cnmf/hdf5: Improve handling of serialisation of NoneType. Also fix some typos.

Author: pgunn

caiman/source_extraction/cnmf/estimates.py

@@ -1421,7 +1421,7 @@ def remove_small_large_neurons(self, min_size_neuro, max_size_neuro,
                 indeces of components with size within the acceptable range
         '''
         if self.A_thr is None:
-            raise Exception('You need to compute thresolded components before calling remove_duplicates: use the threshold_components method')
+            raise Exception('You need to compute thresholded components before calling remove_duplicates: use the threshold_components method')
 
         A_gt_thr_bin = self.A_thr.toarray() > 0
         size_neurons_gt = A_gt_thr_bin.sum(0)
@@ -1451,7 +1451,7 @@ def remove_duplicates(self, predictions=None, r_values=None, dist_thr=0.1,
             plot_duplicates
         '''
         if self.A_thr is None:
-            raise Exception('You need to compute thresolded components before calling remove_duplicates: use the threshold_components method')
+            raise Exception('You need to compute thresholded components before calling remove_duplicates: use the threshold_components method')
 
         A_gt_thr_bin = (self.A_thr.toarray() > 0).reshape([self.dims[0], self.dims[1], -1], order='F').transpose([2, 0, 1]) * 1.
 
@@ -1492,7 +1492,7 @@ def masks_2_neurofinder(self, dataset_name):
         """
         if self.A_thr is None:
             raise Exception(
-                'You need to compute thresolded components before calling this method: use the threshold_components method')
+                'You need to compute thresholded components before calling this method: use the threshold_components method')
         bin_masks = self.A_thr.reshape([self.dims[0], self.dims[1], -1], order='F').transpose([2, 0, 1])
         return nf_masks_to_neurof_dict(bin_masks, dataset_name)
 
@@ -1711,10 +1711,10 @@ def compare_components(estimate_gt, estimate_cmp,  Cn=None, thresh_cost=.8, min_
                        labels=['GT', 'CMP'], plot_results=False):
     if estimate_gt.A_thr is None:
         raise Exception(
-            'You need to compute thresolded components for first argument before calling remove_duplicates: use the threshold_components method')
+            'You need to compute thresholded components for first argument before calling remove_duplicates: use the threshold_components method')
     if estimate_cmp.A_thr is None:
         raise Exception(
-            'You need to compute thresolded components for second argument before calling remove_duplicates: use the threshold_components method')
+            'You need to compute thresholded components for second argument before calling remove_duplicates: use the threshold_components method')
 
     if plot_results:
         plt.figure(figsize=(20, 10))

caiman/source_extraction/cnmf/spatial.py

@@ -455,7 +455,7 @@ def construct_ellipse_parallel(pars):
     return np.sqrt(np.sum([old_div((dist_cm * V[:, k]) ** 2, dkk[k]) for k in range(len(dkk))], 0)) <= dist
 
 def threshold_components(A, dims, medw=None, thr_method='max', maxthr=0.1, nrgthr=0.9999, extract_cc=True,
-                         se=None, ss=None, dview=None):
+                         se=None, ss=None, dview=None) -> np.ndarray:
     """
     Post-processing of spatial components which includes the following steps
 

caiman/utils/utils.py

@@ -544,6 +544,10 @@ def recursively_load_dict_contents_from_group(h5file:h5py.File, path:str) -> Dic
     Starting with Caiman 1.9.9 we started saving strings as attributes rather than independent datasets,
     which gets us a better syntax and less damage to the strings, at the cost of scanning properly for them
     being a little more involved. In future versions of Caiman we may store all scalars as attributes.
+
+    There's some special casing here that should be solved in a more general way; anything serialised into
+    hdf5 and then deserialised should probably go back through the class constructor, and revalidated
+    so all the fields end up with appropriate data types.
     '''
 
     ans:Dict = {}
@@ -560,7 +564,6 @@ def recursively_load_dict_contents_from_group(h5file:h5py.File, path:str) -> Dic
                     ans[key] = item[()]
 
             elif key in ['dims', 'medw', 'sigma_smooth_snmf', 'dxy', 'max_shifts', 'strides', 'overlaps']:
-
                 if isinstance(item[()], np.ndarray):
                     ans[key] = tuple(item[()])
                 else:
@@ -570,6 +573,8 @@ def recursively_load_dict_contents_from_group(h5file:h5py.File, path:str) -> Dic
                     ans[key] = bool(item[()])
                 else:
                     ans[key] = item[()]
+                    if isinstance(ans[key], bytes) and ans[key] == b'NoneType':
+                        ans[key] = None
 
         elif isinstance(item, h5py._hl.group.Group):
             if key in ('A', 'W', 'Ab', 'downscale_matrix', 'upscale_matrix'):