[coordinates] introduced new config var "coordinates_check_output" to…

… check for inf and NaN in iterator output.

Can be enabled by config.coordinates_check_input=True. Exception contains position information.

pyemma/coordinates/data/_base/datasource.py

@@ -671,6 +671,14 @@ def next(self):
                 (not self.return_traj_index and len(X) == 0) or (self.return_traj_index and len(X[1]) == 0)
         ):
             X = self._it_next()
+        if config.coordinates_check_output:
+            array = X if not self.return_traj_index else X[1]
+            if not np.all(np.isfinite(array)):
+                # determine position
+                start = self.pos
+                msg = "Found invalid values in chunk in trajectory index {itraj} at chunk [{start}, {stop}]" \
+                    .format(itraj=self.current_trajindex, start=start, stop=start+len(array))
+                raise InvalidDataInStreamException(msg)
         return X
 
     def __iter__(self):
@@ -683,3 +691,6 @@ def __exit__(self, exc_type, exc_val, exc_tb):
         self.close()
         return False
 
+
+class InvalidDataInStreamException(Exception):
+    """Data stream contained NaN or (+/-) infinity"""

pyemma/coordinates/tests/test_coordinates_iterator.py

@@ -2,6 +2,7 @@
 import numpy as np
 
 from pyemma.coordinates.data import DataInMemory
+from pyemma.util.contexts import settings
 from pyemma.util.files import TemporaryDirectory
 import os
 from glob import glob
@@ -153,5 +154,25 @@ def test_write_to_csv_propagate_filenames(self):
             for a, e in zip(actual, expected):
                 np.testing.assert_allclose(a, e)
 
+    def test_invalid_data_in_input_nan(self):
+        self.d[0][-1] = np.nan
+        r = DataInMemory(self.d)
+        it = r.iterator()
+        from pyemma.coordinates.data._base.datasource import InvalidDataInStreamException
+        with settings(coordinates_check_output=True):
+            with self.assertRaises(InvalidDataInStreamException):
+                for itraj, X in it:
+                    pass
+
+    def test_invalid_data_in_input_inf(self):
+        self.d[1][-1] = np.inf
+        r = DataInMemory(self.d, chunksize=5)
+        it = r.iterator()
+        from pyemma.coordinates.data._base.datasource import InvalidDataInStreamException
+        with settings(coordinates_check_output=True):
+            with self.assertRaises(InvalidDataInStreamException) as cm:
+                for itraj, X in it:
+                    pass
+
 if __name__ == '__main__':
     unittest.main()

pyemma/pyemma.cfg

@@ -24,4 +24,7 @@ use_trajectory_lengths_cache = True
 # maximum entries in database
 traj_info_max_entries = 50000
 # max size in MB
-traj_info_max_size = 500
+traj_info_max_size = 500
+
+# check output of iterators in pyemma.coordinates for infinity and NaN, useful for debug purposes.
+coordinates_check_output = False

pyemma/util/config.py

@@ -45,6 +45,7 @@
            'use_trajectory_lengths_cache',
            'traj_info_max_entries',
            'traj_info_max_size',
+           'coordinates_check_output',
            )
 
 if six.PY2:
@@ -364,6 +365,14 @@ def show_config_notification(self):
     def show_config_notification(self, val):
         self._conf_values.set('pyemma', 'show_config_notification', str(val))
 
+    @property
+    def coordinates_check_output(self):
+        return self._conf_values.getboolean('pyemma', 'coordinates_check_output')
+
+    @coordinates_check_output.setter
+    def coordinates_check_output(self, val):
+        self._conf_values.set('pyemma', 'coordinates_check_output', str(val))
+
     ### FIlE HANDLING
 
     def __copy_default_files_to_cfg_dir(self, target_dir):