10x Analyst — Data Cleaner

Clean and transform raw data files into analysis-ready datasets.

Overview

Automated data cleaning pipeline: parse dates, convert currencies, standardize column names, handle missing values, remove duplicates. Reads from input/<dataset>/, outputs cleaned files to output/<dataset>/cleaned-data/.

When to Use

• User says "clean this data", "fix this dataset", "prepare this for analysis"
• Data has known quality issues (missing values, wrong types, duplicates)
• Before running :analyze manually on pre-cleaned data

Path Resolution

Parse $ARGUMENTS to get the dataset name.

• Input: input/<dataset-name>/
• Output: output/<dataset-name>/cleaned-data/