def test_generate_report():
execution_info = pd.DataFrame.from_dict({
'Start': [functions.get_local_time_str()],
'End': [functions.get_local_time_str()],
})
parameters_dict = Parameters(utils.config_file).__dict__
predictions_dict = {
'y_true': ['label1'],
'classifier_key': [{'label1': 0.0, 'label2': 1.0}],
}
parameters_dict['set_num_accepted_probs'] = 1
expected_df_row0 = pd.concat([
execution_info,
functions.parameters_to_data_frame(parameters_dict),
functions.predictions_to_data_frame(predictions_dict, 1),
], axis=1)
parameters_dict['set_num_accepted_probs'] = {1}
excel_file1 = utils.generate_available_filename(ext='.xlsx')
excel_file2 = utils.generate_available_filename(ext='.xlsx')
expected_df = pd.DataFrame()
try:
for i, file_exists in enumerate([False, True]):
assert exists(excel_file1) is file_exists
df = functions.generate_report(execution_info, parameters_dict, predictions_dict, excel_file1)
df.to_excel(excel_file2, index=False)
assert df.shape == (i + 1, 44)
expected_df = pd.concat([expected_df, expected_df_row0])
pd.util.testing.assert_frame_equal(df, expected_df)
pd.util.testing.assert_frame_equal(pd.read_excel(excel_file1), pd.read_excel(excel_file2))
finally:
utils.remove_and_check(excel_file1)
utils.remove_and_check(excel_file2)
def test_dump_documents(capsys):
df = read_excel(example_excel_file)
docs1 = data_frame_to_document_list(df)
try:
path = create_temporary_file(content=None, text=False)
with pytest.raises(Exception):
pickle_manager.dump_documents(docs1, path)
finally:
remove_and_check(path)
filename = generate_available_filename()
try:
pickle_manager.dump_documents(docs1, filename)
metadata = pickle_manager.get_docs_metadata(filename)
docs2 = list(pickle_manager.get_documents(filename))
assert len(metadata) == 1
assert metadata['total'] == len(docs1)
for doc1, doc2 in zip_longest(docs1, docs2):
assert repr(doc1) == repr(doc2)
finally:
remove_and_check(filename)
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') +
1:].startswith('Storing documents: 100%|')
assert captured.err.endswith('doc/s]\n') or captured.err.endswith(
's/doc]\n')
def test_prepare(capsys):
text_field = 'text field'
class_field = 'class field'
quantity = 2
fields = {text_field: 'Teste value.', class_field: 'c1'}
analyzed_sentences = {
text_field: [[{
'form': 'Teste',
'lemma': 'teste',
'upostag': None
}, {
'form': 'value',
'lemma': 'value',
'upostag': None
}, {
'form': '.',
'lemma': '.',
'upostag': 'PUNCT'
}]] * quantity
}
docs1 = [
Document(index=0, fields=fields,
analyzed_sentences=analyzed_sentences),
Document(index=1, fields=fields, analyzed_sentences=None),
]
synonyms_files = [None, 'contopt_0.1_r2_c0.0.txt']
expected_corpus_str = [[' '.join(['teste value'] * quantity), ''],
[' '.join(['prova value'] * quantity), '']]
expected_classifications = [[fields[class_field]] * quantity
] * len(synonyms_files)
expected_idxs_to_remove = [[1]] * len(synonyms_files)
expected_corpus = [[['teste', 'value'] * quantity, []],
[['prova', 'value'] * quantity, []]]
try:
filename = generate_available_filename()
pickle_manager.dump_documents(docs1, filename)
for i, synonyms_file in enumerate(synonyms_files):
ft = FeatureExtractor(synonyms_file=synonyms_file)
for training_mode in [True, False]:
corpus_str1, classifications1, idxs_to_remove1, corpus1 = ft.prepare(
text_field, class_field, None, docs1, training_mode)
corpus_str2, classifications2, idxs_to_remove2, corpus2 = ft.prepare(
text_field, class_field, filename, None, training_mode)
assert (corpus_str1, classifications1, idxs_to_remove1,
corpus1) == (corpus_str2, classifications2,
idxs_to_remove2, corpus2)
assert corpus_str1 == expected_corpus_str[i]
