liveBook · Manning

Generative modeling

As explained in Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

Artificial intelligence that generates new content, such as text, images, code, or structured outputs, from learned patterns.

Generative modeling uses learned patterns to produce new content or useful outputs. In data work, large language models generate and transform text, assist with feature engineering, write Python, interpret results, and produce summaries or reports. section 1.5

Practical uses include:

  • Generating text from prompts, completing phrases, and producing analytical explanations. section 1.5
  • Processing textual columns by summarizing, categorizing, identifying themes, or creating new features. section 1.5
  • Supporting machine-learning pipelines by answering cloud questions, generating or interpreting code, documenting implementations, and summarizing logs during debugging. section 11.4

From CSV to analysis

A data practitioner can provide a CSV containing textual fields to ChatGPT’s Advanced Data Analytics API, request preprocessing, analysis, visualizations, or a report, and receive executable Python code alongside tables and charts. section 1.5

How Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI covers it

How deep it goes
Explains practical capabilities and workflow applications, but stops short of detailing model architecture, training, or generation algorithms.
Examples
Uses textual table fields, CSV analysis, generated Python functions, visualizations, reports, pipeline code, documentation, and summarized logs.
What it assumes
Assumes familiarity with textual data, Python, machine-learning workflows, and Google Cloud or Vertex AI pipeline tasks.
What you can do after
Apply it via ChatGPT’s Advanced Data Analytics API or Gemini for Google Cloud to analyze data and support pipeline development.
How it connects
Links generative modeling with large language models, tabular data, feature engineering, Python, visualization, and machine-learning pipelines.

Also explained in

Compare how 29 books explain generative modeling →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI. The section links point to the parts of the book it draws on.