def test_update(self):
pars = Query.en(text.split('\n')).where(lambda z: z != '').to_list()
df = Separator.separate_paragraphs(pars)
new_pars = [
pars[0], pars[1], 'Нулевая. Вставка', pars[4], pars[3],
'Первая. Вставка', 'Вторая. Вставка', pars[6], 'Третья. Вставка'
]
df1 = Separator.separate_paragraphs(new_pars)
df2 = Separator.update_separation(
df, new_pars, [0, 1, None, 4, 3, None, None, 6, None])
for c in df1.columns:
self.assertListEqual(list(df1[c]), list(df2[c]))
pd.options.display.width = None
self.assertListEqual([
False, False, False, False, False, False, True, True, True, False,
False, False, False, False, False, True, True, True, True, True,
True, False, False, False, True, True, True
], list(df2.updated))
self.assertListEqual([
0, 1, 2, 3, 4, 5, -1, -1, -1, 12, 13, 14, 9, 10, 11, -1, -1, -1,
-1, -1, -1, 18, 19, 20, -1, -1, -1
], list(df2.original_word_id))
self.assertListEqual([
0, 0, 1, 2, 2, 3, -1, -1, -1, 8, 8, 9, 6, 6, 7, -1, -1, -1, -1, -1,
-1, 12, 12, 13, -1, -1, -1
], list(df2.original_sentence_id))
self.assertListEqual([
0, 0, 0, 1, 1, 1, -1, -1, -1, 4, 4, 4, 3, 3, 3, -1, -1, -1, -1, -1,
-1, 6, 6, 6, -1, -1, -1
], list(df2.original_paragraph_id))
def test_separation_multi(self):
df = Separator.separate_paragraphs(
['первое предожение. Второе.', 'Второй параграф'])
#pd.set_option('max_columns',None); pd.set_option('display.width', 1000);print(df)
self.assertListEqual([0, 0, 0, 1, 1, 2, 2], list(df.sentence_id))
self.assertListEqual([0, 1, 2, 3, 4, 5, 6], list(df.word_id))
self.assertListEqual([0, 0, 0, 0, 0, 1, 1], list(df.paragraph_id))
def test_update_enrich_pymorphy(self):
enricher = PyMorphyFeaturizer().as_enricher()
pars0 = Query.en(text.split('\n')).where(lambda z: z != '').to_list()
df0 = Separator.separate_paragraphs(pars0)
db0 = DataBundle(src=df0)
enricher.enrich(db0)
pars1 = [pars0[1], pars0[0], 'Вставленное предложение.', pars0[2]]
df_test = Separator.update_separation(df0, pars1, [1, 0, None, 2])
db_test = DataBundle(src=df_test)
enricher.update_enrich(db0, db_test)
df_control = Separator.separate_paragraphs(pars1)
db_control = DataBundle(src=df_control)
enricher.enrich(db_control)
py_test = db_test.pymorphy.reset_index().sort_values('word_id')
py_control = db_control.pymorphy.reset_index().sort_values('word_id')
for c in py_control.columns:
self.check(py_control, py_test, c)