Section 24 of 24 · 3 lessons

Complete Projects

Bring the pieces together around a question Botie needs to answer. Each small project includes a baseline, a repeatable procedure, held-out evaluation, and cases where the method fails. The datasets are small enough to inspect, so the reasoning stays visible as the work becomes more complete.

0 of 3 finished

Putting the Pieces Together

A complete small project needs a question, a baseline, a fair test, and an explanation of failures. Follow Botie through sensor inspection, demand forecasting, and counting seeds in images.

  1. 01Investigate a Sensor Before Calling It FaultyFit a reference from earlier readings, select an alert rule on validation records, and evaluate that fixed rule on later labelled cases.
    Build with Botie →Read the lesson
  2. 02Forecast Tomorrow’s Water Demand Without Seeing TomorrowBuild lagged inputs, compare an autoregressive model with persistence, and evaluate both through a sequence of later forecast origins.
    Build with Botie →Read the lesson
  3. 03Count Seeds While Keeping the Image Assumptions VisibleTurn a small tray image into a binary mask, label connected regions, and investigate when a region count stops matching the number of seeds.
    Build with Botie →Read the lesson