Can I preview a course before enrolling?

Yes, you can preview the first video and view the syllabus before you enroll. You must purchase the course to access content not included in the preview.

When will I have access to the lectures and assignments?

If you decide to enroll in the course before the session start date, you will have access to all of the lecture videos and readings for the course. You’ll be able to submit assignments once the session starts.

What will I get when I enroll?

Once you enroll and your session begins, you will have access to all videos and other resources, including reading items and the course discussion forum. You’ll be able to view and submit practice assessments, and complete required graded assignments to earn a grade and a Course Certificate.

When will I receive my Course Certificate?

If you complete the course successfully, your electronic Course Certificate will be added to your Accomplishments page - from there, you can print your Course Certificate or add it to your LinkedIn profile.

Why can’t I audit this course?

This course is currently available only to learners who have paid or received financial aid, when available.

Is financial aid available?

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Hands-On Data Science with PyTorch & Pandas

Sparen Sie mit 40% Rabatt auf 3 Monate Coursera Plus bei den Fähigkeiten, die Sie zum Strahlen bringen. Jetzt sparen

kurs ist nicht verfügbar in Deutsch (Deutschland)

Wir übersetzen es in weitere Sprachen.

Hands-On Data Science with PyTorch & Pandas

Dozent: Packt - Course Instructors

Bei enthalten

Mehr erfahren

6 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

Stufe Mittel

Empfohlene Erfahrung

7 Stunden zu vervollständigen

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

6 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

Stufe Mittel

Empfohlene Erfahrung

7 Stunden zu vervollständigen

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

Was Sie lernen werden

Build interactive data dashboards using Shiny for Python with dynamic inputs, outputs, and visualizations for real-time data exploration.
Create CSV-based analytics apps that allow users to upload datasets, generate statistics, and visualize insights through charts and dashboards.
Apply PyTorch tensor operations including broadcasting, indexing, and GPU acceleration to support efficient machine learning workflows.
Develop an image classification app using PyTorch and TorchVision, integrating preprocessing, inference, and an interactive Shiny interface.

Kompetenzen, die Sie erwerben

Kategorie: User Interface (UI)
Kategorie: Interactive Data Visualization
Kategorie: Data Visualization Software
Kategorie: Dashboard Creation
Kategorie: Machine Learning Methods
Kategorie: Application Development
Kategorie: Applied Machine Learning
Kategorie: Data Science
Kategorie: Image Analysis
Kategorie: Computer Programming
Kategorie: Data Visualization

Werkzeuge, die Sie lernen werden

Kategorie: PyTorch (Machine Learning Library)
Kategorie: Shiny (R Package)
Kategorie: Dashboard
Kategorie: AI Workflows
Kategorie: UI Components
Kategorie: Web Development Tools
Kategorie: Web Frameworks
Kategorie: Pandas (Python Package)
Kategorie: Python Programming

Wichtige Details

Zertifikat zur Vorlage

Zu Ihrem LinkedIn-Profil hinzufügen

Kürzlich aktualisiert!

April 2026

Bewertungen

7 Aufgaben

Unterrichtet in Englisch

Erfahren Sie, wie Mitarbeiter führender Unternehmen gefragte Kompetenzen erwerben.

Weitere Informationen zu Coursera für Unternehmen

Logos von Petrobras, TATA, Danone, Capgemini, P&G und L'Oreal

In diesem Kurs gibt es 6 Module

This course features Coursera Coach!

A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. Data science is transforming how organizations analyze information, build intelligent systems, and create interactive data applications. In this course, you will gain hands-on experience using Python tools such as PyTorch, Pandas-style data workflows, and Shiny for Python to build powerful data-driven applications. You will learn how to visualize data, create dashboards, and implement machine learning workflows using modern data science tools and libraries. The course begins by introducing interactive data applications using Shiny. You will learn how to design responsive user interfaces, implement inputs and outputs, and deploy interactive apps directly from development environments like VSCode. Through guided demonstrations and official Shiny examples, you will understand how real-world dashboards and analytical tools are built for data exploration. Next, the course walks you through building a complete CSV data dashboard. You will implement file uploads, compute quick statistics, and create dynamic visualizations such as histograms, bar charts, and pie charts. By the end of this section, you will understand how to transform raw data into interactive visual insights. In the final modules, you will explore PyTorch fundamentals, including tensors, broadcasting, indexing, GPU acceleration, and tensor operations. You will then apply these skills to build a real-world image classification application using PyTorch and TorchVision integrated with a Shiny interface. This course is designed for aspiring data scientists, Python developers, and analytics professionals who want practical experience building data applications and machine learning systems. Basic knowledge of Python programming and data handling concepts is recommended, and the course is suitable for learners at an intermediate level. By the end of the course, you will be able to build interactive data dashboards, manipulate and analyze datasets, implement PyTorch tensor operations, and deploy machine learning–powered applications using Python and Shiny.

