In this part of the course, you’ll get an overview of two possible tracks to complete your case study. You can use a dataset from one of the business cases provided or search for a public dataset and develop a business case for an area of personal interest. In addition, you'll be introduced to several platforms for hosting your completed case study.

• Apply the practices and procedures associated with the data analysis process to a given set of data.
• Discuss the expectations involved in completing a data analysis case study.
• Move their portfolio to Kaggle, post and make it public
• Add R Code to a Kaggle Notebooks
• Recall the different types of Kaggle Notebooks

---

In this part of the course, you will prepare a case study that you can include in your online portfolio. All of the resources provided will help you to succeed in this goal (referred to as the Google Data Analytics Capstone).

There is an old saying that you learn by doing. You have already learned about the importance of each phase in the data analysis process when working with a dataset. You will soon learn about the importance of having an online portfolio. The Google Data Analytics Capstone will enable you to actually put the two together—a dataset you took through the data analysis process for your portfolio.

By completing your capstone project, you will practice:

• Going through the Ask, Prepare, Process, Analyze, and Share phases of the data analysis process
• Stating a business task clearly
• Importing data from a real dataset
• Documenting any data cleaning that you perform on the dataset
• Analyzing the data
• Creating data visualizations from your analysis
• Summarizing key findings from your analysis
• Documenting your conclusions and recommendations
• Creating and publishing your case study

Your case study will demonstrate these fundamental skills to prospective employers and showcase what you have learned from the Google Data Analytics Certificate. It will represent your knowledge and capabilities in your portfolio.

---

The first track involves a case study similar to what you might be asked for in a job interview. You will be given a business task, dataset, and list of specific deliverables that you must present to stakeholders. The first track will help you to create a case study that you could include in your portfolio to demonstrate job skills for future interviews. You can choose from between two cases. Once you decide which case study packet to use, you will read the details, complete the analysis, and create your finished case study.

If this track interests you, explore the case study options and decide which one you want to perform. The case study packets available for download have everything that you need to complete your case study. Then, you will be ready to upload and share your case study with potential employers.

In this case study, you will perform data analysis for a fictional bike-share company in order to help them attract more riders. Along the way, you will perform numerous real-world tasks of a junior data analyst by following the steps of the data analysis process: Ask, Prepare, Process, Analyze, Share, and Act.

In this case study, you will perform data analysis for Bellabeat, a high-tech manufacturer of health-focused products for women. You will analyze smart device data to gain insight into how consumers are using their smart devices. Your analysis will help guide future marketing strategies for your team. Along the way, you will perform numerous real-world tasks of a junior data analyst by following the steps of the data analysis process: Ask, Prepare, Process, Analyze, Share, and Act.

The second track involves finding a public dataset that focuses on something that interests you. You could choose any topic about which you want to analyze data -- public bike use in your neighborhood, local wildlife migration, video game console sales, or anything else you are passionate about. You can follow the steps in the case study packet to guide you through this process. The case study packet provides public dataset recommendations, example business tasks, and steps to complete your analysis. This track is the most flexible, but that flexibility means that this track can be more challenging. You will have to use everything that you have learned so far to help you to complete this case study.

If this track interests you, explore the case study packet to learn more details, find the public dataset that you want to use, and complete your analysis. Then, you will be ready to upload and share your completed case study.

Inspiration is everywhere. You can get ideas for a case study to include in your portfolio from your hobbies, travels, children, volunteer work, and even something as common as waiting in line! For example, you might create a case study examining the effect of customer wait times on a company’s sales.

Let’s imagine you enjoy fishing. You can create a case study for your portfolio that relates to your hobby. It is helpful to browse Medium, GitHub, Tableau, and Kaggle to get an idea of what other people have already created and find some inspiration.

To search for case studies on Medium, go to medium.com/search.

Enter the term “fishing,” ****as an example. Medium will pull up a bunch of articles that are related to fishing. You can also explore topics related to fishing by clicking other tags on the right: Environment, Travel, Fishing and Travel, Outdoors, and more.

To search for case studies on GitHub, go to github.com/search.

If you enter “fishing” in the search field, GitHub returns over 4,000 results. If you enter “fishing case study” in the search field, GitHub returns one result: a case study of a marine fishing bat. Probably not a good match for you though!

To search for case studies in Tableau, go to public.tableau.com and use the search bar at the top of the page.

For example, click the search icon (the magnifying glass) and enter “fishing.” The term “fishing” returns over 400 results, but if you enter the hashtag “#fishing” instead, you get four interesting results.

To search for case studies on Kaggle, go to kaggle.com and use the search bar. For example, if you enter “fishing” in the search bar at the top of the page, you get results similar to the ones displayed below.

