Cleaning Data

Getting rid of errors

Why clean the data?

2. Cleaning

• The Crux: Raw data is messy! Cleaning is imperative for accurate analysis. This involves:
  • Fixing Errors: Handling typos, incorrect values, and inconsistencies.
  • Addressing Missing Data: Filling in gaps (imputation) or removing incomplete entries.
  • Removing Duplicates: Keeping only unique data points.
  • Normalization: Standardizing formats (e.g., dates, units of measurement).
  • Outlier Detection: Identifying unusual data points that might skew results.