A YouTube-first Data Analyst roadmap that turns a complete beginner into someone who can take a messy dataset and produce a clear business insight. It moves through Excel, statistics, SQL and PostgreSQL, Python with NumPy/Pandas, EDA and visualization, Power BI (Power Query, data modeling, DAX, dashboard design), business and product analytics, A/B testing, data storytelling, automation, data quality — and a portfolio plus an end-to-end capstone presented like a real stakeholder deliverable.
Track your progress, earn XP, and pick up where you left off.
Milestone 01 (Understand Data Analytics). Learn the analyst role, the types of analytics, and the workflow: Question → Collect → Clean → Explore → Analyze → Visualize → Interpret → Communicate → Decide.
The Data Analyst Role & Workflow
What analytics is, analyst vs scientist vs engineer, descriptive/diagnostic/predictive/prescriptive, KPIs and metrics.
~4h · 2 resources
Milestone 02 (Excel Fundamentals). The interface, tables, formatting, sorting/filtering, and the core formula set.
Interface, Tables & Core Formulas
Workbooks, worksheets, cells, formatting, sorting, filtering, tables, and SUM/AVERAGE/COUNT/IF/MIN/MAX/ROUND.
~8h · 4 resources
Text functions, lookups and conditional aggregation — turning messy sheets into analysis-ready data.
Text, Lookups & Conditional Aggregation
TRIM/CLEAN/LEFT/RIGHT/MID/SUBSTITUTE, VLOOKUP/XLOOKUP/INDEX-MATCH, SUMIFS/COUNTIFS/AVERAGEIFS, data validation.
~8h · 3 resources
Milestone 03 (Excel Dashboard). Pivot tables, slicers, calculated fields and interactive dashboards.
Pivot Tables & Interactive Dashboards
Pivot tables/charts, slicers, grouping, calculated fields, conditional formatting and dashboard layout.
~8h · 4 resources
The descriptive statistics and business metrics an analyst uses daily — plus correlation vs causation.
Descriptive Statistics & Business Metrics
Mean/median/mode, variance/SD, percentiles/quartiles, distributions, outliers; AOV, conversion, retention, churn, margin; correlation vs causation.
~8h · 2 resources
Milestone 04 (SQL Fundamentals). Query data with PostgreSQL: SELECT, WHERE, ORDER BY, aggregation and GROUP BY.
SELECT, Filtering & Aggregation
Tables, keys, SELECT/DISTINCT/WHERE/ORDER BY/LIMIT, operators, COUNT/SUM/AVG/MIN/MAX, GROUP BY, HAVING.
~12h · 9 resources
Combine multiple tables correctly — and avoid the classic join mistakes.
Joins & Multi-Table Analysis
INNER/LEFT/RIGHT/FULL/CROSS/SELF joins, why joins are needed, duplicate-row pitfalls.
~8h · 3 resources
Milestone 05 (Advanced SQL). Subqueries, CASE, CTEs and window functions for real analytics.
CTEs, Window Functions & Analytics
Subqueries, correlated subqueries, CASE, COALESCE, CTEs, recursive CTE concepts, ROW_NUMBER/RANK/LAG/LEAD/SUM OVER/PARTITION BY.
~10h · 5 resources
Milestone 06 (First SQL Analytics Project). Build a full e-commerce SQL analytics project.
E-Commerce SQL Analytics
Model customers/orders/order_items/products/categories/payments/reviews and answer revenue, AOV, top products/customers, retention and regional questions.
~10h · 4 resources
Milestone 07 (Python Data Analysis) begins. Only the Python an analyst needs — not a full developer curriculum.
Python Essentials for Analysts
Variables, lists, dicts, functions, loops, comprehensions, modules, files and exceptions.
~10h · 18 resources
Vectorized numerical computing — the foundation under pandas.
Arrays & Vectorized Operations
Arrays, shapes, indexing/slicing, vectorized ops, aggregation, broadcasting and basic statistics.
~6h · 2 resources
The analyst's core tool: load, select, filter, group and aggregate tabular data.
Series, DataFrames & Aggregation
read_csv/excel/json, head/info/describe, loc/iloc, filtering, sorting, groupby and aggregation.
~10h · 3 resources
Turn a messy real-world dataset into a clean, documented one.
Cleaning, Reshaping & Merging
Missing/duplicate data, type fixes, string cleaning, date parsing, outliers, merge/join/concat, pivot/melt.
