Mercurial > pylearn
view test_dataset.py @ 75:90e4c0784d6e
Added draft of LinearRegression learner
author | bengioy@bengiomac.local |
---|---|
date | Sat, 03 May 2008 21:59:26 -0400 |
parents | dde1fb1b63ba |
children | b4159cbdc06b 4b0859606d05 |
line wrap: on
line source
#!/bin/env python from dataset import * from math import * import numpy def test1(): global a,ds a = numpy.random.rand(10,4) print a ds = ArrayDataSet(a,{'x':slice(3),'y':3,'z':[0,2]}) print "len(ds)=",len(ds) assert(len(ds)==10) print "example 0 = ",ds[0] # assert print "x=",ds["x"] print "x|y" for x,y in ds("x","y"): print x,y minibatch_iterator = ds.minibatches(fieldnames=['z','y'],n_batches=1,minibatch_size=3,offset=4) minibatch = minibatch_iterator.__iter__().next() print "minibatch=",minibatch for var in minibatch: print "var=",var print "take a slice and look at field y",ds[1:6:2]["y"] def test_ArrayDataSet(): #don't test stream #tested only with float value a = numpy.random.rand(10,4) print a ds = ArrayDataSet(a,{'x':slice(3),'y':3,'z':[0,2]}) assert len(ds)==10 #assert ds==a? should this work? for i in range(len(ds)): assert ds[i]['x'].all()==a[i][:2].all() assert ds[i]['y']==a[i][3] assert ds[i]['z'].all()==a[i][0:3:2].all() print "x=",ds["x"] print "x|y" i=0 for x in ds('x','y'): assert numpy.append(x['x'],x['y']).all()==a[i].all() i+=1 # i=0 # for x in ds['x','y']: # don't work # assert numpy.append(x['x'],x['y']).all()==a[i].all() # i+=1 # for (x,y) in (ds('x','y'),a): #don't work # haven't found a variant that work. # assert numpy.append(x,y)==z i=0 for x,y in ds('x','y'): assert numpy.append(x,y).all()==a[i].all() i+=1 for minibatch in ds.minibatches(['x','z'], minibatch_size=3): assert minibatch[0][:,0:3:2].all()==minibatch[1].all() for x,z in ds.minibatches(['x','z'], minibatch_size=3): assert x[:,0:3:2].all()==z.all() # for minibatch in ds.minibatches(['z','y'], minibatch_size=3): # print minibatch # minibatch_iterator = ds.minibatches(fieldnames=['z','y'],n_batches=1,minibatch_size=3,offset=4) # minibatch = minibatch_iterator.__iter__().next() # print "minibatch=",minibatch # for var in minibatch: # print "var=",var # print "take a slice and look at field y",ds[1:6:2]["y"] have_thrown = False try: ds['h'] # h is not defined... except : have_thrown = True assert have_thrown == True assert len(ds.fields())==3 for field in ds.fields(): for field_value in field: # iterate over the values associated to that field for all the ds examples pass for field in ds('x','z').fields(): pass for field in ds.fields('x','y'): pass for field_examples in ds.fields(): for example_value in field_examples: pass assert ds == ds.fields().examples() #test missing value assert len(ds[:3])==3 i=0 for x,z in ds[:3]('x','z'): assert ds[i]['z'].all()==a[i][0:3:2].all() i+=1 #ds[i1:i2:s]# returns a ds with the examples i1,i1+s,...i2-s. #ds[i]# returns an Example. #ds[[i1,i2,...in]]# returns a ds with examples i1,i2,...in. #ds[fieldname]# an iterable over the values of the field fieldname across #the ds (the iterable is obtained by default by calling valuesVStack #over the values for individual examples). #ds.<property># returns the value of a property associated with #the name <property>. The following properties should be supported: # - 'description': a textual description or name for the ds # - 'fieldtypes': a list of types (one per field) #* ds1 | ds2 | ds3 == ds.hstack([ds1,ds2,ds3]) #* ds1 & ds2 & ds3 == ds.vstack([ds1,ds2,ds3]) test_ArrayDataSet()