The “R Markdown - Fishing by Countries” notebook in Kaggle might be promising. You discover from this notebook that there is a public domain dataset called “Annual Nominal Fish Catches: Explore the impact of overfishing in the Northeast Atlantic region.“

You might have just found a great dataset to use to create your own case study. You wouldn’t want to repeat the same analysis related to overfishing, but the data could reveal another pattern worth analyzing.

You can use the same procedure completed for the fishing example to search for case studies and data about any other topic that interests you. By including case studies that are personally meaningful to you in your portfolio, you give prospective employers a better sense of the kind of person you are and what inspires your work.

This reading provides a checklist about what to include in your portfolio, where you can set up accounts to host your portfolio, and how to add content to your portfolio.

You learned that a portfolio represents your skills and showcases some of your previous projects to potential employers. Keep your portfolio:

• Personal: Show who you are, what you are interested in, and what is important to you.
• Simple: Display your work with easy navigation and without cluttered pages.
• Relevant: Match your work to the skills included in job descriptions.
• Presentable: Emphasize quality in the samples you show.
• Unique: Showcase your own work; cite sources of content to avoid plagiarism.

Choose a platform to host your portfolio. Medium, Google Sites, and Wordpress are good for blogging. GitHub and Kaggle are better for code. And finally, as you know, Tableau is great for visualizations. Next, create an account on the platform that you chose. Check out these steps to set up accounts on various platforms:

• Set up an account on GitHub
• Set up an account on Kaggle
• Set up an account on Tableau Public – Click the orange "Sign Up" button
• Set up an account on Medium
• Set up an account on WordPress
• Set up a site on Google Sites

Finally, refer to the following table for some links to articles that can help you to manage your portfolio. Articles are free but some sites limit the number of articles you can view per month. in that case, bookmark the article to view it later.

Platform	Information to help you manage your portfolio
GitHub	8 steps to publishing your portfolio on GitHub: Follow the steps in this article to create a repository for your portfolio.
Kaggle	Kaggle Kernels Guide for Beginners: Follow this tutorial to create a new Kernel and share it. Publishing your first dataset on Kaggle: Follow the steps in this article to publish your own dataset and make it public.
Tableau	Any visualization created in Tableau Public is already public by default. A lot more is involved to add a Tableau visualization to another hosted site. For that reason, it is probably best to link to Tableau visualizations when your portfolio is hosted on a personal website or on a different platform, like GitHub.
Medium	Getting started with a Medium publication: Follow the process in this guide to create your own publication.
WordPress	Get Published: Follow these instructions to create pages or post content on your site.
Google Sites	Publish & share your site: Follow these instructions to publish your site and share it publicly. Use a custom domain for your site: Refer to these instructions if you want to use a custom URL for your portfolio.

As you create your data analytics portfolio, you might find yourself using Kaggle or another online platform to host it. Kaggle hosts interactive notebooks that let you showcase your programming and hard work. If you have an existing portfolio already, you can copy your content into Kaggle to have an additional way to share it.

By the time you complete this activity, you will have created a Kaggle notebook containing your portfolio content. Then you can easily share your work with a Kaggle link, enabling you to send your portfolio to more people.

First, it’s helpful to know the different kinds of Notebooks on Kaggle. Every kind of Kaggle Notebook utilizes code, but each one contains different languages for programming or writing text. The different types include:

• Scripts: Typically code-only documents. Cells can be formatted in R or Python only. They execute each cell as code sequentially.
• RMarkdown scripts: Cells can be formatted in R and RMarkdown only. These files are preferred by many R authors.
• Jupyter Notebooks: Cells can be formatted in Markdown, R, or Python. These are most suited to flexibility.

Before you create a Notebook in Kaggle, you should know which kind of Notebook you intend to use. Will you use any Markdown or RMarkdown to add context to your work? Will you be using R or Python? The answer to these questions will determine which Notebook you use.

To share the code you wrote in this course, you should choose a Kaggle Notebook that supports R and Markdown, such as an R Markdown script or a Jupyter Notebook.

1. To begin, log in to Kaggle and go to Kaggle.com/code.

2. Click + New Notebook to create a new notebook. If you want to use an existing notebook, go to the Your work tab and scroll to the notebook you want to use.

3. Decide whether you want to use a type of script or a Jupyter notebook, based on your project’s needs. The editor will begin on default as a notebook. If you want to change your notebook to a script, click on File at the top of your editor and hover over Editor Type. This opens a drop-down menu to select Notebook or Script. For this activity, select Notebook.

4. Since the work you did in the last course was in R instead of Python, you need to change the notebook’s language. Click on File at the top of your editor and hover over Language. This opens a dropdown menu with both options available. Select R if it isn’t selected already.

5. Open the file of a project you want to use in your portfolio. This can be the capstone project you completed during this course, an earlier activity you completed in a past course, or a personal project you created. Ideally, this project should demonstrate your coding ability and your data analytics knowledge.

