# DTC Zoomcamp Q&A Challenge — Data

来源：https://www.kaggle.com/competitions/dtc-zoomcamp-qa-challenge/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

### Dataset Description

The dataset for the DataTalks.Club Q&A Matching Challenge consists of four CSV files and an attachments folder. These files contain questions and answers from DataTalks.Club courses, along with relevant metadata. Participants are expected to use these files to develop models that can accurately match questions to their correct answers.

#### 1. `train_questions.csv`:
   - **Purpose:** This file is used for training your model. It contains the questions along with metadata and the correct answer IDs.
   - **Columns:**
     - `question_id`: A unique identifier for each question.
     - `question`: The text of the question.
     - `course`: The specific course from which the question was sourced.
     - `year`: The year in which the course was conducted.
     - `candidate_answers`: A list of answer IDs that are potential matches for the question.
     - `answer_id`: The ID of the actual correct answer for the question.

#### 2. `train_answers.csv`:
   - **Purpose:** This file provides the answers for training, corresponding to the questions in `train_questions.csv`.
   - **Columns:**
     - `answer_id`: A unique identifier for each answer.
     - `answer`: The text of the answer.
     - `course`: The specific course from which the answer was sourced.
     - `year`: The year in which the course was conducted.
     - `attachments_files`: Names of any attachment files related to the answer, including images.

#### 3. `test_questions.csv`:
   - **Purpose:** Contains questions for evaluating your model's performance. It does not include the correct answer IDs.
   - **Columns:** Same as `train_questions.csv`, but excluding the `answer_id` column.

#### 4. `test_answers.csv`:
   - **Purpose:** Provides the answers for the test set. Participants need to match these answers to the questions in `test_questions.csv`.
   - **Columns:** Same as `train_answers.csv`.

#### 5. Attachments Folder:
   - **Contents:** Contains all the attachment files that are referenced in the answers. This includes images and potentially other types of files.
   - **Usage:** These attachments are part of some answers and can be critical for correctly matching questions to answers, especially for questions where visual context is important.

Participants are encouraged to explore and utilize the rich information available in these files, including textual content, course context, and temporal data, to develop robust models capable of accurately matching questions and answers.

### External Data Usage

#### Allowing External Data:
- **Policy:** In this competition, the use of external data is not only allowed but also encouraged. Participants are welcome to augment the provided dataset with additional relevant sources to enhance their models.
- **Sharing Requirement:** If you use external data, you are required to share the details and sources of this data with the community. This sharing should be done both on the Kaggle forum and on the DataTalks.Club (DTC) Slack channel.

#### Examples of External Data:
- **Slack Dump:** Conversations and Q&A sessions from relevant Slack channels that pertain to data science and the topics covered in DataTalks.Club courses.
- **ZoomCamp Q&A Google Documents:** Documents containing Q&A sessions from ZoomCamp courses or similar educational activities.
- **YouTube Videos (as text):** Transcripts or textual analysis of YouTube videos that are relevant to the course content or the subject of the questions in the dataset.

#### Purpose and Benefits:
- **Enhancing Models:** External data can provide additional context, variations in language use, and broader coverage of topics, which can be crucial for building more robust and accurate models.
- **Community Learning:** Sharing external data sources fosters a collaborative environment where all participants can learn from each other and build upon a diverse set of data.

Participants are encouraged to be creative and thoughtful in selecting external data that can genuinely contribute to the challenge's objective. The goal is to not only improve individual model performance but also to enrich the collective resources available to all competitors.