Skill area · Data Science & Analytics

Turn raw data into answers with Python and AI

Load it, clean it, analyze it, and show what it means

Real Python takes you from your first DataFrame to confident analysis with pandas, Polars, NumPy, and Matplotlib. Follow a guided path, practice on real datasets, and get help the moment you’re stuck.

Data Science & Analytics on Real Python

What you’ll be able to do

The whole analysis workflow, one skill at a time

Data work follows the same arc whether you’re digging into sales numbers, survey results, or sensor logs. Real Python covers each step with hands-on material built around real datasets.

Collect and load

Read CSV, JSON, Excel, and SQL data into DataFrames, and query local files directly with DuckDB.

CSVSQLDuckDB

Clean and reshape

Handle missing values, fix messy columns, and merge, sort, and pivot datasets until they’re ready to trust.

pandasPolars

Analyze

Group and aggregate, compute descriptive statistics and correlations, and fit your first regression models.

NumPySciPystatistics

Visualize and share

Build clear charts, interactive dashboards, and maps, and present your work in reproducible notebooks.

MatplotlibSeabornJupyter

Your roadmap

A clear path from first DataFrame to real analysis

Not sure where to start? Work through these learning paths in order. Each one mixes tutorials, video courses, quizzes, and exercises, and tracks your progress as you go.

  1. 1

    Start here

    Set up Jupyter, load CSV and JSON data into pandas, clean and group it, then plot and analyze it with Matplotlib and NumPy.

    Learning Path

    Data Science With Python Core Skills

    22 Resources ⋅ Skills: Pandas, NumPy, Data Cleaning, Data Visualization, Statistics, CSV, JSON, Jupyter Notebooks

  2. 2

    Go deeper on DataFrames: indexing, GroupBy, merging, sorting, pivot tables, and the performance tips that keep big analyses fast.

    Learning Path

    pandas for Data Science

    15 Resources ⋅ Skills: pandas, Data Science, Data Visualization, DataFrame, GroupBy, Data Cleaning

  3. 3

    Tell the story in your data with Matplotlib, Seaborn, Bokeh, Dash, and Folium, from quick plots to interactive dashboards and maps.

    Learning Path

    Data Visualization With Python

    10 Resources ⋅ Skills: NumPy, Matplotlib, Bokeh, Seaborn, pandas, Dash, Folium, ggplot

  4. 4

    Build the statistical foundations: descriptive statistics, correlation, linear and logistic regression, and gradient descent.

    Learning Path

    Math for Data Science

    5 Resources ⋅ Skills: Statistics, Correlation, Linear Regression, Logistic Regression, NumPy, SciPy, pandas, Gradient Descent

  5. +

    Take it anytime

    Bring in data from files, Excel, SQL databases, and the cloud, and store your results so others can use them.

    Learning Path

    Data Collection & Storage

    9 Resources ⋅ Skills: CSV, JSON, pandas, Excel, SQL, SQLite, SQLAlchemy, AWS S3, Databases

Ready for what comes next? Continue with Machine Learning With Python. New to Python itself? Start with Python Basics first.

Try it now

Rank college majors by popularity

This is a real exercise from the Plot With pandas video course, using the same dataset as the notebook above. Write your function in the editor and click Run Tests.

Loading exercise...

Running tests, hints, and solutions are included with a Real Python membership. Not a member yet? You can still read the task and write your solution before you join.

Learn it every way

Read it, watch it, test it, practice it

Every data science topic comes in the formats that help it stick. Mix them however you like.

Tutorials

In-depth, example-driven guides to pandas, Polars, NumPy, plotting, statistics, and more.

Browse tutorials →

Video courses

Follow along as an instructor works through a real dataset, one bite-sized lesson at a time.

Start with Introduction to pandas →

Quizzes

Check what you’ve learned in a few minutes and see exactly which concepts to review.

Test your core skills →

Coding exercises

Write real pandas, Polars, and NumPy code in your browser and get instant test feedback.

How exercises work →

Mentor AI

Stuck on a groupby? Ask right where you are

Data code fails in confusing ways: a KeyError from a column name with a stray space, a SettingWithCopyWarning, a result that’s a DataFrame when you expected a Series.

Mentor AI sees the tutorial, lesson, or exercise you’re on and your code, and nudges you toward the fix one hint at a time, so you understand what pandas is actually doing.

Meet Mentor AI →

The modern data stack

Learn the tools data teams actually use

From long-standing staples to newer tools that are changing how Python developers work with data.

pandas
DataFrames
Polars
Fast DataFrames
NumPy
Arrays & math
DuckDB
SQL on your files
Matplotlib
Plotting
Seaborn
Statistical plots
Altair
Declarative charts
Dash
Dashboards
JupyterLab
Notebooks
marimo
Reactive notebooks
GeoPandas
Maps & spatial
Pointblank
Data validation

Fresh from the library

New and updated for 2026

The Real Python team keeps publishing and refreshing data science content, so what you learn matches the tools and versions you’ll use at work.

See all data science content →

Questions and answers

You should be comfortable with Python basics like variables, lists, loops, and functions. If you’re not there yet, the Python Basics learning path gets you ready, and you can switch to data science as soon as you finish it.

No. You can load, clean, analyze, and visualize data with very little math. When you want to go further, the Math for Data Science path explains statistics and regression with Python code rather than proofs.

Start with pandas. It’s the most widely used DataFrame library, and most examples and job postings assume it. Once you’re comfortable, Polars is a great addition for larger datasets. Our Polars vs pandas tutorial walks through the differences.

Not quite. Data science and analytics are about understanding data and communicating what it shows. Machine learning builds on those skills to train models that make predictions. When you’re ready for that step, continue with Machine Learning With Python.

Every Real Python membership includes all video courses, quizzes, coding exercises, and learning paths for data science and every other topic, along with Mentor AI as it rolls out.

Start making sense of your data

Get your free learning plan and follow the full data science roadmap, with courses, quizzes, coding exercises, and a mentor at your side.

Get your free learning plan