From ec0dbf0399c4187a1d17e66de17265c67588373f Mon Sep 17 00:00:00 2001
From: Manoj Kumar <mks542@nyu.edu>
Date: Mon, 26 Jun 2017 04:02:16 +0530
Subject: [PATCH] [MRG+1] Fixes predicting std and cov without fitting in GPR
by default. (#9177)
* If self.kernel_ is None then self.kernel_ is set to RBFKernel in predict() as fit(). Fixes #6573
* xxx_ attributes can not be altered outside fit. Removing self.kernel_ from predict() and using previously implemented self.kernel attribute.
* Cleanup and add non-regression-test
---
doc/whats_new.rst | 7 ++++++-
sklearn/gaussian_process/gpr.py | 9 +++++++--
sklearn/gaussian_process/tests/test_gpr.py | 19 ++++++++++++++++++-
3 files changed, 31 insertions(+), 4 deletions(-)
diff --git a/doc/whats_new.rst b/doc/whats_new.rst
index 04480f7879..761c98ef27 100644
--- a/doc/whats_new.rst
+++ b/doc/whats_new.rst
@@ -273,7 +273,7 @@ Bug fixes
``max_iter`` if finds a large inlier group early. :issue:`8251` by :user:`aivision2020`.
- Fixed a bug where :class:`sklearn.naive_bayes.MultinomialNB` and :class:`sklearn.naive_bayes.BernoulliNB`
- failed when `alpha=0`. :issue:`5814` by :user:`Yichuan Liu <yl565>` and
+ failed when `alpha=0`. :issue:`5814` by :user:`Yichuan Liu <yl565>` and
:user:`Herilalaina Rakotoarison <herilalaina>`.
- Fixed a bug where :func:`datasets.make_moons` gives an
@@ -425,6 +425,11 @@ Bug fixes
hence :func:`metrics.cohen_kappa_score`. :issue:`8354`, :issue:`7929`
by `Joel Nothman`_ and :user:`Jon Crall <Erotemic>`.
+ - Fixed a bug in :class:`gaussian_process.GaussianProcessRegressor`
+ when the standard deviation and covariance predicted without fit
+ would fail with a unmeaningful error by default.
+ :issue:`6573` by :user:`Quazi Marufur Rahman <qmaruf>` and
+ `Manoj Kumar`_.
- Fixed the implementation of `explained_variance_`
in :class:`decomposition.PCA`,
diff --git a/sklearn/gaussian_process/gpr.py b/sklearn/gaussian_process/gpr.py
index 5c29c5258a..4f9ff9cee7 100644
--- a/sklearn/gaussian_process/gpr.py
+++ b/sklearn/gaussian_process/gpr.py
@@ -297,12 +297,17 @@ class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
X = check_array(X)
if not hasattr(self, "X_train_"): # Unfitted;predict based on GP prior
+ if self.kernel is None:
+ kernel = (C(1.0, constant_value_bounds="fixed") *
+ RBF(1.0, length_scale_bounds="fixed"))
+ else:
+ kernel = self.kernel
y_mean = np.zeros(X.shape[0])
if return_cov:
- y_cov = self.kernel(X)
+ y_cov = kernel(X)
return y_mean, y_cov
elif return_std:
- y_var = self.kernel.diag(X)
+ y_var = kernel.diag(X)
return y_mean, np.sqrt(y_var)
else:
return y_mean
diff --git a/sklearn/gaussian_process/tests/test_gpr.py b/sklearn/gaussian_process/tests/test_gpr.py
index 1502a820f2..b645a6be18 100644
--- a/sklearn/gaussian_process/tests/test_gpr.py
+++ b/sklearn/gaussian_process/tests/test_gpr.py
@@ -14,7 +14,8 @@ from sklearn.gaussian_process.kernels import DotProduct
from sklearn.utils.testing \
import (assert_true, assert_greater, assert_array_less,
- assert_almost_equal, assert_equal, assert_raise_message)
+ assert_almost_equal, assert_equal, assert_raise_message,
+ assert_array_almost_equal)
def f(x):
@@ -327,3 +328,19 @@ def test_duplicate_input():
assert_almost_equal(y_pred_equal, y_pred_similar)
assert_almost_equal(y_std_equal, y_std_similar)
+
+
+def test_no_fit_default_predict():
+ # Test that GPR predictions without fit does not break by default.
+ default_kernel = (C(1.0, constant_value_bounds="fixed") *
+ RBF(1.0, length_scale_bounds="fixed"))
+ gpr1 = GaussianProcessRegressor()
+ _, y_std1 = gpr1.predict(X, return_std=True)
+ _, y_cov1 = gpr1.predict(X, return_cov=True)
+
+ gpr2 = GaussianProcessRegressor(kernel=default_kernel)
+ _, y_std2 = gpr2.predict(X, return_std=True)
+ _, y_cov2 = gpr2.predict(X, return_cov=True)
+
+ assert_array_almost_equal(y_std1, y_std2)
+ assert_array_almost_equal(y_cov1, y_cov2)
--
GitLab