def get_formatted_msd_track_title_csv(db_file,
filename='./msd_formatted_titles.csv'):
"""
Remove and reformat all the msd song titles and store it as csvfile.
The output csv file is structured as follows :
msd_track_id, msd_song_title, msd_new_song_title
Inputs :
db_file - track_metadata.db file provided by the labrosa
filename - filename for the output csvfile ('./msd_formatted_titles.csv' by default)
[NOTE] : tested runtime ~ 33.76 minutes
"""
def double_format(string):
s = title_formatter(string)
return title_formatter(s)
con = init_connection(db_file)
query = con.execute("""SELECT track_id, title FROM songs""")
results = query.fetchall()
con.close()
with open(filename, 'w') as csvfile:
writer = csv.DictWriter(csvfile,
fieldnames=['msd_id', 'msd_title', 'title'])
writer.writeheader()
cnt = 0
for track_id, track_name in results:
print "--%s--" % cnt
if track_name:
title = double_format(track_name).encode('utf8')
writer.writerow({
'msd_id': track_id,
'msd_title': track_name,
'title': title
})
cnt += 1
print "~Done..."
return
print("created {} nodes".format(n_nodes))
@print_information
def connect_teams_divisions_conferences(df):
n_rels = 0
for _, row in df.iterrows():
# get entities
t = Team.nodes.get(name=row["team"])
d = Division.nodes.get(name=row["division"])
c = Conference.nodes.get(name=row["conference"])
# create relationships
t.division.connect(d)
d.conference.connect(c)
n_rels += 2
print("created {} relationships".format(n_rels))
if __name__ == "__main__":
# read underlying data
df = pd.read_csv("./data/teams-divisions-conferences.csv", sep=";")
# connect to Neo4J
init_connection()
# create nodes
create_teams(df)
create_divisions(df)
create_conferences(df)
connect_teams_divisions_conferences(df)
import random
import sys
from os import path
import pika
sys.path.append(path.dirname(path.dirname(path.abspath(__file__))))
from config import Config
from utils import init_connection
config = Config()
connection = init_connection(connector=pika,
host=config.host,
port=config.port)
channel = connection.channel()
channel.exchange_declare(exchange='result', type='direct')
result = channel.queue_declare(exclusive=True)
queue_name = result.method.queue
channel.queue_bind(exchange='result', queue=queue_name, routing_key='result')
print(' [*] Waiting for logs. To exit press CTRL+C')
def callback(ch, method, properties, body):
def clear_graph():
init_connection()
n_nodes = db.cypher_query("MATCH (n) RETURN count(n)")[0][0][0]
n_relations = db.cypher_query("MATCH ()-[r]->() RETURN count(r)")[0][0][0]
clear_neo4j_database(db)
print("deleted {} nodes and {} relationships".format(n_nodes, n_relations))