assert classifications1 == expected_classifications[i]
assert idxs_to_remove1 == expected_idxs_to_remove[i]
assert corpus1 == expected_corpus[i]
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') + 1:].startswith(
'Preparing to create classification: 100%|')
assert captured.err.endswith(
'doc/s]\n') or captured.err.endswith('s/doc]\n')
if synonyms_file is not None:
remove_and_check(synonyms_file)
finally:
remove_and_check(filename)
def test_check_data(capsys):
df = read_excel(example_excel_file)
docs = data_frame_to_document_list(df)
filename = generate_available_filename()
try:
pickle_manager.dump_documents(docs, filename)
pickle_manager.check_data(filename)
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') +
1:].startswith('Checking data: 100%|')
assert captured.err.endswith('doc/s]\n') or captured.err.endswith(
's/doc]\n')
count = 10
metadata1 = {'total': count}
pda1 = pickle_manager.PickleDumpAppend(metadata1, filename)
for not_Document in range(count):
pda1.dump_append(not_Document)
pda1.close()
with pytest.raises(AssertionError):
pickle_manager.check_data(filename)
metadata2 = {'total': -1}
pickle_manager.PickleDumpAppend(metadata2, filename).close()
with pytest.raises(AssertionError):
pickle_manager.check_data(filename)
finally:
remove_and_check(filename)
def test_dump_json():
d1 = {'test_random_values': [np.random.random()]}
filename = utils.generate_available_filename()
try:
trainer.dump_json(d1, filename)
f = open(filename, 'r')
d2 = json.load(f)
finally:
f.close()
utils.remove_and_check(filename)
assert d1 == d2
def test_get_docs_metadata():
df = read_excel(example_excel_file)
docs = data_frame_to_document_list(df)
filename = generate_available_filename()
try:
pickle_manager.dump_documents(docs, filename)
metadata = pickle_manager.get_docs_metadata(filename)
finally:
remove_and_check(filename)
assert type(metadata) is dict
assert len(metadata) == 1
assert metadata['total'] == len(docs)
def test_generate_roc_plot():
filename = '%s.png' % (generate_available_filename())
for n_class in [2, 10]:
X_test, y_test = load_digits(n_class=n_class, return_X_y=True)
for f in clfs:
clf = f(n_jobs=1, class_weight=None)
clf.fit(X_test, y_test)
assert not exists(filename)
try:
classifiers.generate_roc_plot(clf, X_test, y_test, filename)
assert exists(filename)
finally:
remove_and_check(filename)
def test_PickleDumpAppend_close():
metadata = {'total': 0}
filename = generate_available_filename()
try:
for expected_value in [False, True]:
assert exists(filename) == expected_value
pda = pickle_manager.PickleDumpAppend(metadata, filename)
assert not pda.file.closed
assert exists(pda.file.name)
pda.close()
assert pda.file.closed
assert not exists(pda.file.name)
finally:
remove_and_check(filename)
def test___init__():
filename = generate_available_filename()
try:
assert not exists(filename)
parser = ContoPTParser(filename)
assert exists(filename)
synonyms = ContoPTParser._load_synonyms(filename)
finally:
remove_and_check(filename)
assert type(parser.synonyms) is dict
assert len(parser.synonyms) > 0
assert parser.synonyms == synonyms
assert synonyms['adjudicatário'] == 'adjudicante'
assert synonyms['melancolia'] == 'misantropia'
assert synonyms['tristeza'] == 'misantropia'
def test_main():
old_dir = os.getcwd()
new_dir = utils.generate_available_filename()
base_parameters = Parameters(utils.config_file)
base_parameters.preprocessed_data_file = os.path.basename(base_parameters.preprocessed_data_file)
try:
os.makedirs(new_dir, exist_ok=False)
os.chdir(new_dir)
parameters = deepcopy(base_parameters)
parameters.excel_file = "invalid_excel_file"
parameters.preprocessed_data_file = "invalid_data_file"
