def main(): loader = MsdBbLoader( hits_file_path= './storage/msd_bb_matches.csv', non_hits_file_path= './storage/msd_bb_non_matches.csv', features_path='./tools', non_hits_per_hit=1, features=['hl'], label='weeks', ) print(loader.load()[0][0].shape, loader.load()[1].shape) print(loader.configuration()) print(loader.load()[0][0].columns)
from sklearn.pipeline import Pipeline from sklearn.preprocessing import MinMaxScaler import common from dataloaders import MsdBbLoader import evaluations dataloader = MsdBbLoader( hits_file_path='/storage/nas3/datasets/music/billboard/msd_bb_matches.csv', non_hits_file_path= '/storage/nas3/datasets/music/billboard/msd_bb_non_matches.csv', features_path='/storage/nas3/datasets/music/billboard', non_hits_per_hit=1, features=[ *common.hl_list(), ], label='peak', nan_value=150, random_state=42, ) pipeline = Pipeline([ ('scale', MinMaxScaler()), ('linreg', Lasso(alpha=1.0, normalize=False)), ]) evaluator = GridEvaluator( parameters={}, grid_parameters=evaluations.grid_parameters(),