def test_transform_target_regressor_2d_transformer(X, y):
# Check consistency with transformer accepting only 2D array and a 1D/2D y
# array.
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
if y.ndim == 1: # create a 2D array and squeeze results
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
else:
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
if y.ndim == 1: # create a 2D array and squeeze results
lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze())
else:
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_1d_transformer(X, y):
# All transformer in scikit-learn expect 2D data. FunctionTransformer with
# validate=False lift this constraint without checking that the input is a
# 2D vector. We check the consistency of the data shape using a 1D and 2D y
# array.
transformer = FunctionTransformer(func=lambda x: x + 1,
inverse_func=lambda x: x - 1)
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_shifted_by_one(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_huber_equals_lr_for_high_epsilon():
# Test that Ridge matches LinearRegression for large epsilon
X, y = make_regression_with_outliers()
lr = LinearRegression()
lr.fit(X, y)
huber = HuberRegressor(epsilon=1e3, alpha=0.0)
huber.fit(X, y)
assert_almost_equal(huber.coef_, lr.coef_, 3)
assert_almost_equal(huber.intercept_, lr.intercept_, 2)
def test_omp_reaches_least_squares():
# Use small simple data; it's a sanity check but OMP can stop early
rng = check_random_state(0)
n_samples, n_features = (10, 8)
n_targets = 3
X = rng.randn(n_samples, n_features)
Y = rng.randn(n_samples, n_targets)
omp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_features)
lstsq = LinearRegression()
omp.fit(X, Y)
lstsq.fit(X, Y)
assert_array_almost_equal(omp.coef_, lstsq.coef_)
def test_plot_partial_dependence_fig(pyplot):
# Make sure fig object is correctly used if not None
(X, y), _ = regression_data
clf = LinearRegression()
clf.fit(X, y)
fig = pyplot.figure()
grid_resolution = 25
plot_partial_dependence(clf,
X, [0, 1],
target=0,
grid_resolution=grid_resolution,
fig=fig)
assert pyplot.gcf() is fig
def test_plot_partial_dependence_multioutput(pyplot):
# Test partial dependence plot function on multi-output input.
(X, y), _ = multioutput_regression_data
clf = LinearRegression()
clf.fit(X, y)
grid_resolution = 25
plot_partial_dependence(clf,
X, [0, 1],
target=0,
grid_resolution=grid_resolution)
fig = pyplot.gcf()
axs = fig.get_axes()
assert len(axs) == 2
assert all(ax.has_data for ax in axs)
plot_partial_dependence(clf,
X, [0, 1],
target=1,
grid_resolution=grid_resolution)
fig = pyplot.gcf()
axs = fig.get_axes()
assert len(axs) == 2
assert all(ax.has_data for ax in axs)
def test_transform_target_regressor_2d_transformer_multioutput():
# Check consistency with transformer accepting only 2D array and a 2D y
# array.
X = friedman[0]
y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(
y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
from mrex.ensemble import GradientBoostingRegressor
from mrex.ensemble import RandomForestRegressor
from mrex.linear_model import LinearRegression
from mrex.ensemble import VotingRegressor
# Loading some example data
X, y = datasets.load_boston(return_X_y=True)
# Training classifiers
reg1 = GradientBoostingRegressor(random_state=1, n_estimators=10)
reg2 = RandomForestRegressor(random_state=1, n_estimators=10)
reg3 = LinearRegression()
ereg = VotingRegressor([('gb', reg1), ('rf', reg2), ('lr', reg3)])
reg1.fit(X, y)
reg2.fit(X, y)
reg3.fit(X, y)
ereg.fit(X, y)
xt = X[:20]
plt.figure()
plt.plot(reg1.predict(xt), 'gd', label='GradientBoostingRegressor')
plt.plot(reg2.predict(xt), 'b^', label='RandomForestRegressor')
plt.plot(reg3.predict(xt), 'ys', label='LinearRegression')
plt.plot(ereg.predict(xt), 'r*', label='VotingRegressor')
plt.tick_params(axis='x',
which='both',
bottom=False,
top=False,
labelbottom=False)
plt.ylabel('predicted')
from mrex.utils import check_random_state
n = 100
x = np.arange(n)
rs = check_random_state(0)
y = rs.randint(-50, 50, size=(n,)) + 50. * np.log1p(np.arange(n))
# #############################################################################
# Fit IsotonicRegression and LinearRegression models
ir = IsotonicRegression()
y_ = ir.fit_transform(x, y)
lr = LinearRegression()
lr.fit(x[:, np.newaxis], y) # x needs to be 2d for LinearRegression
# #############################################################################
# Plot result
segments = [[[i, y[i]], [i, y_[i]]] for i in range(n)]
lc = LineCollection(segments, zorder=0)
lc.set_array(np.ones(len(y)))
lc.set_linewidths(np.full(n, 0.5))
fig = plt.figure()
plt.plot(x, y, 'r.', markersize=12)
plt.plot(x, y_, 'b.-', markersize=12)
plt.plot(x, lr.predict(x[:, np.newaxis]), 'b-')
plt.gca().add_collection(lc)
plt.legend(('Data', 'Isotonic Fit', 'Linear Fit'), loc='lower right')
relevant_features = np.random.randint(0, n_features, 10)
for i in relevant_features:
w[i] = stats.norm.rvs(loc=0, scale=1. / np.sqrt(lambda_))
# Create noise with a precision alpha of 50.
alpha_ = 50.
noise = stats.norm.rvs(loc=0, scale=1. / np.sqrt(alpha_), size=n_samples)
# Create the target
y = np.dot(X, w) + noise
# #############################################################################
# Fit the Bayesian Ridge Regression and an OLS for comparison
clf = BayesianRidge(compute_score=True)
clf.fit(X, y)
ols = LinearRegression()
ols.fit(X, y)
# #############################################################################
# Plot true weights, estimated weights, histogram of the weights, and
# predictions with standard deviations
lw = 2
plt.figure(figsize=(6, 5))
plt.title("Weights of the model")
plt.plot(clf.coef_,
color='lightgreen',
linewidth=lw,
label="Bayesian Ridge estimate")
plt.plot(w, color='gold', linewidth=lw, label="Ground truth")
plt.plot(ols.coef_, color='navy', linestyle='--', label="OLS estimate")
plt.xlabel("Features")
plt.ylabel("Values of the weights")