| import numpy as np | |
| from pprint import pprint | |
| from collections import defaultdict | |
| m = np.matrix( | |
| [ | |
| [1, 2, 0], | |
| [3, 0, 5], | |
| [0, 7, 0], | |
| [4, 0, 0], |
| def get_artist_cluster_id_using_artist_mbids(connection, artist_credit_mbids): | |
| """Returns the artist_credit_cluster_id that corresponds | |
| to the given artist MBIDs | |
| """ | |
| query = text("""SELECT artist_credit_cluster_id | |
| FROM artist_credit_redirect_json | |
| WHERE artist_mbids_json::text = :artist_credit_mbids | |
| """) |
247427b9-9042-4ba6-a260-a365d835d042 , f6a77fbe-f88a-4647-a334-32b90ca08cd7 both these recording MBIDs redirect to 9475f8ef-e785-4b9f-a8c2-03ceb817553e . So should we store 9475f8ef-e785-4b9f-a8c2-03ceb817553e or go on with storing 247427b9-9042-4ba6-a260-a365d835d042, f6a77fbe-f88a-4647-a334-32b90ca08cd7 in recording_artist_join table?
according to me it will make things complicated. e.g. fetching recording mbids that are in recording_json table but not in recording_artist_joi
| id | data | data_sha256 | meta_sha256 |
|---|---|---|---|
| 1 | {"artist":"Jay\u2010Z & Beyonc\u00e9","recording_mbid":"5465ca86-3881-4349-81b2-6efbd3a59451","title":"'03 Bonnie & Clyde"} | 9db1d48646b94fd517e0906f6f0540a02f520cd99d6ab5cb25a4475e2417b040 | 93840a6e5c3b29f6192625687e40a377abb7f136ef5bc0a14705259d07c4acb4 |
| 2 | {"artist":"Lil\u2019 Kim","recording_mbid":"6ba092ae-aaf7-4154-b987-9eb9d05f8616","title":"Don't Mess With Me"} | 782606d8332acfe42349b6dff05a8675a9f69deb511d9daa9b8100b4bf295 |