我正在编写一个 Airflow 管道,其中涉及将结果写入本地文件系统上的 csv 文件。
我使用的是 MacOS,文件路径类似于 /User/name/file_path/file_name.csv)
这是我的代码:
from airflow import DAG
from airflow.operators.bash_operator import BashOperator
from datetime import datetime, timedelta
from airflow.models import Variable
import os
from airflow.operators.python_operator import PythonOperator
#Import boto3 module
import boto3
import logging
from botocore.exceptions import ClientError
import csv
import numpy as np
import pandas as pd
bucket='my_bucket_name'
s3 = boto3.resource('s3',
aws_access_key_id=ACCESS_KEY,
aws_secret_access_key=SECRET_KEY
)
def load_into_csv(years):
df = pd.DataFrame()
for year in years:
for buckett in s3.buckets.all():
for aobj in buckett.objects.filter(Bucket=bucket,Prefix=PREFIX):
if year in …Run Code Online (Sandbox Code Playgroud)