def load_sentiment_seeds():
"""
加载情感种子(网上搜集的情感集合)
把情感种子存放到字典中，键为情感种子，值为情感种子得分
"""
pos_lines = read_lines(pos_seeds_path)
neg_lines = read_lines(neg_seeds_path)
neu_lines = read_lines(neu_seeds_path)
pos_seeds = dict()
neg_seeds = dict()
neu_seeds = dict()
for line in pos_lines:
if len(line.split(',')) > 2: # 多个,的情况忽略
continue
seed, score = line.split(',')[0], line.split(',')[1]
pos_seeds[seed] = int(score)
for line in neg_lines:
if len(line.split(',')) > 2:
continue
seed, score = line.split(',')[0], line.split(',')[1]
neg_seeds[seed] = int(score)
for line in neu_lines:
if len(line.split(',')) > 2:
continue
seed, score = line.split(',')[0], line.split(',')[1]
neu_seeds[seed] = int(score)
print(len(pos_seeds), len(neg_seeds), len(neu_seeds))
temp = []
# 去除冲突的情感词
for i in pos_seeds:
flag = 0
if i in neg_seeds:
flag = 1
del neg_seeds[i]
if i in neu_seeds:
flag = 1
del neu_seeds[i]
if flag:
temp.append(i)
for i in temp:
del pos_seeds[i]
temp = []
for i in neg_seeds:
if i in neu_seeds:
temp.append(i)
del neu_seeds[i]
for i in temp:
del neg_seeds[i]
print(len(pos_seeds), len(neg_seeds), len(neu_seeds))
return pos_seeds, neg_seeds, neu_seeds
def brute(docs_path, qrys_path, out_path):
docs = preprocess(read_lines(docs_path))
qrys = preprocess(read_lines(qrys_path))
def process_queries():
for qry_id, qry in qrys:
candidates = (doc_id for doc_id, doc in docs if matches(qry, doc))
retrieved = nlargest(5, candidates)
yield qry_id, retrieved
result_strs = imap(to_str, process_queries())
write_lines(out_path, result_strs)
def docs(docs_path, qrys_path, out_path):
docs = preprocess(read_lines(docs_path))
qrys = preprocess(read_lines(qrys_path))
index = inverted_index(docs)
def process_queries():
for qry_id, qry in qrys:
inv_lists = (index[term] for term in qry)
retrieved = simple_kway_merge(inv_lists)[::-1][:5]
yield qry_id, retrieved
result_strs = imap(to_str, process_queries())
write_lines(out_path, result_strs)
def load_sentiment_seeds():
"""
加载情感种子
"""
pos_lines = read_lines(pos_seeds_path)
neg_lines = read_lines(neg_seeds_path)
neu_lines = read_lines(neu_seeds_path)
lines = pos_lines + neg_lines + neu_lines
sentiment_seeds = get_seeds(lines, 1.0)
pos_seeds = get_seeds(pos_lines, 0.32)
neg_seeds = get_seeds(neg_lines, 1.0)
neu_seeds = get_seeds(neu_lines, 0.13)
pos_seeds, neg_seeds, neu_seeds = norm_seeds(pos_seeds, neg_seeds,
neu_seeds)
return sentiment_seeds, pos_seeds, neg_seeds, neu_seeds
def main():
data = read_lines("../resources/aoc2020/input21")
food = [(line[:line.index(' (')].split(' '),
line[line.index('(') + 10:-1].split(', ')) for line in data]
# part 1
ing_map = dict()
for f in food:
for a in f[1]:
if a in ing_map:
ing_map.update({a: set(f[0]).intersection(ing_map.get(a))})
else:
ing_map.update({a: set(f[0])})
allergens = reduce(set.union, ing_map.values())
result1 = sum(
[len([ing for ing in f[0] if ing not in allergens]) for f in food])
print("result1 =", result1) # 2170
# part 2
for i1 in ing_map:
for i2 in ing_map:
if i1 == i2:
continue
in1 = ing_map.get(i1)
in2 = ing_map.get(i2)
if len(in1) >= len(in2):
ing_map.update({i1: in1.difference(in2)})
else:
ing_map.update({i2: in2.difference(in1)})
result2 = ','.join(
[ing_map.get(ing).pop() for ing in sorted(list(ing_map.keys()))])
print("result2 =",
result2) # nfnfk,nbgklf,clvr,fttbhdr,qjxxpr,hdsm,sjhds,xchzh
def total_fuel(input_file: str, fuel: Callable[[int], int] = fuel_calc) -> int:
"""
for all modules in input, return the mass required to launch them
using the specified calculation
"""
inputs = util.read_lines(input_file)
return sum(fuel(int(mass)) for mass in inputs)
def import_biologic(self, m_file):
"""Function to import CA mpt files from Biologic potentiostats.
