pandas from Zero: Clean a Messy Customer Survey

<p>Priya Raman runs marketing at Fernhill Coffee Roasters, a speciality roaster in Bengaluru that sells online to seven countries. A few hundred customers answered her survey, and on Monday the founder decides whether to launch a subscription box using her numbers: how many answered, their average age, the share who are happy, and what a typical customer spends. The export is a mess: people pressed Submit twice, 999 means "unknown", dates come in three formats, every amount has a dollar sign and one country is spelled five ways.</p><p>Across five lessons you clean it with pandas, one problem at a time, on your own personal copy of the data: loading and profiling a file, duplicates, placeholders and missing values, converting text to dates, numbers and True/False, normalising categories, medians and a chart. In every lesson you write the step yourself first, then hand the same job to your AI (ChatGPT, Claude, Copilot or Gemini) and learn exactly where it goes wrong. In the capstone your AI writes the whole clean-up from one brief, and you prove every number before it reaches the founder.</p><p>Bartman runs your script on its own servers against your data and checks the files it writes, so every check is about your real output, not a screenshot.</p>

Tools: Python, pandas, Data Cleaning, Missing Values, Dates and Types, matplotlib, AI Assistants for Python