Added category dataset

system/dataset.py

@@ -1,4 +1,4 @@
-from scipy import atleast_2d,asarray,ArrayType,shape
+from scipy import atleast_2d,asarray,ArrayType,shape,nonzero
 from scipy import sort as array_sort
 from itertools import izip
 
@@ -182,7 +182,7 @@ class Dataset:
         else:
             index = [self._map[dim][key] for key in idents]
         return asarray(index)
-     
+
 class CategoryDataset(Dataset):
     """The category dataset class.
 
@@ -192,25 +192,30 @@ class CategoryDataset(Dataset):
     There is support for using a less memory demanding, and
     fast intersection look-ups by representing the binary matrix as a
     dictionary in each dimension.
+
+    Always has linked dimension in first dim:
+    ex matrix:
+             go_term1    go_term2  ...
+    gene_1
+    gene_2
+    gene_3
+    .
+    .
+    .
     """
     
-    def __init__(self):
+    def __init__(self,array,identifiers=None,name='A'):
-        Dataset.__init__(self)
+        Dataset.__init__(self,array,identifiers=identifiers,name=name)
+        self.has_dictlists = False
             
-    def as_collection(self,dim):
+    def as_dict_lists(self):
-        """Returns data as collection along dim"""
+        """Returns data as dict of indices along first dim"""
-        pass
+        data={}
-    
+        for name,ind in self._map[self.get_dim_name(0)].items():
-    def add_collection(self,input_dict):
+            data[name] = list(nonzero(self._array[ind,:]))
-        """Adds a category data as collection.
+        self._dictlists = data
-
+        self.has_dictlists=True
-        A collection is a datastructure that contains a dictionary for
+        return data       
-        each pair of dimension in dataset, keyed by identifiers and
-        values is a set of identifiers in the other dimension
-        """
-        #build category data as double dicts
-        pass
-
 
 class GraphDataset(Dataset):
     """The graph dataset class.