In this module, we will introduce the course structure and learning journey you’ll follow throughout the program. You’ll explore how tools like PyTorch, Python, and interactive dashboards fit into modern data science workflows. By the end, you’ll clearly understand what to expect and how the upcoming modules will build your practical skills.

Das ist alles enthalten

1 Video

In this module, we will explore the fundamentals of building interactive data visualization apps using Shiny. You’ll learn how to design user interfaces, connect inputs to server logic, and create dynamic components. Through hands-on examples, you’ll build and deploy functional Shiny apps while understanding the framework’s core capabilities.

Das ist alles enthalten

9 Videos1 Aufgabe

9 VideosInsgesamt 73 Minuten

Input Sliders, Text Output with Simple Server Logic6 Minuten
Shiny Input Demo14 Minuten
Using HTML to Build a Multiplication Table in Shiny (Part 1)4 Minuten
Using HTML to Build a Multiplication Table in Shiny (Part 2)9 Minuten
Using Shiny in VSCode and Deploying Your App8 Minuten
Exploring Shiny Components12 Minuten
Working with Action Buttons and Checkboxes5 Minuten
Using Checkbox Groups, Selectize, and Row-Column Structures10 Minuten
Introduction to Shiny Express for Python5 Minuten

1 AufgabeInsgesamt 15 Minuten

Data Visualization and Shiny - Assessment15 Minuten

In this module, we will explore official Shiny demo projects to better understand real-world application design. You’ll walk through examples such as sidebar layouts, KDE visualizations, and dashboard implementations. These demos will help you analyze best practices and gain inspiration for building your own interactive data applications.

Das ist alles enthalten

3 Videos1 Aufgabe

In this module, we will build a fully functional interactive CSV data dashboard using Shiny for Python. You’ll implement file uploads, dynamic column selection, and summary statistics for real-time data exploration. By the end, you’ll create visualizations and dashboard components that allow users to analyze datasets interactively.

Das ist alles enthalten

9 Videos1 Aufgabe

9 VideosInsgesamt 32 Minuten

Project Setup2 Minuten
Adding the Imports2 Minuten
Uploading a CSV File3 Minuten
Displaying Quick Stats5 Minuten
Dynamic Column Picker for CSV Data2 Minuten
Displaying Column Details in an Info Card5 Minuten
Visualizing Numeric Columns with Histograms5 Minuten
Visualizing Categorical Columns with Pie or Bar Charts4 Minuten
Conditional Pie or Bar Charts and No-Data Messaging6 Minuten

1 AufgabeInsgesamt 15 Minuten

Building an Interactive CSV Data Dashboard in Shiny for Python - Assessment15 Minuten

In this module, we will introduce the core foundations of PyTorch and tensor-based computation. You’ll explore tensor operations, indexing, masking, cloning, and broadcasting through practical coding examples. The lessons will also demonstrate how to leverage GPUs and development tools to accelerate machine learning workflows.

Das ist alles enthalten

13 Videos1 Aufgabe

13 VideosInsgesamt 96 Minuten

Google Colab and tqdm4 Minuten
How to Get Help with PyTorch5 Minuten
Exploring Additional Help Resources4 Minuten
Introduction to PyTorch and Tensors (Part 1)10 Minuten
Introduction to PyTorch and Tensors (Part 2)9 Minuten
Leveraging the GPU for PyTorch in Google Colab2 Minuten
Understanding Mathematical Operations on Tensors13 Minuten
Understanding Indexing and Masking in Tensors14 Minuten
Expanding on Masking in PyTorch14 Minuten
Cloning Tensors for Safe Operations4 Minuten
Broadcasting in PyTorch: The First Steps5 Minuten
Broadcasting: Next Steps8 Minuten
Hands-on with More Broadcasting Examples4 Minuten

1 AufgabeInsgesamt 15 Minuten

PyTorch Fundamentals - Assessment15 Minuten

In this module, we will build TorchSight, an interactive image classification application powered by PyTorch. You’ll integrate TorchVision models, apply image transformations, and prepare images for neural network inference. By the end, you’ll create a complete Shiny-based interface that allows users to upload images and view classification results instantly.

