Overview Welcome to the Data Wrangling Quest! Your mission is to clean a messy dataset known as “Shark Attacks” using data wrangling techniques. By doing so, you will prepare the dataset for analysis based on a use case of your choice.

Throughout this quest, you will strengthen your Python skills, take further steps toward becoming a data analyst, collaborate with your team, and develop your problem-solving abilities.

Setup Teamwork You will work on this quest in teams. How you organize yourselves, divide tasks, and collaborate is entirely up to you.

Vildan: Structure & Identity columns - Date/Year/Time, Type (unprovoked/provoked), Country, Area, Location

Moci: Victim columns - Name, Sex, Age, Activity

Keagan: Outcome & Species columns - Fatal (Y/N), Injury, Species

How to Approach the Quest Each day, you should aim to:

Make progress on data cleaning and transformation Research and apply relevant concepts Share knowledge within your team Continuously improve your dataset and analysis You are responsible for organizing your time and workflow in a way that allows you to meet the final objectives of the quest.

Quest Brief You will begin by exploring the Shark Attack dataset, understanding its structure, and identifying potential issues.

From there, you should formulate one or more hypotheses. For example:

“Shark attacks are more common in certain locations” “Certain activities are more dangerous than others” “Shark attacks affect specific age groups more frequently” You may also frame your work around a business case, such as:

Suggesting destinations for shark spotting Identifying safe locations for surf-related businesses Throughout the project, you will use Python and pandas to apply at least five data cleaning techniques to handle issues such as missing values, duplicates, inconsistent formatting, etc.

Once your dataset is clean, you will perform exploratory data analysis (EDA) to validate your hypotheses and extract meaningful insights.

Suggested Progression by Day These are suggested guidelines to help you structure your work. You are free to adapt them as needed.

Day 1: Understanding the Data & Defining Direction Load and explore the dataset Understand the meaning of columns and values Identify data quality issues Define one or more hypotheses Outline a plan for your project Day 2: Data Cleaning Apply data cleaning techniques (excluding dates if you prefer to handle them later) Handle missing values, duplicates, inconsistent formats, etc. Work with strings and text data Explore the use of Regular Expressions (Regex) if relevant Begin thinking about how dates might be used in your analysis Day 3: Structuring & Initial Analysis Finalize data cleaning and formatting Transform the dataset to make it analysis-ready Create new columns if needed Group or aggregate data Start performing exploratory data analysis Look for patterns and trends related to your hypotheses Day 4: Final Analysis & Presentation Preparation Complete your analysis Validate or refute your hypotheses Refine your code and workflow Prepare your presentation Collaboration Guidelines You will be working collaboratively (e.g., using Google Colab or similar tools). Some general tips:

Keep your team aligned on changes and decisions Avoid working on the same part of the code simultaneously Save your work frequently Use version history if needed Ensure everyone understands the project progress Coding Best Practices Try to keep your code clean and organized:

Use clear and descriptive variable and function names Remove unused code Add comments where necessary to explain your logic Structure your work in a logical and readable way Refactor your code as you progress Deliverables To complete the project, you should submit:

A repository named data-cleaning-pandas on your GitHub account A working solution that meets the technical requirements At least one Jupyter Notebook Any additional files needed for your project A README with documentation A link to your presentation slides Paste your repository link in the Student Portal Project Activity Presentation Each team will present their project to the class.

Duration: 5 to 7 minutes per team When preparing your presentation, you may want to consider including:

The dataset and your initial hypothesis Your data cleaning approach and challenges Key transformations or techniques you applied Insights from your analysis Any major obstacles or learnings Final conclusions and takeaways The structure and format of the presentation are up to you. Focus on communicating your work clearly and effectively.