Data Analyst Roadmap: Excel, SQL, Python and Power BI

What a data analyst does

Data analysts turn raw data into answers. They clean data, write queries, build dashboards and explain what the numbers mean so that managers can make decisions. Strong analysts combine technical skills with clear thinking and clear communication.

Common titles: Data Analyst, Business Analyst, BI Analyst, Reporting Analyst, Junior Analytics Engineer.

Month 1: spreadsheets and basic statistics

Start with Excel or Google Sheets. It is still used in almost every company.

• Formulas: SUMIFS, COUNTIFS, XLOOKUP/VLOOKUP, IF, text and date functions
• Pivot tables and charts
• Cleaning data: removing duplicates, fixing formats, handling blanks
• Basic statistics: mean, median, mode, standard deviation, percentiles, correlation, sampling, and what a p-value does and does not tell you

Month 2: SQL (the most important skill)

Most analyst interviews include SQL. Learn it properly:

• SELECT, WHERE, ORDER BY, LIMIT
• Joins (inner, left, right), GROUP BY, HAVING
• Subqueries and CTEs
• Window functions: ROW_NUMBER, RANK, LAG, running totals
• Date handling and CASE statements

Practise with the exercises in our SQL for interviews guide and on free platforms such as SQLZoo, Mode's SQL tutorial or HackerRank.

Month 3: Python for analysis

• Python basics (beginner guide)
• Pandas: loading CSVs, filtering, grouping, merging, cleaning
• Matplotlib or Seaborn for charts
• Jupyter notebooks for readable analysis

Do not try to learn machine learning yet. Strong data cleaning and exploration skills matter more at the start.

Month 4: dashboards and storytelling

Learn one BI tool well: Power BI is common in Indian companies, Tableau is the other major option, and Looker Studio is a free starting point.

• Connect data, model relationships, create measures (DAX in Power BI)
• Design a dashboard that answers a question, not one that shows every chart
• Learn to write a short summary: the question, the finding, the recommended action

Month 5: projects and portfolio

Build 3–4 projects from real public datasets (Kaggle, government open data portals, public APIs):

1. Sales or retail analysis with a dashboard and written insights
2. Customer or user behaviour analysis (churn, cohorts, funnels)
3. A SQL-only project answering 10 business questions on a database
4. A story-driven project on a topic you care about (sports, cricket, finance, transport)

Publish them on GitHub or a simple portfolio page with a short write-up: the question, method, findings and limitations. See build portfolio projects that get interviews.

Month 6: interviews and applications

Expect:

• SQL tests and Excel tasks
• A case question: "Sales dropped 10% last month. How would you investigate?"
• Basic statistics and A/B testing questions
• A take-home analysis or live dashboard walkthrough
• HR questions (sample answers)

Tailor your resume to analyst roles (fresher resume guide) and list tools, projects and measurable results.

Common mistakes

• Learning tools without practising on messy, real data
• Dashboards that are beautiful but answer no question
• Ignoring business context: always ask "so what?"
• Skipping SQL

Next steps

If you enjoy modelling and prediction, continue to the data scientist and ML roadmap. If you enjoy pipelines and engineering, see the data engineer roadmap. Browse fresher analyst openings to see the tools employers ask for.