From the course: Natural Language Processing in Python
Unlock this course with a free trial
Join today to access over 26,400 courses taught by industry experts.
Setting expectations - Python Tutorial
From the course: Natural Language Processing in Python
Setting expectations
Now, before we get started, let's set some expectations. First, this course covers both traditional and modern NLP. For the traditional piece, we're going to be talking about text preprocessing, as well as machine learning algorithms that are good for text data. And then for the modern piece, that's when we'll be introducing concepts such as neural networks, deep learning, transformers, and LLMs. If you're an experienced data scientist and you already know the traditional piece, feel free to jump ahead to the modern piece, starting with the neural network section. On the other hand, if you want to get a good general idea of the NLP space, I recommend that you take this course from beginning to end. In terms of the technical piece, we're going to be using Anaconda as our package and environment manager. We'll be talking a lot more about what that means exactly in the next section, but for the time being, just know that this is the software we'll be using throughout this course…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
Contents
-
-
(Locked)
Section introduction1m 19s
-
(Locked)
Anaconda overview2m 21s
-
(Locked)
Installing Anaconda2m 37s
-
(Locked)
Launching Jupyter Notebook5m 48s
-
(Locked)
Conda environments4m 27s
-
(Locked)
Conda workflow2m 55s
-
(Locked)
Conda commands2m 30s
-
(Locked)
Demo: Create a conda environment5m 45s
-
(Locked)
Environments in this course1m 22s
-
(Locked)
-
-
(Locked)
Section introduction59s
-
(Locked)
NLP pipeline2m 43s
-
(Locked)
Text preprocessing overview2m 35s
-
(Locked)
Assignment: Create a new environment1m 28s
-
(Locked)
Solution: Create a new environment3m 20s
-
(Locked)
Text preprocessing with pandas4m 19s
-
(Locked)
Demo: Text preprocessing setup6m 4s
-
(Locked)
Demo: Text preprocessing with pandas8m 14s
-
(Locked)
Pro tip: Create a function4m 25s
-
(Locked)
Assignment: Text preprocessing with pandas3m 22s
-
(Locked)
Solution: Text preprocessing with pandas8m 12s
-
(Locked)
Text preprocessing with spaCy1m 38s
-
(Locked)
Tokenization2m 5s
-
(Locked)
Lemmatization2m 42s
-
(Locked)
Stop words1m 17s
-
(Locked)
Parts of speech tagging2m 1s
-
(Locked)
Demo: Tokens, lemmas, and stop words8m
-
(Locked)
Pro tip: Use the apply method5m 59s
-
(Locked)
Demo: Parts of speech tagging9m 27s
-
(Locked)
Demo: Create an NLP pipeline6m 15s
-
(Locked)
Assignment: Text preprocessing with spaCy41s
-
(Locked)
Solution: Text preprocessing with spaCy7m 57s
-
(Locked)
Vectorization4m 45s
-
(Locked)
CountVectorizer in Python8m 4s
-
(Locked)
Demo: CountVectorizer5m 48s
-
(Locked)
Demo: CountVectorizer parameters5m 5s
-
(Locked)
Pro tip: Exploratory data analysis2m 13s
-
(Locked)
Assignment: CountVectorizer1m 16s
-
(Locked)
Solution: CountVectorizer7m 36s
-
(Locked)
Term frequency–inverse document frequency (TF-IDF)6m 30s
-
(Locked)
TF-IDF vectorizer in Python5m 8s
-
(Locked)
Demo: TF-IDF vectorizer4m 52s
-
(Locked)
Assignment: TF-IDF vectorizer1m 7s
-
(Locked)
Solution: TF-IDF vectorizer7m 38s
-
(Locked)
Key takeaways4m 13s
-
(Locked)
-
-
(Locked)
Section introduction1m 20s
-
(Locked)
What is machine learning (ML)?2m 55s
-
(Locked)
Common ML algorithms for NLP2m 51s
-
(Locked)
Traditional NLP overview2m 31s
-
(Locked)
Traditional vs. modern NLP1m 55s
-
(Locked)
Demo: Create a new environment4m 9s
-
(Locked)
Sentiment analysis1m 28s
-
(Locked)
Sentiment analysis in Python2m 46s
-
(Locked)
Demo: Sentiment analysis in Python6m 11s
-
(Locked)
Assignment: Sentiment analysis58s
-
(Locked)
Solution: Sentiment analysis8m 50s
-
(Locked)
Text classification basics1m 51s
-
(Locked)
Text classification algorithms2m 6s
-
(Locked)
Naive Bayes8m 4s
-
(Locked)
Naive Bayes in Python3m 8s
-
(Locked)
Demo: Naive Bayes setup9m 19s
-
(Locked)
Demo: Naive Bayes workflow8m 33s
-
(Locked)
Demo: Naive Bayes prediction3m 8s
-
(Locked)
