def test_boston_dataset(n_bins):
X, y = load_boston(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
mapper = _BinMapper(n_bins=n_bins, random_state=42)
X_train_binned = mapper.fit_transform(X_train)
# Init gradients and hessians to that of least squares loss
gradients = -y_train.astype(G_H_DTYPE)
hessians = np.ones(1, dtype=G_H_DTYPE)
min_samples_leaf = 8
max_leaf_nodes = 31
grower = TreeGrower(X_train_binned,
gradients,
hessians,
min_samples_leaf=min_samples_leaf,
max_leaf_nodes=max_leaf_nodes,
n_bins=n_bins,
n_bins_non_missing=mapper.n_bins_non_missing_)
grower.grow()
predictor = grower.make_predictor(bin_thresholds=mapper.bin_thresholds_)
assert r2_score(y_train, predictor.predict(X_train)) > 0.85
assert r2_score(y_test, predictor.predict(X_test)) > 0.70
def test_partial_dependence_easy_target(est, power):
# If the target y only depends on one feature in an obvious way (linear or
# quadratic) then the partial dependence for that feature should reflect
# it.
# We here fit a linear regression_data model (with polynomial features if
# needed) and compute r_squared to check that the partial dependence
# correctly reflects the target.
rng = np.random.RandomState(0)
n_samples = 200
target_variable = 2
X = rng.normal(size=(n_samples, 5))
y = X[:, target_variable]**power
est.fit(X, y)
averaged_predictions, values = partial_dependence(
est, features=[target_variable], X=X, grid_resolution=1000)
new_X = values[0].reshape(-1, 1)
new_y = averaged_predictions[0]
# add polynomial features if needed
new_X = PolynomialFeatures(degree=power).fit_transform(new_X)
lr = LinearRegression().fit(new_X, new_y)
r2 = r2_score(new_y, lr.predict(new_X))
assert r2 > .99
def test_regression_metrics(n_samples=50):
y_true = np.arange(n_samples)
y_pred = y_true + 1
assert_almost_equal(mean_squared_error(y_true, y_pred), 1.)
assert_almost_equal(
mean_squared_log_error(y_true, y_pred),
mean_squared_error(np.log(1 + y_true), np.log(1 + y_pred)))
assert_almost_equal(mean_absolute_error(y_true, y_pred), 1.)
assert_almost_equal(median_absolute_error(y_true, y_pred), 1.)
assert_almost_equal(max_error(y_true, y_pred), 1.)
assert_almost_equal(r2_score(y_true, y_pred), 0.995, 2)
assert_almost_equal(explained_variance_score(y_true, y_pred), 1.)
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=0),
mean_squared_error(y_true, y_pred))
# Tweedie deviance needs positive y_pred, except for p=0,
# p>=2 needs positive y_true
# results evaluated by sympy
y_true = np.arange(1, 1 + n_samples)
y_pred = 2 * y_true
n = n_samples
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=-1),
5 / 12 * n * (n**2 + 2 * n + 1))
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=1),
(n + 1) * (1 - np.log(2)))
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=2),
2 * np.log(2) - 1)
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=3 / 2),
((6 * np.sqrt(2) - 8) / n) * np.sqrt(y_true).sum())
assert_almost_equal(mean_tweedie_deviance(y_true, y_pred, p=3),
np.sum(1 / y_true) / (4 * n))
def test_regression_custom_weights():
y_true = [[1, 2], [2.5, -1], [4.5, 3], [5, 7]]
y_pred = [[1, 1], [2, -1], [5, 4], [5, 6.5]]
msew = mean_squared_error(y_true, y_pred, multioutput=[0.4, 0.6])
rmsew = mean_squared_error(y_true,
y_pred,
multioutput=[0.4, 0.6],
squared=False)
maew = mean_absolute_error(y_true, y_pred, multioutput=[0.4, 0.6])
rw = r2_score(y_true, y_pred, multioutput=[0.4, 0.6])
evsw = explained_variance_score(y_true, y_pred, multioutput=[0.4, 0.6])
assert_almost_equal(msew, 0.39, decimal=2)
assert_almost_equal(rmsew, 0.62, decimal=2)
assert_almost_equal(maew, 0.475, decimal=3)
assert_almost_equal(rw, 0.94, decimal=2)
assert_almost_equal(evsw, 0.94, decimal=2)
# Handling msle separately as it does not accept negative inputs.
y_true = np.array([[0.5, 1], [1, 2], [7, 6]])
y_pred = np.array([[0.5, 2], [1, 2.5], [8, 8]])
msle = mean_squared_log_error(y_true, y_pred, multioutput=[0.3, 0.7])
msle2 = mean_squared_error(np.log(1 + y_true),
np.log(1 + y_pred),
multioutput=[0.3, 0.7])
assert_almost_equal(msle, msle2, decimal=2)
def test_regression_metrics_at_limits():
assert_almost_equal(mean_squared_error([0.], [0.]), 0.00, 2)
assert_almost_equal(mean_squared_error([0.], [0.], squared=False), 0.00, 2)
assert_almost_equal(mean_squared_log_error([0.], [0.]), 0.00, 2)
assert_almost_equal(mean_absolute_error([0.], [0.]), 0.00, 2)
assert_almost_equal(median_absolute_error([0.], [0.]), 0.00, 2)
assert_almost_equal(max_error([0.], [0.]), 0.00, 2)
assert_almost_equal(explained_variance_score([0.], [0.]), 1.00, 2)
assert_almost_equal(r2_score([0., 1], [0., 1]), 1.00, 2)
assert_raises_regex(
ValueError, "Mean Squared Logarithmic Error cannot be "
"used when targets contain negative values.", mean_squared_log_error,
[-1.], [-1.])
