skpro/examples/benchmark_baseline_regressors.py at 9b18283db236001040469f1bd7a6f1481e148131 · sktime/skpro · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
"""Benchmark script for baseline probabilistic regressors."""
import logging

import numpy as np
from sklearn.linear_model import LinearRegression

from skpro.metrics import PinballLoss
from skpro.regression.deterministic_reduction import DeterministicReductionRegressor
from skpro.regression.unconditional_distfit import UnconditionalDistfitRegressor

# Generate synthetic data
X = np.random.randn(200, 5)
y = 3 * X[:, 0] - 2 * X[:, 1] + np.random.randn(200)

# Split
X_train, X_test = X[:150], X[150:]
y_train, y_test = y[:150], y[150:]

# Baseline 1: Unconditional
reg1 = UnconditionalDistfitRegressor()
reg1.fit(X_train, y_train)
dist1 = reg1.predict_proba(X_test)

# Baseline 2: Deterministic reduction
reg2 = DeterministicReductionRegressor(LinearRegression(), distr_type="gaussian")
reg2.fit(X_train, y_train)
dist2 = reg2.predict_proba(X_test)

# Evaluate pinball loss at alpha=0.1, 0.5, 0.9
alphas = [0.1, 0.5, 0.9]
for alpha in alphas:
    loss1 = PinballLoss(alpha=alpha)(y_test, dist1)
    loss2 = PinballLoss(alpha=alpha)(y_test, dist2)
    logging.info(
        "Alpha=%s: UnconditionalDistfitRegressor pinball loss=%.4f, "
        "DeterministicReductionRegressor pinball loss=%.4f",
        alpha,
        loss1,
        loss2,
    )