Excel for Data Science
Somebody sends you a spreadsheet
Now what? That is the part nobody teaches. You can write a SUM; what you do not know yet is which number they actually asked for, what to check before you trust a column, what to fix and what to leave alone, and what a finished answer looks like sitting next to the raw data. This track walks the whole thing, start to finish, on grids small enough to check by counting.
No pivot tables, no charts, no macros — every chapter is formulas you could type into any build of Excel, running live on a real engine in this page. The Excel tutorial and Spreadsheet Fundamentals stay free forever. This track is included with Basic, and the first chapter is open to everyone.
Sign in to track your progress across chapters.
Phase 1 Look at it
3 chaptersBefore a single formula: what you were actually asked for, and what is really in the sheet somebody sent you.
- 01Somebody sends you a spreadsheet7 minFreeThe whole job end to end on ten rows: what arrived, what to check, what to fix, and the number you hand back.
- 02What are they actually asking7 min"Did the promo work?" is not a question yet — and two honest readings of it give opposite answers on the same ten rows.
- 03First look at a sheet7 minFive checks on a file you have never opened — and the one that tells you what a single row actually stands for.
Phase 2 Clean it
4 chaptersCounting the right things, one name spelled four ways, which duplicate survives, and what a lookup that finds nothing is telling you.
- 04Counting things correctly7 minOne column of ratings, and four honest ways to count it — including the percentage that has three right answers.
- 05The same branch, four ways8 minEnumerate the spellings before you fix any of them — and find the one your formula silently handled and the one it did not.
- 06Which duplicate do you keep8 minTwo rows with the same order id are not one problem — find out whether they agree before you decide which one survives.
- 07When a lookup finds nothing8 minA lookup that fails is telling you something true about your data — and the failure that returns a number instead of an error is the one to fear.
Phase 3 Work with it
2 chaptersSorting rows into the buckets the question needs, and pulling in the second sheet without quietly losing half of them.
- 08Putting rows into buckets8 minSmall, medium and large are not in your data — you invent them, and every number downstream inherits the boundaries you picked.
- 09Bringing in the other sheet8 minThe customer list answers one question per row, quietly, and the two things it never tells you are which row it picked and which of your rows it dropped.
Phase 4 Deliver it
1 chapterA summary block somebody can act on: rounded, labelled, sitting beside the raw data with the exclusions written down.
If SQL is the half you need
The same ten steps exist for SQL, on the same kind of small table: SQL for Data Science. Both are included with Basic, and most analyst jobs want both — the spreadsheet is what gets sent to you, the database is where it came from.
Included with Basic
Chapter 1 is open in full, and the first section of every other chapter is too — read before you decide. Basic opens the rest of both data-science tracks, the full question bank, and Data Lab, where the same work happens on a warehouse too big to eyeball.
See Basic plans