liveBook · Manning

ChatGPT

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

ChatGPT is a conversational AI system based on large language models that generates responses to user prompts.

ChatGPT supports tabular-data work as an analytical assistant, helping users write commands, interpret results, summarize findings, and present charts or reports. section 1.5

Use ChatGPT to:

  • Engineer features from textual columns by summarizing, categorizing, identifying themes, and generating Python processing code. section 1.5
  • Analyze CSV files through preprocessing, analysis, visualization, summarization, and report generation, while producing executable Python code. section 1.5
  • Interact with tables through natural-language questions, data manipulation, visualization, reporting, and automated prediction. section 1.5

Practical workflow

Give ChatGPT a CSV, request preprocessing and a chart, then inspect the generated Python and visualizations before using the results in a report. section 1.5

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

How deep it goes
Demonstrates end-to-end analytical tasks but reports weaker tabular prediction performance than fully supervised models.
Examples
Uses CSV files, textual columns, matplotlib commands, regular expressions, charts, tables, and generated analytical reports.
What you can do after
Apply it via the Advanced Data Analytics API to analyze CSV data and reproduce results with generated Python code.
How it connects
Connects large language models with tabular data, feature engineering, Python, visualization, and supervised prediction.

Also explained in

Compare how 20 books explain ChatGPT →

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.