While data analysis is always technical (and sometimes even a little bit repetitive), you can still have fun with it. Playing around with existing online datasets is great practice, and you\u2019ll find various data-driven projects put together by experts and aficionados, many of them available in open-source communities like Github.<\/p>\n\n\n\n
What\u2019s more, you can easily find data sets that relate to your non-data-related hobbies and interests, from your favorite TV show to tracking the 2020 election.<\/p>\n\n\n\n
In this blog, we\u2019ll cover some of the fun datasets you can use to hone your skills, which are free, publically available, and range from entertainment to animals to sports. For a more tailored approach to your learning journey, we\u2019ve also organized the data sets into four top skills that all data analysts should master: data cleaning; data visualization; machine learning; and data analysis.<\/p>\n\n\n\n
Get started below!<\/p>\n\n\n\n
\u201cFun\u201d datasets concern topics that are of personal interest, and can be used to answer unexpected questions and explore relationships that aren\u2019t immediately intuitive. Perhaps you start with a question or hypothesis, and then find a dataset<\/a> to prove (or disprove) your theory. Or, you might even generate your own dataset using web scraping techniques or an open API. In fact, creating your own dataset enables you to collect, label, and prepare a clean dataset. <\/p>\n\n\n\n Working with fun datasets will make your data science portfolio<\/a> more eye-catching to employers, who have probably seen their fair share of Netflix-inspired recommendation engines and Twitter sentiment analysis projects. <\/p>\n\n\n\n Play with your data as much as you can before you begin your analysis. See if you can cross-reference two different datasets to compare different variables. For example: how do rising gas prices affect hotel occupancy in different parts of the country?<\/p>\n\n\n\n The dataset should be rich enough to let you play with it and derive patterns. In other words, it must have at least a few thousand rows and at least 20-25 columns, and a reasonable mix of continuous and categorical variables. <\/p>\n\n\n\n These datasets can be a perfect way to find new inspiration within the data science<\/a> world. In such a dynamic industry, it\u2019s important to stay sharp. Practicing without pressure is a surefire way to boost your skills on your own.<\/p>\n\n\n