Das ist alles enthalten

8 Videos3 Aufgaben

8 VideosInsgesamt 29 Minuten

Getting Started with TorchSight4 Minuten
Adding the PyTorch and Image Processing Imports3 Minuten
Importing the TorchVision Models1 Minute
Implementing the Get Model Function3 Minuten
Image Transformations3 Minuten
Creating the Title and Sidebar4 Minuten
Getting the ImageNet Labels and Prompting the User for Images5 Minuten
PyTorch Inference5 Minuten

3 AufgabenInsgesamt 90 Minuten

Full Course Practice Assessment15 Minuten
Torch Sight - PyTorch Image Classification using Python and Shiny - Assessment15 Minuten
Full Course Assessment60 Minuten

Dozent

Packt - Course Instructors

Packt

1.857 Kurse514.430 Lernende

von

Packt

Warum entscheiden sich Menschen für Coursera für ihre Karriere?

Felipe M.

Lernender seit 2018

„Es ist eine großartige Erfahrung, in meinem eigenen Tempo zu lernen. Ich kann lernen, wenn ich Zeit und Nerven dazu habe.“

Jennifer J.

Lernender seit 2020

„Bei einem spannenden neuen Projekt konnte ich die neuen Kenntnisse und Kompetenzen aus den Kursen direkt bei der Arbeit anwenden.“

Larry W.

Lernender seit 2021

„Wenn mir Kurse zu Themen fehlen, die meine Universität nicht anbietet, ist Coursera mit die beste Alternative.“

Chaitanya A.

„Man lernt nicht nur, um bei der Arbeit besser zu werden. Es geht noch um viel mehr. Bei Coursera kann ich ohne Grenzen lernen.“

Häufig gestellte Fragen

Data Science with PyTorch and Pandas involves using Python tools and libraries to analyze data, build machine learning models, and create interactive data applications. PyTorch is widely used for deep learning and neural network development, while Pandas is essential for data manipulation and analysis. Together, these tools allow developers and analysts to transform raw data into insights and intelligent systems. This skill set is highly relevant today because organizations rely heavily on data-driven decision-making and AI-powered applications across industries.

This course provides a practical introduction to data science using PyTorch, Pandas, and Shiny for Python. You will learn how to visualize and analyze data, build interactive dashboards, and work with machine learning fundamentals using PyTorch. The course walks through building real-world projects such as an interactive CSV data dashboard and an image classification application using pre-trained models. Through hands-on examples, you will explore data visualization techniques, tensor operations, and model inference while learning how to deploy interactive apps.

After completing this course, you will be able to analyze and manipulate datasets using Python tools, build interactive data dashboards with Shiny, and implement basic machine learning workflows with PyTorch. You will understand how tensors work, perform mathematical operations for machine learning tasks, and use GPU acceleration in environments like Google Colab. Additionally, you will gain experience creating real applications such as dashboards that visualize CSV data and an image classification app powered by pre-trained neural networks.

Basic familiarity with Python programming is recommended to get the most out of this course. Understanding simple programming concepts such as variables, functions, and data structures will help you follow the exercises more easily. While prior experience with machine learning or deep learning is not required, some exposure to data analysis concepts can be helpful as the course introduces key tools and techniques used in data science.

This course is designed for aspiring data scientists, machine learning enthusiasts, Python developers, and analysts who want hands-on experience with modern data science tools. It is also suitable for learners who want to explore how interactive applications can be built using data visualization and machine learning frameworks. Anyone interested in combining Python-based data analysis with deep learning and practical projects will benefit from this course.

The course is designed to be completed in approximately four hours. It is structured into multiple short lessons covering data visualization, interactive dashboards, PyTorch fundamentals, and an image classification project. This concise format allows learners to gain practical exposure to key data science concepts in a short amount of time while working through hands-on demonstrations and examples.