# Eedi - Mining Misconceptions in Mathematics — Data

来源：https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

On Eedi, students answer Diagnostic Questions (DQs), which are multiple-choice questions featuring one correct answer and three incorrect answers, known as distractors. Each question targets a specific _construct_ (also referred to as a skill), representing the most granular level of knowledge relevant to the question. Each distractor is designed to correspond with a potential _misconception_. Below is an example of a DQ:

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F59561%2F6b5e8a44a3cba072a05f6579f2fc0d6b%2Fexample_image.png?generation=1727211641939246&alt=media)

In this example, the options for the question are labeled with misconceptions as follows:

- **A**: Divides total amount by each side of the ratio instead of dividing by the sum of the parts
- **B**: Mixes up sides of a ratio
- **C**: Finds one part of a ratio but doesn't multiply that by the number of parts needed
- **D**: Correct answer

The Diagnostic Questions were originally presented in image format, and the text, including mathematical content, has been extracted using a human-in-the-loop OCR process.

## File and Field Information ##

- **[train/test].csv** 
  - `QuestionId` - Unique question identifier (`int`).
  - `ConstructId` - Unique construct identifier (`int`) .
  - `ConstructName` - Most granular level of knowledge related to question (`str`).
  - `CorrectAnswer` - A, B, C or D (`char`).
  - `SubjectId` - Unique subject identifier (`int`).
  - `SubjectName` - More general context than the `construct` (`str`).
  - `QuestionText` - Question text extracted from the question image using human-in-the-loop OCR (`str`) .
  - `Answer[A/B/C/D]Text` - Answer option A text extracted from the question image using human-in-the-loop OCR (`str`).
  - `Misconception[A/B/C/D]Id` - Unique misconception identifier (`int`). Ground truth labels in `train.csv`; your task is to predict these labels for `test.csv`.
- **misconception_mapping.csv** - maps `MisconceptionId` to its `MisconceptionName`
- **sample_submission.csv** - A submission file in the correct format.
  - `QuestionId_Answer` - Each question has three incorrect answers for which need you predict the `MisconceptionId`.
  - `MisconceptionId` - You can predict up to 25 values, space delimited. 

Please note that this is a [**Code Competition**](https://www.kaggle.com/competitions/eedi-mining-misconceptions-in-mathematics/overview/code-requirements).  The hidden test set has approximately 1,000 questions.