Exploratory Data Analysis & Data Cleaning — Data Science Roadmap
Turning a raw, messy dataset into something trustworthy enough to analyze
Steps in Exploratory Data Analysis & Data Cleaning
- The EDA Process — intermediate · A repeatable approach to getting to know a new dataset before drawing conclusions
- Handling Missing Data — intermediate · Detecting, understanding and deciding how to treat missing values
- Duplicate & Inconsistent Data — intermediate · Finding and resolving duplicate records and inconsistent formatting
- Outlier Detection — intermediate · Identifying unusual values and deciding whether to investigate, cap or remove them
- Data Profiling & Quality Assessment — intermediate · Systematically assessing a dataset's completeness, validity and consistency
- Univariate & Bivariate Analysis — intermediate · Understanding single variables and relationships between pairs of variables
Part of
- Data Science roadmap — the full learning path