The Scenario
You are a sports analytics student. You have a data science project due in three weeks: a clustering model that groups college football players by physical profile — position, height, weight, year in school. You need the full 2023 Michigan Wolverines roster as your test dataset before you can write a single line of scikit-learn.
It is Saturday morning. The project kickoff meeting is Monday.
The bad version:
- You look up the roster endpoint on CollegeFootballData.com
- You hit it for the 2023 Michigan roster and get back 120 players in JSON format
- You spend an hour writing Power Query M to extract name, number, position, height, weight, and year
- Height comes back in a "6-3" string format — Power Query needs custom logic to convert it to total inches
- You walk into Monday's kickoff with a half-formatted table and an apology.
The fast version is one prompt.
The Easy Way: One Prompt in SheetXAI
SheetXAI handles the JSON parsing and can normalize height to inches in the same pull.
Open the SheetXAI sidebar and type:
Pull the complete 2023 Michigan Wolverines roster from College Football Data into my Excel workbook with columns for name, number, position, height, weight, and year in school.
SheetXAI pulls the full roster, parses the response fields, and writes a clean table. 120 players, six columns, ready for the model.
What You Get
A clean roster table with 120 rows:
- Player name — full name for each player on the roster
- Jersey number — for cross-referencing with other data sources
- Position — position code (QB, WR, OL, DB, LB, etc.)
- Height — as recorded in the API
- Weight — in pounds
- Academic year — Freshman, Sophomore, Junior, Senior, or Graduate
The table is import-ready. Export from Excel to CSV and load directly into pandas.
What If the Data Is Not Quite Ready
Roster data for clustering models often needs transformation before it is useful. SheetXAI handles it.
When height is in "6-3" string format and you need total inches
Your clustering model requires numeric inputs. "6-3" is not numeric.
In this Excel workbook, add a column called "Height (inches)" that converts the height column from "feet-inches" format (e.g. "6-3") to total inches (e.g. 75). Use this column as the numeric height input for downstream analysis.
When you want to group players by position unit
Your model needs a position group label, not just position code.
Add a column called "Position Group" to this workbook. Use these groupings: QB = Quarterback; RB, FB = Backfield; WR, TE = Skill; OL, OT, OG, C = Offensive Line; DE, DT, NT = Defensive Line; LB, ILB, OLB = Linebacker; CB, S, DB = Secondary; K, P, LS = Special Teams. Fill in the group for every player.
When you want to compare the Michigan 2023 roster to the 2022 roster
Your project includes a year-over-year physical profile comparison.
Fetch the 2022 roster for Michigan from College Football Data and write it into a new tab called "Michigan 2022" with the same columns as the 2023 tab. Then in a third tab called "Year-Over-Year," calculate the average height and average weight by position group for each year and show them side by side.
When you want multiple programs for a conference-wide clustering study
Your professor expanded the scope: you now need the full 2023 roster for every Big Ten program.
Fetch the 2023 roster for every Big Ten program from College Football Data. Write each roster into a separate tab named after the school. Then in a tab called "Combined Roster," append all rosters together with a "School" column added. Normalize height to total inches and add the Position Group column using the same groupings as Michigan.
The pattern: one roster is one prompt. Every Big Ten roster is still one prompt, with a combined output.
Try It
Get the 7-day free trial of SheetXAI and ask it to pull the roster for any program and year. The CollegeFootballData.com integration is included in every SheetXAI plan. For more, see how to export player position stats or the CollegeFootballData.com in Excel overview.