Args:
file (str): Path to file which will be imported.
"""
self.lines = util.read_lines(m_file, range(57))
if "Chrono" in self.lines[3]:
self.extract_par = [
[r"ecell", r"Ei", r"Ei\s\(V\)\s*(\S*)"],
[r"skiprows", r"Nb header lines", r"lines\s:\s*(\d*)\s*"],
]
ext = util.extract_value(self.extract_par, self.lines.values())
for x in ext:
setattr(self, x[0], str(x[1]))
self.file_trimmed = codecs.open(m_file, encoding="cp1252")
self.data = np.loadtxt(
self.file_trimmed,
usecols=(7, 10),
skiprows=int(self.skiprows),
delimiter="\t",
)
self.time = pandas.DataFrame(
{"time [s]": self.data[:, 0].tolist()})
self.icell = pandas.DataFrame(
{"Icell [mA]": self.data[:, 1].tolist()})
self.chronodata = pandas.concat([self.chronodata, self.time],
axis=1)
self.chronodata = pandas.concat([self.chronodata, self.icell],
axis=1)
def import_biologic(self, m_file):
"""Function to import PEIS mpt files from Biologic potentiostats.
Args:
file (str): Path to file which will be imported.
"""
self.lines = util.read_lines(m_file, range(83))
if "Potentio Electrochemical Impedance Spectroscopy" in self.lines[3]:
self.extract_par = [
[r"ecell", r"E (V)", r"E\s\(V\)\s*(\S*)"],
[r"fi", r"fi ", r"^fi\s*(\S*)"],
[r"fi_unit", r"unit fi", r"\sfi\s*(\S*)"],
[r"ff", r"ff ", r"^ff\s*(\S*)"],
[r"ff_unit", r"unit ff", r"\sff\s*(\S*)"],
[r"amplitude", r"Va", r"\(mV\)\s*(\S*)"],
[r"skiprows", r"Nb header lines", r"lines\s:\s*(\d*)\s*"],
]
ext = util.extract_value(self.extract_par, self.lines.values())
for x in ext:
setattr(self, x[0], str(x[1]))
self.file_trimmed = codecs.open(m_file, encoding="cp1252")
self.data = np.loadtxt(
self.file_trimmed,
usecols=(0, 1, 2),
skiprows=int(self.skiprows),
delimiter="\t",
)
self.rer = pandas.DataFrame({"re R": self.data[:, 1].tolist()})
self.imgr = pandas.DataFrame({"img R": self.data[:, 2].tolist()})
self.peisdata = pandas.concat([self.peisdata, self.rer], axis=1)
self.peisdata = pandas.concat([self.peisdata, self.imgr], axis=1)
def import_ec4(self, m_file):
"""Imports Nordic Electrochemistry EC4 file format.
Args:
file (str): Path to file which will be imported.
"""
self.lines = util.read_lines(m_file, range(96))
self.extract_par = [
[r"vs", r"Start", r"Start\s(\S*.\S)"],
[r"v1", r"V1", r"V1\s(\S*.\S)"],
[r"v2", r"V2", r"V2\s(\S*.\S)"],
[r"rate", r"Rate", r"Rate\s(\S*.\S)"],
]
ext = util.extract_value(self.extract_par, self.lines.values())
for x in ext:
setattr(self, x[0], ureg(x[1].replace(",", ".")))
