def test_multiple_targets(self):
from sklearn.linear_model import LinearRegression as sk_LinearRegression
X = np.linspace(-1, 1, 1000)
y = np.vstack((X.copy(), X.copy(), X.copy(), X.copy())).T
X = X[:, np.newaxis]
clf_dp = LinearRegression(epsilon=2,
fit_intercept=False,
bounds_X=(-1, 1),
bounds_y=(-1, 1))
with self.assertRaises(ValueError):
clf_dp.fit(X, y.T)
clf_dp.fit(X, y)
clf_sk = sk_LinearRegression(fit_intercept=False)
clf_sk.fit(X, y)
x0 = np.array([[0.5]])
self.assertEqual(clf_dp.coef_.shape, clf_sk.coef_.shape)
self.assertEqual(clf_dp.predict(x0).shape, clf_sk.predict(x0).shape)
clf_dp2 = LinearRegression(epsilon=2,
fit_intercept=True,
bounds_X=(-1, 1),
bounds_y=(-1, 1)).fit(X, y)
self.assertIsNotNone(clf_dp2)
self.assertEqual(clf_dp2.intercept_.shape, (4, ))
self.assertEqual(clf_dp2.coef_.shape, clf_sk.coef_.shape)
self.assertEqual(clf_dp2.predict(x0).shape, clf_sk.predict(x0).shape)
def test_different_results(self):
from sklearn import datasets
from sklearn import linear_model
from sklearn.model_selection import train_test_split
dataset = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.2)
clf = LinearRegression(bounds_X=([4.3, 2.0, 1.1,
0.1], [7.9, 4.4, 6.9, 2.5]),
bounds_y=(0, 2))
clf.fit(X_train, y_train)
predict1 = clf.predict(X_test)
clf = LinearRegression(bounds_X=([4.3, 2.0, 1.1,
0.1], [7.9, 4.4, 6.9, 2.5]),
bounds_y=(0, 2))
clf.fit(X_train, y_train)
predict2 = clf.predict(X_test)
clf = linear_model.LinearRegression()
clf.fit(X_train, y_train)
predict3 = clf.predict(X_test)
self.assertFalse(np.all(predict1 == predict2))
self.assertFalse(
np.all(predict3 == predict1) and np.all(predict3 == predict2))
def test_same_results(self):
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import linear_model
dataset = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.2)
clf = LinearRegression(data_norm=12,
epsilon=float("inf"),
bounds_X=([4.3, 2.0, 1.0,
0.1], [7.9, 4.4, 6.9, 2.5]),
bounds_y=(0, 2))
clf.fit(X_train, y_train)
predict1 = clf.predict(X_test)
clf = linear_model.LinearRegression(normalize=False)
clf.fit(X_train, y_train)
predict2 = clf.predict(X_test)
self.assertTrue(np.allclose(predict1, predict2))
def test_different_results(self):
from sklearn import datasets
from sklearn import linear_model
from sklearn.model_selection import train_test_split
dataset = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.2)
clf = LinearRegression(data_norm=12,
range_X=[3.6, 2.2, 5.9, 2.4],
range_y=2)
clf.fit(X_train, y_train)
predict1 = clf.predict(X_test)
clf = LinearRegression(data_norm=12,
range_X=[3.6, 2.2, 5.9, 2.4],
range_y=2)
clf.fit(X_train, y_train)
predict2 = clf.predict(X_test)
clf = linear_model.LinearRegression()
clf.fit(X_train, y_train)
predict3 = clf.predict(X_test)
self.assertFalse(np.all(predict1 == predict2))
self.assertFalse(
np.all(predict3 == predict1) and np.all(predict3 == predict2))
def test_simple(self):
X = np.linspace(-1, 1, 1000)
y = X.copy()
X = X[:, np.newaxis]
clf = LinearRegression(epsilon=2,
fit_intercept=False,
bounds_X=(-1, 1),
bounds_y=(-1, 1))
clf.fit(X, y)
print(clf.predict(np.array([0.5]).reshape(-1, 1)))
self.assertIsNotNone(clf)
self.assertAlmostEqual(clf.predict(np.array([0.5]).reshape(-1, 1))[0],
0.5,
delta=.05)
def test_simple(self):
X = np.linspace(-1, 1, 1000)
y = X.copy()
X = X[:, np.newaxis]
clf = LinearRegression(epsilon=2, data_norm=1, fit_intercept=False)
clf.fit(X, y)
self.assertIsNotNone(clf)
self.assertAlmostEqual(clf.predict(np.array([0.5]).reshape(-1, 1))[0],
0.5,
places=3)
def test_same_results(self):
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import linear_model
dataset = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.2)
clf = LinearRegression(data_norm=12,
epsilon=float("inf"),
range_X=[3.6, 2.2, 5.9, 2.4],
range_y=2)
clf.fit(X_train, y_train)
predict1 = clf.predict(X_test)
clf = linear_model.LinearRegression(normalize=False)
clf.fit(X_train, y_train)
predict2 = clf.predict(X_test)
self.assertTrue(np.allclose(predict1, predict2))