More persumably non-working stuff.

workflows/go_workflow.py

@@ -112,6 +112,7 @@ class GoWorkflow (workflow.Workflow):
         load = workflow.Stage('load', 'Load GO Annotations')
         load.add_function(LoadGOFunction())
         load.add_function(LoadAnnotationsFunction())
+        load.add_function(LoadTextDatasetFunction())
         self.add_stage(load)
         
         go = workflow.Stage('go', 'Gene Ontology')
@@ -143,6 +144,7 @@ class LoadTextDatasetFunction(workflow.Function):
         identifiers = {}
         type = 'dataset'
         name = 'Unnamed dataset'
+        graphtype = 'graph'
 
         # Read header lines from file.
         line = fd.readline()
@@ -168,13 +170,45 @@ class LoadTextDatasetFunction(workflow.Function):
                 elif key == 'name':
                     name = val
 
+                elif key == 'graphtype':
+                    graphtype = val
+
             else:
                 break
             line = f.readline()
 
-            
+        # Dimensions in the form [(dim1, [id1, id2, id3 ..) ...] 
+        dims = [(x, identifiers[x]) for x in dimensions]
+        dim_lengths = [len(identifiers[x]) for x in dimensions]
+
+        # Create dataset of specified type
+        if type == 'category':
+            matrix = zeros(dim_lengths, dtype=bool)
+            ds = dataset.CategoryDataset(matrix, dims)
+        elif type == 'network':
+            matrix = zeros(dim_lengths)
+            ds = dataset.GraphDataset(matrix, dims)
+        else:
+            matrix = zeros(dim_lengths)
+            ds = dataset.Dataset(matrix, dims)
+
+        line = f.readline()
+        y = 0
+        while line:
+            values = line.split()
+            for x, v in enumerate(values):
+                matrix[x,y] = float(v)
+            y += 1
+            line = f.readline()
+
+        # Build NetowrkX graph from matrix.
+        if type == 'network':
+            matrix = zeros(dim_lengths)
+            ds = dataset.NetworkDataset(matrix, dims)
+
+
     def run(self):
-        f = open('/home/einarr/foodata.tds')
+        f = open('/home/einarr/foodata.fcsv')
         return read_text_dataset(f)