Pro tip: Compare ML models8m 56s
-
(Locked)
Text classification next steps3m 11s
-
(Locked)
Assignment: Text classification1m 25s
-
(Locked)
Solution: Text classification14m 3s
-
(Locked)
Topic modeling basics2m 16s
-
(Locked)
Topic modeling algorithms1m 42s
-
(Locked)
Non-negative matrix factorization (NMF)4m 22s
-
(Locked)
NMF in Python2m 28s
-
(Locked)
Demo: Fit an NMF model5m 1s
-
(Locked)
Pro tip: Display topics function9m 30s
-
(Locked)
Demo: Tune an NMF model8m 51s
-
(Locked)
Topic modeling next steps1m 56s
-
(Locked)
Pro tip: Combine ML algorithms5m 3s
-
(Locked)
Assignment: Topic modeling1m 45s
-
(Locked)
Solution: Topic modeling13m 5s
-
(Locked)
Key takeaways2m 57s
-
(Locked)
-
-
(Locked)
Section introduction1m 47s
-
(Locked)
Modern NLP overview4m 41s
-
(Locked)
Intro to neural networks (NNs)2m 2s
-
(Locked)
Logistic regression refresher10m 36s
-
(Locked)
Logistic regression: Visually explained7m 3s
-
(Locked)
Neural networks: Visually explained5m 42s
-
(Locked)
Neural network summary3m 20s
-
(Locked)
Exercise: Neural network components31s
-
(Locked)
Solution: Neural network components5m 1s
-
(Locked)
Neural networks in Python6m 12s
-
(Locked)
Demo: Neural networks in Python6m 30s
-
(Locked)
Demo: Neural network matrices4m 16s
-
(Locked)
Pro tip: NN notation and matrices6m 12s
-
(Locked)
How a neural network is trained3m 59s
-
(Locked)
Neural network training: Visually explained16m 21s
-
(Locked)
Exercise: Neural network training22s
-
(Locked)
Solution: Neural network training8m 17s
-
(Locked)
Introduction to deep learning2m 22s
-
(Locked)
Deep learning architectures10m 34s
-
(Locked)
Deep learning in practice7m 50s
-
(Locked)
Pretrained deep learning models5m 21s
-
(Locked)
Exercise: Deep learning concepts16s
-
(Locked)
Solution: Deep learning concepts3m 18s
-
(Locked)
Key takeaways5m 22s
-
(Locked)
-
-
(Locked)
Section introduction2m 20s
-
(Locked)
Modern NLP recap59s
-
(Locked)
Transformers and large language models (LLMs) overview2m 41s
-
(Locked)
Transformer architecture2m 59s
-
(Locked)
Transformer architecture: Embeddings9m 8s
-
(Locked)
Transformer architecture: Attention11m 52s
-
(Locked)
Transformer architecture: Feedforward neural network3m 47s
-
(Locked)
Transformers summary5m 54s
-
(Locked)
Breaking down the transformer diagram3m 3s
-
(Locked)
Encoders and decoders5m 36s
-
(Locked)
LLMs9m 28s
-
(Locked)
Exercise: Transformers and LLMs concepts22s
-
(Locked)
Solution: Transformers and LLMs concepts5m 51s
-
(Locked)
Key takeaways3m 30s
-
(Locked)
-
-
(Locked)
Section introduction2m 33s
-
(Locked)
Hugging Face overview5m 3s
-
(Locked)
Demo: Create a new environment2m 48s
-
(Locked)
Sentiment analysis with LLMs5m 15s
-
(Locked)
Demo: Basic sentiment analysis pipeline8m 21s
-
(Locked)
Demo: Timing, logging, and device setup4m 33s
-
(Locked)
Demo: Compare sentiment scores7m 7s
-
(Locked)
Pro tip: Speed up transformers code5m 31s
-
(Locked)
Assignment: Sentiment analysis with LLMs1m 32s
-
(Locked)
Solution: Sentiment analysis with LLMs9m 9s
-
(Locked)
Named entity recognition (NER)5m 2s
-
(Locked)
Demo: Basic NER pipeline3m 8s
-
(Locked)
Demo: Hugging Face Model Hub2m 23s
-
(Locked)
Demo: Clean NER output7m 35s
-
(Locked)
Assignment: NER51s
-
(Locked)
Solution: NER14m 53s
-
(Locked)
Zero-shot classification4m 16s
-
(Locked)
Demo: Zero-shot classification7m 7s
-
(Locked)
Assignment: Zero-shot classification32s
-
(Locked)
Solution: Zero-shot classification5m
-
(Locked)
Text summarization3m
-
(Locked)
Demo: Text summarization3m 22s
-
(Locked)
Demo: Multiple pipelines7m 26s
-
(Locked)
Assignment: Text summarization27s
-
(Locked)
Solution: Text summarization4m 50s
-
(Locked)
Pro tip: Text generation3m 38s
-
(Locked)
Document embeddings2m 59s
-
(Locked)
Cosine similarity5m 5s
-
(Locked)
Document similarity with embeddings2m
-
(Locked)
Demo: Feature extraction and embeddings10m 17s
-
(Locked)
Demo: Cosine and document similarity5m 58s
-
(Locked)
Pro tip: Recommender function12m 55s
-
(Locked)
Assignment: Document similarity48s
-
(Locked)
Solution: Document similarity6m 10s
-
(Locked)
Key takeaways2m 52s
-
(Locked)