with pytest.raises(SystemExit):
trainer.main(parameters)
parameters = deepcopy(base_parameters)
assert not os.path.exists(parameters.preprocessed_data_file)
try:
trainer.main(parameters)
assert os.path.exists(parameters.preprocessed_data_file)
assert os.path.exists("predictions.json")
assert os.path.exists("report.xlsx")
finally:
utils.remove_and_check(parameters.preprocessed_data_file)
utils.remove_and_check("predictions.json")
utils.remove_and_check("report.xlsx")
parameters.excel_file = os.path.abspath("20newsgroups")
parameters.preprocess_data = False
excel_file_20newsgroups = "20newsgroups.xlsx"
assert not os.path.exists(excel_file_20newsgroups)
try:
trainer.main(parameters)
pytest.fail()
except SystemExit:
assert os.path.exists(excel_file_20newsgroups)
finally:
utils.remove_and_check(excel_file_20newsgroups)
parameters = deepcopy(base_parameters)
parameters.final_training = True
try:
trainer.main(parameters)
finally:
assert not os.path.exists("predictions.json")
assert not os.path.exists("report.xlsx")
utils.remove_and_check(parameters.preprocessed_data_file)
finally:
os.chdir(old_dir)
rmtree(new_dir)
def test_PickleDumpAppend_dump_append():
count = 10
metadata = {'total': 0}
filename = generate_available_filename()
try:
pda = pickle_manager.PickleDumpAppend(metadata, filename)
for i in range(count):
pda.dump_append(i)
pda.close()
input_file = open(filename, 'rb')
assert load(input_file) == metadata
for i in range(count):
data = load(input_file)
assert data == i
finally:
input_file.close()
remove_and_check(filename)
def test_get_documents(capsys):
df = read_excel(example_excel_file)
docs1 = data_frame_to_document_list(df)
filename = generate_available_filename()
try:
dump_documents(docs1, filename)
for d1, d2 in [(None, '100%|'),
('Loading documents', 'Loading documents: 100%|')]:
docs2 = list(get_documents(filename, description=d1))
for doc1, doc2 in zip_longest(docs1, docs2):
assert repr(doc1) == repr(doc2)
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') + 1:].startswith(d2)
assert captured.err.endswith('doc/s]\n') or captured.err.endswith(
's/doc]\n')
finally:
remove_and_check(filename)
def test_generate_X_y(capsys):
quantity = 2
corpus = ['Test lemma 1 . ' * quantity, 'Test lemma 2 . ' * quantity]
classifications = [1, 2]
filename = generate_available_filename()
dpe_out = 'Please, ignore the message above indicating that the sentence is too long. The problem has been solved.\n' * 6
combinations = [
('CountVectorizer', None, True, ''),
('CountVectorizer', 'LDA', True, ''),
('CountVectorizer', 'MDS', True, ''),
('HashingVectorizer', None, True, ''),
('HashingVectorizer', 'MDS', True, ''),
('TfidfVectorizer', None, True, ''),
('TfidfVectorizer', 'LDA', True, ''),
('TfidfVectorizer', 'MDS', True, ''),
('DocumentPoolEmbeddings', None, False, dpe_out),
('DocumentPoolEmbeddings', 'MDS', False, dpe_out),
]
for vectorizer, fr, expect_file, expected_out in combinations:
try:
ft = FeatureExtractor(vectorizer_name=vectorizer,
feature_reduction=fr,
vectorizer_file=filename)
for training_mode in [True, False]:
assert exists(filename) is (not training_mode and expect_file)
_X, y = ft.generate_X_y(corpus, classifications, training_mode)
assert exists(filename) is expect_file
assert y == classifications
captured = capsys.readouterr()
assert captured.out == expected_out
assert captured.err[captured.err.rfind('\r') + 1:].startswith(
'Extracting features: 100%|')
assert captured.err.endswith(
'doc/s]\n') or captured.err.endswith('s/doc]\n')
finally:
if expect_file:
remove_and_check(filename)
if fr == 'LDA':
remove_and_check('LatentDirichletAllocation.pkl')
