# CSE/STAT 416 24sp - Assignment 5 — Data

来源：https://www.kaggle.com/competitions/cse-stat-416-24-sp-assignment-5/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# Dataset Description

For this assignment, we will be looking at edX (anonymized) student data to try to predict whether a student received a certification (completed) a course. The target column is the `certified` column that you see in our training dataset.

## File Descriptions

This assignment uses two files
* `edx_train.csv` - The file containing the labeled training data
* `edx_test.csv` - The file containing the unlabeled test data that will be used to evaluate your submission

## Using these data files in your notebook

How you will access these files depends on which environment you are using.

### Colab

If you're working with Colab Jupyter notebooks, you can use the starter code linked from the overview page to download the files to your Colab instance.

```py
save_file('https://courses.cs.washington.edu/courses/cse416/23sp/homeworks/hw5/edx_train.csv', 'edx_train.csv') save_file('https://courses.cs.washington.edu/courses/cse416/23sp/homeworks/hw5/edx_test.csv', 'edx_test.csv')
```

You can then refer to these files directly as `edx_train.csv` and `edx_test.csv`.

### Kaggle

The starter notebook shows you the files available in the Kaggle system. For example, to refer to the training data you could use the file path `/kaggle/input/csestat-416-23sp-assignment-5/edx_test.csv`.

### Local

If you set this up, you will need to download the data from Kaggle and then refer to the files in your code as you downloaded them on your computer.

## Data Inputs

The data inputs are described in more detail in the `edX_column_description.pdf` below. We highly recommend that you read through this to understand what the columns mean.

The `userId_DI` field is necessary for evaluating your results but is likely not useful for your model in any way. You are encouraged to exclude `userId_DI` from being a feature that the model uses, but you must keep the `userId_DI` field so that you can properly identify the examples for evaluation.

Note that some categorical values can have the value `unk` or `nan` for unknown. In the numerical categories, like `YoB` which represents Year of Birth, `-1` is filled in for unknown values. Unknown values will be present in the test set as well so your model will need to be able to handle them.