由于luigi Task,我想在S3上存储一个pickle文件。下面是定义任务的类:
class CreateItemVocabulariesTask(luigi.Task):
def __init__(self):
self.client = S3Client(AwsConfig().aws_access_key_id,
AwsConfig().aws_secret_access_key)
super().__init__()
def requires(self):
return [GetItem2VecDataTask()]
def run(self):
filename = 'item2vec_results.tsv'
data = self.client.get('s3://{}/item2vec_results.tsv'.format(AwsConfig().item2vec_path),
filename)
df = pd.read_csv(filename, sep='\t', encoding='latin1')
unique_users = df['CustomerId'].unique()
unique_items = df['ProductNumber'].unique()
item_to_int, int_to_item = utils.create_lookup_tables(unique_items)
user_to_int, int_to_user = utils.create_lookup_tables(unique_users)
with self.output()[0].open('wb') as out_file:
pickle.dump(item_to_int, out_file)
with self.output()[1].open('wb') as out_file:
pickle.dump(int_to_item, out_file)
with self.output()[2].open('wb') as out_file:
pickle.dump(user_to_int, out_file)
with self.output()[3].open('wb') as out_file:
pickle.dump(int_to_user, out_file)
def output(self):
files = [S3Target('s3://{}/item2int.pkl'.format(AwsConfig().item2vec_path), client=self.client),
S3Target('s3://{}/int2item.pkl'.format(AwsConfig().item2vec_path), client=self.client),
S3Target('s3://{}/user2int.pkl'.format(AwsConfig().item2vec_path), client=self.client),
S3Target('s3://{}/int2user.pkl'.format(AwsConfig().item2vec_path), client=self.client),]
return files
运行此任务时,出现错误ValueError: Unsupported open mode 'wb'
。我尝试转储到pickle文件中的项目只是python词典。
完整追溯:
Traceback (most recent call last):
File "C:\Anaconda3\lib\site-packages\luigi\worker.py", line 203, in run
new_deps = self._run_get_new_deps()
File "C:\Anaconda3\lib\site-packages\luigi\worker.py", line 140, in _run_get_new_deps
task_gen = self.task.run()
File "C:\Users\user\Documents\python workspace\pipeline.py", line 60, in run
with self.output()[0].open('wb') as out_file:
File "C:\Anaconda3\lib\site-packages\luigi\contrib\s3.py", line 714, in open
raise ValueError("Unsupported open mode '%s'" % mode)
ValueError: Unsupported open mode 'wb'
答案 0 :(得分:1)
这是一个仅在python 3.x上发生的问题,如here所述。为了使用python 3并编写二进制文件或目标文件(即使用“ wb”模式),只需将S3Target的格式参数设置为Nop
。像这样:
S3Target('s3://path/to/file', client=self.client, format=luigi.format.Nop)
请注意,这只是一个把戏,不是那么直观也没有记录。