constant number of eigenvalues (#565)

rasbt · Jul 15, 2019 · 0abf710 · 0abf710
1 parent 87cfbf9
commit 0abf710
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 0 deletions.
diff --git a/docs/sources/CHANGELOG.md b/docs/sources/CHANGELOG.md
@@ -35,6 +35,7 @@ The CHANGELOG for the current development version is available at
 ##### Bug Fixes
 
 - Fixed documentation of `iris_data()` under `iris.py` by adding a note about differences in the iris data in R and UCI machine learning repo.
+- Make sure that if the `'svd'` mode is used in PCA, the number of eigenvalues is the same as when using `'eigen'` (append 0's zeros in that case) ([#565](https://github.com/rasbt/mlxtend/pull/565))
 
 ### Version 0.16.0 (05/12/2019)
 

diff --git a/mlxtend/feature_extraction/principal_component_analysis.py b/mlxtend/feature_extraction/principal_component_analysis.py
@@ -160,6 +160,10 @@ def _decomposition(self, mat, n_samples):
             u, s, v = np.linalg.svd(mat_centered.T)
             e_vecs, e_vals = u, s
             e_vals = e_vals ** 2 / n_samples
+            if e_vals.shape[0] < e_vecs.shape[1]:
+                new_e_vals = np.zeros(e_vecs.shape[1])
+                new_e_vals[:e_vals.shape[0]] = e_vals
+                e_vals = new_e_vals
 
         sort_idx = np.argsort(e_vals)[::-1]
         e_vals, e_vecs = e_vals[sort_idx], e_vecs[:, sort_idx]