self.data = np.loadtxt(m_file, usecols=(0, 1, 2), skiprows=96)
self.ecell = pandas.DataFrame(
{"Cycle 1: Ecell": self.data[:, 1].tolist()})
self.cvdata = pandas.concat([self.cvdata, self.ecell], axis=1)
self.icell = pandas.DataFrame(
{"Cycle 1: Icell": self.data[:, 2].tolist()})
self.cvdata = pandas.concat([self.cvdata, self.icell], axis=1)
def terms(docs_path, qrys_path, out_path):
docs = preprocess(read_lines(docs_path))
qrys = preprocess(read_lines(qrys_path))
inv_index = inverted_index(docs)
def process_queries():
for qry_id, qry in qrys:
candidates = set(inv_index[qry.pop()])
for term in qry:
candidates.intersection_update(inv_index[term])
retrieved = nlargest(5, candidates)
yield qry_id, retrieved
result_strs = imap(to_str, process_queries())
write_lines(out_path, result_strs)
def main():
data = read_lines("../resources/aoc2020/input13")
timestamp = int(data[0])
busses = data[1].split(",")
# part 1
relevant = [int(b) for b in busses if b != 'x']
t1, found, bus = 0, False, None
while not found:
t1 = t1 + 1
for r in relevant:
if (timestamp + t1) % r == 0:
found = True
bus = r
break
result1 = bus * t1
print("result1 =", result1) # 246
# part 2
indexed = []
for i in range(0, len(busses)):
if busses[i] != 'x':
indexed.append((i, int(busses[i])))
t2, step = 0, indexed[0][1]
for i in range(1, len(indexed)):
index = indexed[i][0]
number = indexed[i][1]
while (t2 + index) % number != 0:
t2 = t2 + step
step = step * number
result2 = t2
print("result2 =", result2) # 939490236001473
def test():
"""
In console, you will see::
info
warning
error
critical
In logfile, you will see::
debug
info
warning
error
critical
"""
path = os.path.join(os.path.dirname(__file__), "SingleFile.log")
logger = SingleFileLogger(rand_name=True, path=path, reset=True)
logger.debug("debug") # nothing
logger.info("info") # displayed, but not logged
logger.warning("warning") # displayed and logged
logger.error("error") # displayed and logged
logger.critical("critical") # displayed and logged
logger.remove_all_handler()
lines = read_lines(path)
assert len(lines) == 5
def load_train_data(word_voc,
tag_voc,
label_voc,
max_sent_len=100,
word_embed_dim=50,
sentence_len=False):
"""
加载训练数据
:param max_sent_len: 最大句子长度
:param word_embed_dim: ...
:return: xx
"""
# 构造训练数据
lines = read_lines('./com_data/data_h/Train.csv')
train_count = len(lines)
train_num = []
train_targets_str = [] # targets
train_target_indices = np.zeros((train_count, ), dtype='int32')
train_sentence = np.zeros((train_count, max_sent_len),
dtype='int32') # sent
train_sentence_len = np.zeros((train_count, ), dtype='int32') # 句子长度
train_tag = np.zeros((train_count, max_sent_len), dtype='int32') # tags
train_position = np.zeros((train_count, max_sent_len),
dtype='int32') # target 在句子中的下标
train_target = np.zeros((train_count, max_sent_len), dtype='int32')
train_label = np.zeros((train_count, ), dtype='int32') # label
for i in range(train_count):
line = lines[i]
items = line.split('|')
num, target, label = items[:3]
label_id = label_voc[label] # label id
sentence_all = ' '.join(items[3:])
words_all, tags_all = get_words_tags(sentence_all)
words, tags = cut_sentence(target, words_all, tags_all,
max_sent_len) # sentence 截取
train_sentence_len[i] = len(words)
target_index = words.index(
target) if target in words else 0 # target 在句子中的下标
word_arr, tag_arr, position_arr = \
get_sentence_ids(words,tags,word_voc,tag_voc,target_index,max_sent_len)
train_num.append(num)
train_targets_str.append(target)
train_target_indices[i] = target_index # new add 16-12-09
train_sentence[i, :] = word_arr[:]
train_tag[i, :] = tag_arr[:]
train_position[i, :] = position_arr[:]
if target in word_voc:
train_target[i, :] = [0] * (
max_sent_len - len(words)) + [word_voc[target]] * len(words)
else:
train_target[i, :] = [0] * max_sent_len
train_label[i] = label_id
train_data = [
train_target_indices, train_sentence, train_tag, train_position,
train_target, train_label, train_num, train_targets_str
]
if sentence_len:
train_data.append(train_sentence_len)
return train_data
def load_external_data(word_voc, tag_voc, label_voc, max_sent_len=100, word_embed_dim=50):
