Errors when identifers dont match shape, + whitespace

fluents/dataset.py

@@ -42,22 +42,24 @@ class Dataset:
         self._name = name
         self._identifiers = identifiers
         self._type = 'n'
-        try:
+
+        if len(array.shape)==1:
             array = atleast_2d(asarray(array))
-        except:
-            print "Cant cast array as numpy-array"
-            return
             # vectors are column vectors 
             if array.shape[0]==1:
                 array = array.T
         self.shape = array.shape
-
         if identifiers!=None:
+            identifier_shape = [len(i[1]) for i in identifiers]
+            if len(identifier_shape)!=len(self.shape):
+                raise ValueError, "Identifier list length must equal array dims"
+            for ni, na in zip(identifier_shape, self.shape):
+                if ni!=na:
+                    raise ValueError, "identifier-array mismatch in %s: (idents: %s, array: %s)" %(self._name, ni, na)
             self._set_identifiers(identifiers, self._all_dims)
         else:
             self._identifiers = self._create_identifiers(self.shape, self._all_dims)
             self._set_identifiers(self._identifiers, self._all_dims)
-            
         self._array = array
 
     def __iter__(self):
@@ -103,7 +105,6 @@ class Dataset:
                 all_dims.add(dim)
             else:
                 raise ValueError, "Dimension names must be unique whitin dataset"
-            
             for pos, id in enumerate(ids):
                 pos_map[id] = pos
             self._map[dim] = pos_map
@@ -125,7 +126,6 @@ class Dataset:
         """Adds array as an ArrayType object.
         A one-dim array is transformed to a two-dim array (row-vector)
         """
-        
         if self.shape!=array.shape:
             raise ValueError, "Input array must be of similar dimensions as dataset"
         self._array = atleast_2d(asarray(array))
@@ -178,7 +178,6 @@ class Dataset:
         You can optionally provide a list of identifiers to retrieve a
         index subset.
         
-        
         Identifiers are the unique names (strings) for a variable in a
         given dim.  Index (Indices) are the Identifiers position in a
         matrix in a given dim.  If none of the input identifiers are
@@ -254,7 +253,7 @@ class GraphDataset(Dataset):
 
     A dataset class for representing graphs using an (weighted)
     adjacency matrix
-    (aka. restricted to square symmetric matrices)
+    (restricted to square symmetric matrices)
     
     If the library NetworkX is installed, there is support for
     representing the graph as a NetworkX.Graph, or NetworkX.XGraph structure.
@@ -310,6 +309,7 @@ class GraphDataset(Dataset):
         
 Dataset._all_dims = set()
 
+
 class ReverseDict(dict):
     """
     A dictionary which can lookup values by key, and keys by value.
@@ -341,12 +341,15 @@ def to_file(filepath,dataset,name=None):
         names = data.keys()
         if name in names:
             print "Data with name: %s overwritten" %dataset._name
-    sub_data = {'array':dataset._array,'idents':dataset._identifiers,'type':dataset._type}
+    
+    sub_data = {'array':dataset._array,
+                'idents':dataset._identifiers,
+                'type':dataset._type}
     data[name] = sub_data 
     data.close()
 
 def from_file(filepath):
-    """Read dataset from file """
+    """Read dataset(s) from file """
     data = shelve.open(filepath, flag='r')
     out_data = []
     for name in data.keys():
@@ -360,6 +363,7 @@ def from_file(filepath):
             
     return out_data
 
+
 class Selection(dict):
     """Handles selected identifiers along each dimension of a dataset"""