def test_subtopic_labels(kvl, store, label_store):
def lab(cid1, sid1, cid2, sid2, neg=False):
coref_val = CorefValue.Negative if neg else CorefValue.Positive
return Label(cid1, cid2, 'unknown', coref_val, sid1, sid2)
nlab = lambda a, b, c, d: lab(a, b, c, d, neg=True)
def has_label(haystack, needle):
return any(lab.same_subject_as(needle) and lab.value == needle.value
for lab in haystack)
folders = Folders(kvl)
folders.add_folder('top')
folders.add_item('top', 'foo', 'a', 'ax')
folders.add_item('top', 'foo', 'b', 'bx')
folders.add_item('top', 'bar', 'c', 'cx')
folders.add_item('top', 'bar', 'd', 'dx')
folders.add_folder('other')
folders.add_item('other', 'baz', 'e', 'ex')
# Simulates a negative label from a search result.
label_store.put(nlab('a', 'ax', 'r', None))
label_store.put(nlab('b', 'bx', 'r', None))
pairwise = PairwiseFeatureLearner(store, label_store, 'a', 'ax')
labels = pairwise.infer_subtopic_labels()
print('\n'.join(map(repr, labels)))
assert has_label(labels, nlab('a', 'ax', 'e', 'ex'))
assert has_label(labels, nlab('a', 'ax', 'c', 'cx'))
assert has_label(labels, nlab('a', 'ax', 'd', 'dx'))
assert has_label(labels, lab('a', 'ax', 'b', 'bx'))
assert has_label(labels, nlab('a', 'ax', 'r', None))
assert has_label(labels, nlab('b', 'bx', 'r', None))
assert len(labels) == 8 # 2 for folders, 2 for results, 4 inferred
def test_only_negative_labels(store, label_store):
'''Make sure the learner can handle one class of labels.'''
content_objs, labels = interesting_training_data()
store.put(content_objs)
for lab in labels:
if lab.value == CorefValue.Negative:
label_store.put(lab)
# Overwrite the query so we get some hits.
store.put([('q', counter_fc({'x': 5, 'y': 90}))])
# And assign a label to the query.
label_store.put(neg_label('q', 'a'))
results = (mod_pairwise.similar(store, label_store)
.set_query_id('q')
.set_query_params({'limit': 100})
.recommendations())
# The search engine will fall back to a plain index scan if it has
# insufficient training data.
assert len(results['results']) >= 0
def test_only_negative_labels(store, label_store):
'''Make sure the learner can handle one class of labels.'''
content_objs, labels = interesting_training_data()
store.put(content_objs)
for lab in labels:
if lab.value == CorefValue.Negative:
label_store.put(lab)
# Overwrite the query so we get some hits.
store.put([('q', counter_fc({'x': 5, 'y': 90}))])
# And assign a label to the query.
label_store.put(neg_label('q', 'a'))
results = (mod_pairwise.similar(
store, label_store).set_query_id('q').set_query_params({
'limit': 100
}).recommendations())
# The search engine will fall back to a plain index scan if it has
# insufficient training data.
assert len(results['results']) >= 0
def test_search_engine(store, label_store):
'''Pretty much the same as classify, but for the search engine.'''
content_objs, labels = interesting_training_data()
store.put(content_objs)
for lab in labels:
label_store.put(lab)
# Overwrite the query so we get some hits.
store.put([('q', counter_fc({'x': 5, 'y': 90}))])
# And assign some labels to the query.
# (label expansion should fill in the rest)
label_store.put(pos_label('q', 'b'))
label_store.put(neg_label('q', 'a'))
# These can be removed in negative label inference returns. ---AG
label_store.put(neg_label('q', 'b'))
label_store.put(neg_label('q', 'c'))
results = (mod_pairwise.similar(store, label_store)
.set_query_id('q')
.set_query_params({'limit': 1})
.recommendations())
assert results['results'][0][0] != 'a'
def test_search_engine(store, label_store):
'''Pretty much the same as classify, but for the search engine.'''
content_objs, labels = interesting_training_data()
store.put(content_objs)
for lab in labels:
label_store.put(lab)
# Overwrite the query so we get some hits.
store.put([('q', counter_fc({'x': 5, 'y': 90}))])
# And assign some labels to the query.
# (label expansion should fill in the rest)
label_store.put(pos_label('q', 'b'))
label_store.put(neg_label('q', 'a'))
# These can be removed in negative label inference returns. ---AG
label_store.put(neg_label('q', 'b'))
label_store.put(neg_label('q', 'c'))
results = (mod_pairwise.similar(
store, label_store).set_query_id('q').set_query_params({
'limit': 1
}).recommendations())
assert results['results'][0][0] != 'a'
def test_subtopic_labels(kvl, store, label_store):
def lab(cid1, sid1, cid2, sid2, neg=False):
coref_val = CorefValue.Negative if neg else CorefValue.Positive
return Label(cid1, cid2, 'unknown', coref_val, sid1, sid2)
nlab = lambda a, b, c, d: lab(a, b, c, d, neg=True)
def has_label(haystack, needle):
return any(
lab.same_subject_as(needle) and lab.value == needle.value
for lab in haystack)
folders = Folders(kvl)
folders.add_folder('top')
folders.add_item('top', 'foo', 'a', 'ax')
folders.add_item('top', 'foo', 'b', 'bx')
folders.add_item('top', 'bar', 'c', 'cx')
folders.add_item('top', 'bar', 'd', 'dx')
folders.add_folder('other')
folders.add_item('other', 'baz', 'e', 'ex')
# Simulates a negative label from a search result.
label_store.put(nlab('a', 'ax', 'r', None))
label_store.put(nlab('b', 'bx', 'r', None))
pairwise = PairwiseFeatureLearner(store, label_store, 'a', 'ax')
labels = pairwise.infer_subtopic_labels()
print('\n'.join(map(repr, labels)))
assert has_label(labels, nlab('a', 'ax', 'e', 'ex'))
assert has_label(labels, nlab('a', 'ax', 'c', 'cx'))
assert has_label(labels, nlab('a', 'ax', 'd', 'dx'))
assert has_label(labels, lab('a', 'ax', 'b', 'bx'))
assert has_label(labels, nlab('a', 'ax', 'r', None))
assert has_label(labels, nlab('b', 'bx', 'r', None))
assert len(labels) == 8 # 2 for folders, 2 for results, 4 inferred