# HG changeset patch
# User Thierry Bertin-Mahieux <bertinmt@iro.umontreal.ca>
# Date 1211405970 14400
# Node ID bd728c83faffb1bfb9880ee6c76c8fed7c530195
# Parent  ffd50efefb705bb116a72e6831a9a7b140f945ae
in __get__, problem if the i.stop was None, i being the slice, added one line replacing None by the len(self)

diff -r ffd50efefb70 -r bd728c83faff dataset.py
--- a/dataset.py	Sat May 17 00:01:47 2008 -0400
+++ b/dataset.py	Wed May 21 17:39:30 2008 -0400
@@ -442,7 +442,9 @@
         rows=None
         # or a slice
         if type(i) is slice:
+            #print 'i=',i
             if not i.start: i=slice(0,i.stop,i.step)
+            if not i.stop: i=slice(i.start,len(self),i.step)
             if not i.step: i=slice(i.start,i.stop,1)
             if i.step is 1:
                 return self.minibatches(minibatch_size=i.stop-i.start,n_batches=1,offset=i.start).next().examples()
@@ -662,6 +664,7 @@
         and a values_hstack(fieldnames,fieldvalues) functions behaving with the same
         semantics as the DataSet methods of the same name (but without the self argument).
         """
+
         self._fields=fields_lookuplist
         assert len(fields_lookuplist)>0
         self.length=len(fields_lookuplist[0])
@@ -1140,6 +1143,9 @@
       Note that the expected semantics of the function differs in minibatch mode
       (it takes minibatches of inputs and produces minibatches of outputs, as
       documented in the class comment).
+
+      TBM: are filedtypes the old field types (from input_dataset) or the new ones
+      (for the new dataset created)?
       """
       self.input_dataset=input_dataset
       self.function=function
@@ -1182,6 +1188,7 @@
                   return all_outputs
               return Example(fieldnames,[all_outputs[name] for name in fieldnames])
 
+
       return ApplyFunctionIterator(self)
 
   def __iter__(self): # only implemented for increased efficiency
diff -r ffd50efefb70 -r bd728c83faff denoising_aa.py
--- a/denoising_aa.py	Sat May 17 00:01:47 2008 -0400
+++ b/denoising_aa.py	Wed May 21 17:39:30 2008 -0400
@@ -104,6 +104,7 @@
     def __call__(self, training_set=None):
         model = DenoisingAutoEncoderModel(self)
         if training_set:
+            print 'what do I do if training set????'
             
     def compile(self, inputs, outputs):
         return theano.function(inputs,outputs,unpack_single=False,linker=self.linker)
@@ -118,6 +119,7 @@
 
     def update(self, training_set, train_stats_collector=None):
         
+        print 'dont update you crazy frog!'
 
 # old stuff
 
diff -r ffd50efefb70 -r bd728c83faff learner.py
--- a/learner.py	Sat May 17 00:01:47 2008 -0400
+++ b/learner.py	Wed May 21 17:39:30 2008 -0400
@@ -1,3 +1,4 @@
+
 
 from exceptions import *
 from dataset import AttributesHolder
diff -r ffd50efefb70 -r bd728c83faff mlp_factory_approach.py
--- a/mlp_factory_approach.py	Sat May 17 00:01:47 2008 -0400
+++ b/mlp_factory_approach.py	Wed May 21 17:39:30 2008 -0400
@@ -6,6 +6,7 @@
 
 from tlearn import dataset, nnet_ops, stopper
 
+
 def _randshape(*shape): 
     return (numpy.random.rand(*shape) -0.5) * 0.001
 
@@ -31,7 +32,8 @@
         params = self.params
         #TODO: why should we have to unpack target like this?
         for input, target in input_target:
-            self.update_fn(input, target[:,0], *params)
+            rval= self.update_fn(input, target[:,0], *params)
+            print rval[0]
 
     def __call__(self, testset, fieldnames=['output_class']):
         """Apply this model (as a function) to new data"""
@@ -102,7 +104,7 @@
         # prefer caching in _Model.__call__
         return theano.function(inputs, outputs, unpack_single=False, linker=self.linker)
 
-    def __call__(self, trainset=None, iparams=None):
+    def __call__(self, trainset=None, iparams=None, input='input', target='target'):
         """Allocate and optionally train a model"""
         if iparams is None:
             iparams = [_randshape(self.nhid, self.nclass), _randshape(self.nclass)]\
@@ -119,8 +121,9 @@
             best = rval
             for stp in self.early_stopper():
                 rval.update(
-                    trainset.minibatches(['input', 'target'], minibatch_size=min(32,
+                    minset.minibatches([input, target], minibatch_size=min(32,
                         len(trainset))))
+                print 'mlp.__call__(), we did an update'
                 if stp.set_score:
                     stp.score = rval(valset, ['loss_01'])
                     if (stp.score < stp.best_score):
@@ -154,7 +157,7 @@
                 , linker='c&py'
                 , early_stopper = lambda:stopper.NStages(100,1))
 
-        model1 = learn_algo(training_set1)
+        model1 = learn_algo(training_set1,input='input',target='target')
 
         model2 = learn_algo(training_set2)
 
diff -r ffd50efefb70 -r bd728c83faff stopper.py
--- a/stopper.py	Sat May 17 00:01:47 2008 -0400
+++ b/stopper.py	Wed May 21 17:39:30 2008 -0400
@@ -75,6 +75,9 @@
 
     E_set_score = 'when iter.set_score is True, caller must assign a score to iter.score'
     def next(self):
+
+        print 'ICML08 stopper, were doing a next'
+
         if self.set_score: #left over from last time
             if self.score is None:
                 raise Exception(ICML08Stopper.E_set_score)