● Covered by 1 source · 1 reportMedium impact1 neutral
BigQuery DataFrames Introduces .bigquery Accessor for Zero-Shot ML Predictions in Pandas
Key points
- New .bigquery accessor integrates BigQuery AI functions into pandas.
- Enables zero-shot ML predictions directly from pandas DataFrames.
- Translates pandas operations to Google Standard SQL for execution on BigQuery.
- Simplifies ML workflows by bypassing local model training.
Seamless ML Integration in Pandas
The new .bigquery accessor from BigQuery DataFrames (BigFrames) allows users to execute advanced machine learning workflows, including forecasting, classification, and high-dimensional embedding generation, directly within a pandas DataFrame. This integration means data scientists can invoke BigQuery's enterprise-grade AI functions without leaving their familiar pandas environment.
Simplified Machine Learning Workflows
Traditionally, running regression tasks in pandas involved extracting data locally, manually selecting features, and training a scikit-learn model. With the .bigquery accessor, users can now leverage BigQuery's ai.predict() function directly on their data, simplifying the entire ML process by bypassing local training and model development.
How the Accessor Works
The .bigquery accessor utilizes the BigQuery DataFrames library to push computations to Google Cloud. When an AI method like .ai.predict() is called, it translates the pandas operation into Google Standard SQL. This SQL query is then executed against foundational models, such as TabFM, on BigQuery's infrastructure, with the results returned as a standard pandas DataFrame.
Setup and Configuration
To use the new functionality, users need a Google Cloud project with specific roles granted, including BigQuery Job User and Agent Platform User. After installing pandas and bigframes in a Jupyter environment, importing the bigframes library and specifying the Google Cloud project ID enables all subsequent AI function calls to be routed through the authorized project.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub google/bigframesReporting from
BigQuery DataFrames has released a new .bigquery accessor, allowing users to run BigQuery's AI functions directly within pandas DataFrames. This integration enables zero-shot machine learning predictions, such as forecasting and classification, by translating pandas operations into Google Standard SQL and executing them on BigQuery's infrastructure.