Marketplace

CSV Data Cleaner

The CSV Data Cleaner is a fully browser-based AI agent that turns messy, inconsistent spreadsheet data into clean, analysis-ready CSV files — without uploading your data to any external server. Upload your CSV by clicking or dragging and dropping, and the agent immediately runs a Python-based quality audit using pandas-style logic via Pyodide (Python compiled to WebAssembly). The automated issue detection scans every column for four categories of data quality problems: missing values (flagged HIGH if more than 20% of rows are empty, MEDIUM otherwise), duplicate rows (exact matches across all fields), inconsistent date formats (e.g. a column mixing YYYY-MM-DD, MM/DD/YYYY, and DD-MM-YYYY), and whitespace issues (leading or trailing spaces that break joins and lookups). Every issue is displayed with a severity badge before you do anything. From there, you have three ways to clean. Quick actions — Remove Duplicates, Fill Missing Values, Standardize Formats, Clean Whitespace — run with one click and log exactly what changed. AI Suggestions asks the language model to inspect your column names, data types, and detected issues and return 5–8 prioritised cleaning recommendations (e.g. "normalise phone numbers in the contact column", "convert revenue to float and fill nulls with 0"), each with an Apply button. Custom tasks let you describe any transformation in plain English — "split the full_name column into first and last", "replace all blank cells in status with 'pending'", "remove rows where age is over 120" — and the agent generates and executes the Python code in-browser. All cleaning steps are logged with timestamps in the activity panel. When finished, download the result as a clean CSV file. Compatible with GPT-4o, Claude 3.5 Sonnet, or a fully local WebLLM model. No data ever leaves your machine.