Ml Cluster

Cluster and Label Data

Find natural groups in a dataset using unsupervised clustering, then label each group with a plain-language description. No ML expertise required — the algorithm selection, parameter tuning, and result interpretation are all handled automatically.

Input

• File path (required): CSV, JSON, Parquet file, or directory of text files
• Objective (optional): Natural language description of what to find (e.g., "find customer segments", "group these documents by topic")

If no objective is provided, discover the most natural groupings in the data.

Workflow

Phase 1: Environment Check and Data Loading

Check required packages:

uv run python3 -c "import pandas; import sklearn; print('Core packages available')"