1. Tests and Quizzes
1.1. Sample Multiple-Choice Quiz
Subject: Introduction to Data Science
Topic: Basic Statistics and Probability
Instructions: Choose the correct answer for each question. Each question is worth 1 point.
- What is the mean of the following data set: {5, 8, 10, 12, 15}?
- a) 8.0
- b) 10.0
- c) 12.0
- d) 11.0
- Which of the following is NOT a measure of central tendency?
- a) Mean
- b) Median
- c) Mode
- d) Variance
- What is the probability of flipping a coin and landing heads?
- a) 1/2
- b) 1/3
- c) 1/4
- d) 1
- Which distribution is typically used to model the number of successes in a fixed number of independent Bernoulli trials?
- a) Normal Distribution
- b) Poisson Distribution
- c) Binomial Distribution
- d) Exponential Distribution
1.2. Sample True/False Question
Subject: Machine Learning
Topic: Supervised vs. Unsupervised Learning
Instructions: Write “True” or “False” next to each statement.
- In supervised learning, the algorithm learns from labeled data to make predictions. _______
- Unsupervised learning is used when the data is already labeled. _______
- K-means clustering is an example of unsupervised learning. _______
- In supervised learning, the output variable is known during the training process. _______
2. Assignments
2.1. Programming Assignment
Subject: Python for Data Science
Topic: Data Cleaning and Preprocessing
Instructions:
Using the provided dataset (CSV format), complete the following tasks in Python:
- Load the dataset and inspect the first 10 rows.
- Handle missing values by using appropriate techniques (e.g., imputation, removal).
- Remove duplicates from the dataset and explain how they were identified.
- Normalize the data columns to ensure they are on a similar scale (use StandardScaler or MinMaxScaler).
- Provide a summary of your findings and discuss how the data was prepared for analysis.
Submission Format:
Submit the Jupyter Notebook file (.ipynb) containing the code, along with an explanation for each step you performed.
2.2. Research Paper Assignment
Subject: Ethical Data Science
Topic: Bias and Fairness in Machine Learning Algorithms
Instructions:
Write a 1500-word research paper on the following topic:
“The Impact of Bias in Machine Learning Algorithms and How to Mitigate It.”
Your paper should include the following:
- A brief introduction to machine learning and its applications.
- An explanation of the different types of bias that can occur in machine learning models (e.g., data bias, algorithmic bias).
- Examples of real-world cases where bias has impacted machine learning models (e.g., facial recognition, hiring algorithms).
- Techniques and methods for mitigating bias in machine learning algorithms.
- Ethical considerations regarding algorithmic fairness.
Assessment Criteria:
- Clarity and coherence of writing.
- Depth of research and understanding of ethical issues in AI.
- Application of concepts to real-world scenarios.
- Proper citations and referencing.
3. Project-Based Assessments
3.1. Data Science Capstone Project
Subject: Advanced Data Science Applications
Topic: Predictive Modeling for Business Problem
Project Brief:
You are provided with a business dataset (such as sales data, customer demographics, etc.) and tasked with creating a predictive model to forecast future sales for a retail company.
Instructions:
- Data Exploration: Analyze the data and clean it as necessary (handling missing data, feature selection).
- Modeling: Choose at least two machine learning models (e.g., Linear Regression, Random Forest, XGBoost) and evaluate them using appropriate metrics (e.g., RMSE, MAE).
- Feature Engineering: Create new features that could improve the model’s performance.
- Model Evaluation: Compare the performance of the different models and choose the best one based on evaluation metrics.
- Final Report: Prepare a final report (maximum 3000 words) that includes the following:
- Problem definition and data exploration.
- Data preprocessing steps.
- Model selection and evaluation.
- Recommendations based on the model’s output.
- A discussion of ethical considerations related to predictive modeling in business.
Submission Format:
- Python code and Jupyter notebooks.
- A detailed project report (PDF or Word format).
- Final presentation slides for the defense.
4. Peer and Self-Assessment
4.1. Peer Review
Subject: Data Science Group Project
Topic: Team Collaboration and Model Development
Instructions:
Evaluate your peers based on the following criteria. Use a 1-5 scale for each aspect (1 being poor, 5 being excellent).
- Collaboration: How well did your team members communicate and share responsibilities?
- Problem-Solving: How effectively did the team approach the data science problem?
- Creativity: How innovative were the solutions proposed for data analysis and modeling?
- Presentation: How well did the team present their findings, both technically and non-technically?
- Code Quality: How clean, well-documented, and efficient was the team’s code?
4.2. Self-Assessment
Subject: Data Science Individual Reflection
Topic: Self-Evaluation of Learning Progress
Instructions:
Reflect on your learning journey throughout the semester. Answer the following questions:
- What do you believe are your key strengths in data science at this point in your learning journey?
- Which areas do you feel you need to improve on and why?
- How did you contribute to your group projects, and what skills did you develop through that collaboration?
- What challenges did you face during this course, and how did you overcome them?
Submission Format:
A 500-word reflection document.
5. Rubrics and Grading Criteria
To ensure transparent grading, detailed rubrics are provided for each assessment. Below is a sample rubric for a Programming Assignment.
Programming Assignment Rubric
Criteria | Excellent (5) | Good (4) | Satisfactory (3) | Needs Improvement (2) | Unsatisfactory (1) |
---|---|---|---|---|---|
Code Quality | Well-organized, efficient, and fully functional code with proper comments | Clear code with minimal errors and good organization | Code works but with some inefficiencies and minor errors | Code is hard to follow with significant issues | Code is not functional |
Completeness of Task | All tasks are completed with high attention to detail | All tasks completed but with some minor gaps | Most tasks completed but lacking some details | Several tasks incomplete or missing | Many tasks not completed |
Data Processing | Excellent handling of missing data, outliers, and feature engineering | Adequate handling with minor issues | Basic data cleaning, but some issues remain | Inadequate data handling | No data cleaning or incorrect processing |
Report and Explanation | Clear, concise, and comprehensive explanation with insights | Good explanation with some gaps in detail | Sufficient explanation but lacking clarity | Poor explanation with significant gaps | No explanation or unclear |
Leave a Reply
You must be logged in to post a comment.