Self-paced course
Self-paced course
Natural Language Processing in Python
Natural Language Processing in Python
Course Description
This is a practical, hands-on course designed to give you a comprehensive overview of all the essential concepts for Natural Language Processing (NLP) in Python.
We’ll start by reviewing the history and evolution of NLP over the past 70 years, including today’s most popular architecture, Transformers. We’ll then walk through the initial text-pre-processing steps required for modeling, where you’ll learn how to clean and normalize data with pandas and spaCy, then vectorize that data into a Document-Term Matrix using both word counts and TF-IDF scores.
From there, the course is split into two parts: the first half covers traditional machine-learning techniques and the second half covers modern deep-learning and LLM (large language model) approaches.
For the traditional NLP applications, we’ll begin with Sentiment Analysis to determine text polarity using the VADER library. Then we’ll cover Text Classification on labeled data with Naïve Bayes, as well as Topic Modeling on unlabeled data using Non-Negative Matrix Factorization—all with scikit-learn.
Once you have a solid grasp of foundational NLP concepts, we’ll move on to modern techniques and the data-science mindset shift of the last decade.
We’ll start with the basic building blocks of modern NLP—neural networks. You’ll learn how they’re trained, get familiar with layers, nodes, weights, and activation functions, and see popular deep-learning architectures in action.
Next, we’ll dive into Transformers, the architecture behind LLMs like ChatGPT, Gemini, and Claude. We’ll unpack embeddings, attention, and feed-forward layers, explain encoder-only vs. decoder-only vs. encoder-decoder models, and look at which LLMs fall into each category.
Last but not least, we’ll apply everything in Python using Hugging Face’s transformers library and Model Hub to demo six practical NLP applications: Sentiment Analysis, Named Entity Recognition, Zero-Shot Classification, Text Summarization, Text Generation, and Document Similarity.
If you’re an aspiring or seasoned data scientist seeking a hands-on overview of both traditional and modern NLP techniques in Python, this is the course for you.
Course Description
This is a practical, hands-on course designed to give you a comprehensive overview of all the essential concepts for Natural Language Processing (NLP) in Python.
We’ll start by reviewing the history and evolution of NLP over the past 70 years, including today’s most popular architecture, Transformers. We’ll then walk through the initial text-pre-processing steps required for modeling, where you’ll learn how to clean and normalize data with pandas and spaCy, then vectorize that data into a Document-Term Matrix using both word counts and TF-IDF scores.
From there, the course is split into two parts: the first half covers traditional machine-learning techniques and the second half covers modern deep-learning and LLM (large language model) approaches.
For the traditional NLP applications, we’ll begin with Sentiment Analysis to determine text polarity using the VADER library. Then we’ll cover Text Classification on labeled data with Naïve Bayes, as well as Topic Modeling on unlabeled data using Non-Negative Matrix Factorization—all with scikit-learn.
Once you have a solid grasp of foundational NLP concepts, we’ll move on to modern techniques and the data-science mindset shift of the last decade.
We’ll start with the basic building blocks of modern NLP—neural networks. You’ll learn how they’re trained, get familiar with layers, nodes, weights, and activation functions, and see popular deep-learning architectures in action.
Next, we’ll dive into Transformers, the architecture behind LLMs like ChatGPT, Gemini, and Claude. We’ll unpack embeddings, attention, and feed-forward layers, explain encoder-only vs. decoder-only vs. encoder-decoder models, and look at which LLMs fall into each category.
Last but not least, we’ll apply everything in Python using Hugging Face’s transformers library and Model Hub to demo six practical NLP applications: Sentiment Analysis, Named Entity Recognition, Zero-Shot Classification, Text Summarization, Text Generation, and Document Similarity.
If you’re an aspiring or seasoned data scientist seeking a hands-on overview of both traditional and modern NLP techniques in Python, this is the course for you.
Course Content
22 course hours
13 assignments & solutions
0 skill assessments
Who should take this course
Aspiring Data Scientists who want a practical overview of natural language processing techniques in Python
Seasoned Data Scientists looking to learn the latest NLP techniques, such as Transformers, LLMs and Hugging Face
Meet your instructors
Alice Zhao
Lead Data Science Instructor
Alice Zhao is a seasoned data scientist and author of the book, SQL Pocket Guide, 4th Edition (O'Reilly). She has taught numerous courses in Python, SQL, and R as a data science instructor at Maven Analytics and Metis, and as a co-founder of Best Fit Analytics.
Featured review
"I'm really impressed that this course walks you through beginner-friendly NLP techniques and then makes LLMs easy to understand too! And my favorite part is the practical section on leveraging pre-trained models. It really feels like we are in a new era where anyone with a little know-how can leverage these new powerful tools, and this course is just what I needed!"
Ari S.
Included learning paths
Course credential
You’ll earn the course certification by completing this course and passing the assessment requirements
Natural Language Processing in Python
Natural Language Processing in Python
CPE Accreditation
CPE Credits:
0
Field of Study:
Information Technology
Delivery Method:
QAS Self Study
Maven Analytics LLC is registered with the National Association of State Boards of Accountancy (NASBA) as a sponsor of continuing professional education on the National Registry of CPE Sponsors. State boards of accountancy have the final authority on the acceptance of individual courses for CPE credit. Complaints regarding registered sponsors may be submitted to the National Registry of CPE Sponsors through its website: www.nasbaregistry.org.
For more information regarding administrative policies such as complaints or refunds, please contact us at admin@mavenanalytics.io or (857) 256-1765.