assert_raises_regex(
ValueError, "Mean Squared Logarithmic Error cannot be "
"used when targets contain negative values.", mean_squared_log_error,
[1., 2., 3.], [1., -2., 3.])
assert_raises_regex(
ValueError, "Mean Squared Logarithmic Error cannot be "
"used when targets contain negative values.", mean_squared_log_error,
[1., -2., 3.], [1., 2., 3.])
# Tweedie deviance error
p = -1.2
assert_allclose(mean_tweedie_deviance([0], [1.], p=p),
2. / (2. - p),
rtol=1e-3)
with pytest.raises(ValueError,
match="can only be used on strictly positive y_pred."):
mean_tweedie_deviance([0.], [0.], p=p)
assert_almost_equal(mean_tweedie_deviance([0.], [0.], p=0), 0.00, 2)
msg = "only be used on non-negative y_true and strictly positive y_pred."
with pytest.raises(ValueError, match=msg):
mean_tweedie_deviance([0.], [0.], p=1.0)
p = 1.5
assert_allclose(mean_tweedie_deviance([0.], [1.], p=p), 2. / (2. - p))
msg = "only be used on non-negative y_true and strictly positive y_pred."
with pytest.raises(ValueError, match=msg):
mean_tweedie_deviance([0.], [0.], p=p)
p = 2.
assert_allclose(mean_tweedie_deviance([1.], [1.], p=p), 0.00, atol=1e-8)
msg = "can only be used on strictly positive y_true and y_pred."
with pytest.raises(ValueError, match=msg):
mean_tweedie_deviance([0.], [0.], p=p)
p = 3.
assert_allclose(mean_tweedie_deviance([1.], [1.], p=p), 0.00, atol=1e-8)
msg = "can only be used on strictly positive y_true and y_pred."
with pytest.raises(ValueError, match=msg):
mean_tweedie_deviance([0.], [0.], p=p)
with pytest.raises(ValueError,
match="deviance is only defined for p<=0 and p>=1."):
mean_tweedie_deviance([0.], [0.], p=0.5)
def test_regression_scorers():
# Test regression scorers.
diabetes = load_diabetes()
X, y = diabetes.data, diabetes.target
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = Ridge()
clf.fit(X_train, y_train)
score1 = get_scorer('r2')(clf, X_test, y_test)
score2 = r2_score(y_test, clf.predict(X_test))
assert_almost_equal(score1, score2)
def test_multioutput_regression():
y_true = np.array([[1, 0, 0, 1], [0, 1, 1, 1], [1, 1, 0, 1]])
y_pred = np.array([[0, 0, 0, 1], [1, 0, 1, 1], [0, 0, 0, 1]])
error = mean_squared_error(y_true, y_pred)
assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)
error = mean_squared_error(y_true, y_pred, squared=False)
assert_almost_equal(error, 0.645, decimal=2)
error = mean_squared_log_error(y_true, y_pred)
assert_almost_equal(error, 0.200, decimal=2)
# mean_absolute_error and mean_squared_error are equal because
# it is a binary problem.
error = mean_absolute_error(y_true, y_pred)
assert_almost_equal(error, (1. + 2. / 3) / 4.)
error = r2_score(y_true, y_pred, multioutput='variance_weighted')
assert_almost_equal(error, 1. - 5. / 2)
error = r2_score(y_true, y_pred, multioutput='uniform_average')
assert_almost_equal(error, -.875)
def test_regression_multioutput_array():
y_true = [[1, 2], [2.5, -1], [4.5, 3], [5, 7]]
y_pred = [[1, 1], [2, -1], [5, 4], [5, 6.5]]
mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
r = r2_score(y_true, y_pred, multioutput='raw_values')
evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')
assert_array_almost_equal(mse, [0.125, 0.5625], decimal=2)
assert_array_almost_equal(mae, [0.25, 0.625], decimal=2)
assert_array_almost_equal(r, [0.95, 0.93], decimal=2)
assert_array_almost_equal(evs, [0.95, 0.93], decimal=2)
