:
kfolder = FoldingRegressor(SklearnRegressor(GradientBoostingRegressor(n_estimators=5)), n_folds=2)
kfolder.fit(X, y, sample_weight=sample_weight)
preds = kfolder.predict(X)
for p in kfolder.staged_predict(X):
pass
assert numpy.allclose(p, preds)
importances = kfolder.feature_importances_
other_importances = kfolder.get_feature_importances()
def test_folding_regressor(n_samples=100, n_features=3):
"""
checking mostly different things with quality of predictions and not using train data during predictions.
"""
from sklearn.metrics import mean_squared_error
X = numpy.random.normal(size=[n_samples, n_features])
y = numpy.random.normal(size=n_samples)
kfolder = FoldingRegressor(SklearnRegressor(GradientBoostingRegressor()), n_folds=2)
kfolder.fit(X, y)
preds = kfolder.predict(X)
# checking that we fitted fine
assert mean_squared_error(y, preds) > mean_squared_error(y * 0., preds) * 0.5
# shuffled predictions
p = numpy.random.permutation(n_samples)
preds2 = kfolder.predict(X[p])[numpy.argsort(p)]
# Now let's compare this with shuffled kFolding:
assert mean_squared_error(y, preds) > mean_squared_error(y, preds2) * 0.5
preds_mean = kfolder.predict(X, vote_function=lambda x: numpy.mean(x, axis=0))
# Now let's compare this with mean prediction:
assert mean_squared_error(y, preds) > mean_squared_error(y, preds_mean)
def test_folding_regressor_with_check_model():
base_clf = SklearnRegressor(GradientBoostingRegressor(n_estimators=4))
folding_str = FoldingRegressor(base_clf, n_folds=2)
check_regression(folding_str, True, True, True)
