What problem does it solve? Writing pandas-style data analysis and machine learning code against BigQuery often leads to mistakes like pulling entire datasets into local memory, using unsupported scikit-learn patterns, or writing raw SQL that breaks lazy execution. This Skill generates correct BigFrames (BigQuery DataFrames) code that keeps computation in BigQuery. ## Core Features & Use Cases - DataFrame API Best Practices: Generates BigFrames code with partial ordering mode, peek() previews, accessor-based transformations, and cloud-side processing instead of local materialization. - BigQuery ML Integration: Uses bigframes.bigquery.ml for training linear/logistic regression and other models directly in BigQuery, with reference examples for common ML tasks. - Pipeline & Notebook Readiness: Produces environment-agnostic setup code for BigQuery Studio, Colab Enterprise, and scheduled pipelines, including to_gbq() output materialization and headless validation guidance. - Use Case: A data scientist in a notebook wants to train a logistic regression model on a large BigQuery table without downloading data. The Skill generates BigFrames code that loads the table, cleans it, trains via bigframes.bigquery.ml, and writes predictions back to BigQuery. ## Quick Start Ask the AI to write BigFrames code that loads a BigQuery table, cleans it, and trains a linear regression model using bigframes.bigquery.ml.
