Pandas for Data Analysis

This hands-on Pandas course takes you from your first DataFrame to writing efficient, production-ready data analysis pipelines. Learn data cleaning, transformation, aggregation, merging, time series, reshaping, and performance optimization using one realistic e-commerce dataset. Build five complete portfolio projects covering sales, customer cohorts, inventory, revenue trends, and survey analysis. By the end, you'll confidently handle and analyze real-world data for data analyst and data science roles.

Rutvik Acharya

Principal Data Scientist

Atlassian

Loading modules...

What You'll Learn

Load, clean, and inspect real-world messy data handling missing values, duplicates, and inconsistent formatting with confidence

Select, filter, and reshape data precisely using .loc, .iloc, boolean indexing, pivot tables, and MultiIndex operations

Aggregate and analyze data with groupby, merges/joins, and full time series techniques (resampling, rolling windows, datetime indexing)

Write fast, production-ready pandas code by applying vectorization, memory optimization, and method chaining best practices

Who Should Attend

Aspiring data analysts who want hands-on, job-ready pandas skills, not just theory

Excel/spreadsheet users looking to level up to programmatic, scalable data analysis

Python beginners who already know basic syntax and want to specialize in data work

Working professionals (analysts, BI developers, junior data scientists) who want to close gaps in cleaning, merging, or time series analysis

CERTIFICATION

Certificate of Completion

11 Modules

16 Hours 40 Minutes

60 Lessons

55 Challenges

Language: English

FAQ

FREQUENTLY ASKED QUESTIONS

You should have basic familiarity with Python syntax, such as variables, lists, and functions, before starting. The course does not teach Python from scratch, but it does teach pandas from first principles, starting with installation and the core Series and DataFrame data structures.

The course teaches modern pandas syntax and conventions, including current recommended practices such as named aggregation and the DataFrame.map() method. The concepts and techniques apply broadly across recent pandas versions.

Yes. The course uses one consistent, evolving dataset called Gradient Retail, a fictional e-commerce business with customers, products, and orders tables. The same dataset is used and built upon across all 11 modules, so each new skill connects directly to what you learned before.

Yes. The final module contains five complete, end-to-end portfolio projects covering sales performance analysis, customer cohort analysis, inventory and reorder point analysis, revenue trend analysis, and survey data reshaping. Each project includes a business problem, dataset setup, specific questions to answer, and a fully worked solution.

The course consists of 11 modules and roughly 16 to 17 hours of content in total, including lessons, practice exercises, and the five portfolio projects. You can work through it at your own pace.

Scroll Up

GET FREE CAREER COUNSELING