2020KDD-CUP阿里天池一篇baseline复现debiasingRush（二）

上面一篇介绍了所用数据的分割，这篇主要是训练数据的构建。

For Video Recommendation in Deep learning QQ Group 277356808
 
For Visual in deep learning QQ Group 629530787
 
I'm here waiting for you
 

 关于数据的介绍参考这一篇。

1-读取及初步处理item-feat

获取item-feat毫无疑问，就一个csv文件，我很好奇，这种数据是咋存的。。。。如下

42844,[4.514945030212402, -2.3837196826934814, 0.5004140138626099, 0.40706828236579895, -1.995228886604309, 0.10907801240682602, -0.6917753219604492, 2.2274599075317383, -6.437974452972412, -0.8248971700668335, -0.13872423768043518, -0.3793291747570038, 0.6276600956916809, 0.41837671399116516, 4.441218376159668, 0.29981935024261475, 0.5785568356513977, -4.699289321899414, -0.39474016427993774, -2.3916513919830322, 0.37053167819976807, -1.355466