def downloadData(param: Param, download: bool = True):
'''Download user data (if {download} is True) to json files, merge them into a flat pandas.DataFrame, and write it to disk.'''
logging.info(f"{param.filePath().name.replace('.','|')}")
if download:
subMethod = param.splitMethod(lower=True)
for f in param.filePath(glob='*json'):
f.unlink()
pbarManager = enlighten.get_manager()
with pbarManager.counter(unit='page', leave=False) as pbar:
while param.page <= param.nPages:
fileName = param.filePath(ext=f'.{param.page:04d}.json')
response = getReq(param=param,
pbarManager=pbarManager,
collapse=False)
param.page = int(
response.get(subMethod).get('@attr').get('page'))
param.nPages = int(
response.get(subMethod).get('@attr').get('totalPages'))
pbar.total = param.nPages # [tqdm: update total without resetting time elapsed](https://stackoverflow.com/a/58961015/13019084)
pbar.update()
param.filePath().parent.mkdir(exist_ok=True)
with open(file=fileName, mode='w') as jsonF:
json.dump(obj=response, fp=jsonF)
param.page += 1
time.sleep(param.sleep)
pbarManager.stop()
DF = loadJSON(param)
df = flattenDF(param=param, DF=DF, writeToDisk=True)
if param.splitMethod() in ['TopArtists', 'TopAlbums', 'TopTracks']:
writeCSV(param=param, df=df)
def recommFromNeighbor(neighbor:str=None, method:str='user.getTopArtists', neighborThr:int=100, myThr:int=1000, **kwargs) -> pandas.DataFrame:
'''Return neighbor's top artists/albums/songs missing from the user's top listens'''
if not neighbor: return lastfmNeighbors()
else:
myData = loadUserData(Param(method=method)).head(myThr)
param = Param(method=method, user=neighbor, lim=neighborThr)
entity = param.splitMethod(lower=True, plural=False, strip=True)
neighborData = getReq(param)
cols = [f'{entity}_name', f'{entity}_playcount']
if entity != 'artist': cols = [f'artist_name', *cols]
# numpy.setdiff1d(neighborData.get(f'{entity}_name'), myData.get(f'{entity}_name')) # [Compare and find missing strings in pandas Series](https://stackoverflow.com/a/58544291/13019084)
return neighborData[[item not in myData.get(f'{entity}_name').to_list() for item in neighborData.get(f'{entity}_name').to_list()]][cols]