What problem does it solve? Writing correct BigFrames (BigQuery DataFrames) code requires knowing pandas-style APIs that execute remotely on BigQuery, and common mistakes like materializing data locally or using scikit-learn cause OOM errors and slow queries. This Skill guides code generation so dataframe and ML work stays in BigQuery's distributed engine. ## Core Features & Use Cases - Dataframe API Best Practices: Enforces partial ordering mode, peek() previews, accessor-based transformations, and avoidance of to_pandas() and raw SQL via read_gbq(). - BigQuery ML Integration: Generates model training, evaluation, and prediction code using bigframes.bigquery.ml functions like create_model, evaluate, and predict. - Use Case: A data scientist in a notebook wants to train a logistic regression model on the BigQuery penguins dataset without downloading data; the Skill produces code that creates the model, evaluates it, and runs predictions entirely in BigQuery. ## Quick Start Write BigFrames Python code that loads the penguins dataset from BigQuery and trains a linear regression model to predict penguin body mass.
