def get_project(project_name):
class Object(object):
pass
project = Object()
project.id = project_name
project.language = 'fr'
project.analyzer = annif.analyzer.get_analyzer('snowball(french)')
if "dewey" in project_name:
project.vocab = 'dewey'
project.subjects = SubjectIndex.load('.data\vocabs\dewey\subjects')
else:
project.vocab = 'rameau'
project.subjects = SubjectIndex.load('.data\vocabs\rameau\subjects')
return project
def test_analysishits_vector_notfound(document_corpus):
subjects = SubjectIndex(document_corpus)
hits = ListAnalysisResult([
AnalysisHit(
uri='http://example.com/notfound', label='not found', score=1.0)
], subjects)
assert hits.vector.sum() == 0
def test_list_suggestions_vector_notfound(document_corpus):
subjects = SubjectIndex(document_corpus)
suggestions = ListSuggestionResult(
[
SubjectSuggestion(
uri='http://example.com/notfound',
label='not found',
score=1.0)],
subjects)
assert suggestions.vector.sum() == 0
def test_load_tsv_uri_brackets(tmpdir):
tmpfile = tmpdir.join('subjects.tsv')
tmpfile.write("<http://www.yso.fi/onto/yso/p8993>\thylyt\n" +
"<http://www.yso.fi/onto/yso/p9285>\tneoliittinen kausi")
index = SubjectIndex.load(str(tmpfile))
assert len(index) == 2
assert index[0] == ('http://www.yso.fi/onto/yso/p8993', 'hylyt', None)
assert index[1] == ('http://www.yso.fi/onto/yso/p9285',
'neoliittinen kausi', None)
def test_load_tsv_with_notations(tmpdir):
tmpfile = tmpdir.join('subjects-with-notations.tsv')
tmpfile.write("http://www.yso.fi/onto/yso/p8993\thylyt\t42.42\n" +
"http://www.yso.fi/onto/yso/p9285\tneoliittinen kausi\t42.0")
index = SubjectIndex.load(str(tmpfile))
assert len(index) == 2
assert index[0] == ('http://www.yso.fi/onto/yso/p8993', 'hylyt', '42.42')
assert index[1] == ('http://www.yso.fi/onto/yso/p9285',
'neoliittinen kausi', '42.0')
def test_load_tsv_with_deprecated(tmpdir):
tmpfile = tmpdir.join('subjects.tsv')
tmpfile.write("<http://www.yso.fi/onto/yso/p8993>\thylyt\n" +
"<http://example.org/deprecated>\t\n" +
"<http://www.yso.fi/onto/yso/p9285>\tneoliittinen kausi")
index = SubjectIndex.load(str(tmpfile))
assert len(index) == 3
assert len(index.active) == 2
active = list(index.active)
assert active[0] == (0, 'http://www.yso.fi/onto/yso/p8993', 'hylyt', None)
assert active[1] == \
(2, 'http://www.yso.fi/onto/yso/p9285', 'neoliittinen kausi', None)
def test_analysishits_vector(document_corpus):
subjects = SubjectIndex(document_corpus)
hits = ListAnalysisResult([
AnalysisHit(uri='http://www.yso.fi/onto/yso/p7141',
label='sinetit',
score=1.0),
AnalysisHit(uri='http://www.yso.fi/onto/yso/p6479',
label='viikingit',
score=0.5)
], subjects)
assert isinstance(hits.vector, np.ndarray)
assert len(hits.vector) == len(subjects)
assert hits.vector.sum() == 1.5
for subject_id, score in enumerate(hits.vector):
if subjects[subject_id][1] == 'sinetit':
assert score == 1.0
elif subjects[subject_id][1] == 'viikingit':
assert score == 0.5
else:
assert score == 0.0
def test_list_suggestions_vector(document_corpus):
subjects = SubjectIndex(document_corpus)
suggestions = ListSuggestionResult(
[
SubjectSuggestion(
uri='http://www.yso.fi/onto/yso/p7141',
label='sinetit',
score=1.0),
SubjectSuggestion(
uri='http://www.yso.fi/onto/yso/p6479',
label='viikingit',
score=0.5)],
subjects)
assert isinstance(suggestions.vector, np.ndarray)
assert len(suggestions.vector) == len(subjects)
assert suggestions.vector.sum() == 1.5
for subject_id, score in enumerate(suggestions.vector):
if subjects[subject_id][1] == 'sinetit':
assert score == 1.0
elif subjects[subject_id][1] == 'viikingit':
assert score == 0.5
else:
assert score == 0.0
LazySuggestionResult, ListSuggestionResult, SuggestionFilter
from annif.corpus import SubjectIndex
class DotDict(dict):
pass
project = DotDict()
project.name = 'Letters Omikuji Parabel English'
project.language = 'en'
project.backend = 'letters-omikuji-bonsai-en'
project.analyzer = annif.analyzer.get_analyzer('snowball(english)')
project.limit = 10
project.vocab = 'letters-unesco'
project.subjects = SubjectIndex.load('./data/vocabs/letters-unesco/subjects')
project.datadir = str('./data/projects/letters-omikuji-bonsai-en')
backend_type = annif.backend.get_backend("omikuji")
backend = backend_type(backend_id='letters-omikuji-bonsai-en',
config_params={'limit': 5},
project=project)
def append_suggestions_node(results, txt_xml_path):
# https://stackoverflow.com/questions/28782864/modify-xml-file-using-elementtree
tree = ET.ElementTree(file=txt_xml_path)
root = tree.getroot()
#subjects = ET.SubElement(root, "subjects")
subjects = ET.Element('subjects')