def test_short(self):
seq1 = "ACGACG"
seq2 = "ACGAT"
expected = "ACGACG", "ACGA-T"
sim_matrix = utils.make_similarity_matrix(1, -2)
result = global_seq.run_global_sequence_algorithm(seq1, seq2, sim_matrix, -2)[0]
self.assertEquals(expected, result)
def test_BinfSnipacademy(self):
seq1 = "CGTTCTA"
seq2 = "AACGTTGG"
expected = "--CGTTCTA", "AACGTT-GG"
sim_matrix = utils.make_similarity_matrix(5, -3)
result = global_seq.run_global_sequence_algorithm(seq1, seq2, sim_matrix, -4)[0]
self.assertEquals(expected, result)
def testVlabArmita(self):
seq1 = "CGTGAATTCAT"
seq2 = "GACTTAC"
expected1 = "GAATT-C", "GACTTAC"
sim_matrix = utils.make_similarity_matrix(5, -3)
result = local_seq.run_local_sequence_algorithm(seq1, seq2, sim_matrix, -4)[0]
self.assertEquals(expected1, result)
def test_matrix_parses_simple_matrix(self):
filename = "inputs/matrix1.txt"
expected = utils.make_similarity_matrix(1, -2)
with open(filename, "r") as f:
result = handlers.parse_matrix_file(f)
self.assertEqual(expected, result)
make_sentences_vectors, make_similarity_matrix, apply_pagerank, ask_top_n_sentences_to_extract, extract_sentences
pd.set_option('display.max_columns', None)
pd.set_option('display.expand_frame_repr', False)
pd.set_option('max_colwidth', -1)
dataset_path = Path.cwd() / "data" / "Reviews.csv"
if __name__ == '__main__':
dataset = pd.read_csv(dataset_path, nrows=100)
dataset.drop_duplicates(subset=['Text'], inplace=True)
dataset.dropna(axis=0, inplace=True)
sentences_list = split_in_sentences(dataset['Text'])
sentences_list = remove_html_tag(sentences_list)
pre_processed_sentences = pre_processing(sentences_list)
embedding_dimensionality = ask_embedding_dim()
embeddings = get_word_embeddings(embedding_dimensionality)
sents_vects = make_sentences_vectors(pre_processed_sentences, embeddings, int(embedding_dimensionality))
similarity_matrix = make_similarity_matrix(sentences_list, sents_vects, int(embedding_dimensionality))
pagerank_scores = apply_pagerank(similarity_matrix)
number_sentences_to_extract = ask_top_n_sentences_to_extract()
for ex_sent in extract_sentences(number_sentences_to_extract, sentences_list, pagerank_scores):
print(ex_sent, "\n")
users.append(row[0])
while(True):
try:
if(function == 'fetch'):
# Get neighbours of each user in the list
for i, user in enumerate(users):
print('\n', i, user)
user_obj = api.get_user(user)
n = fetch_neighbours(user_obj.id, api, direction=direction, force=force)
print("neighbours: ", n)
# Save user info and the id-screen_name pair since we have it already
utils.save_user(user_obj)
utils.save_screen_name(user_obj.id, user)
if(function == 'make_similarity'):
print("Creating similarity matrix")
fout = 'similarity' + '_' + file.split('.')[0] + '_' + direction + '.csv'
make_similarity_matrix(users, direction = direction, file = fout)
if(function == 'make_adjacency'):
print("Creating adjacency matrix")
fout = 'adjacency' + '-' + file.split('.')[0] + '_' + direction + '.csv'
make_adjacency_matrix(users, direction = direction, file = fout)
break
except TweepError as e:
print(e)
time.sleep(60)
# Get neighbours of each user in the list
for i, user in enumerate(users):
print('\n', i, user)
user_obj = api.get_user(user)
n = fetch_neighbours(user_obj.id,
api,
direction=direction,
force=force)
print("neighbours: ", n)
# Save user info and the id-screen_name pair since we have it already
utils.save_user(user_obj)
utils.save_screen_name(user_obj.id, user)
if (function == 'make_similarity'):
print("Creating similarity matrix")
fout = 'similarity' + '_' + file.split(
'.')[0] + '_' + direction + '.csv'
make_similarity_matrix(users, direction=direction, file=fout)
if (function == 'make_adjacency'):
print("Creating adjacency matrix")
fout = 'adjacency' + '-' + file.split(
'.')[0] + '_' + direction + '.csv'
make_adjacency_matrix(users, direction=direction, file=fout)
break
except TweepError as e:
print(e)
time.sleep(60)