with pytest.raises(ValueError):
FeatureExtractor(feature_reduction='invalid',
vectorizer_file=filename).generate_X_y(
corpus, classifications)
remove_and_check(filename)
def test_PickleDumpAppend___init__():
metadata = {'total': 0}
filename = generate_available_filename()
try:
not_dict = 'test_str'
not_str = -1
params = [[not_dict, filename], [metadata, not_str]]
for m, f in params:
with pytest.raises(AssertionError):
pda = pickle_manager.PickleDumpAppend(m, f)
pda = pickle_manager.PickleDumpAppend(metadata, filename)
assert pda.filename_upon_completion == filename
assert exists(pda.file.name)
pda.close()
assert pickle_manager.load(filename) == metadata
assert not exists(pda.file.name)
assert exists(filename)
finally:
remove_and_check(filename)
def test_get_dict():
for data_dir in [mkdtemp(), generate_available_filename()]:
try:
for lang in ['en_US', 'pt_PT']:
aff_file = os.path.join(data_dir, '%s.aff' % (lang))
dic_file = os.path.join(data_dir, '%s.dic' % (lang))
assert not os.path.exists(aff_file)
assert not os.path.exists(dic_file)
SpellChecker.get_dict(lang, data_dir)
assert os.path.exists(aff_file)
assert os.path.exists(dic_file)
aff_mtime = os.path.getmtime(aff_file)
dic_mtime = os.path.getmtime(dic_file)
SpellChecker.get_dict(lang, data_dir)
assert aff_mtime == os.path.getmtime(aff_file)
assert dic_mtime == os.path.getmtime(dic_file)
with pytest.raises(requests.HTTPError):
SpellChecker.get_dict('pt_NotExists', data_dir)
finally:
rmtree(data_dir)
def test_set_docs_metadata(capsys):
df = read_excel(example_excel_file)
docs1 = data_frame_to_document_list(df)
filename = generate_available_filename()
try:
pickle_manager.dump_documents(docs1, filename)
metadata1 = pickle_manager.get_docs_metadata(filename)
metadata2 = metadata1.copy()
metadata2['new_field'] = 'test_field_value'
assert metadata1 != metadata2
pickle_manager.set_docs_metadata(metadata2, filename)
assert pickle_manager.get_docs_metadata(filename) == metadata2
docs2 = list(pickle_manager.get_documents(filename))
for doc1, doc2 in zip_longest(docs1, docs2):
assert repr(doc1) == repr(doc2)
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') +
1:] == 'Storing subsets: 0MB [00:00, ?MB/s]\n'
finally:
remove_and_check(filename)
def test_load_20newsgroups():
p1 = Parameters(utils.config_file)
p1.excel_file = '20newsgroups'
excel_file = utils.generate_available_filename('.xlsx')
try:
p2 = trainer.load_20newsgroups(p1, excel_file)
assert p1 is not p2
assert p1 != p2
assert p2.excel_column_with_text_data == 'data'
assert p2.excel_column_with_classification_data == 'target'
assert os.path.exists(excel_file)
df = pd.read_excel(excel_file)
assert df.shape == (18846, 3)
assert list(df.keys()) == ['Unnamed: 0', 'data', 'target']
expected_mtime = os.path.getmtime(excel_file)
p3 = trainer.load_20newsgroups(p1, excel_file)
assert os.path.getmtime(excel_file) == expected_mtime
assert p3.__dict__ == p2.__dict__
finally:
utils.remove_and_check('20news-bydate_py3.pkz')
utils.remove_and_check(excel_file)
def test_LatentDirichletAllocation():
X = np.asarray([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
y = np.asarray([0, 1, 2])
expected_new_X = np.asarray([[
0.01428573, 0.87142845, 0.01428573, 0.01428573, 0.01428573, 0.01428573,
0.01428573, 0.01428573, 0.01428573, 0.01428573
],
[
0.00625001, 0.94374995, 0.00625001,
0.00625001, 0.00625001, 0.00625001,
0.00625001, 0.00625001, 0.00625001,
0.00625001
],
[
0.00400000, 0.96399997, 0.00400000,
0.00400000, 0.00400000, 0.00400000,
0.00400000, 0.00400000, 0.00400000,
0.00400000
]])
filename = generate_available_filename()
assert not exists(filename)
try:
