Free Data Analytics Course

Learn SQL from scratch: querying, filtering, grouping, and joining data for analytics use cases.

Intermediate1 weeks

SQL Advanced (Analytics)

Master analytics-grade SQL: CTEs, window functions, subqueries, advanced queries, and optimization techniques.

Beginner2 weeks

Python Essentials for Data Analytics

Start simple. Build strong foundations. Learn the Python every analyst needs. Clean, analyse, and explore data like a pro.

Excel for Data Analytics (Short & Focused)

Excel for Data Analytics (Short & Focused)

Tableau for Data Analytics (Short & Focused)

Tableau for Data Analytics (Short & Focused)

Stats & Product Analytics for Analysts

The stats and product-analytics every data analyst is expected to know - without graduate-school math. Read dashboards correctly, design A/B tests that actually work, and stop being fooled by 'average X is Y'. Built for the Topfolio Data Analyst career track.

DA Career Playbook & Interview Prep

The complete playbook to transition into corporate Data Analytics. Technical interview patterns, business case-study walkthroughs, behavioral STAR frameworks, salary negotiation for Indian tech, recruiter-grade resume rewrites, and public portfolio verification.

Git & GitHub for Data Analysts

The visual, portfolio-first Git workflow every analyst needs. Learn to version Python scripts and SQL files, manage .gitignore for sensitive datasets, and showcase your capstone portfolio on GitHub using VS Code GUI without scary terminal commands.

Intermediate5 weeks

Data Modeling & Warehousing Fundamentals

Stop writing SQL into a void. Learn how the warehouse should be shaped so that every dashboard query is fast, every metric is consistent, and every model survives the next product change. Star schemas, slowly changing dimensions, columnar storage, partitioning, and 6 hands-on modeling case studies drawn from real e-commerce and SaaS shops. Built for the Topfolio Data Engineer track (Phase 1).

dbt Fundamentals

The analytics-engineering standard. Learn dbt the way you'll actually use it in production: models, ref(), tests, snapshots, incremental, macros, packages, and CI/CD. Six hands-on cases mirroring real Shopify / Stripe / event-data projects. The natural next course after Data Modeling & Warehousing Fundamentals.

Intermediate4 weeks

Statistics for Data Science

The statistics every data scientist is expected to actually understand — not just import from scipy. Probability foundations, sampling distributions, hypothesis testing properly (with multiple-testing corrections), bootstrap, linear and logistic regression with assumptions, Bayesian intuition, and a causal-inference primer. Six hands-on DS cases. The natural next course after Stats & Product Analytics for Analysts.

Intermediate4 weeks

ML Foundations

The end-to-end machine learning course you actually need. Supervised and unsupervised, scikit-learn workflow done right, gradient boosting (XGBoost / LightGBM / CatBoost), feature engineering, class imbalance, evaluation metrics for real decisions, data leakage diagnosis, and hyperparameter tuning. Six hands-on cases (churn pipeline, leakage diagnosis, fraud detection, metric selection, customer segmentation, light MLOps). Builds on Statistics for Data Science.

Advanced3 weeks

ML in Practice — Lightweight MLOps

The course that turns a trained model into a working production system. Reproducibility (MLflow, DVC), feature stores, model registry, batch vs online serving, FastAPI + Docker deployment, scaling and latency, A/B testing, drift detection, retraining strategy, and incident response. Six end-to-end cases mirroring what small ML teams actually build. Builds on ML Foundations; lightweight enough for teams without dedicated platform engineering.

LLMs & Generative AI for Practitioners

The applied LLM course. Skip the math; learn what you actually need to ship LLM-powered features. Tokens, prompts, RAG, fine-tuning, evaluation, guardrails, and cost optimization — for engineers and data scientists who already know ML. Six hands-on cases mirror real production builds. Covers Claude, GPT, and open models (Llama, Mistral) in 2026. Builds on ML Foundations and ML in Practice.

Advanced3 weeks

LangChain & LangGraph for AI Agents

Go beyond single-call LLM apps. Build production-grade agentic systems with LangChain (LCEL composition, tools) and LangGraph (state machines, conditional routing, persistence, human-in-the-loop). Multi-agent patterns, memory architectures, observability via LangSmith, and evaluation. Six end-to-end cases from support agents to multi-agent research systems. Builds on LLMs & GenAI for Practitioners; assumes Python comfort and basic LLM knowledge.

