op

system/dataset.py

@@ -6,8 +6,10 @@ from itertools import izip
 
 
 class Dataset:
-    """
-    Dataset base class
+    """Dataset base class.
+
+    A Dataset is an n-way array with defined string identifiers across
+    all dimensions.
     """
     def __init__(self,input_array,def_list,parents=None):
         self._data = asarray(input_array)
@@ -18,6 +20,7 @@ class Dataset:
         self.ids={}
         self.children=[]
         self._dim_num = {}
+        self._dim_names = []
         if parents!=None:
             for parent in self.parents:
                 parent.children.append(self)
@@ -34,13 +37,23 @@ class Dataset:
             self.ids[dim_name] = enum_ids
             self._ids_set = self._ids_set.union(set(ids))
             self._dim_num[dim_name] = axis
+            self._dim_names.append(dim_name)
         for df,d in izip(def_list,self.dims):
             df=df[1]
             if len(df)!=d and df:
                 raise ValueError,"dim size and identifyer mismatch"
 
-            
+    def names(self,axis=0):
+        """Returns identifier names of a dimension. NB: not in any order! """
+        
+        if type(axis)==int:
+            dim_name = self._dim_names[axis]
+        elif type(axis)==str:
+            dim_name = axis
+        return self.ids[dim_name].keys()
+    
     def extract_data(self,ids,dim_name):
+        """Extracts data along a dimension by identifiers"""
         new_def_list = self.def_list[:]
         ids_index = [self.ids[dim_name][id_name] for id_name in ids]
         dim_number = self._dim_num[dim_name]
@@ -49,13 +62,15 @@ class Dataset:
         except:
             raise ValueError
         new_def_list[dim_number][1] = ids
-        D = Dataset(out_data,def_list=new_def_list,parents=self.parents)
-        return D
+        extracted_data = Dataset(out_data,def_list=new_def_list,parents=self.parents)
+        return extracted_data
 
     def _create_identifiers(self,axis):
+        """Creates identifiers along an axis"""
         n_dim = self.dims[axis]
         return [str(axis) + '_' + str(i) for i in range(n_dim)]
         
 class Selection:
+    """Handles selected identifiers along each dimension of a dataset"""
     def __init__(self):
         self.current_selection={}