"""
加载外部数据
"""
lines = read_lines('./external_train_data/external_train.csv')
test_count = len(lines)
test_nums = [] # 测试编号
test_targets_str = [] # targets
test_sentence = np.zeros((test_count, max_sent_len), dtype='int32') # sent
test_tag = np.zeros((test_count, max_sent_len), dtype='int32') # tags
test_position = np.zeros((test_count, max_sent_len), dtype='int32') # target
test_target = np.zeros((test_count, max_sent_len), dtype='int32')
for i in range(test_count):
line = lines[i]
items = line.split('|')
num, target = items[:2]
sentence_all = ' '.join(items[2:])
words_all, tags_all = get_words_tags(sentence_all)
words, tags = cut_sentence(target, words_all, tags_all, max_sent_len) # sentence 截取
target_index = words.index(target)+1 if target in words else 0 # target 在句子中的下标
word_arr, tag_arr, position_arr = \
get_sentence_ids(words,tags,word_voc,tag_voc,target_index,max_sent_len)
# xx
test_nums.append(num)
test_targets_str.append(target)
test_sentence[i, :] = word_arr[:]
test_tag[i, :] = tag_arr[:]
test_position[i, :] = position_arr[:]
if target in word_voc:
test_target[i, :] = [0]*(max_sent_len-len(words)) + [word_voc[target]]*len(words)
else:
test_target[i, :] = [0] * max_sent_len
test_data = [test_nums, test_targets_str, test_sentence, test_tag, test_position, test_target]
return test_data
def main():
data = read_lines("../resources/aoc2020/input19")
rules = parse_rules(data)
messages = data[len(rules) + 1:]
# part 1
rule0 = resolve(rules, '0')
result1 = len([m for m in messages if re.fullmatch(rule0, m) is not None])
print("result1 =", result1) # 213
# part 2
# re-parse and update rules
rules = parse_rules(data)
rules.update({'8': '42 | 42 8'})
rules.update({'11': '42 31 | 42 11 31'})
result2 = 0
for i in range(2, 10):
prev = result2
rule0 = resolve(rules, '0', i)
result2 = len(
[m for m in messages if re.fullmatch(rule0, m) is not None])
if result2 == prev:
break
print("result2 =", result2) # 325
def main():
data = read_lines("../resources/aoc2020/input17")
# part 1
cubes = set()
for y in range(0, len(data)):
for x in range(0, len(data[0])):
if data[y][x] == '#':
cubes.add((x, y, 0))
for _ in range(0, 6):
cubes = proceed_3d(cubes)
result1 = len(cubes)
print("result1 =", result1) # 273
# part 2
hcubes = set()
for y in range(0, len(data)):
for x in range(0, len(data[0])):
if data[y][x] == '#':
hcubes.add((x, y, 0, 0))
for _ in range(0, 6):
hcubes = proceed_4d(hcubes)
result2 = len(hcubes)
print("result1 =", result2) # 1504
def main():
instructions = read_lines("../resources/aoc2020/input14")
# part 1
memory, mask = {}, None
for inst in instructions:
if inst.startswith("mask"):
mask = inst[7:]
else:
address = int(inst[inst.index('[') + 1:inst.index(']')])
value = mask_value(int(inst[inst.index('=') + 2:]), mask)
memory.update({address: value})
result1 = sum(memory.values())
print("result1 =", result1) # 9967721333886
# part 2
memory, mask = {}, None
for inst in instructions:
if inst.startswith("mask"):
mask = inst[7:]
else:
address = int(inst[inst.index('[') + 1:inst.index(']')])
value = int(inst[inst.index('=') + 2:])
for a in mask_address(address, mask):
memory.update({a: value})
result2 = sum(memory.values())
print("result2 =", result2) # 4355897790573
def main():
program = read_lines("../resources/aoc2020/input08")
# part 1
result1 = execute_program(program)[1]
print("result1 =", result1) # 1614
# part 2
result2 = -1
for i in range(0, len(program)):
if program[i].startswith("acc"):
continue
elif program[i].startswith('jmp'):
p2 = program.copy()
p2[i] = program[i].replace('jmp', 'nop')
r = execute_program(p2)
if r[0]:
result2 = r[1]
break
else:
p2 = program.copy()
p2[i] = program[i].replace('nop', 'jmp')
r = execute_program(p2)
if r[0]:
result2 = r[1]
break
print("result2 =", result2) # 1260
def main():
numbers = read_lines("../resources/aoc2020/input01")
# part 1
print("result1 =", part1(numbers)) # 877971
# part 2
print("result2 =", part2(numbers)) # 203481432
def read_float(path):
for line in read_lines(path):
if line.startswith('#'):
continue
try:
yield float(line)
except ValueError:
continue
def init_voc():
"""
Initing vocabulary.