# mean_absolute_error and mean_squared_error are equal because
# it is a binary problem.
y_true = [[0, 0]] * 4
y_pred = [[1, 1]] * 4
mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
r = r2_score(y_true, y_pred, multioutput='raw_values')
assert_array_almost_equal(mse, [1., 1.], decimal=2)
assert_array_almost_equal(mae, [1., 1.], decimal=2)
assert_array_almost_equal(r, [0., 0.], decimal=2)
r = r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]], multioutput='raw_values')
assert_array_almost_equal(r, [0, -3.5], decimal=2)
assert np.mean(r) == r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
multioutput='uniform_average')
evs = explained_variance_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
multioutput='raw_values')
assert_array_almost_equal(evs, [0, -1.25], decimal=2)
# Checking for the condition in which both numerator and denominator is
# zero.
y_true = [[1, 3], [-1, 2]]
y_pred = [[1, 4], [-1, 1]]
r2 = r2_score(y_true, y_pred, multioutput='raw_values')
assert_array_almost_equal(r2, [1., -3.], decimal=2)
assert np.mean(r2) == r2_score(y_true,
y_pred,
multioutput='uniform_average')
evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')
assert_array_almost_equal(evs, [1., -3.], decimal=2)
assert np.mean(evs) == explained_variance_score(y_true, y_pred)
# Handling msle separately as it does not accept negative inputs.
y_true = np.array([[0.5, 1], [1, 2], [7, 6]])
y_pred = np.array([[0.5, 2], [1, 2.5], [8, 8]])
msle = mean_squared_log_error(y_true, y_pred, multioutput='raw_values')
msle2 = mean_squared_error(np.log(1 + y_true),
np.log(1 + y_pred),
multioutput='raw_values')
assert_array_almost_equal(msle, msle2, decimal=2)
# Split the targets into training/testing sets
diabetes_y_train = diabetes_y[:-20]
diabetes_y_test = diabetes_y[-20:]
# Create linear regression object
regr = linear_model.LinearRegression()
# Train the model using the training sets
regr.fit(diabetes_X_train, diabetes_y_train)
# Make predictions using the testing set
diabetes_y_pred = regr.predict(diabetes_X_test)
# The coefficients
print('Coefficients: \n', regr.coef_)
# The mean squared error
print('Mean squared error: %.2f' %
mean_squared_error(diabetes_y_test, diabetes_y_pred))
# The coefficient of determination: 1 is perfect prediction
print('Coefficient of determination: %.2f' %
r2_score(diabetes_y_test, diabetes_y_pred))
# Plot outputs
plt.scatter(diabetes_X_test, diabetes_y_test, color='black')
plt.plot(diabetes_X_test, diabetes_y_pred, color='blue', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()
# reported by the median absolute error (MAE).
f, (ax0, ax1) = plt.subplots(1, 2, sharey=True)
regr = RidgeCV()
regr.fit(X_train, y_train)
y_pred = regr.predict(X_test)
ax0.scatter(y_test, y_pred)
ax0.plot([0, 2000], [0, 2000], '--k')
ax0.set_ylabel('Target predicted')
ax0.set_xlabel('True Target')
ax0.set_title('Ridge regression \n without target transformation')
ax0.text(
100, 1750, r'$R^2$=%.2f, MAE=%.2f' %
(r2_score(y_test, y_pred), median_absolute_error(y_test, y_pred)))
ax0.set_xlim([0, 2000])
ax0.set_ylim([0, 2000])
regr_trans = TransformedTargetRegressor(regressor=RidgeCV(),
func=np.log1p,
inverse_func=np.expm1)
regr_trans.fit(X_train, y_train)
y_pred = regr_trans.predict(X_test)
ax1.scatter(y_test, y_pred)
ax1.plot([0, 2000], [0, 2000], '--k')
ax1.set_ylabel('Target predicted')
ax1.set_xlabel('True Target')
ax1.set_title('Ridge regression \n with target transformation')
ax1.text(
y += 0.01 * np.random.normal(size=n_samples)
# Split data in train set and test set
n_samples = X.shape[0]
X_train, y_train = X[:n_samples // 2], y[:n_samples // 2]
X_test, y_test = X[n_samples // 2:], y[n_samples // 2:]
# #############################################################################
# Lasso
from mrex.linear_model import Lasso
alpha = 0.1
lasso = Lasso(alpha=alpha)
y_pred_lasso = lasso.fit(X_train, y_train).predict(X_test)
r2_score_lasso = r2_score(y_test, y_pred_lasso)
print(lasso)
print("r^2 on test data : %f" % r2_score_lasso)
# #############################################################################
# ElasticNet
from mrex.linear_model import ElasticNet
enet = ElasticNet(alpha=alpha, l1_ratio=0.7)
y_pred_enet = enet.fit(X_train, y_train).predict(X_test)
r2_score_enet = r2_score(y_test, y_pred_enet)
print(enet)
print("r^2 on test data : %f" % r2_score_enet)
m, s, _ = plt.stem(np.where(enet.coef_)[0], enet.coef_[enet.coef_ != 0],
def score(y_test, y_pred, case):
r2 = r2_score(y_test, y_pred)
print("r^2 on test data (%s) : %f" % (case, r2))
