def test_permutation_importance_correlated_feature_regression(n_jobs):
# Make sure that feature highly correlated to the target have a higher
# importance
rng = np.random.RandomState(42)
n_repeats = 5
X, y = load_boston(return_X_y=True)
y_with_little_noise = (y +
rng.normal(scale=0.001, size=y.shape[0])).reshape(
-1, 1)
X = np.hstack([X, y_with_little_noise])
clf = RandomForestRegressor(n_estimators=10, random_state=42)
clf.fit(X, y)
result = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng,
n_jobs=n_jobs)
assert result.importances.shape == (X.shape[1], n_repeats)
# the correlated feature with y was added as the last column and should
# have the highest importance
assert np.all(result.importances_mean[-1] > result.importances_mean[:-1])
from mrex import datasets
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)
y,
train_size=400,
test_size=200,
random_state=4)
max_depth = 30
regr_multirf = MultiOutputRegressor(
RandomForestRegressor(n_estimators=100,
max_depth=max_depth,
random_state=0))
regr_multirf.fit(X_train, y_train)
regr_rf = RandomForestRegressor(n_estimators=100,
max_depth=max_depth,
random_state=2)
regr_rf.fit(X_train, y_train)
# Predict on new data
y_multirf = regr_multirf.predict(X_test)
y_rf = regr_rf.predict(X_test)
# Plot the results
plt.figure()
s = 50
a = 0.4
plt.scatter(y_test[:, 0],
y_test[:, 1],
edgecolor='k',
c="navy",
s=s,
marker="s",