view test_dataset.py @ 142:ad144fa72bf5

Automated merge with ssh://p-omega1@lgcm.iro.umontreal.ca/tlearn
author Frederic Bastien <bastienf@iro.umontreal.ca>
date Mon, 12 May 2008 14:15:16 -0400
parents 0c6fec172ae1
children 933db7ece663
line wrap: on
line source

#!/bin/env python
from dataset import *
from math import *
import numpy

def have_raised(to_eval):
    have_thrown = False
    try:
        eval(to_eval)
    except :
        have_thrown = True
    return have_thrown

def test1():
    print "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
    #don't always test with y
    #don't test missing value
    #don't test with tuple
    #don't test proterties
    def test_iterate_over_examples(array,ds):
#not in doc!!!
        i=0
        for example in range(len(ds)):
            assert (ds[example]['x']==a[example][:3]).all()
            assert ds[example]['y']==a[example][3]
            assert (ds[example]['z']==a[example][[0,2]]).all()
            i+=1
        assert i==len(ds)
        del example,i

#     - for example in dataset:
        i=0
        for example in ds:
            assert len(example)==3
            assert (example['x']==array[i][:3]).all()
            assert example['y']==array[i][3]
            assert (example['z']==array[i][0:3:2]).all()
            assert (numpy.append(example['x'],example['y'])==array[i]).all()
            i+=1
        assert i==len(ds)
        del example,i

#     - for val1,val2,... in dataset:
        i=0
        for x,y,z in ds:
            assert (x==array[i][:3]).all()
            assert y==array[i][3]
            assert (z==array[i][0:3:2]).all()
            assert (numpy.append(x,y)==array[i]).all()
            i+=1
        assert i==len(ds)
        del x,y,z,i

#     - for example in dataset(field1, field2,field3, ...):
        i=0
        for example in ds('x','y','z'):
            assert len(example)==3
            assert (example['x']==array[i][:3]).all()
            assert example['y']==array[i][3]
            assert (example['z']==array[i][0:3:2]).all()
            assert (numpy.append(example['x'],example['y'])==array[i]).all()
            i+=1
        assert i==len(ds)
        del example,i
        i=0
        for example in ds('y','x'):
            assert len(example)==2
            assert (example['x']==array[i][:3]).all()
            assert example['y']==array[i][3]
            assert (numpy.append(example['x'],example['y'])==array[i]).all()
            i+=1
        assert i==len(ds)
        del example,i

#     - for val1,val2,val3 in dataset(field1, field2,field3):
        i=0
        for x,y,z in ds('x','y','z'):
            assert (x==array[i][:3]).all()
            assert y==array[i][3]
            assert (z==array[i][0:3:2]).all()
            assert (numpy.append(x,y)==array[i]).all()
            i+=1
        assert i==len(ds)
        del x,y,z,i
        i=0
        for y,x in ds('y','x',):
            assert (x==array[i][:3]).all()
            assert y==array[i][3]
            assert (numpy.append(x,y)==array[i]).all()
            i+=1
        assert i==len(ds)
        del x,y,i

        def test_minibatch_size(minibatch,minibatch_size,len_ds,nb_field,nb_iter_finished):
            ##full minibatch or the last minibatch
            for idx in range(nb_field):
                test_minibatch_field_size(minibatch[idx],minibatch_size,len_ds,nb_iter_finished)
            del idx
        def test_minibatch_field_size(minibatch_field,minibatch_size,len_ds,nb_iter_finished):
            assert len(minibatch_field)==minibatch_size or ((nb_iter_finished*minibatch_size+len(minibatch_field))==len_ds and len(minibatch_field)<minibatch_size)

#     - for minibatch in dataset.minibatches([field1, field2, ...],minibatch_size=N):
        i=0
        mi=0
        m=ds.minibatches(['x','z'], minibatch_size=3)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for minibatch in m:
            assert len(minibatch)==2
            test_minibatch_size(minibatch,m.minibatch_size,len(ds),2,mi)
            assert (minibatch[0][:,0:3:2]==minibatch[1]).all()
            mi+=1
            i+=len(minibatch[0])
        assert i==len(ds)
        assert mi==4
        del minibatch,i,m,mi

        i=0
        mi=0
        m=ds.minibatches(['x','y'], minibatch_size=3)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for minibatch in m:
            assert len(minibatch)==2
            test_minibatch_size(minibatch,m.minibatch_size,len(ds),2,mi)
            mi+=1
            for id in range(len(minibatch[0])):
                assert (numpy.append(minibatch[0][id],minibatch[1][id])==a[i]).all()
                i+=1
        assert i==len(ds)
        assert mi==4
        del minibatch,i,id,m,mi

