def write_to_file(output_file, prices):
file_exists = os.path.isfile(output_file)
with open(output_file, "a") as f:
if not file_exists:
f.write(",".join(sorted(prices[0].keys())) + "\n")
for p in prices:
sorted_values = list(p.items()) | sort() | select(lambda x: x[1])
f.write((sorted_values | select(str) | join(",")) + "\n")
def test_pipe():
def fib():
a, b = 0, 1
while True:
yield a
a, b = b, a + b
# 计算小于4000000的斐波那契数中的偶数之和
amount = fib() | where(lambda x: x % 2 == 0) | take_while(
lambda x: x < 4000000) | add()
print(amount)
# 读取文件，统计文件中每个单词出现的次数，然后按照次数从高到低对单词排序
with open('argparse.py') as f:
fs = f.read()
print(findall('\w+', fs))
print(fs
| Pipe(lambda x: findall('\w+', x))
# | Pipe(lambda x: (i for i in x if i.strip()))
| groupby(lambda x: x)
| select(lambda x: (x[0], (x[1] | count)))
| sort(key=lambda x: x[1], reverse=True))
if os.path.exists(tag_list_path):
with open(tag_list_path) as tag_list_file:
logging.info("Processing " + tag_list_path)
for key in tag_list_file:
key = key.strip().decode("utf-8")
if key in vocabs:
ktag_to_utags[key].add(key)
if len(ktag_to_utags) == 0:
raise BaseException("Cannot find tag.csv or labelled_word.csv")
with open(unlabelled_word_path) as unlabelled_word_file:
with open(result_path, "w") as result_file:
for word in [
line.strip().decode("utf-8") for line in unlabelled_word_file
]:
try:
sim_tags_info = [
(tag, model.n_similarity([word], ktag_to_utags[tag]))
for tag in ktag_to_utags.keys()
] | sort(key=lambda tag_info: tag_info[1],
reverse=True) | as_list
sim_tags_info = [
t[0] + "," + str(t[1]) for t in sim_tags_info[0:10]
]
output_line = "\t".join([word] + sim_tags_info)
result_file.write(output_line.encode("utf-8") + "\n")
except Exception, ex:
logging.exception(ex)
logging.warning("Cannot tag the word " + word)
def upload_time(self):
tmp = self._versions | pipe.map(lambda v: v.upload_time) \
| pipe.sort(reverse=True) | pipe.first
return tmp
line = line.strip().decode("utf-8")
if len(line.split("\t")) == 2:
utag = line.split("\t")[0]
ktag = line.split("\t")[1]
if utag in vocabs:
ktag_to_utags[ktag].add(utag)
if os.path.exists(tag_list_path):
with open(tag_list_path) as tag_list_file:
logging.info("Processing " + tag_list_path)
for key in tag_list_file:
key = key.strip().decode("utf-8")
if key in vocabs:
ktag_to_utags[key].add(key)
if len(ktag_to_utags) == 0:
raise BaseException("Cannot find tag.csv or labelled_word.csv")
with open(unlabelled_word_path) as unlabelled_word_file:
with open(result_path, "w") as result_file:
for word in [line.strip().decode("utf-8") for line in unlabelled_word_file]:
try:
sim_tags_info = [(tag, model.n_similarity([word], ktag_to_utags[tag])) for tag in
ktag_to_utags.keys()] | sort(
key=lambda tag_info: tag_info[1], reverse=True) | as_list
sim_tags_info = [t[0] + "," + str(t[1]) for t in sim_tags_info[0:10]]
output_line = "\t".join([word] + sim_tags_info)
result_file.write(output_line.encode("utf-8") + "\n")
except Exception, ex:
logging.exception(ex)
logging.warning("Cannot tag the word " + word)
