workflow update

workflows/pca_workflow.py

@@ -2,7 +2,7 @@ import gtk
 import logger
 from workflow import *
 from scipy import array
-from data import read_affy_annot
+from data import read_affy_annot,read_mootha,data_dict_to_matrix
 import plots
 
 class PCAWorkflow(Workflow):
@@ -12,7 +12,7 @@ class PCAWorkflow(Workflow):
         self.name = 'PCAs Workflow'
 
         load = Stage('load', 'Load Data')
-        load.add_function(Function('load_mootha', 'Load Microarrays'))
+        load.add_function(Function('load_mootha', 'Load'))
         self.add_stage(load)
 
         preproc = Stage('preprocess', 'Preprocessing')
@@ -103,3 +103,34 @@ class PCAFunction(Function):
 
         return [T,P,E,r]
 
+class LoadMoothaData(Function):
+    def __init__(self):
+        Function.__init__(self, 'load', 'Load diabetes data')
+        self.annotations = None
+
+    def load_expression_file(self, filename):
+        f = open(filename)
+        logger.log('notice', 'Loading expression file: %s' % filename)
+        self.file = f
+        
+    def on_response(self, dialog, response):
+        if response == gtk.RESPONSE_OK:
+            logger.log('notice', 'Reading file: %s' % dialog.get_filename())
+            self.load_expression_file(dialog.get_filename())
+
+    def run(self, data):
+        btns = ('Open', gtk.RESPONSE_OK, \
+                'Cancel', gtk.RESPONSE_CANCEL)
+        dialog = gtk.FileChooserDialog('Open Affy Annotation File',
+                                       buttons=btns)
+        dialog.connect('response', self.on_response)
+        dialog.run()
+        dialog.destroy()
+
+        ### Reading and parsing here
+        d,sample_names = read_mootha(self.file)
+        x,gene_ids = data_dict_to_matrix(d)
+        gene_def = ['genes',gene_ids]
+        sample_def = ['samples', sample_names]
+        X = dataset.Dataset(x,[sample_def,gene_def]) # samples x genes
+        return X