What problem does it solve? Writing pandas-style data analysis and machine learning code against BigQuery requires knowing BigFrames-specific APIs, ordering modes, and ML packages that differ from standard pandas and scikit-learn. This Skill provides the correct patterns so generated code runs distributed on BigQuery instead of pulling data into local memory. ## Core Features & Use Cases - BigFrames DataFrame best practices: Enforces partial ordering mode, peek() previews, accessor-based transformations, and avoidance of to_pandas() and raw SQL via read_gbq(). - Serverless ML with bigframes.bigquery.ml: Generates linear regression, logistic regression, and other model training code that delegates computation to BigQuery ML instead of scikit-learn. - Legacy BigFrames ML guidance: Covers bigframes.ml specifics such as DataFrame-returning predict(), no random_state, custom hyperparameter loops, ARIMA Plus forecasting, and model persistence via to_gbq(). - Use Case: In a notebook, ask for a logistic regression model on the public penguins dataset and receive complete BigFrames code that loads data, trains with bbq.ml.create_model, evaluates, and predicts entirely inside BigQuery. ## Quick Start Ask the AI to write BigFrames code that loads a BigQuery table and trains a linear regression model using bigframes.bigquery.ml.