return:
word_voc: 词表
tag_voc: 词性表
label_voc: label
"""
tags_list = ['neg', 'pos', 'a', 'car', 'p', 'd', 'vn']
have = 0
lines = read_lines('./com_data/data_h/Train1.csv')
lines += read_lines('./com_data/data_h/Test1.csv')
# 单词->id, 词性标注->id, label->id
word_dict = defaultdict(int)
tag_set = []
label_set = ['pos', 'neu', 'neg']
for line in lines:
sentence = ' '.join(line.split('|')[3:])
words, tags = get_words_tags(sentence)
tag_set += tags
for word in words:
word_dict[word] += 1
# 排序
word_dict = sorted(word_dict.items(),key=lambda d:d[1], reverse=True)
word_voc = dict()
word_voc['<'] = 2
word_voc['>'] = 3
for i, item in enumerate(word_dict):
if item[0] in word_voc:
continue
word_voc[item[0]] = i + 4 # 单词下标从2开始
tag_set = sorted(list(set(tag_set)))
tag_voc = dict()
for i, item in enumerate(tag_set):
have += 1
tag_voc[item] = i + 1 # 词性下标从1开始
label_voc = dict()
label_set = sorted(label_set)
for i, item in enumerate(label_set):
label_voc[item] = i
label_voc_rev = dict() # 反转dict
for item in label_voc.items():
label_voc_rev[item[1]] = item[0]
print('have:', have)
return word_voc, tag_voc, label_voc, label_voc_rev
def part1():
highest_seat_id = 0
for line in read_lines("../input5.txt"):
if not line:
break
highest_seat_id = max(highest_seat_id, get_seat_id(line))
print(highest_seat_id)
def parse_grid(dims):
grid = defaultdict(bool)
all_lines = util.read_lines("inputs/day17.txt")
for row, line in enumerate(all_lines):
for col, char in enumerate(line):
if char == "#":
pad = (0, ) * (dims - 2)
grid[(col, row, *pad)] = True
return grid
def load_train_data(word_voc, tag_voc, label_voc, max_sent_len=100, word_embed_dim=50,
sentence_len=False):
"""
加载训练数据
:param max_sent_len: 最大句子长度
:param word_embed_dim: ...
