Python data analysis with pandas

About this track

The working analyst track. You already know Python basics; here you learn the library that professionals actually use. Load messy files, fix broken types and dates, handle missing values, group and join tables, reshape between wide and long, and produce charts a manager can read. Finish with a reproducible analysis you can show an employer.

Every lesson is written and hosted here on Yanjye — you never leave the site. Work through them in order, then sit the exam to earn your certificate.

Create a free account or log in to track your progress and earn the certificate.

Lessons

1. 1
   Why pandas, and how it thinks

   Columns instead of loops, and the mental shift that comes with it.

   ~20 min
2. 2
   Series, DataFrames and the index

   Building tables, naming columns, and controlling row labels.

   ~25 min
3. 3
   Loading data: CSV, Excel, JSON and SQL

   read_csv and the arguments that rescue broken files.

   ~25 min
4. 4
   First contact: inspecting a new dataset

   The eight commands to run before you analyse anything.

   ~25 min account needed
5. 5
   Selecting and filtering rows

   loc, iloc, boolean masks, query and isin.

   ~30 min account needed
6. 6
   Missing data: find it, understand it, decide

   NaN, why it is missing, and the four honest options.

   ~30 min account needed
7. 7
   Cleaning types, text and dates

   to_numeric, the .str accessor, and datetime handling.

   ~30 min account needed
8. 8
   groupby: the heart of analysis

   Split, apply, combine — plus agg and transform.

   ~30 min account needed
9. 9
   Joining and combining tables

   merge, concat, join types, and the row-count check.

   ~30 min account needed
10. 10
    Reshaping: pivot, melt and crosstab

    Wide for humans, long for tools, and how to switch.

    ~25 min account needed
11. 11
    Charts that get read

    pandas plotting, matplotlib control, and honest design.

    ~30 min account needed
12. 12
    Turning it into work someone can trust

    Structure, reproducibility, sanity checks and the write-up.

    ~30 min account needed