forked from InnovateTheExisting/Data-Engineering-Nanodegree
-
Notifications
You must be signed in to change notification settings - Fork 1
/
etl.py
52 lines (34 loc) · 1.21 KB
/
etl.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
import configparser
import psycopg2
from sql_queries import copy_table_queries, insert_table_queries
def load_staging_tables(cur, conn):
"""
Load data from files stored in S3 to the staging tables.
"""
print("Loading data from JSON files stored in S3 buckets into staging tables")
for query in copy_table_queries:
cur.execute(query)
conn.commit()
print("Complete.\n")
def insert_tables(cur, conn):
"""
Insert data from staging tables into the tables.
"""
print("Inserting data from staging tables into Redshift tables")
for query in insert_table_queries:
cur.execute(query)
conn.commit()
print("Complete.\n")
def main():
"""
Extract song metadata and user activity data from S3, transform it using a staging table, and load it into fact and dimensional tables for analysis
"""
config = configparser.ConfigParser()
config.read('dwh.cfg')
conn = psycopg2.connect("host={} dbname={} user={} password={} port={}".format(*config['CLUSTER'].values()))
cur = conn.cursor()
load_staging_tables(cur, conn)
insert_tables(cur, conn)
conn.close()
if __name__ == "__main__":
main()