yesterday = date.today() - timedelta(days=1)
dt = yesterday.strftime("%Y-%m-%d")
# define where you want to store the tweets csv file in your local directory
local_dir = "/tmp/"
# define the location where you want to store in HDFS
hdfs_dir = " /tmp/"
for channel in to_channels:
file_name = "from_" + channel + "_" + yesterday.strftime("%Y-%m-%d") + ".csv"
load_to_hdfs = BashOperator(
task_id="put_" + channel + "_to_hdfs",
bash_command="HADOOP_USER_NAME=hdfs hadoop fs -put -f " +
local_dir + file_name +
hdfs_dir + channel + "/",
dag=dag)
load_to_hdfs.set_upstream(clean_data)
load_to_hive = HiveOperator(
task_id="load_" + channel + "_to_hive",
hql="LOAD DATA INPATH '" +
hdfs_dir + channel + "/" + file_name + "' "
"INTO TABLE " + channel + " "
"PARTITION(dt='" + dt + "')",
dag=dag)
load_to_hive.set_upstream(load_to_hdfs)
load_to_hive.set_downstream(hive_to_posgres)
load_to_hdfs = BashOperator(
task_id="put_" + channel + "_to_hdfs",
bash_command="HADOOP_USER_NAME=hdfs hadoop fs -put -f " + local_dir +
file_name + hdfs_dir + channel + "/",
dag=dag)
load_to_hdfs.set_upstream(analyze_tweets)
load_to_hive = HiveOperator(task_id="load_" + channel + "_to_hive",
hql="LOAD DATA INPATH '" + hdfs_dir + channel +
"/" + file_name + "' "
"INTO TABLE " + channel + " "
"PARTITION(dt='" + dt + "')",
dag=dag)
load_to_hive.set_upstream(load_to_hdfs)
load_to_hive.set_downstream(hive_to_mysql)
for channel in from_channels:
file_name = "from_" + channel + "_" + yesterday.strftime(
"%Y-%m-%d") + ".csv"
load_to_hdfs = BashOperator(
task_id="put_" + channel + "_to_hdfs",
bash_command="HADOOP_USER_NAME=hdfs hadoop fs -put -f " + local_dir +
file_name + hdfs_dir + channel + "/",
dag=dag)
load_to_hdfs.set_upstream(analyze_tweets)
load_to_hive = HiveOperator(task_id="load_" + channel + "_to_hive",
hql="LOAD DATA INPATH '" + hdfs_dir + channel +
"/" + file_name + "' "
bash_command="HADOOP_USER_NAME=hdfs hadoop fs -put -f " +
local_dir + file_name +
hdfs_dir + channel + "/",
dag=dag)
load_to_hdfs.set_upstream(analyze_tweets)
load_to_hive = HiveOperator(
task_id="load_" + channel + "_to_hive",
hql="LOAD DATA INPATH '" +
hdfs_dir + channel + "/" + file_name + "' "
"INTO TABLE " + channel + " "
"PARTITION(dt='" + dt + "')",
dag=dag)
load_to_hive.set_upstream(load_to_hdfs)
load_to_hive.set_downstream(hive_to_mysql)
for channel in from_channels:
file_name = "from_" + channel + "_" + yesterday.strftime("%Y-%m-%d") + ".csv"
load_to_hdfs = BashOperator(
task_id="put_" + channel + "_to_hdfs",
bash_command="HADOOP_USER_NAME=hdfs hadoop fs -put -f " +
local_dir + file_name +
hdfs_dir + channel + "/",
dag=dag)
load_to_hdfs.set_upstream(analyze_tweets)
load_to_hive = HiveOperator(
task_id="load_" + channel + "_to_hive",
hql="LOAD DATA INPATH '" +
