Text Analytics with Python: A Practical Real-World Approach to Gaining Actionable Insights from Your Data

by Dipanjan Sarkar

Leverage Natural Language Processing (NLP) fundamentals in Python and learn how to set up your own robust environment for performing text analytics. This updated version will show you how to use the latest state-of-the-art frameworks and how to work with text data in Python.

You'll explore several new topics, including working with Python for NLP, illustrated with more hands-on examples. There are also new chapters on engineering text data (both traditional and newer deep learning based embedding methods) and deep learning for advanced text analytics and NLP.
While the overall structure of the book remains the same, the entire code base, modules, and frameworks will be updated to the latest Python 3.x release. You'll review new and improved methods for evaluating and interpreting classification models, and will look at newer lexicons and methodologies for unsupervised learning.
What You'll Learn

-Understand NPL and text syntax, semantics and structure-Discover text cleaning and feature engineering-Review text classification and text clustering - Assess text summarization and topic models- Study deep learning for NLP
Who This Book Is For
IT professionals, data analysts, developers, linguistic experts, data scientists and engineers and basically anyone with a keen interest in linguistics, analytics and generating insights from textual data.

Genres: Reference, Programming

674 pages, Paperback

Published May 22, 2019

Reviews

[Mike Martos · Rating 5 out of 5]

Great book, easy to follow and great examples. It provides complete examples and can help you start your NPL solution.

[Eugene · Rating 5 out of 5]

easy to understand explanations of NLP techniques and processes. Good read, yet simple to understand

[Uyen · Rating 4 out of 5]

If you are new to text analytics, natural language processing and all that jazz, this will be a good introductory book to guide you through the concepts, the high level ideas and what will/should be included in the pipeline. Plus it comes with Python implementation (source code available on Github) which is greatttt. However, bear in mind that the stuffs written here will be quite simple, conventional and not particularly in-depth of any techniques which are not unusual for this kind of "introductory" book. Although I wish the author dived a bit deeper into discussing the results from the implementation rather than just showing the mere results and visualisations. Still a good read though.

[Mervat · Rating 4 out of 5]

It's a very useful book though it's a little bit confusing for beginners.
in"lemmatization "section for example the code was too complex, otherwise it can be written in three lines with (pattern)library :
import pattern
from pattern.en import lemma

def lemmatization(text):

lemmatization =" ".join([lemma(wd) for wd in text.split()])
return lemmatization