def test_count_matches(brexit):
corpus = Corpus(brexit['corpus_name'])
corpus.query(cqp_query='[lemma="nigel"]',
context=10,
context_break='tweet',
name='Test',
save=True)
cqp = corpus.start_cqp()
counts = corpus.counts.matches(cqp, 'Test')
assert ("Nigel" in counts.index)
def test_concordance_options(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump.concordance(form='raw'))
print(dump.concordance(form='simple'))
print(dump.concordance(form='kwic'))
print(dump.concordance(form='dataframes'))
print(dump.concordance(form='extended'))
def test_argmin_query(brexit):
corpus = Corpus(brexit['corpus_name'], lib_path=brexit['lib_path'])
query = brexit['query_argmin']
dump = corpus.query(cqp_query=query['cqp'],
context=query.get('context', None),
context_break=query.get('s_context', None),
corrections=query['corrections'],
match_strategy=query['match_strategy'])
conc = dump.concordance(p_show=query['p_show'],
s_show=query['s_show'],
p_text=query['p_text'],
p_slots=query['p_slots'],
slots=query['slots'],
order='first',
cut_off=None,
form='extended')
print(conc)
print(conc['df'].iloc[0])
def test_context_matches(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump.matches())
print(dump.context())
def test_keywords_options(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD" expand to s')
print(dump.keywords(order='log_ratio', cut_off=200))
def test_query2dump(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump)
def test_keywords(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD" expand to s')
print(dump.keywords())
def test_collocates_options(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump.collocates(order='log_likelihood', cut_off=200))
def test_collocates(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump.collocates())
def test_breakdown(germaparl):
corpus = Corpus(germaparl['corpus_name'],
registry_path=germaparl['registry_path'])
dump = corpus.query('"SPD"')
print(dump.breakdown())