~8h · 3 resources
Milestone 08 (First EDA Project). Systematically explore data for trends, patterns and anomalies.
EDA Workflow & Insights
Univariate/bivariate/multivariate analysis, distributions, correlations, outliers, trends and anomalies with Matplotlib/Seaborn.
~10h · 4 resources
Choose the right chart, avoid misleading visuals, and communicate clearly.
Chart Selection & Clarity
Bar/line/scatter/histogram/box/heatmap/area charts, when NOT to use a chart, and avoiding misleading axes/clutter.
~6h · 3 resources
Milestone 09 (Power BI Dashboard) begins. Import, model and visualize data in Power BI.
Power BI Interface & First Report
Importing CSV/Excel/databases, Power Query basics, relationships, visuals, filters and slicers.
~10h · 6 resources
Repeatable data transformation and cleanup inside Power BI/Excel.
Transform & Combine Data
Type changes, remove/replace, split/merge columns, append/merge queries, pivot/unpivot, conditional columns.
~8h · 3 resources
A good data model is the difference between a fragile and a robust report.
Star Schema & Relationships
Fact/dimension tables, star schema, relationships, cardinality, filter direction and date tables.
~6h · 2 resources
Measures, CALCULATE and time intelligence for real business metrics.
Measures, CALCULATE & Time Intelligence
Calculated columns vs measures, SUM/COUNT/DISTINCTCOUNT, CALCULATE/FILTER/ALL/VALUES/DIVIDE, TOTALYTD/DATEADD/SAMEPERIODLASTYEAR.
~10h · 3 resources
Design principles: minimal, professional, readable — every visual answers a question.
Layout, Interactivity & Storytelling
Layout, visual hierarchy, KPI cards, drillthrough, tooltips, bookmarks and navigation.
~6h · 3 resources
Milestone 09 evidence: build an executive sales dashboard end to end.
Executive Sales Dashboard
Executive overview, sales/product/customer/regional analysis and profitability with KPIs, trends, filters and drillthrough.
~12h · 4 resources
Milestone 10 (Business Analytics). Think like an analyst about revenue, costs, retention and growth.
Business Metrics & Case Studies
Revenue, profit, costs, acquisition, retention, churn, conversion, AOV, CLV, growth; case studies across e-commerce/SaaS/FinTech/retail.
~8h · 2 resources
Users, funnels, cohorts and retention for digital products.
Funnels, Cohorts & Retention
Users/sessions/events, activation, retention, churn, conversion funnels, cohorts, DAU/WAU/MAU.
~8h · 3 resources
Practical experimentation — hypotheses, significance and pitfalls, with examples not memorization.
Experiments, Significance & Pitfalls
Control/treatment groups, hypotheses, sample size, statistical significance, p-values, confidence intervals, false positives, practical significance.
~6h · 2 resources
Turn analysis into a clear narrative for non-technical stakeholders.
From Insight to Executive Communication
Finding the story, context, problem, evidence, insight, recommendation and executive communication.
~5h · 2 resources
Automate repetitive reporting with Python.
Python Reporting Pipelines
Scripts, scheduled reports, CSV/Excel automation, reusable functions and pandas pipelines.
~6h · 4 resources
Pull data from CSV, Excel, databases and public APIs.
APIs, JSON & Public Datasets
CSV/Excel/SQL/APIs/JSON, public datasets and consuming an API with requests.
~6h · 5 resources
Trustworthy data: accuracy, completeness, consistency, lineage and PII handling.
Quality Dimensions & Data Protection
Accuracy/completeness/consistency/validity/uniqueness/freshness, lineage, metadata, data dictionaries; PII, access control, least privilege.
~5h · 2 resources
Milestone 11 (Portfolio Ready). Assemble a professional portfolio and prepare for interviews.
Portfolio, GitHub & Interview Prep
Package projects (Excel dashboard, SQL analysis, Python EDA, Power BI dashboard, product analytics) with READMEs, problem statements, methodology and recommendations; SQL interview practice.
~10h · 4 resources
Milestone 12 (Final Capstone). One complete end-to-end analytics project: Raw data → Collection → Cleaning → SQL → Python analysis → Statistics → Power BI → Business insights → Recommendations → Executive report.
End-to-End Analytics Capstone
Combine SQL, Python, statistics and Power BI on one real dataset to answer real business questions and present to a stakeholder.
~30h · 5 resources