# 2.14.22:🍿Netflix — Data

来源：https://www.kaggle.com/competitions/21422netflix/data

采集时间：2026-10-19T11:05:29Z

The original dataset has been subsampled/oversampled and augmented. 
 
1. `XY_Netflix.csv`: Contains ~7.4 million movie ratings (with level 1,2,3,4,5) identified by user id (`uid`) and movie id (`mid`). The first 20K rows have NaN rating values, which need to be predicted and submitted to Kaggle with their IDs, which are computed from `uid` and `mid` (see Starter Colab).
1. `XY_Netflix_matrix.csv` is a matrix of user rows and movie columns. It contains the same ratings as `XY_Netflix.csv` does, but because all other NaN values are also specified, ratings required for Kaggle submission are trickier to identify.
1. `movie.csv` contains additional information on movies in the above datasets