:return: xx
"""
# TODO 构造训练数据
lines = read_lines('./com_data/data_h/Train1.csv')
train_count = len(lines)
train_num = []
train_targets_str = [] # targets
train_sentence = np.zeros((train_count, max_sent_len), dtype='int32') # sent
train_sentence_len = np.zeros((train_count,), dtype='int32') # 句子长度
train_tag = np.zeros((train_count, max_sent_len), dtype='int32') # tags
train_position = np.zeros((train_count, max_sent_len), dtype='int32') # target 在句子中的下标
train_target = np.zeros((train_count, max_sent_len), dtype='int32')
train_label = np.zeros((train_count,), dtype='int32') # label
for i in range(train_count):
line = lines[i]
items = line.split('|')
num, target, label = items[:3]
label_id = label_voc[label] # label id
sentence_all = ' '.join(items[3:])
words_all, tags_all = get_words_tags(sentence_all)
#print(line)
if len(words_all)>max_sent_len - 2:
words, tags = cut_sentence(target, words_all, tags_all, max_sent_len) # sentence 截取
else:
words, tags = words_all, tags_all
get_persentence_target_count(num, target, words, words_all, en='train')
train_sentence_len[i] = len(words)
target_index = words.index(target)+1 if target in words else 0 # target 在句子中的下标
if target in words: # 标志target的位置，如<宝马>
words.insert(words.index(target), '<')
words.insert(words.index(target) + 2, '>')
tags.insert(words.index(target),'wcar') # 词性标为wcar
tags.insert(words.index(target)+2,'wcar')
word_arr, tag_arr, position_arr = \
get_sentence_ids(words,tags,word_voc,tag_voc,target_index,max_sent_len)
# xx
train_num.append(num)
train_targets_str.append(target)
train_sentence[i, :] = word_arr[:]
train_tag[i, :] = tag_arr[:]
train_position[i, :] = position_arr[:]
if target in word_voc:
train_target[i, :] = [0]*(max_sent_len-len(words)) + [word_voc[target]]*len(words)
else:
train_target[i, :] = [0] * max_sent_len
train_label[i] = label_id
train_data = [train_sentence, train_tag, train_position, train_target, train_label, train_num, train_targets_str]
if sentence_len:
train_data.append(train_sentence_len)
return train_data
def main():
data = read_lines("../resources/aoc2020/input18")
# part 1
result1 = sum([evaluate_ltr(expr) for expr in data])
print("result1 =", result1) # 36382392389406
# part 2
result2 = sum([evaluate_adv(expr) for expr in data])
print("result2 =", result2) # 381107029777968
def read_int(path):
for line in read_lines(path):
if line.startswith('#'):
if 'float' in line:
raise Float
continue
try:
yield int(line)
except ValueError:
continue
def load_test_data(word_voc, tag_voc, label_voc, max_sent_len=100, word_embed_dim=50,
sentence_len=False):
"""
加载测试数据
"""
# 构造测试数据
w_fp = open('./com_data/data_h/guize1.csv', 'w', encoding='utf-8')
lines = read_lines('./com_data/data_h/Test1.csv')
test_count = len(lines)
test_nums = [] # 测试编号
test_targets_str = [] # targets
test_sentence = np.zeros((test_count, max_sent_len), dtype='int32') # sent
test_sentence_len = np.zeros((test_count,), dtype='int32') # 句子长度
test_tag = np.zeros((test_count, max_sent_len), dtype='int32') # tags
test_position = np.zeros((test_count, max_sent_len), dtype='int32') # target
test_target = np.zeros((test_count, max_sent_len), dtype='int32')
for i in range(test_count):
line = lines[i]
items = line.split('|')
num, target = items[:2]
sentence_all = ' '.join(items[2:])
words_all, tags_all = get_words_tags(sentence_all)
if pol != '':
t_target = re.sub('_', ' ', target)
string1 = num + ',' + t_target + ',' + pol + '\n'
w_fp.write(string1)
if len(words_all)>max_sent_len - 2:
words, tags = cut_sentence(target, words_all, tags_all, max_sent_len) # sentence 截取
else:
words, tags = words_all, tags_all
get_persentence_target_count(num, target, words, words_all, en='test')
test_sentence_len[i] = len(words)
target_index = words.index(target)+1 if target in words else 0 # target 在句子中的下标
if target in words: # 标志target的位置，如<宝马>
words.insert(words.index(target), '<')
words.insert(words.index(target) + 2, '>')
tags.insert(words.index(target),'wcar') # 词性标为wcar
tags.insert(words.index(target)+2,'wcar')
word_arr, tag_arr, position_arr = \
get_sentence_ids(words,tags,word_voc,tag_voc,target_index,max_sent_len)
