diff test_dataset.py @ 259:621faba17c60

created 'dummytests', tests that checks consistency of new weird datasets, where we can't compare with actual values in a matrix, for instance. Useful as a first debugging when creating a dataset
author Thierry Bertin-Mahieux <bertinmt@iro.umontreal.ca>
date Tue, 03 Jun 2008 16:41:55 -0400
parents bf0a1ebc6e52
children 792f81d65f82
line wrap: on
line diff
--- a/test_dataset.py	Tue Jun 03 16:06:21 2008 -0400
+++ b/test_dataset.py	Tue Jun 03 16:41:55 2008 -0400
@@ -558,6 +558,95 @@
     f_ds_mb2(ds,10000)
 
 
+
+
+
+
+#****************************************************************
+# dummy tests, less powerful than the previous tests, but can work with any new weird dataset.
+# Basically, emphasis is put on consistency, but it never checks the actual values.
+# To be used as a checklist, or a first test, when creating a new dataset
+
+def dummytest_all(ds) :
+    """ Launches all the dummytests with a given dataset. """
+
+
+def test1_basicstats(self,ds) :
+    """print basics stats on a dataset, like length"""
+
+    print 'len(ds) = ',len(ds)
+    print 'num fields = ', len(ds.fieldNames())
+    print 'types of field: ',
+    for k in ds.fieldNames() :
+        print type(ds[0](k)[0]),
+    print ''
+
+def dummytest1_basicstats(self,ds) :
+    """print basics stats on a dataset, like length"""
+
+    print 'len(ds) = ',len(ds)
+    print 'num fields = ', len(ds.fieldNames())
+    print 'types of field: ',
+    for k in ds.fieldNames() :
+        print type(ds[0](k)[0]),
+    print ''
+
+def dummytest2_slicing(self,ds) :
+    """test if slicing works properly"""
+    print 'testing slicing...',
+    sys.stdout.flush()
+        
+    middle = len(ds) / 2
+    tenpercent = int(len(ds) * .1)
+    set1 = ds[:middle+tenpercent]
+    set2 = ds[middle-tenpercent:]
+    for k in range(tenpercent + tenpercent -1):
+        for k2 in ds.fieldNames() :
+            if type(set1[middle-tenpercent+k](k2)[0]) == N.ndarray :
+                for k3 in range(len(set1[middle-tenpercent+k](k2)[0])) :
+                    assert set1[middle-tenpercent+k](k2)[0][k3] == set2[k](k2)[0][k3]
+            else :
+                assert set1[middle-tenpercent+k](k2)[0] == set2[k](k2)[0]
+    assert tenpercent > 1
+    set3 = ds[middle-tenpercent:middle+tenpercent:2]
+    for k2 in ds.fieldNames() :
+        if type(set2[2](k2)[0]) == N.ndarray :
+            for k3 in range(len(set2[2](k2)[0])) :
+                assert set2[2](k2)[0][k3] == set3[1](k2)[0][k3]
+        else :
+            assert set2[2](k2)[0] == set3[1](k2)[0]
+
+    print 'done'
+
+
+def dummytest3_fields_iterator_consistency(self,ds) :
+    """ check if the number of iterator corresponds to the number of fields"""
+    print 'testing fields/iterator consistency...',
+    sys.stdout.flush()
+
+    # basic test
+    maxsize = min(len(ds)-1,100)
+    for iter in ds[:maxsize] :
+        assert len(iter) == len(ds.fieldNames())
+    if len(ds.fieldNames()) == 1 :
+        print 'done'
+        return
+
+    # with minibatches iterator
+    ds2 = ds[:maxsize].minibatches([ds.fieldNames()[0],ds.fieldNames()[1]],minibatch_size=2)
+    for iter in ds2 :
+        assert len(iter) == 2
+
+    print 'done'
+
+
+
+
+
+
+
+
+
 if __name__=='__main__':
     test1()
     test_LookupList()