*Last Updated: May 25, 2023
Course Description
This is a practical, hands-on course designed to give you a comprehensive overview of all the essential concepts for Natural Language Processing (NLP) in Python.
We’ll start by reviewing the history and evolution of NLP over the past 70 years, including today’s most popular architecture, Transformers. We’ll then walk through the initial text-pre-processing steps required for modeling, where you’ll learn how to clean and normalize data with pandas and spaCy, then vectorize that data into a Document-Term Matrix using both word counts and TF-IDF scores.
From there, the course is split into two parts: the first half covers traditional machine-learning techniques and the second half covers modern deep-learning and LLM (large language model) approaches.
For the traditional NLP applications, we’ll begin with Sentiment Analysis to determine text polarity using the VADER library. Then we’ll cover Text Classification on labeled data with Naïve Bayes, as well as Topic Modeling on unlabeled data using Non-Negative Matrix Factorization—all with scikit-learn.
Once you have a solid grasp of foundational NLP concepts, we’ll move on to modern techniques and the data-science mindset shift of the last decade.
We’ll start with the basic building blocks of modern NLP—neural networks. You’ll learn how they’re trained, get familiar with layers, nodes, weights, and activation functions, and see popular deep-learning architectures in action.
Next, we’ll dive into Transformers, the architecture behind LLMs like ChatGPT, Gemini, and Claude. We’ll unpack embeddings, attention, and feed-forward layers, explain encoder-only vs. decoder-only vs. encoder-decoder models, and look at which LLMs fall into each category.
Last but not least, we’ll apply everything in Python using Hugging Face’s transformers library and Model Hub to demo six practical NLP applications: Sentiment Analysis, Named Entity Recognition, Zero-Shot Classification, Text Summarization, Text Generation, and Document Similarity.
If you’re an aspiring or seasoned data scientist seeking a hands-on overview of both traditional and modern NLP techniques in Python, this is the course for you.
Course Description
This is a practical, hands-on course designed to give you a comprehensive overview of all the essential concepts for Natural Language Processing (NLP) in Python.
We’ll start by reviewing the history and evolution of NLP over the past 70 years, including today’s most popular architecture, Transformers. We’ll then walk through the initial text-pre-processing steps required for modeling, where you’ll learn how to clean and normalize data with pandas and spaCy, then vectorize that data into a Document-Term Matrix using both word counts and TF-IDF scores.
From there, the course is split into two parts: the first half covers traditional machine-learning techniques and the second half covers modern deep-learning and LLM (large language model) approaches.
For the traditional NLP applications, we’ll begin with Sentiment Analysis to determine text polarity using the VADER library. Then we’ll cover Text Classification on labeled data with Naïve Bayes, as well as Topic Modeling on unlabeled data using Non-Negative Matrix Factorization—all with scikit-learn.
Once you have a solid grasp of foundational NLP concepts, we’ll move on to modern techniques and the data-science mindset shift of the last decade.
We’ll start with the basic building blocks of modern NLP—neural networks. You’ll learn how they’re trained, get familiar with layers, nodes, weights, and activation functions, and see popular deep-learning architectures in action.
Next, we’ll dive into Transformers, the architecture behind LLMs like ChatGPT, Gemini, and Claude. We’ll unpack embeddings, attention, and feed-forward layers, explain encoder-only vs. decoder-only vs. encoder-decoder models, and look at which LLMs fall into each category.
Last but not least, we’ll apply everything in Python using Hugging Face’s transformers library and Model Hub to demo six practical NLP applications: Sentiment Analysis, Named Entity Recognition, Zero-Shot Classification, Text Summarization, Text Generation, and Document Similarity.
If you’re an aspiring or seasoned data scientist seeking a hands-on overview of both traditional and modern NLP techniques in Python, this is the course for you.
Curriculum
Meet your instructors
Alice Zhao
Lead Data Science Instructor
Alice Zhao is a seasoned data scientist and author of the book, SQL Pocket Guide, 4th Edition (O'Reilly). She has taught numerous courses in Python, SQL, and R as a data science instructor at Maven Analytics and Metis, and as a co-founder of Best Fit Analytics.
Student reviews
I'm really impressed that this course walks you through beginner-friendly NLP techniques and then makes LLMs easy to understand too! And my favorite part is the practical section on leveraging pre-trained models. It really feels like we are in a new era where anyone with a little know-how can leverage these new powerful tools, and this course is just what I needed!
Ari S.
The Natural Language Processing in Python course, has built on the foundations laid in the other four data science in Python courses. I thoroughly enjoyed this course. It was eye-opening. The course is broken down into two sections Traditional NLP and Modern NLP. The second section builds on the concepts covered in the first. For me it was insightful to learn that a Logistic Regression is a simple neural network! Alice Zhao was a great teacher. I have learned so much and I'm already applying what I've learned to my own projects.
Andrew Hubbard
Included learning paths
Course credential
You’ll earn the course certification by completing this course and passing the assessment requirements
Natural Language Processing in Python
Natural Language Processing in Python
CPE Accreditation
CPE Credits:
0
Field of Study:
Information Technology
Delivery Method:
QAS Self Study
Maven Analytics LLC is registered with the National Association of State Boards of Accountancy (NASBA) as a sponsor of continuing professional education on the National Registry of CPE Sponsors. State boards of accountancy have the final authority on the acceptance of individual courses for CPE credit. Complaints regarding registered sponsors may be submitted to the National Registry of CPE Sponsors through its website: www.nasbaregistry.org.
For more information regarding administrative policies such as complaints or refunds, please contact us at admin@mavenanalytics.io or (857) 256-1765.
*Last Updated: May 25, 2023
More courses you may like