new_X1, new_y1 = FeatureExtractor.LatentDirichletAllocation(
X, y, filename)
assert exists(filename)
assert new_X1.shape == (X.shape[0], 10)
assert np.allclose(expected_new_X, new_X1)
assert np.array_equal(y, new_y1)
mtime = getmtime(filename)
new_X2, new_y2 = FeatureExtractor.LatentDirichletAllocation(
X, y, filename)
assert getmtime(filename) == mtime
assert np.array_equal(new_X1, new_X2)
assert np.array_equal(new_y1, new_y2)
finally:
remove_and_check(filename)
def test_get_documents():
df = read_excel(example_excel_file)
docs1 = data_frame_to_document_list(df)
filename = generate_available_filename()
try:
pickle_manager.dump_documents(docs1, filename)
docs2 = list(pickle_manager.get_documents(filename))
for doc1, doc2 in zip_longest(docs1, docs2):
assert repr(doc1) == repr(doc2)
try:
f = open(filename, 'ab')
dump(obj=0, file=f, protocol=pickle_manager._pickle_protocol)
f.close()
docs2 = list(pickle_manager.get_documents(filename))
for doc1, doc2 in zip_longest(docs1, docs2):
assert repr(doc1) == repr(doc2)
pytest.fail()
except Exception as e:
assert len(e.args) == 1
assert e.args[
0] == "The file '%s' has more documents than indicated in the metadata." % (
filename)
finally:
remove_and_check(filename)
def test_predict(client):
df = read_excel(utils.example_excel_file)
docs = data_frame_to_document_list(df)
prediction_server._text_field = 'Example column'
prediction_server._class_field = 'Classification column'
clfs_filenames = []
try:
vectorizer_path = utils.create_temporary_file(content=None, text=False)
p = Preprocessor()
p.preprocess(text_field=prediction_server._text_field,
preprocessed_data_file=None,
docs=docs)
ft = FeatureExtractor(training_mode=True,
vectorizer_file=vectorizer_path)
corpus, classifications, _, _ = ft.prepare(
text_field=prediction_server._text_field,
class_field=prediction_server._class_field,
preprocessed_data_file=None,
docs=docs,
training_mode=True)
X, y = ft.generate_X_y(corpus, classifications, training_mode=True)
prediction_server._preprocessor = Preprocessor()
prediction_server._feature_extractor = FeatureExtractor(
training_mode=False, vectorizer_file=vectorizer_path)
res = client.post('/', headers=valid_headers)
assert res.status_code == prediction_server.BAD_REQUEST
res = client.post('/',
json={
'text': 1,
'classifier': 'LinearSVC'
},
headers=valid_headers)
assert res.status_code == prediction_server.BAD_REQUEST
assert utils.decode(res.data).endswith('<p>Invalid text</p>\n')
res = client.post('/',
json={
'text': 'Test text.',
'classifier': 1
},
headers=valid_headers)
assert res.status_code == prediction_server.BAD_REQUEST
assert utils.decode(res.data).endswith('<p>Invalid classifier</p>\n')
res = client.post('/',
json={
'text': 'Test text.',
'classifier': '../LinearSVC'
},
headers=valid_headers)
assert res.status_code == prediction_server.BAD_REQUEST
assert utils.decode(res.data).endswith('<p>Invalid classifier</p>\n')
res = client.post('/',
json={
'text': 'Test text.',
'classifier': 'LinearSVC'
},
headers=valid_headers)
assert res.status_code == prediction_server.BAD_REQUEST
assert utils.decode(
res.data).endswith('<p>Invalid classifier model</p>\n')
for f in clfs:
clf_filename_base = utils.generate_available_filename()
clf_filename = '%s.pkl' % (clf_filename_base)
clfs_filenames.append(clf_filename)
clf = f(n_jobs=1, class_weight=None)
clf.fit(X, y)
dump(clf, clf_filename)
res = client.post('/',
json={
'text': 'Test text.',
'classifier': clf_filename_base
},
headers=valid_headers)
assert res.status_code == 200
assert repr(
prediction_server._classifiers[clf_filename_base]) == repr(clf)
assert replace_final_dict_values(res.json, value=0) in [{
'feature_weights': {
