Machine Learning Academy · 2 / 5

Define the training rows

Select only the columns the model needs and make the training cap explicit.

YOUR TASK

Make this happen

3 steps

Add queries/training.sql selecting quantity and priority from jobs, excluding missing quantity and limiting to 1000 rows. Attach through dataQuerySQL.
Keep the working capabilities from the previous lesson and connect the new pieces to the same solution.
Check the complete solution, then inspect any unmet requirements.

THE IDEA BEHIND IT

What this step adds

Add queries/training.sql selecting quantity and priority from jobs, excluding missing quantity and limiting to 1000 rows. Attach through dataQuerySQL.

Files to work in

main.cococo, queries/training.sql. Other files are the working baseline. New files include named resource skeletons and TODO guidance. Complete their fields and connect them using the objectives, schema completion and reference guide.

Preview is not a training cap

A preview sample limit controls displayed samples, not the complete training dataset. An intentional SQL LIMIT belongs in the query itself.

Sampling needs review

This fixed query teaches source authoring. In a real project, choose a representative cohort and an ordering or sampling strategy appropriate to the domain; a limited sample alone is not an evaluation design.

Checks validate native model configuration and lesson requirements. They do not run SQL, normalize rows, train a model, score predictions or establish predictive quality.

Files to change: main.cococo, queries/training.sql

What you’re building: Author a reviewable job-quantity regression model with explicit features, missing-value handling and deliberate publication.

This step starts with the earlier solution and one new challenge. Each lesson keeps its own draft.

Read the starter files

main.cococo

ml_model_document "main" {
  format = "1"
  name = "job-quantity"
  backend = "xgboost"
  spec = {
    tabular = ml_model_tabular.quantity
  }
}

model.cococo

ml_model_tabular "quantity" {
  task = "REGRESSION"
  targetColumn = "quantity"
  featureColumns = [ml_model_feature.priority]
}

features.cococo

ml_model_feature "priority" {
  column = "priority"
}

queries/training.sql

SELECT quantity, priority
FROM jobs
-- TODO: exclude rows without a target and limit the training cohort.

Supplied supporting files

Reference: machine-learning · authoring