[] - 2022-07-10 XGBoost如何用2GB内存训练100GB的数据！.pdf
需积分: 0 162 浏览量
2023-12-11
20:10:40
上传
评论
收藏 88KB PDF 举报
XGBoost如何用2GB内存训练100GB的数据！
class IterLoadForDMatrix(xgb.core.DataIter):
def __init__(self, df=None, features=None, target=None, batch_size=256*1
024):
self.features = features
self.target = target
self.df = df
self.batch_size = batch_size
self.batches = int( np.ceil( len(df) / self.batch_size ) )
self.it = 0 # set iterator to 0
super().__init__()
def reset(self):
'''Reset the iterator'''
self.it = 0
def next(self, input_data):
'''Yield next batch of data.'''
if self.it == self.batches:
return 0 # Return 0 when there's no more batch.
a = self.it * self.batch_size
b = min( (self.it + 1) * self.batch_size, len(self.df) )
dt = pd.DataFrame(self.df.iloc[a:b])
input_data(data=dt[self.features], label=dt[self.target]) #, weight=
dt['weight'])
self.it += 1
return 1
调用方法（此种方式比较适合GPU训练）：
Xy_train = IterLoadForDMatrix(train.loc[train_idx], FEATURES, 'target')
dtrain = xgb.DeviceQuantileDMatrix(Xy_train, max_bin=256)
参考文档：
资源评论
