# Improving the quality of museums data — Data

来源：https://www.kaggle.com/competitions/caps-in-museums-data/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Files

## unique_types.csv 
This file represents the unique museum object types that can be predicted. All types are in Estonian language.

## train.csv 
Training set that should be used to build your machine learning models. The training set includes both the descriptive variables of the museum object and the ground truth about the ``type`` of the object. 

## test.csv 
Test set should be used to see how well your model performs on unseen data. The test set includes the descriptive variables about the objects but not the ``type`` of the object. It is your job to predict it using the model you built on the training data!

## sample_submission.csv
An example of what the submission file should look like. For every row in the test data, submission files should contain two columns: ``id`` (representing the id of the museum object) and ``type`` (representing the **type** of the object). Example format:

``id, type``

``2652198, foto``

``3851731, kiri``

``Etc.``

*NB: the types in the sample file are picked randomly*.