def test_partial_dependence_helpers(est, method, target_feature):
# Check that what is returned by _partial_dependence_brute or
# _partial_dependence_recursion is equivalent to manually setting a target
# feature to a given value, and computing the average prediction over all
# samples.
# This also checks that the brute and recursion methods give the same
# output.
# Note that even on the trainset, the brute and the recursion methods
# aren't always strictly equivalent, in particular when the slow method
# generates unrealistic samples that have low mass in the joint
# distribution of the input features, and when some of the features are
# dependent. Hence the high tolerance on the checks.
X, y = make_regression(random_state=0, n_features=5, n_informative=5)
# The 'init' estimator for GBDT (here the average prediction) isn't taken
# into account with the recursion method, for technical reasons. We set
# the mean to 0 to that this 'bug' doesn't have any effect.
y = y - y.mean()
est.fit(X, y)
# target feature will be set to .5 and then to 123
features = np.array([target_feature], dtype=np.int32)
grid = np.array([[.5], [123]])
if method == 'brute':
pdp, predictions = _partial_dependence_brute(est,
grid,
features,
X,
response_method='auto')
else:
pdp = _partial_dependence_recursion(est, grid, features)
mean_predictions = []
for val in (.5, 123):
X_ = X.copy()
X_[:, target_feature] = val
mean_predictions.append(est.predict(X_).mean())
pdp = pdp[0] # (shape is (1, 2) so make it (2,))
# allow for greater margin for error with recursion method
rtol = 1e-1 if method == 'recursion' else 1e-3
assert np.allclose(pdp, mean_predictions, rtol=rtol)
def partial_dependence(estimator, X, features):
"""Calculate the partial dependence of features.
Partial dependence of a feature (or a set of features) corresponds
to the average response of an estimator for each possible value of
the feature. Code from sklearn's _partial_dependence.py. Note that
this implementation always uses method="brute", grid_resolution=100
and percentiles=(0.05, 0.95).
Parameters
----------
estimator : class
Model estimator to use.
X : pd.DataFrame
Feature set used to generate a grid of values for the target
features (where the partial dependence is evaluated), and
also to generate values for the complement features.
features : int, str or sequence
The feature or pair of interacting features for which the
partial dependency should be computed.
Returns
-------
averaged_predictions: np.ndarray
Average of the predictions.
values: list
Values used for the predictions.
"""
grid, values = _grid_from_X(_safe_indexing(X, features, axis=1),
(0.05, 0.95), 100)
averaged_predictions, _ = _partial_dependence_brute(
estimator, grid, features, X, "auto")
# Reshape averaged_predictions to (n_outputs, n_values_feature_0, ...)
averaged_predictions = averaged_predictions.reshape(
-1, *[val.shape[0] for val in values])
return averaged_predictions, values