New pca workflow and datset updates

fluent

@@ -19,6 +19,7 @@ import logger
 import plots
 import navigator
 import go_workflow
+import pca_workflow
 import scipy
 
 PROGRAM_NAME = 'fluent'
@@ -45,7 +46,8 @@ class FluentApp:
         self.current_data = None
         gtk.glade.set_custom_handler(self.custom_object_factory)
         self.widget_tree = gtk.glade.XML(GLADEFILENAME, 'appwindow')
-        self.workflow = go_workflow.EinarsWorkflow(self)
+        self.workflow = pca_workflow.PCAWorkflow(self)
+        self.workflow.add_project(self.project)
 
     def custom_object_factory(self, glade, function_name, widget_name,\
                               str1, str2, int1, int2):

system/dataset.py

@@ -12,12 +12,16 @@ class Dataset:
     """
     def __init__(self,input_array,def_list):
         self._data = asarray(input_array)
-        self.dims = shape(self._data)
+        dims = shape(self._data)
         self.def_list = def_list
         self._ids_set = set()
         self.ids={}
         self._dim_num = {}
         self._dim_names = []
+        if len(dims)==1: # a vector is defined to be column vector!
+            self.dims = (dims[0],1)
+        else:
+            self.dims = dims
         if len(def_list)!=len(self.dims):
             raise ValueError,"array dims and identifyer mismatch"
         for axis,(dim_name,ids) in enumerate(def_list):
@@ -25,7 +29,7 @@ class Dataset:
             #if dim_name not in project.c_p.dim_names:
             #    dim_name = project.c_p.suggest_dim_name(dim_name)
             if not ids:
-                logger.log('debug','Creating identifiers along: '+dim_name)
+                logger.log('debug','Creating identifiers along: '+ str(dim_name))
                 ids = self._create_identifiers(axis)
             for num,name in enumerate(ids):
                 enum_ids[name] = num
@@ -40,13 +44,21 @@ class Dataset:
                 raise ValueError,"dim size and identifyer mismatch"
             
     def names(self,axis=0):
-        """Returns identifier names of a dimension. NB: not in any order! """
+        """Returns identifier names of a dimension.
+        NB: sorted by values!
+        OK? necessary?"""
         
         if type(axis)==int:
             dim_name = self._dim_names[axis]
         elif type(axis)==str:
             dim_name = axis
-        return self.ids[dim_name].keys()
+        if dim_name not in self._dim_names:
+            raise ValueError, dim_name + " not a dimension in dataset" 
+        items = self.ids[dim_name].items()
+        backitems=[ [v[1],v[0]] for v in items]
+        backitems.sort()
+        sorted_ids=[ backitems[i][1] for i in range(0,len(backitems))]
+        return sorted_ids
     
     def extract_data(self,ids,dim_name):
         """Extracts data along a dimension by identifiers"""

system/workflow.py

@@ -27,6 +27,9 @@ class Workflow:
             for fun in stage.functions:
                 print '        %s' % fun.name
 
+    def add_project(self,project):
+        self.project = project
+
 class Stage:
     """A stage is a part of the data analysis process.
 

workflows/pca_workflow.py

@@ -0,0 +1,89 @@
+import gtk
+import logger
+from workflow import *
+from scipy import array
+from data import read_affy_annot
+import plots
+
+class PCAWorkflow(Workflow):
+
+    def __init__(self, app):
+        Workflow.__init__(self, app)
+        self.name = 'PCAs Workflow'
+
+        load = Stage('load', 'Load Data')
+        load.add_function(Function('load_mootha', 'Load Microarrays'))
+        self.add_stage(load)
+
+        preproc = Stage('preprocess', 'Preprocessing')
+        preproc.add_function(Function('log2', 'Logarithm'))
+        self.add_stage(preproc)
+
+        annot = Stage('annot', 'Affy annotations')
+        annot.add_function(LoadAnnotationsFunction())
+        self.add_stage(annot)
+
+        model = Stage('model', 'Model')
+        model.add_function(Function('pca', 'PCA'))
+        self.add_stage(model)
+        
+        logger.log('debug', '\tPCA\'s workflow is now active')
+
+class LoadAnnotationsFunction(Function):
+
+    def __init__(self):
+        Function.__init__(self, 'load', 'Load Annotations')
+        self.annotations = None
+
+    def load_affy_file(self, filename):
+        f = open(filename)
+        logger.log('notice', 'Loading annotation 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_affy_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 aprsing here
+        annot = read_affy_annot(self.file)
+        return [self.annotations]
+
+class PCAFunction(Function):
+
+    def __init__(self):
+        Function.__init__(self, 'X', 'a_opt')
+        self.output = None
+
+    def run(self, data):
+        logger.log('debug', 'datatype: %s' % type(data))
+        if not isinstance(data,dataset.Dataset):
+            return None
+        logger.log('debug', 'dimensions: %s' % data.dims)
+
+        ## calculations
+        T,P,E,tsq = pca(data._data,a_opt=2)
+        comp_def = ['comp',['1','2']]
+        singel_def = ['1',['s']]
+        col_def = [data._dim_names[0],data.names(0)]
+        row_def = [data._dim_names[1],data.names(1)]
+        T = dataset.Dataset(T,[col_def,comp_def])
+        P = dataset.Dataset(T,[row_def,comp_def])
+        E = dataset.Dataset(E,[col_def,row_def])
+        tsq = dataset.Dataset(tsq,[row_def,sigel_def])
+        
+        ## plots
+        loading_plot = plots.ScatterPlot()
+        
+
+        return [T,P,E,r]
+