from IPython import get_ipython

ipython = get_ipython()
ipython.magic('load_ext autoreload')
ipython.magic('autoreload 2')

config = confuse.Configuration('course_project')

ONTO_BASE = '../ontologies/'
CORRECT_INSTANCES_BASE = '../instances/'
CORRECT_INSTANCES = correct_instances.parse_instances_from_txt(
    CORRECT_INSTANCES_BASE + config['correct_instances'].get())

# %%

text_to_parse = input_reader.read(config)

print(text_to_parse[:500])

# %%
sentences = nlp.tokenize_text(text_to_parse)

words_amount = sum([len(sent) for sent in sentences])
print(f'Кол-во предложений: {str(len(sentences))}')
print(f'Кол-во слов: {str(words_amount)}')

# %%

morph = pymorphy2.MorphAnalyzer()

sentences = [[morph.parse(word)[0].normal_form for word in sent]
Example #2
0
from input_reader import read
import datetime

data = read(__file__)
test_data = read(__file__, name='test')


def parse_data(input_data):
    output_list = list()
    for idx, line in enumerate(input_data):
        parsed_line = line.rstrip().replace('#', '').split(' ')
        time_date = ' '.join(parsed_line[0:2])[1:-1]
        time_stamp = datetime.datetime.fromisoformat(time_date)
        output_list.append([time_stamp.timestamp(), time_stamp.minute, parsed_line[3]])
    return output_list


def sort_list(input_data):
    sorted_list = sorted(input_data, key=lambda x: x[0])  # TODO wrong direction
    return [x[1:] for x in sorted_list]


def task_one(input_data):
    sleep = [None, None]
    sorted_data = sort_list(parse_data(input_data))
    big_dict = dict()
    dict_key = ''
    for entry in sorted_data:
        minute = entry[0]
        value = entry[1]
        if value.isdigit() and dict_key == '':
Example #3
0
from input_reader import read

data = read(__file__)


def task_one(input_data):
    return sum([int(x) for x in input_data])


def task_two(input_data):
    current_freq = 0
    seen_set = set()
    while True:
        for row in input_data:
            current_freq += int(row)
            if current_freq not in seen_set:
                seen_set.add(current_freq)
            else:
                return current_freq


print('Task one: ', task_one(data))
print('Task two: ', task_two(data))