#     - for mini1,mini2,mini3 in dataset.minibatches([field1, field2, field3], minibatch_size=N):
        i=0
        mi=0
        m=ds.minibatches(['x','z'], minibatch_size=3)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for x,z in m:
            test_minibatch_field_size(x,m.minibatch_size,len(ds),mi)
            test_minibatch_field_size(z,m.minibatch_size,len(ds),mi)
            assert (x[:,0:3:2]==z).all()
            i+=len(x)
            mi+=1
        assert i==len(ds)
        assert mi==4
        del x,z,i,m,mi
        i=0
        mi=0
        m=ds.minibatches(['x','y'], minibatch_size=3)
        for x,y in m:
            test_minibatch_field_size(x,m.minibatch_size,len(ds),mi)
            test_minibatch_field_size(y,m.minibatch_size,len(ds),mi)
            mi+=1
            for id in range(len(x)):
                assert (numpy.append(x[id],y[id])==a[i]).all()
                i+=1
        assert i==len(ds)
        assert mi==4
        del x,y,i,id,m,mi

#not in doc
        i=0
        m=ds.minibatches(['x','y'],n_batches=1,minibatch_size=3,offset=4)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for x,y in m:
            assert len(x)==3
            assert len(y)==3
            for id in range(3):
                assert (numpy.append(x[id],y[id])==a[i+4]).all()
                i+=1
        assert i==3
        del x,y,i,id,m

        i=0
        m=ds.minibatches(['x','y'],n_batches=2,minibatch_size=3,offset=4)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for x,y in m:
            assert len(x)==3
            assert len(y)==3
            for id in range(3):
                assert (numpy.append(x[id],y[id])==a[i+4]).all()
                i+=1
        assert i==6
        del x,y,i,id,m

        i=0
        m=ds.minibatches(['x','y'],n_batches=20,minibatch_size=3,offset=4)
        assert isinstance(m,DataSet.MinibatchWrapAroundIterator)
        for x,y in m:
            assert len(x)==3
            assert len(y)==3
            for id in range(3):
                assert (numpy.append(x[id],y[id])==a[(i+4)%a.shape[0]]).all()
                i+=1
        assert i==m.n_batches*m.minibatch_size
        del x,y,i,id


    def test_ds_iterator(array,iterator1,iterator2,iterator3):
        i=0
        for x,y in iterator1:
            assert (x==array[i][:3]).all()
            assert y==array[i][3]
            assert (numpy.append(x,y)==array[i]).all()
            i+=1
        assert i==len(ds)
        i=0
        for y,z in iterator2:
            assert y==array[i][3]
            assert (z==array[i][0:3:2]).all()
            i+=1
        assert i==len(ds)
        i=0
        for x,y,z in iterator3:
            assert (x==array[i][:3]).all()
            assert y==array[i][3]
            assert (z==array[i][0:3:2]).all()
            assert (numpy.append(x,y)==array[i]).all()
            i+=1
        assert i==len(ds)

    def test_getitem(array,ds):
        
        def test_ds(orig,ds,index):
            i=0
            assert len(ds)==len(index)
            for x,z,y in ds('x','z','y'):
                assert (orig[index[i]]['x']==array[index[i]][:3]).all()
                assert (orig[index[i]]['x']==x).all()
                assert orig[index[i]]['y']==array[index[i]][3]
                assert orig[index[i]]['y']==y
                assert (orig[index[i]]['z']==array[index[i]][0:3:2]).all()
                assert (orig[index[i]]['z']==z).all()
                i+=1
            del i
            ds[0]
            if len(ds)>2:
                ds[:1]
                ds[1:1]
                ds[1:1:1]
            if len(ds)>5:
                ds[[1,2,3]]
            for x in ds:
                pass

    #ds[:n] returns a dataset with the n first examples.
        ds2=ds[:3]
        assert isinstance(ds2,DataSet)
        test_ds(ds,ds2,index=[0,1,2])
        del ds2

    #ds[i1:i2:s]# returns a ds with the examples i1,i1+s,...i2-s.
        ds2=ds[1:7:2]
        assert isinstance(ds2,DataSet)
        test_ds(ds,ds2,[1,3,5])
        del ds2