# xx
test_nums.append(num)
test_targets_str.append(target)
test_sentence[i, :] = word_arr[:]
test_tag[i, :] = tag_arr[:]
test_position[i, :] = position_arr[:]
if target in word_voc:
test_target[i, :] = [0]*(max_sent_len-len(words)) + [word_voc[target]]*len(words)
else:
test_target[i, :] = [0] * max_sent_len
w_fp.close()
test_data = [test_nums, test_targets_str, test_sentence, test_tag, test_position, test_target]
if sentence_len:
test_data.append(test_sentence_len)
return test_data
def init_sentence_id():
"""
初始化待提交sentence id
"""
sentence_id = set()
lines = read_lines('./com_data/data_ori/Test.csv')
for line in lines[1:]:
items = line.split('\t')
num = items[0]
sentence_id.add(num)
return sentence_id
def main():
data = read_lines("../resources/aoc2020/input06")
groups = " ".join(data).split(" ")
# part 1
result1 = sum([len(set(g.replace(" ", ""))) for g in groups])
print("result1 =", result1) # 6585
# part 2
result2 = sum([len(reduce(set.intersection, [set(p) for p in g.split(" ")])) for g in groups])
print("result2 =", result2) # 3276
def main():
pattern = "(N|S|E|W|L|R|F)([0-9]+)$"
data = read_lines("../resources/aoc2020/input12")
instructions = [re.match(pattern, line) for line in data]
# part 1
x, y, i = 0, 0, 1
directions = ['N', 'E', 'S', 'W']
for instruction in instructions:
action = instruction[1]
value = int(instruction[2])
if (action == 'N') | ((action == 'F') & (directions[i] == 'N')):
y = y - value
if (action == 'S') | ((action == 'F') & (directions[i] == 'S')):
y = y + value
if (action == 'E') | ((action == 'F') & (directions[i] == 'E')):
x = x - value
if (action == 'W') | ((action == 'F') & (directions[i] == 'W')):
x = x + value
if action == 'L':
i = (i - int(value / 90)) % 4
if action == 'R':
i = (i + int(value / 90)) % 4
result1 = abs(x) + abs(y)
print("result1 =", result1) # 562
# part 2
x, y = 0, 0
waypoint = (-10, -1)
for instruction in instructions:
action = instruction[1]
value = int(instruction[2])
if action == 'N':
waypoint = (waypoint[0], waypoint[1] - value)
if action == 'S':
waypoint = (waypoint[0], waypoint[1] + value)
if action == 'E':
waypoint = (waypoint[0] - value, waypoint[1])
if action == 'W':
waypoint = (waypoint[0] + value, waypoint[1])
if (action == 'L') | (action == 'R'):
angle = radians(value)
if action == 'R': angle = - angle
w1 = (int(waypoint[0] * cos(angle)) - int(waypoint[1] * sin(angle)))
w2 = (int(waypoint[0] * sin(angle)) + int(waypoint[1] * cos(angle)))
waypoint = (w1, w2)
if action == 'F':
x = x + (value * waypoint[0])
y = y + (value * waypoint[1])
result2 = abs(x) + abs(y)
print("result2 =", result2) # 101860
def main():
data = read_lines("../resources/aoc2020/input05")
seats = sorted([seat_id(d) for d in data])
# part 1
print("result1 =", seats[-1]) # 894
# part 2
i = 1
while seats[i] - seats[i - 1] == 1:
i = i + 1
print("result2 =", seats[i] - 1) # 579
def load_data(sentiment_seeds):
"""
加载测试集
"""
lines = read_lines(test_path)
lines += read_lines(test_path_second)
candidate_sentiment_words = list()
for line in lines:
sentence = line.split('|')[3]
for word_tag in sentence.split(' '):
if '/' not in word_tag:
continue
word = word_tag.split('/')[0]
if len(word) <= 1:
continue
tag = word_tag.split('/')[1]
if tag == 'v' or tag == 'vi' or tag == 'd' or tag == 'a'\
or tag == 'vn' or tag == 'pos' or tag == 'neg':
if word not in sentiment_seeds and word not in candidate_sentiment_words:
candidate_sentiment_words.append(word)
return candidate_sentiment_words
def main():
data = read_lines("../resources/aoc2020/input04")
passports = " ".join(data).split(" ")
# part 1
result1 = len(list(filter(is_valid, passports)))
print("result1 =", result1) # 233
# part 2
filtered = list(filter(is_valid_strict, passports))
result2 = len(filtered)
print("result2 =", result2) # 111
def get_vocab(file):
lines = read_lines(file)
# lines = random.sample(lines, 30)
entries = []
vocab = set()
for line in lines:
split = line.split("\t")
assert len(split) == 3
entries.append(split)
vocab.add(
split[1]) # there could be repeated word with different pos tags
return entries, vocab
