German Student Responses to Probability Theory and Statistics Bachelor Course (WuS24): Evaluated with Rubrics

Description:

This dataset contains questions and answers from an introductory computer science bachelor course on statistics and probability theory at Hochschule Bonn-Rhein-Sieg. The dataset includes three questions and a total of 90 answers, each evaluated using binary rubrics (yes/no) associated with specific scores.

Dataset Components:

1. questions.csv: Contains the details of the three questions.
   • Columns:
     • question_id: Unique identifier for each question
     • question: The text of the question
     • solution: The reference answer for the question
     • max_score: The maximum score for this question
2. rubrics.csv: Contains the grading rubrics for each question.
   • Columns:
     • question_id: Unique identifier for each question
     • rubric_id: Unique identifier for each rubric within a question
     • rubric: The rubric phrased as a question
     • score: The score associated with fulfilling the rubric
3. answers.csv: Contains 90 student answers to the questions.
   • Columns:
     • answer_id: Unique identifier for each answer
     • question_id: Unique identifier of the question that is answered
     • answer: The text of the student's answer
     • score: The score associated with fulfilling the rubric
4. answer_rubrics.csv: Contains the evaluations of rubrics for each answer.
   
   • Columns:
     • answer_id: The identifier of the answer.
     • question_id: The identifier of the question.
     • rubric_id: The identifier of the rubric for that question.
     • label: Indicates if the rubric crierion is fulfilled for the specific answer (true / false).

Working with the Dataset:

The easiest way to work with this dataset is using the class `RubricsDataset` defined in the file `dataloader.py`. 

Example:

from dataloader import RubricsDataset

dataset = RubricsDataset.from_directory("data")

dataset.get_question(1) # Get a dictionary containing info about the first question, including rubrics
dataset.get_answers(1)  # Get all the answers for the first question as a list. Each answer is a dictionary with answer, score, rubrics.