Data Cleaning 101
Eight lessons on identifying and fixing data quality problems — from missing values to address validation to building a repeatable cleaning process.
Why Data Gets Messy
Data quality problems don't appear by accident. Learn the common causes of messy data and how to prevent them at the source.
Read Lesson →Missing Values
Missing data is one of the most common quality problems. Learn how to identify, assess, and handle missing values appropriately.
Read Lesson →Duplicate Records
Duplicates inflate counts and cause confusion. Learn how to find and resolve duplicate records in your datasets.
Read Lesson →Formatting Issues
Inconsistent formats — dates, phone numbers, postal codes — are a major source of data problems. Learn how to standardize them.
Read Lesson →Address Validation
Addresses are notoriously messy. Learn techniques for validating, parsing, and standardizing address data.
Read Lesson →Data Standardization
Standardization makes data consistent and comparable. Learn how to apply standards to names, codes, categories, and values.
Read Lesson →Quality Assurance
QA is about preventing problems, not just fixing them. Learn how to build validation rules and quality checks into your data processes.
Read Lesson →Building a Data Refinery
A data refinery is a repeatable process for cleaning and improving data. Learn how to design one for your organization.
Read Lesson →