Ghost in the Dataset | AI-Powered Data Analysis with Gemma 2B

Description and use

Ghost in the Dataset is a Streamlit app that uses Gemma 2B and Isolation Forest to automatically detect anomalies and generate explanations for CSV data.

Problem

Users need an interactive way to uncover hidden patterns and anomalies in CSV datasets without complex tooling.

Outcome

The application demonstrates that an open‑weight AI model can be integrated locally to provide automated, interactive data investigation, reducing manual effort and making anomaly detection accessible to beginners.

Workflow

• Upload CSV file via Streamlit interface
• Display dataset overview and preview
• Run missing‑value analysis with Pandas
• Apply Isolation Forest (scikit‑learn) to detect anomalies
• Visualize numerical columns with Matplotlib
• Send dataset summary and anomalous records to Gemma 2B via Ollama
• Generate AI explanations and next‑step suggestions
• Allow download of investigation report

Evidence

Ghost in the Dataset is an AI-powered CSV data analysis application that helps users discover hidden patterns and unusual records in their datasets.

Source

Users can upload CSV files and explore: Dataset overview and preview, Missing value analysis, Anomaly detection using Isolation Forest, Numerical data visualization, AI-generated investigation explanations using Gemma 2B, Downloadable investigation reports

Source