DOCUMENTATION

Hand a SQL result to the ML Lab

Filter, join or aggregate in SQL, then train on the result — with no intermediate file.

The gesture

  1. Open the Data Studio and load a file.
  2. In the SQL console, write your query. The active dataset is queryable by name, and you can attach other files — CSV, Parquet or JSON.
  3. Once the result is right, click Send to the ML Lab.

The result becomes the lab's active dataset. Nothing is written to disk on the way.

Open the Data Studio

## When this is the right tool
  • Filter before training: keep one region, one period, one segment.
  • Join several files on a key, when the Data Studio's own join is not enough.
  • Aggregate: go from one row per event to one row per customer, which is what most real ML problems need.

What leaves the console

The console paints the first 200 rows so it stays responsive, and always states how many rows the query returned. The exports are the query, not the screen: the CSV, the Parquet file and the ML Lab handoff are written by the engine itself, and carry every row.

  • A NULL stays a missing value. It leaves as an empty cell, which the lab reads as missing. A numeric column with NULLs arrives as a number with gaps.
  • Each query has a file name of its own, such as query-3f2a91c4.csv: a fingerprint of the query, never its text. The lab's test-set ledger knows a file by its name and shape, and two queries of the same shape must not share one count.
  • The lab's cell budget applies. A result past 20 million cells (rows times columns) is refused before it is built, with the advice to aggregate or filter. It is the same budget a file is read under.

Until V69 the exports were built from the painted rows: a query returning 590 rows handed 200 to the lab, and a NULL arrived as the mark the console shows for it, which turned a numeric column into text. Measured after the fix: the 590 rows arrive, and a plain SELECT * over each of the lab's six demos gives back the same rows, the same columns and the same inferred types as the file itself.

The cost, announced

The SQL engine is an 18–22 MB download, optional. Until you open it, it is not downloaded. It is single-threaded: LabML does not serve the headers that would unlock multi-threading.

That is also why cross-column consistency checks do not go through SQL: they have to work for everyone, including people who never open the console.

Where to go next