8000 DOC Ensures that PowerTransformer passes numpydoc validation (#21015) · samronsin/scikit-learn@b0ea5ba · GitHub
[go: up one dir, main page]
Skip to content

Commit b0ea5ba

Browse files
jmloyolaglemaitre
authored and
samronsin
committed
DOC Ensures that PowerTransformer passes numpydoc validation (scikit-learn#21015)
Co-authored-by: Guillaume Lemaitre <g.lemaitre58@gmail.com>
1 parent e5218e1 commit b0ea5ba

File tree

2 files changed

+31
-16
lines changed

2 files changed

+31
-16
lines changed

‎maint_tools/test_docstrings.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -42,7 +42,6 @@
4242
"PassiveAggressiveRegressor",
4343
"PatchExtractor",
4444
"PolynomialFeatures",
45-
"PowerTransformer",
4645
"QuadraticDiscriminantAnalysis",
4746
"QuantileRegressor",
4847
"QuantileTransformer",

‎sklearn/preprocessing/_data.py

Lines changed: 31 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -2974,21 +2974,6 @@ class PowerTransformer(_OneToOneFeatureMixin, TransformerMixin, BaseEstimator):
29742974
29752975
.. versionadded:: 1.0
29762976
2977-
Examples
2978-
--------
2979-
>>> import numpy as np
2980-
>>> from sklearn.preprocessing import PowerTransformer
2981-
>>> pt = PowerTransformer()
2982-
>>> data = [[1, 2], [3, 2], [4, 5]]
2983-
>>> print(pt.fit(data))
2984-
PowerTransformer()
2985-
>>> print(pt.lambdas_)
2986-
[ 1.386... -3.100...]
2987-
>>> print(pt.transform(data))
2988-
[[-1.316... -0.707...]
2989-
[ 0.209... -0.707...]
2990-
[ 1.106... 1.414...]]
2991-
29922977
See Also
29932978
--------
29942979
power_transform : Equivalent function without the estimator API.
@@ -3014,6 +2999,21 @@ class PowerTransformer(_OneToOneFeatureMixin, TransformerMixin, BaseEstimator):
30142999
30153000
.. [2] G.E.P. Box and D.R. Cox, "An Analysis of Transformations", Journal
30163001
of the Royal Statistical Society B, 26, 211-252 (1964).
3002+
3003+
Examples
3004+
--------
3005+
>>> import numpy as np
3006+
>>> from sklearn.preprocessing import PowerTransformer
3007+
>>> pt = PowerTransformer()
3008+
>>> data = [[1, 2], [3, 2], [4, 5]]
3009+
>>> print(pt.fit(data))
3010+
PowerTransformer()
3011+
>>> print(pt.lambdas_)
3012+
[ 1.386... -3.100...]
3013+
>>> print(pt.transform(data))
3014+
[[-1.316... -0.707...]
3015+
[ 0.209... -0.707...]
3016+
[ 1.106... 1.414...]]
30173017
"""
30183018

30193019
def __init__(self, method="yeo-johnson", *, standardize=True, copy=True):
@@ -3044,6 +3044,22 @@ def fit(self, X, y=None):
30443044
return self
30453045

30463046
def fit_transform(self, X, y=None):
3047+
"""Fit `PowerTransformer` to `X`, then transform `X`.
3048+
3049+
Parameters
3050+
----------
3051+
X : array-like of shape (n_samples, n_features)
3052+
The data used to estimate the optimal transformation parameters
3053+
and to be transformed using a power transformation.
3054+
3055+
y : Ignored
3056+
Not used, present for API consistency by convention.
3057+
3058+
Returns
3059+
-------
3060+
X_new : ndarray of shape (n_samples, n_features)
3061+
Transformed data.
3062+
"""
30473063
return self._fit(X, y, force_transform=True)
30483064

30493065
def _fit(self, X, y=None, force_transform=False):

0 commit comments

Comments
 (0)
0