F1 Telemetry Analyzer

Turns raw F1 22 lap telemetry into compact Markdown reports you can paste into an LLM for analysis. A full raw lap is ~1M tokens; these reports are 1–35k.

# from the tool/ folder
python -m telemetry technique ../zandvoort_P_L7_74.074_ferrari.csv
# -> ../reports/zandvoort_P_L7_74.074_ferrari_technique.md   (~34k tokens)

Or just double-click run-gui.bat and click Generate report.

Install

Python 3.10+ (uses only the standard library — no pip install).
Tk is required for the GUI; it ships with the standard Python installer on Windows/macOS. The CLI works without it.

Download or clone the repository. Keep your telemetry CSVs in the parent folder of tool/ (see folder layout).

What it does

Five modes. Four produce reports, one renames files.

Mode	Input	Use it to analyse
`technique`	one lap	how you drive — braking points, apex speeds, throttle application, lockups, resource cost
`setup`	one lap	what is set — balance (US/OS), tyre temps, brakes, suspension rake & roll
`compare`	two+ laps	where one lap is faster — per-corner and cumulative delta
`race`	a folder of laps	the whole race — pace, stint degradation, tyre wear, ERS per lap
`rename`	files/folder	insert the lap number into each filename (`..._74.074_...` → `..._L7_74.074_...`)

Reports include a legend explaining every column, so the LLM understands the data without extra prompting. Ready-made analysis prompts live in prompts/ — one per mode.

Folder layout

The program lives in tool/; your telemetry sits one level up, output lands next to it:

Telemetry/
  zandvoort_P_L7_74.074_ferrari.csv   <- raw laps here
  races/
    Zandvoort_Race_2026/              <- one folder per race (for `race` mode)
  reports/                            <- generated reports land here
  tool/                               <- this repository
    telemetry/
    prompts/
    run-gui.bat

Handy things

GUI — double-click run-gui.bat (or run-gui.pyw for no console window, or run python -m telemetry gui). Pick a mode, browse to the file/folder, click Generate. The Rename unprocessed button adds lap numbers to files that don't have them yet and leaves the rest alone.

CLI — from the tool/ folder:

python -m telemetry technique ../lap.csv
python -m telemetry setup     ../lap.csv
python -m telemetry compare   ../lap_a.csv ../lap_b.csv
python -m telemetry race      ../races/Zandvoort_Race_2026
python -m telemetry rename    ../races/Zandvoort_Race_2026   # or individual files

Every report run prints the output path and a token estimate:

C:\...\Telemetry\reports\lap_technique.md
~33834 tokens (budget 60k)

Rename only touches unprocessed files. A file is "processed" once its name contains an L<number> token, so re-running rename is safe and idempotent.

Input format

F1 22 UDP telemetry exported to CSV (tested with F1Laps). UTF-8, ~1800 rows per lap (≈29 Hz), 108 channels. One file = one lap. For race mode, drop all of a race's lap files into one folder.

For developers

Pure-stdlib Python. Pipeline: parser → segments (+ corner_metrics) → resample → report_*. See ARCHITECTURE.md.

cd tool
python -m pytest -q        # run the test suite
python -m telemetry gui    # launch the GUI

Adding a mode: drop a telemetry/report_<mode>.py exposing generate(...) -> (abs_path, tokens) and wire one line into telemetry/__main__.py. The parser, corner detection, adaptive trace, and shared report blocks are reused.

Credits

Built for analysing personal F1 22 hotlaps. Telemetry export format from F1Laps.

License

MIT — see LICENSE.

3.8 KiB Raw Blame History Unescape Escape