This repository has been archived by the owner on Feb 28, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 546
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Test by estimating the quantiles of the normal
- Loading branch information
Showing
2 changed files
with
46 additions
and
32 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,28 +1,25 @@ | ||
import numpy as np | ||
|
||
from sklearn.base import BaseEstimator, RegressorMixin | ||
from sklearn.ensemble import GradientBoostingRegressor | ||
from sklearn.utils import check_random_state | ||
|
||
|
||
class GradientBoostingRegressorWithStd(BaseEstimator, RegressorMixin): | ||
def __init__(self, alpha): | ||
self.alpha = alpha | ||
class GBTQuantiles(BaseEstimator, RegressorMixin): | ||
def __init__(self, quantiles=[0.16, 0.5, 0.84], random_state=None): | ||
self.quantiles = quantiles | ||
self.random_state = random_state | ||
|
||
def fit(self, X, y): | ||
"""Fit regressor""" | ||
self.regressor_ = GradientBoostingRegressor(loss='quantile') | ||
self.rgr_up_ = GradientBoostingRegressor(loss='quantile', | ||
alpha=0.5 + self.alpha/2.) | ||
self.rgr_down_ = GradientBoostingRegressor(loss='quantile', | ||
alpha=0.5 - self.alpha/2.) | ||
|
||
self.regressor_.fit(X, y) | ||
self.rgr_up_.fit(X, y) | ||
self.rgr_down_.fit(X, y) | ||
|
||
def predict(self, X, return_std=False): | ||
"""Prediction with uncertainties""" | ||
up = self.rgr_up_.predict(X) | ||
down = self.rgr_down_.predict(X) | ||
std = up - down | ||
central = self.regressor_.predict(X) | ||
"""Fit one regressor for each quantile""" | ||
rng = check_random_state(self.random_state) | ||
self.regressors_ = [GradientBoostingRegressor(loss='quantile', | ||
alpha=a, | ||
random_state=rng) | ||
for a in self.quantiles] | ||
for rgr in self.regressors_: | ||
rgr.fit(X, y) | ||
|
||
return (central, std) | ||
def predict(self, X): | ||
"""Predictions for each quantile""" | ||
return np.vstack([rgr.predict(X) for rgr in self.regressors_]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,38 +1,55 @@ | ||
import numpy as np | ||
from scipy import stats | ||
|
||
from sklearn.utils.testing import assert_equal | ||
from sklearn.utils import check_random_state | ||
from sklearn.utils.testing import assert_equal, assert_almost_equal | ||
|
||
from skopt.gbt import GradientBoostingRegressorWithStd | ||
from skopt.gbt import GBTQuantiles | ||
|
||
|
||
rng = np.random.RandomState(324) | ||
|
||
def truth(X): | ||
return 0.5 * np.sin(1.75*X[:, 0]) | ||
|
||
def constant_noise(X): | ||
return np.ones_like(X) | ||
|
||
def sample_noise(X, std=0.2, noise=constant_noise): | ||
def sample_noise(X, std=0.2, noise=constant_noise, | ||
random_state=None): | ||
"""Uncertainty inherent to the process | ||
The regressor should try and model this. | ||
""" | ||
rng = check_random_state(random_state) | ||
return np.array([rng.normal(0, std*noise(x)) for x in X]) | ||
|
||
def test_gbt_gaussian(): | ||
# estiamte quantiles of the normal distribution | ||
rng = np.random.RandomState(1) | ||
N = 10000 | ||
X = np.ones((N, 1)) | ||
y = rng.normal(size=N) | ||
|
||
rgr = GBTQuantiles() | ||
rgr.fit(X, y) | ||
|
||
estimates = rgr.predict(X) | ||
assert_almost_equal(stats.norm.ppf(rgr.quantiles), | ||
np.mean(estimates, axis=1), | ||
decimal=2) | ||
|
||
def test_gbt_with_std(): | ||
# simple test of the interface | ||
rng = np.random.RandomState(1) | ||
# simple test of interface | ||
X = rng.uniform(0, 5, 500)[:, np.newaxis] | ||
|
||
noise_level = 0.5 | ||
y = truth(X) + sample_noise(X, noise_level) | ||
y = truth(X) + sample_noise(X, noise_level, random_state=rng) | ||
|
||
X_ = np.linspace(0, 5, 1000)[:, np.newaxis] | ||
|
||
model = GradientBoostingRegressorWithStd(alpha=0.68) | ||
model = GBTQuantiles() | ||
model.fit(X, y) | ||
|
||
p, s = model.predict(X_) | ||
assert_equal(p.shape, s.shape) | ||
assert_equal(p.shape[0], X_.shape[0]) | ||
l, c, h = model.predict(X_) | ||
assert_equal(l.shape, c.shape, h.shape) | ||
assert_equal(l.shape[0], X_.shape[0]) |