handle n_pca < n_samples

KrishnaswamyLab · Feb 21, 2019 · 34243be · 34243be
1 parent 560ea76
commit 34243be
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/graphtools/base.py b/graphtools/base.py
@@ -105,10 +105,10 @@ class Data(Base):
     def __init__(self, data, n_pca=None, random_state=None, **kwargs):
 
         self._check_data(data)
-        if n_pca is not None and data.shape[1] <= n_pca:
+        if n_pca is not None and np.min(data.shape) <= n_pca:
             warnings.warn("Cannot perform PCA to {} dimensions on "
-                          "data with {} dimensions".format(n_pca,
-                                                           data.shape[1]),
+                          "data with min(n_samples, n_features) = {}".format(
+                              n_pca, np.min(data.shape)),
                           RuntimeWarning)
             n_pca = None
         try:

diff --git a/test/test_data.py b/test/test_data.py
@@ -44,6 +44,12 @@ def test_too_many_n_pca():
     build_graph(data, n_pca=data.shape[1])
 
 
+@warns(RuntimeWarning)
+def test_too_many_n_pca():
+    build_graph(data[:data.shape[1] - 1],
+                n_pca=data.shape[1] - 1)
+
+
 @warns(RuntimeWarning)
 def test_precomputed_with_pca():
     build_graph(squareform(pdist(data)),