    #ds[i]
        ds2=ds[5]
        assert isinstance(ds2,Example)
        assert have_raised("ds["+str(len(ds))+"]")  # index not defined
        assert not have_raised("ds["+str(len(ds)-1)+"]")
        del ds2
        
    #ds[[i1,i2,...in]]# returns a ds with examples i1,i2,...in.
        ds2=ds[[4,7,2,8]]
        assert isinstance(ds2,DataSet)
        test_ds(ds,ds2,[4,7,2,8])
        del ds2

    #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).
        assert have_raised("ds['h']")  # h is not defined...
        assert have_raised("ds[['x']]")  # bad syntax
        assert not have_raised("ds['x']")
        isinstance(ds['x'],DataSetFields)
        ds2=ds['x']
        assert len(ds['x'])==10
        assert len(ds['y'])==10
        assert len(ds['z'])==10
        i=0
        for example in ds['x']:
            assert (example==a[i][:3]).all()
            i+=1
        i=0
        for example in ds['y']:
            assert (example==a[i][3]).all()
            i+=1
        i=0
        for example in ds['z']:
            assert (example==a[i,0:3:2]).all()
            i+=1
        del ds2,i

    #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])#????
        #hstack([ds('x','y'),ds('z')]
        #hstack([ds('z','y'),ds('x')]
        #assert have_thrown("hstack([ds('x'),ds('x')]")
        #assert not have_thrown("hstack([ds('x'),ds('x')]")
        #accept_nonunique_names
        #assert have_thrown("hstack([ds('y','x'),ds('x')]")
#        i=0
#        for example in hstack([ds('x'),ds('y'),ds('z')]):
#            example==ds[i]
#            i+=1 
#        del i,example
    #* ds1 & ds2 & ds3 == ds.vstack([ds1,ds2,ds3])#????


    print "test_ArrayDataSet"
    a = numpy.random.rand(10,4)
    ds = ArrayDataSet(a,{'x':slice(3),'y':3,'z':[0,2]})###???tuple not tested
    ds = ArrayDataSet(a,LookupList(['x','y','z'],[slice(3),3,[0,2]]))###???tuple not tested
    assert len(ds)==10
    #assert ds==a? should this work?

    test_iterate_over_examples(a, ds)
    test_getitem(a, ds)

#     - for val1,val2,val3 in dataset(field1, field2,field3):
    test_ds_iterator(a,ds('x','y'),ds('y','z'),ds('x','y','z'))


    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()
#    for ((x,y),a_v) in (ds('x','y'),a): #???don't work # haven't found a variant that work.# will not work
#        assert numpy.append(x,y)==z

def test_LookupList():
    #test only the example in the doc???
    print "test_LookupList"
    example = LookupList(['x','y','z'],[1,2,3])
    example['x'] = [1, 2, 3] # set or change a field
    x, y, z = example
    x = example[0]
    x = example["x"]
    assert example.keys()==['x','y','z']
    assert example.values()==[[1,2,3],2,3]
    assert example.items()==[('x',[1,2,3]),('y',2),('z',3)]
    example.append_keyval('u',0) # adds item with name 'u' and value 0
    assert len(example)==4 # number of items = 4 here
    example2 = LookupList(['v','w'], ['a','b'])
    example3 = LookupList(['x','y','z','u','v','w'], [[1, 2, 3],2,3,0,'a','b'])
    assert example+example2==example3
    assert have_raised("example+example")

def test_ApplyFunctionDataSet():
    print "test_ApplyFunctionDataSet"
    raise NotImplementedError()
def test_CacheDataSet():
    print "test_CacheDataSet"
    raise NotImplementedError()
def test_FieldsSubsetDataSet():
    print "test_FieldsSubsetDataSet"
    raise NotImplementedError()
def test_DataSetFields():
    print "test_DataSetFields"
    raise NotImplementedError()
def test_MinibatchDataSet():
    print "test_MinibatchDataSet"
    raise NotImplementedError()
def test_HStackedDataSet():
    print "test_HStackedDataSet"
    raise NotImplementedError()
def test_VStackedDataSet():
    print "test_VStackedDataSet"
    raise NotImplementedError()
def test_ArrayFieldsDataSet():
    print "test_ArrayFieldsDataSet"
    raise NotImplementedError()

test1()
test_LookupList()
test_ArrayDataSet()
#test pmat.py