Intermediate3 weeks

Data Engineering: Pipelines, Orchestration & Reliability

The data engineering layer beneath dbt. How data actually gets into the warehouse, how pipelines are orchestrated, and how to keep them reliable. Ingestion patterns (batch, CDC, streaming), tools (Fivetran, Airbyte, Meltano), orchestration (Airflow, Dagster, Prefect), data quality and observability, streaming basics (Kafka, Pub/Sub), Spark for DE, and lakehouse file formats (Parquet, Iceberg). Six end-to-end pipeline cases. Builds on the SQL, dbt, and Data Modeling courses; completes the DE track.

Python Data Visualization, SQL Connectivity & EDA

Bridge the gap between raw databases and business insights. Learn to connect Python directly to SQL databases with SQLAlchemy, build statistical charts with Matplotlib & Seaborn, execute systematic EDA, and build customer RFM models.

Power BI for Data Analytics & Business Intelligence

The enterprise standard for Power BI, VertiPaq tabular modeling, DAX mechanics, and executive business intelligence. Master data ingestion, Query Folding diagnostics, Kimball Star Schema design, Context Transition, Time Intelligence, Dynamic Row-Level Security (RLS), Tabular Editor Best Practice Analyzer, and Performance Analyzer/DAX Studio profiling. Includes 3 workplace capstones deliverable as code-first PBIP Git repositories.

Beginner2 weeks

DS Bridge — SQL, Python, Stats Refresh + Skip-Gate

P0 bridge into the Data Scientist track (~20 h). Refresh SQL joins/CTEs/windows, pandas wrangling + EDA, distributions/hypothesis tests/A-B readouts, then prove readiness through per-module skip-gate quizzes, an exit battery, and checkpoint submissions. Pass -> P1; else DA track.

ML Case Labs — Validation, Boosting, Segmentation, Pipelines

P2 applied-ML labs (~40 h with course 18): regularized regression + leakage-controlled CV, RF vs boosting with calibration/thresholds, clustering + business readouts, sklearn pipelines + SHAP, closing in two capstones (campaign classifier, churn-ML with SHAP story).

DL Basics — PyTorch MLPs, CNNs, Sequences, Fine-Tuning Discipline

P3 deep-learning basics (~20-24 h, PyTorch-only): tensors + autograd, MLP training loops and overfit diagnosis, CNN concepts + transfer learning, sequence concepts + NLP baselines, fine-tuning discipline + TF parity note, closing in a two-mini-lab defense.

GenAI + RAG Agents (DS Lite)

DS-sequel lite GenAI: prompting + structured extraction, embeddings and vector retrieval, RAG architecture with citation-required evals, and a single-agent tool-calling loop. Caps in a live RAG chatbot with an eval set and cost/latency dashboard. LangGraph/multi-agent stays out of scope (track 95).

Advanced2 weeks

MLOps + Cloud Deploy (AWS-First)

Ship ML like software: Docker reproducibility, FastAPI serving with smoke tests, experiment tracking + registry, CI/CD build gates, monitoring/drift with K8s reading literacy, and a flagship deployed pipeline on a free-tier cloud with cold-clone reproducibility proof. AWS-first with GCP parity notes.

DS Interview Prep — Rounds, Cases, Offer Close

Convert portfolio into offers: timed SQL/Python screens, stats and experimentation rounds (CUPED/Simpson/permutation/DiD), ML case labs with SHAP + threshold storytelling, guesstimates + product sense, resume/portfolio checklist, a vertical domain capstone, the 45Q proctored final, and the 30-50 mocks ladder to job_ready.

Spark Lakehouse: PySpark, Delta, Iceberg & Streaming

The hands-on Spark lakehouse course for data engineers. Run local PySpark jobs, build a partitioned Parquet ETL, implement ACID upserts with Delta Lake, evolve partitions with Apache Iceberg, and wire a Redpanda-to-Spark Structured Streaming mini-pipeline. Closes with 3 graded labs and a streaming mini-lab.

Intermediate1 weeks

DE Track — Capstone Labs

Hands-on lab briefs, fixtures, starters, and interview prep surfaced inside the Data Engineer track (W4 ingestion lab, W12 system design + mock interviews). Unpublished container — never in the public catalogue.

Beginner1 weeks

SQL for Writing Data: DDL, DML, Transactions & Upserts

The write-side SQL every data engineer needs. Create tables with sane types and constraints, load them with INSERT..SELECT, change data safely with UPDATE/DELETE discipline, evolve schemas with ALTER, keep loads atomic with transactions, and handle replays with MERGE / ON CONFLICT upserts. Ends with a graded load lab and an 8-question scenario quiz.

Intermediate3 weeks

Python for Data Engineers

Python for data engineering: language foundations, packaging and OOP, and production reliability (testing, logging, retries) for pipelines. Curated from Python Essentials and Python for Software Engineers.

Intermediate1 weeks

Data Engineering: Ingestion Foundations (W4)