Created
November 1, 2019 10:29
-
-
Save bwesterb/4601744ad81c5092a4927d0c30ad07d4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import csv | |
import json | |
from unidecode import unidecode | |
anum = set('abcdefghijklmnopqrstuvwxyz0123456789') | |
sfxs = {} | |
print("Computing suffices...") | |
for i, x in enumerate(json.load(open('all_songs.json'))): | |
def add(a, t, i): | |
awords = ''.join(x if x in anum else ' ' for x in a.lower()).split() | |
twords = ''.join(x if x in anum else ' ' for x in t.lower()).split() | |
for j in range(len(awords)): | |
for k in range(len(twords)): | |
sfx = ' '.join(awords[j:] + twords[k:]) | |
if sfx not in sfxs: | |
sfxs[sfx] = [] | |
sfxs[sfx].append((i,a+' - '+t)) | |
add(unidecode(x['artist']), unidecode(x['title']), i) | |
print(f" {len(sfxs)}") | |
print("Sorting suffices") | |
sorted_sfxs = list(sfxs.keys()) | |
sorted_sfxs.sort() | |
print("Writing") | |
with open('marietje', 'w') as f: | |
w = csv.writer(f, delimiter=",", quoting=csv.QUOTE_ALL) | |
for sfx in sorted_sfxs: | |
if len(sfxs[sfx]) == 1: | |
w.writerow([sfx, i ]) | |
else: | |
for j, i_at in enumerate(sorted(sfxs[sfx], key=lambda x: x[1])): | |
w.writerow([ | |
sfx + f"\0{j}", | |
i_at[0] | |
]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment