# [NLP] Friends IMDB Rating Prediction — Data

来源：https://www.kaggle.com/competitions/friendsimdbratingprediction/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

This is going to be a NLP hackathon.

There is 3 Categories of Datasets provided to you in a zip file.

Two are a types of train file, that you'll need to combine to train and validate your model.
- There is 1 train file and 8 other season files, that together make up your training data.
- This is the data where you should be doing all your modelling on.

The other Dataset is the test file, with the prediction column missing('ratings').

Your job is to train a model and predict that missing column.

After predicting the missing columns save your predictions in a csv with the column header being "ratings"