# Expert Class | Face Emotions Classification — Data

来源：https://www.kaggle.com/competitions/expertclass2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description


The dataset consists of *48x48* pixels grayscale of faces. The task is to categorize each face based on the emotion shown in the facial expression into one of seven categories:

- 0: Angry
- 1: Disgust
- 2: Fear
- 3: Happy
- 4: Sad
- 5: Surprise
- 6: Neutral


**File descriptions**

We're providing three CSV files. The `train_data.csv` contains the data to train your model and the `test_data.csv` has the images you're going to use to test. To submit a solution, you have to generate a file similar to the `example_submission.csv`.


The CSVs files contain two columns: *emotion* and *pixels*. 
The *emotion* column has a numeric code ranging from 0 to 6 from the emotion in the image.
The *pixels* column has a string containing the image

For examples of how to handle the data, access the notebook [Getting started with the data](https://www.kaggle.com/hugozaniniabi/getting-started-with-the-data).

You can also download these data files via ABI SharePoint [Link](https://anheuserbuschinbev.sharepoint.com/:f:/s/AnalyticsAcademy/EkitLIW3hVtHm4eUWmyvVywBk3GO4ZHGJfFVsiTxzMOSYw?e=MSHeMJ)