Skip to main content
HomePythonFeature Engineering for NLP in Python

Feature Engineering for NLP in Python

Learn techniques to extract useful information from text and process them into a format suitable for machine learning.

Start Course for Free
4 Hours15 Videos52 Exercises
22,875 LearnersTrophyStatement of Accomplishment

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.
GroupTraining 2 or more people?Try DataCamp For Business

Loved by learners at thousands of companies

Course Description

In this course, you will learn techniques that will allow you to extract useful information from text and process them into a format suitable for applying ML models. More specifically, you will learn about POS tagging, named entity recognition, readability scores, the n-gram and tf-idf models, and how to implement them using scikit-learn and spaCy. You will also learn to compute how similar two documents are to each other. In the process, you will predict the sentiment of movie reviews and build movie and Ted Talk recommenders. Following the course, you will be able to engineer critical features out of any text and solve some of the most challenging problems in data science!
For Business

GroupTraining 2 or more people?

Get your team access to the full DataCamp library, with centralized reporting, assignments, projects and more
Try DataCamp for BusinessFor a bespoke solution book a demo.
  1. 1

    Basic features and readability scores

    Free

    Learn to compute basic features such as number of words, number of characters, average word length and number of special characters (such as Twitter hashtags and mentions). You will also learn to compute readability scores and determine the amount of education required to comprehend a piece of text.

    Play Chapter Now
    Introduction to NLP feature engineering
    50 xp
    Data format for ML algorithms
    50 xp
    One-hot encoding
    100 xp
    Basic feature extraction
    50 xp
    Character count of Russian tweets
    100 xp
    Word count of TED talks
    100 xp
    Hashtags and mentions in Russian tweets
    100 xp
    Readability tests
    50 xp
    Readability of 'The Myth of Sisyphus'
    100 xp
    Readability of various publications
    100 xp
  2. 2

    Text preprocessing, POS tagging and NER

    In this chapter, you will learn about tokenization and lemmatization. You will then learn how to perform text cleaning, part-of-speech tagging, and named entity recognition using the spaCy library. Upon mastering these concepts, you will proceed to make the Gettysburg address machine-friendly, analyze noun usage in fake news, and identify people mentioned in a TechCrunch article.

    Play Chapter Now
    Tokenization and Lemmatization
    50 xp
    Identifying lemmas
    50 xp
    Tokenizing the Gettysburg Address
    100 xp
    Lemmatizing the Gettysburg address
    100 xp
    Text cleaning
    50 xp
    Cleaning a blog post
    100 xp
    Cleaning TED talks in a dataframe
    100 xp
    Part-of-speech tagging
    50 xp
    POS tagging in Lord of the Flies
    100 xp
    Counting nouns in a piece of text
    100 xp
    Noun usage in fake news
    100 xp
    Named entity recognition
    50 xp
    Named entities in a sentence
    100 xp
    Identifying people mentioned in a news article
    100 xp
  3. 3

    N-Gram models

    Learn about n-gram modeling and use it to perform sentiment analysis on movie reviews.

    Play Chapter Now
    Building a bag of words model
    50 xp
    Word vectors with a given vocabulary
    50 xp
    BoW model for movie taglines
    100 xp
    Analyzing dimensionality and preprocessing
    100 xp
    Mapping feature indices with feature names
    100 xp
    Building a BoW Naive Bayes classifier
    50 xp
    BoW vectors for movie reviews
    100 xp
    Predicting the sentiment of a movie review
    100 xp
    Building n-gram models
    50 xp
    n-gram models for movie tag lines
    100 xp
    Higher order n-grams for sentiment analysis
    100 xp
    Comparing performance of n-gram models
    100 xp
  4. 4

    TF-IDF and similarity scores

    Learn how to compute tf-idf weights and the cosine similarity score between two vectors. You will use these concepts to build a movie and a TED Talk recommender. Finally, you will also learn about word embeddings and using word vector representations, you will compute similarities between various Pink Floyd songs.

    Play Chapter Now
    Building tf-idf document vectors
    50 xp
    tf-idf weight of commonly occurring words
    50 xp
    tf-idf vectors for TED talks
    100 xp
    Cosine similarity
    50 xp
    Range of cosine scores
    50 xp
    Computing dot product
    100 xp
    Cosine similarity matrix of a corpus
    100 xp
    Building a plot line based recommender
    50 xp
    Comparing linear_kernel and cosine_similarity
    100 xp
    Plot recommendation engine
    100 xp
    The recommender function
    100 xp
    TED talk recommender
    100 xp
    Beyond n-grams: word embeddings
    50 xp
    Generating word vectors
    100 xp
    Computing similarity of Pink Floyd songs
    100 xp
    Congratulations!
    50 xp

In the following tracks

Machine Learning Scientist with PythonNatural Language Processing in Python

Datasets

Russian Troll TweetsMovie Overviews and TaglinesPreprocessed Movie ReviewsTED Talk TranscriptsReal and Fake News Headlines

Collaborators

Collaborator's avatar
Hillary Green-Lerman
Collaborator's avatar
Adrián Soto

Prerequisites

Introduction to Natural Language Processing in PythonSupervised Learning with scikit-learn
Rounak Banik HeadshotRounak Banik

Data Scientist at Fractal Analytics

See More

What do other learners have to say?

    Join over 13 million learners and start Feature Engineering for NLP in Python today!

    Create Your Free Account

    GoogleLinkedInFacebook

    or

    By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.