From 12a0125a3cac4691ff5cad00e50ca80daa22099f Mon Sep 17 00:00:00 2001
From: Olivier Grisel <olivier.grisel@ensta.org>
Date: Sun, 11 Sep 2016 12:02:20 +0200
Subject: [PATCH] DOC fix for svd_solver in PCA docstring
---
sklearn/decomposition/pca.py | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/sklearn/decomposition/pca.py b/sklearn/decomposition/pca.py
index aecab027b7..2a6f0dd013 100644
--- a/sklearn/decomposition/pca.py
+++ b/sklearn/decomposition/pca.py
@@ -108,9 +108,12 @@ class PCA(_BasePCA):
Linear dimensionality reduction using Singular Value Decomposition of the
data to project it to a lower dimensional space.
- It uses the scipy.linalg ARPACK implementation of the SVD or a randomized
- SVD by the method of Halko et al. 2009, depending on which is the most
- efficient.
+ It uses the LAPACK implementation of the full SVD or a randomized truncated
+ SVD by the method of Halko et al. 2009, depending on the shape of the input
+ data and the number of components to extract.
+
+ It can also use the scipy.sparse.linalg ARPACK implementation of the
+ truncated SVD.
Read more in the :ref:`User Guide <PCA>`.
@@ -147,10 +150,13 @@ class PCA(_BasePCA):
svd_solver : string {'auto', 'full', 'arpack', 'randomized'}
auto :
the solver is selected by a default policy based on `X.shape` and
- `n_components` which favors 'randomized' when the problem is
- computationally demanding for 'full' PCA
+ `n_components`: if the input data is larger than 500x500 and the
+ number of components to extract is lower than 80% of the smallest
+ dimension of the data, then then more efficient 'randomized'
+ method is enabled. Otherwise the exact full SVD is computed and
+ optionally truncated afterwards.
full :
- run exact SVD calling ARPACK solver via
+ run exact full SVD calling the standard LAPACK solver via
`scipy.linalg.svd` and select the components by postprocessing
arpack :
run SVD truncated to n_components calling ARPACK solver via
--
GitLab