'I': {},
'II': {},
'III': {}
},
'probabilities': {
'I': 0,
'II': 0,
'III': 0
}
}, {
'feature_weights': {},
'probabilities': {
'I': 0,
'II': 0,
'III': 0
}
}]
finally:
utils.remove_and_check(vectorizer_path)
for clf_filename in clfs_filenames:
utils.remove_and_check(clf_filename)
prediction_server._text_field = None
prediction_server._class_field = None
prediction_server._preprocessor = None
prediction_server._feature_extractor = None
prediction_server._feature_weights = dict()
prediction_server._classifiers = dict()
prediction_server._old_handlers = dict()
def test_preprocess(capsys):
text_field = 'Test field'
index = -1
fields = {text_field: 'Teste\r\nvalue with\ra\nfew tikens. ' * 2}
analyzed_sentences1 = {
text_field: [[{
'form': 'Teste',
'lemma': 'teste',
'upostag': None
}, {
'form': 'value',
'lemma': 'value',
'upostag': None
}, {
'form': 'with',
'lemma': 'with',
'upostag': None
}, {
'form': 'a',
'lemma': 'a',
'upostag': None
}, {
'form': 'few',
'lemma': 'few',
'upostag': None
}, {
'form': 'tikens',
'lemma': 'tikens',
'upostag': None
}, {
'form': '.',
'lemma': '.',
'upostag': 'PUNCT'
}]] * 2
}
analyzed_sentences2 = {
text_field: [[{
'form': 'Test',
'lemma': 'test',
'upostag': None
}, {
'form': 'value',
'lemma': 'value',
'upostag': None
}, {
'form': 'with',
'lemma': 'with',
'upostag': None
}, {
'form': 'a',
'lemma': 'a',
'upostag': None
}, {
'form': 'few',
'lemma': 'few',
'upostag': None
}, {
'form': 'tokens',
'lemma': 'token',
'upostag': None
}, {
'form': '.',
'lemma': '.',
'upostag': 'PUNCT'
}]] * 2
}
for spell_checker_lang, analyzed_sentences in [(None, analyzed_sentences1),
('en_US',
analyzed_sentences2)]:
doc = Document(index=index, fields=fields, analyzed_sentences=dict())
p = Preprocessor(spell_checker_lang=spell_checker_lang)
assert p.stop is False
p.preprocess(text_field=text_field,
preprocessed_data_file=None,
docs=[doc] * 2)
assert p.stop is False
assert doc.index == index
assert doc.fields == fields
assert doc.analyzed_sentences == analyzed_sentences
captured = capsys.readouterr()
assert captured.out == ''
assert captured.err[captured.err.rfind('\r') +
1:].startswith('Preprocessing: 100%|')
assert captured.err.endswith('doc/s]\n') or captured.err.endswith(
's/doc]\n')
p.stop = True
with pytest.raises(SystemExit):
p.preprocess(text_field=text_field,
preprocessed_data_file=None,
docs=[doc] * 2)
del (p)
if spell_checker_lang is not None:
rmtree('./hunspell')
docs = [
Document(index=index, fields=fields, analyzed_sentences=dict())
for index in range(2)
]
preprocessed_data_file = utils.generate_available_filename()
try:
pickle_manager.dump_documents(docs, preprocessed_data_file)
pickle_manager.check_data(preprocessed_data_file)
p = Preprocessor(store_data=True)
assert all([
doc.analyzed_sentences == dict()
for doc in pickle_manager.get_documents(preprocessed_data_file)
])
p.preprocess(text_field, preprocessed_data_file, None)
assert all([
doc.analyzed_sentences == analyzed_sentences1
for doc in pickle_manager.get_documents(preprocessed_data_file)
])
pickle_manager.check_data(preprocessed_data_file)
finally:
utils.remove_and_check(preprocessed_data_file)
def test___init__():
ft1 = FeatureExtractor()
try:
nltk.data.find('corpora/stopwords')
except LookupError:
pytest.fail()
assert ft1.stop_words == set()
assert ft1.vectorizer_file == 'vectorizer.pkl'
assert type(ft1.vectorizer) is feature_extraction.text.TfidfVectorizer
assert ft1.feature_reduction is None
assert 'initial_code_to_run_on_document' in dir(
ft1.document_adjustment_code)
assert ft1.upostags_to_ignore == ['PUNCT']
assert ft1.synonyms is None
assert ft1.n_jobs == 1
ft2 = FeatureExtractor(nltk_stop_words_package='english')
