57: What is Data Science? - Vicki Boykis




Test & Code - Software Testing, Development, Python show

Summary: <p>Data science, data engineering, data analysis, and machine learning are part of the recent massive growth of Python. </p> <p>But really what is data science? </p> <p>Vicki Boykis helps me understand questions like:</p> <ul> <li>No really, what is data science?</li> <li>What does a data pipeline look like?</li> <li>What is it like to do data science, data analysis, data engineering?</li> <li>Can you do analysis on a laptop?</li> <li>How big does data have to be to be considered big?</li> <li>What are the challenges in data science?</li> <li>Does it make sense for software engineers to learn data engineering, data science, pipelines, etc?</li> <li>How could someone start learning data science?</li> </ul> <p>Also covered:</p> <ul> <li>A type work (analysis) vs B type work (building)</li> <li>data lakes and data swamps</li> <li>predictive models</li> <li>data cleaning</li> <li>development vs experimentation</li> <li>Jupyter Notebooks</li> <li>Kaggle</li> <li>ETL pipelines</li> </ul> <p>I learned a lot about the broad field of data science from talking with Vicki.</p><p>Special Guest: Vicki Boykis.</p><p>Sponsored By:</p><ul><li> <a rel="nofollow" href="https://testandcode.com/digitalocean">DigitalOcean</a>: <a rel="nofollow" href="https://testandcode.com/digitalocean">Get started with a free $100 credit </a> </li></ul><p><a rel="payment" href="https://www.patreon.com/testpodcast">Support Test &amp; Code - Software Testing, Development, Python</a></p><p>Links:</p><ul> <li><a title="How to Lie with Statistics : Darrell Huff" rel="nofollow" href="https://amzn.to/2Pv9FfS">How to Lie with Statistics : Darrell Huff</a></li> <li><a title="Should you replace Hadoop with your laptop?" rel="nofollow" href="https://veekaybee.github.io/2017/03/20/hadoop-or-laptop/">Should you replace Hadoop with your laptop?</a></li> <li><a title="Kaggle" rel="nofollow" href="https://www.kaggle.com/">Kaggle</a></li> <li><a title="Project Jupyter" rel="nofollow" href="https://jupyter.org/">Project Jupyter</a></li> <li> <a title="Soviet Art Bot" rel="nofollow" href="https://veekaybee.github.io/soviet-art-bot/">Soviet Art Bot</a> — A bot that finds socialist realism paintings and tweets them out</li> </ul>