Data analysis with pandas: clean, explore and explain data

pandas is the standard Python library for working with tables of data. Analysts, scientists and engineers use it to load spreadsheets and database exports, clean them, combine them and answer questions. If you have ever spent an afternoon fixing a spreadsheet by hand, pandas will change how you work.

This course teaches pandas through real, messy public datasets: city bike trips, a retail sales export and weather records. You will meet the problems real data has, like inconsistent dates, missing values, duplicated rows and typos in categories, and learn a reliable process for dealing with them.

What you will learn

• Setting up Python, Jupyter and pandas
• DataFrames and Series, indexing and selecting data
• Cleaning: types, missing values, duplicates, text and dates
• Grouping and aggregating to answer business questions
• Joining tables and reshaping data
• Working with dates and time series
• Quick charts for exploration
• Writing analysis that someone else can rerun and trust

How the course works

Every lesson is a notebook. We start each section with a question, such as "which stations run out of bikes on weekday mornings", and build the pandas code to answer it step by step. You will also learn to check your results, because a wrong number delivered confidently is worse than no number.

You need basic Python: variables, lists, dictionaries, loops and functions. No statistics background is required.