assert ft2.stop_words == set(nltk.corpus.stopwords.words('english'))
for vectorizer_name in [
'CountVectorizer', 'HashingVectorizer', 'TfidfVectorizer'
]:
with pytest.raises(FileNotFoundError):
FeatureExtractor(vectorizer_name=vectorizer_name,
training_mode=False,
vectorizer_file=generate_available_filename())
try:
path = create_temporary_file(content=None, text=False)
pickle_manager.dump(
FeatureExtractor(vectorizer_name=vectorizer_name).vectorizer,
path)
ft = FeatureExtractor(vectorizer_name=vectorizer_name,
training_mode=False,
vectorizer_file=path)
assert ft.vectorizer.__class__.__name__ == vectorizer_name
finally:
remove_and_check(path)
ft = FeatureExtractor(vectorizer_name=vectorizer_name,
training_mode=True)
assert ft.vectorizer.__class__.__name__ == vectorizer_name
for vectorizer_name in ['DocumentPoolEmbeddings']:
for training_mode in [True, False]:
vectorizer_file = generate_available_filename()
ft = FeatureExtractor(vectorizer_name=vectorizer_name,
training_mode=training_mode,
vectorizer_file=vectorizer_file)
assert ft.vectorizer.__class__.__name__ == vectorizer_name
assert not exists(vectorizer_file)
with pytest.raises(ValueError):
FeatureExtractor(vectorizer_name='invalid_vectorizer',
training_mode=True)
ft3 = FeatureExtractor(remove_adjectives=True)
assert ft3.upostags_to_ignore == ['PUNCT', 'ADJ']
synonyms_file = 'contopt_0.1_r2_c0.0.txt'
filename = generate_available_filename()
try:
ft4 = FeatureExtractor(synonyms_file=synonyms_file)
contoPTParser = ContoPTParser(filename)
assert ft4.synonyms == contoPTParser.synonyms
finally:
remove_and_check(synonyms_file)
remove_and_check(filename)
with pytest.raises(ValueError):
FeatureExtractor(synonyms_file='invalid_file.txt')
ft5 = FeatureExtractor(n_jobs=2)
assert ft5.n_jobs == 2
def test_train_test_split():
text_field = 'Example column'
df = read_excel(example_excel_file)
docs = data_frame_to_document_list(df)
preprocessor = Preprocessor()
preprocessor.preprocess(text_field, None, docs)
ft = FeatureExtractor()
corpus, classifications, _, _ = ft.prepare(
text_field=text_field,
class_field='Classification column',
preprocessed_data_file=None,
docs=docs,
training_mode=False)
test_size = 0.3
preprocessed_data_file = generate_available_filename()
force = False
idxs_to_remove = [5]
try:
pickle_manager.dump_documents(docs, preprocessed_data_file)
assert pickle_manager.get_docs_metadata(preprocessed_data_file) == {
'total': 10
}
desired = {
'total': 10,
'test_size': test_size,
'training_set_indexes': np.array([6, 1, 0, 2, 8, 3]),
'test_set_indexes': np.array([7, 9, 4])
}
for my_force in [False, True]:
train_test_split.train_test_split(corpus, classifications,
test_size,
preprocessed_data_file, my_force,
idxs_to_remove)
np.testing.assert_equal(
pickle_manager.get_docs_metadata(preprocessed_data_file),
desired)
for key in ['test_size', 'training_set_indexes', 'test_set_indexes']:
m = desired.copy()
m[key] = None
pickle_manager.set_docs_metadata(m, preprocessed_data_file)
train_test_split.train_test_split(corpus, classifications,
test_size,
preprocessed_data_file, force,
idxs_to_remove)
np.testing.assert_equal(
pickle_manager.get_docs_metadata(preprocessed_data_file),
desired)
for key, value in [('test_size', 0.2),
('training_set_indexes', np.array([1, 0, 2, 8,
3]))]:
m = desired.copy()
m[key] = value
pickle_manager.set_docs_metadata(m, preprocessed_data_file)
train_test_split.train_test_split(corpus, classifications,
test_size,
preprocessed_data_file, force,
idxs_to_remove)
np.testing.assert_equal(
pickle_manager.get_docs_metadata(preprocessed_data_file), m)
finally:
remove_and_check(preprocessed_data_file)
pass
