def test_residual_prediction():
data = DataManager('boston')
baseline_model = ParametricEstimator(LinearRegression())
model = ParametricEstimator(point=LinearRegression(),
std=ResidualEstimator(LinearRegression()))
baseline = baseline_model.fit(data.X_train,
data.y_train).predict(data.X_test)
y_pred = model.fit(data.X_train, data.y_train).predict(data.X_test)
baseline_loss = linearized_log_loss(data.y_test, baseline)
y_pred_loss = linearized_log_loss(data.y_test, y_pred)
assert baseline_loss > y_pred_loss
def test_simple_model():
data = DataManager('boston')
model = ParametricEstimator(LinearRegression(), LinearRegression())
y_pred = model.fit(data.X_train, data.y_train).predict(data.X_test)
utils.assert_close_prediction(y_pred.point(), data.y_test, within=0.5)
def test_baseline():
data = DataManager('boston')
model = ParametricEstimator()
y_pred = model.fit(data.X_train, data.y_train).predict(data.X_test)
mu = np.mean(data.y_train)
sigma = np.std(data.y_train)
# is the dummy prediction working?
assert (y_pred.point() == np.ones((len(data.X_test))) * mu).all()
assert (y_pred.std() == np.ones((len(data.X_test))) * sigma).all()
# does subsetting work?
assert len(y_pred[1:3].point()) == 2
assert len(y_pred[1:3].lp2()) == 2
# pdf, cdf?
x = np.random.randint(0, 10)
i = np.random.randint(0, len(data.X_test) - 1)
assert y_pred[i].pdf(x) == norm.pdf(x, mu, sigma)
assert y_pred[i].cdf(x) == norm.cdf(x, mu, sigma)
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets.base import load_boston
from sklearn.model_selection import train_test_split
from skpro.parametric import ParametricEstimator
from skpro.parametric.estimators import Constant
from skpro.metrics import log_loss
# Define the parametric model
model = ParametricEstimator(point=RandomForestRegressor(),
std=Constant('std(y)'),
shape='norm')
# Train and predict on boston housing data
X, y = load_boston(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
y_pred = model.fit(X_train, y_train).predict(X_test)
# Obtain the loss
loss = log_loss(y_test, y_pred, sample=True, return_std=True)
print('Loss: %f+-%f' % loss)
# Plot the performance
import sys
sys.path.append('../')
import utils
utils.plot_performance(y_test, y_pred)