From ecd07bc78c089092b244c0b390890da6b03bc1a5 Mon Sep 17 00:00:00 2001
From: "Martin K. Scherer" <marscher@users.noreply.github.com>
Date: Tue, 7 Jun 2016 14:24:31 +0200
Subject: [PATCH] [coor/datasource] in case input files have different
 dimensions, give a useful msg. (#822)

---
 pyemma/coordinates/data/_base/datasource.py      | 15 +++++++++++++--
 pyemma/coordinates/tests/test_numpyfilereader.py | 13 ++++++++++++-
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/pyemma/coordinates/data/_base/datasource.py b/pyemma/coordinates/data/_base/datasource.py
index 2bc340fab..91feb1948 100644
--- a/pyemma/coordinates/data/_base/datasource.py
+++ b/pyemma/coordinates/data/_base/datasource.py
@@ -123,8 +123,19 @@ def filenames(self, filename_list):
 
             # ensure all trajs have same dim
             if not np.unique(ndims).size == 1:
-                raise ValueError("input data has different dimensions!"
-                                 " Dimensions are = %s" % zip(filename_list, ndims))
+                # group files by their dimensions to give user indicator
+                ndims = np.array(ndims)
+                filename_list = np.asarray(filename_list)
+                sort_inds = np.argsort(ndims)
+                import itertools, operator
+                res = {}
+                for dim, files in itertools.groupby(zip(ndims[sort_inds], filename_list[sort_inds]),
+                                                    operator.itemgetter(0)):
+                    res[dim] = list(f[1] for f in files)
+
+                raise ValueError("Input data has different dimensions ({dims})!"
+                                 " Files grouped by dimensions: {groups}".format(dims=res.keys(),
+                                                                                  groups=res))
 
             self._ndim = ndims[0]
             self._lengths = lengths
diff --git a/pyemma/coordinates/tests/test_numpyfilereader.py b/pyemma/coordinates/tests/test_numpyfilereader.py
index eb1c473cf..0d98ce382 100644
--- a/pyemma/coordinates/tests/test_numpyfilereader.py
+++ b/pyemma/coordinates/tests/test_numpyfilereader.py
@@ -197,7 +197,18 @@ def test_usecols(self):
         with it:
             for x in it:
                 np.testing.assert_equal(x, self.d2[:, cols])
-        
+
+    def test_different_shapes_value_error(self):
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.npy') as f:
+            x=np.zeros((3, 42))
+            np.save(f.name, x)
+            myfiles = self.files2d[:]
+            myfiles.insert(1, f.name)
+
+            with self.assertRaises(ValueError) as cm:
+                NumPyFileReader(myfiles)
+            self.assertIn("different dimensions", cm.exception.args[0])
+            print (cm.exception.args)
 
 
 if __name__ == "__main__":