Data Analytics Roadmap
Excel, SQL, Google Sheets, and data visualisation — turn raw data into insights and decisions.
6 stages
6 milestones
1
Stage 1: Spreadsheet Mastery
2–3 weeksExcel and Google Sheets are the most widely used data tools in the world. Master them first.
- Formulas — SUM, IF, COUNTIF, SUMIF, AVERAGEIF
- VLOOKUP, INDEX/MATCH, and XLOOKUP
- Pivot tables — summarising and slicing data
- Data validation and named ranges
- Charts and basic visualisation
- Conditional formatting for data storytelling
Resources
- ExcelJet — Formula referenceArticle
2
Stage 2: SQL Fundamentals
3–4 weeksSQL is the universal language for talking to databases. Every analyst needs it.
- SELECT, WHERE, ORDER BY, LIMIT
- Aggregate functions — COUNT, SUM, AVG, MIN, MAX
- GROUP BY and HAVING
- JOINs — INNER, LEFT, RIGHT, FULL
- Subqueries and CTEs (WITH statements)
- Window functions — ROW_NUMBER, RANK, LAG
Resources
3
Stage 3: Data Cleaning & Preparation
1–2 weeksReal-world data is messy. Cleaning it is 80% of the job.
- Identifying and handling missing values
- Removing duplicates and standardising formats
- Data type conversions
- Outlier detection and handling
- Merging and reshaping datasets
- Documenting your data cleaning process
Resources
4
Stage 4: Data Visualisation
2–3 weeksThe best insight in the world is worthless if you can't communicate it visually.
- Choosing the right chart — bar, line, scatter, pie (and when not to)
- Colour and labelling for clarity
- Looker Studio (formerly Data Studio) dashboards
- Power BI or Tableau basics
- Storytelling with data — from chart to narrative
- Presenting findings to non-technical stakeholders
Resources
5
Stage 5: Python for Data Analysis
4–6 weeksPython unlocks automation, advanced analysis, and machine learning. pandas is the essential library.
- Python basics — variables, lists, dicts, loops, functions
- pandas — DataFrames, indexing, filtering, groupby
- NumPy — arrays and numerical operations
- Matplotlib and Seaborn for charts in Python
- Jupyter Notebooks workflow
- Reading from CSV, Excel, and databases in Python
Resources
6
Stage 6: Real Projects & Portfolio
4–6 weeksEmployers hire analysts who can show their work. Build and publish real projects.
- Finding public datasets — Kaggle, Google Dataset Search
- Scoping an analysis project with a clear question
- End-to-end analysis — clean, explore, visualise, conclude
- Publishing notebooks on Kaggle or GitHub
- Writing clear data project READMEs
- Applying for analyst roles — portfolio tips
Resources
- Kaggle DatasetsTool