6. Add the content of your portfolio piece. Copy the code you wrote into R cells and copy regular text or images into Markdown cells. To add a cell to the document, click + Code or + Markdown. It helps to test your code in the Kaggle interface by running it periodically as you write or copy it in. This way, you ensure that it doesn’t return an error.

7. Repeat steps 2-6 to upload your portfolio pieces to their own Kaggle notebooks.

You have now created (or duplicated) your portfolio in Kaggle! Your next step is to publish your portfolio so it can be publicly available for others to view and provide feedback.

Now, it’s time to publicly publish your portfolio on Kaggle. This will allow peers, hiring managers, and potential employers to view your skill set.

• Note: When you publish your portfolio, you will also need to publicize all documents associated with it. For example, if you include a link to a document on Google Drive, you will need to ensure it is also publicly viewable.

1. To begin, navigate to the Your work tab on the Code screen to bring you to the list of your notebooks and scripts.

2. Click on the first notebook or script you’d like to publicize. At the top right-hand corner, click the Share button with the Lock icon.

3. If the pop-up window states that the document is private, click on the word Private. This will open a drop-down menu where you will be able to select Public. Once it is Public, you’ll be able to add any relevant tags or collaborators who contributed to the document. You can use tags to describe the topics your work relates to. Click here to learn more about which tags you can use on Kaggle.

4. Repeat these steps until you’ve made each piece in your portfolio public on Kaggle.

You have now uploaded your portfolio to Kaggle and can share your accomplishments with friends, family, colleagues, hiring managers, and potential employers. You can update your portfolio as your skills as a data analyst continue to grow.

Now, you can share your portfolio by going to the Your work tab on Kaggle and copying the link from the address bar. Share this link to show the world your hard work!

---

TOTAL POINTS 6

For the following six questions, consider your detailed case study report and the steps of the data analysis process that you followed when creating it: ask, prepare, process, analyze, share, and act.

In the ask phase of your analysis, you wrote a clear statement of the business task. According to the Case Study Roadmap, this statement should 1) identify the specific problem you are trying to solve, and 2) consider key stakeholders. Take a moment to review your statement now. In what ways could you make it more effective at meeting these two requirements?

➖ A well-written business task provides you with a clear purpose when cleaning and analyzing data. It also helps you prioritize the types of visualizations to create and fine-tune the content of your final presentation.

In the prepare phase of your analysis, you described the data sources you used. According to the Case Study Roadmap, this description should include where the data is located and how it is organized. It should also consider issues with bias or credibility, problems with the data, and how you verified its integrity. Finally, your description should explain how the data helped you answer your questions. Take a moment to review your description now. What steps could you take to make it even more descriptive?

➖ As a junior data analyst, the credibility of your data has a big impact on your credibility with stakeholders. Information about your data should be readily available and clearly communicated so stakeholders know you are using high-quality data.

In the process phase of your analysis, you documented your data cleaning and manipulation. According to the Case Study Roadmap, this documentation should include a list of the tools you used and why you selected them. In addition, it was an opportunity to explain how you ensured your data’s integrity and confirmed that it was clean and ready to analyze. Take a moment to review your documentation now. How can you improve it in order to describe your cleaning and manipulation techniques even more thoroughly?

➖ Data analysts are always thinking about how to improve their data analysis documentation skills. Reviewing your documentation sparks new ways of thinking and can highlight where there might be a mistake. This ensures your data-driven recommendations are sound.

In the analyze phase of your analysis, you wrote a summary of your analysis. According to the Case Study Roadmap, this summary should discuss organizing and formatting your data. In addition, it should detail any surprises, trends, or relationships you discovered. Lastly, you should summarize how these insights helped you answer your questions. Take a moment to review your summary now. How can you improve it in order to highlight your analysis process in a more compelling way?

➖ A compelling summary of your data analysis demonstrates that you understand the data, can identify how it relates to the business case, and are sharing what you’ve found in the best possible way.

In the share phase of your analysis, you created data visualizations to support your key findings. According to the Case Study Roadmap, these visualizations should reflect your findings, data story, and audience — while keeping accessibility top of mind. Take a moment to review your visualizations now. Which one are you most proud of? And how can you apply your experiences during this course in order to improve the others?

➖ As a data analyst, it’s important that your visualization skills keep evolving with the changes in technology and design. Reviewing and critiquing your own work provides many opportunities for growth and development.

In the act phase of your analysis, you provided recommendations based on the final conclusion from your analysis. You were also asked what additional data you could analyze to enhance your work. Take a moment to consider this question again now. Respond with at least two ideas that you did not include in your original report.

➖ The act of asking yourself to come up with two more ideas can reveal recommendations that you had not thought of before. Hopefully, each of these questions gave you something new to consider. Reflecting on your work is a valuable step in the data analysis process.